CN112163169A - Multi-mode user emotion analysis method based on knowledge graph - Google Patents
Multi-mode user emotion analysis method based on knowledge graph Download PDFInfo
- Publication number
- CN112163169A CN112163169A CN202011055440.9A CN202011055440A CN112163169A CN 112163169 A CN112163169 A CN 112163169A CN 202011055440 A CN202011055440 A CN 202011055440A CN 112163169 A CN112163169 A CN 112163169A
- Authority
- CN
- China
- Prior art keywords
- user
- graph
- inter
- freq
- social network
- 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
- 230000008451 emotion Effects 0.000 title claims abstract description 46
- 238000004458 analytical method Methods 0.000 title claims abstract description 37
- 230000002996 emotional effect Effects 0.000 claims abstract description 38
- 238000006467 substitution reaction Methods 0.000 claims abstract description 12
- 238000000034 method Methods 0.000 claims abstract description 9
- 238000013475 authorization Methods 0.000 claims abstract description 8
- 230000003993 interaction Effects 0.000 claims abstract description 4
- 238000004891 communication Methods 0.000 claims description 17
- 230000011273 social behavior Effects 0.000 claims description 13
- 230000006399 behavior Effects 0.000 claims description 7
- 238000010276 construction Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 2
- 230000004970 emotional disturbance Effects 0.000 abstract description 2
- 208000027534 Emotional disease Diseases 0.000 description 5
- 230000002159 abnormal effect Effects 0.000 description 3
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 201000010099 disease Diseases 0.000 description 2
- 241000282414 Homo sapiens Species 0.000 description 1
- 206010027940 Mood altered Diseases 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002860 competitive effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9536—Search customisation based on social or collaborative filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/01—Social networking
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Economics (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Human Resources & Organizations (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a multimode user emotion analysis method based on a knowledge graph, which comprises the following steps: receiving an emotion analysis service request of a user or acquiring authorization of social network data of a monitored user applied to emotion analysis service; obtaining user social network data, establishing a user graph model based on the user social network data, the user graph model including a data graph DGraphInformation map IGraphAnd knowledge map KGraphSeparately store DDIK、IDIK、KDIKThree types of resources; extracting interaction relation tuples Inter (user) of the user and others from the user atlas model, calculating an Inter (user) substitution function, and analyzing the emotional tendency of the user according to the calculation result; and sending the emotional tendency analysis result to a corresponding user. The method and the system can analyze the emotional tendency of the user based on massive social network data under the condition that the user does not sense the emotional tendency, so that the emotional tendency of the user is analyzedThe user is helped to know the self emotional tendency condition in time and prevent the emotional disturbance.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a knowledge graph-based multi-modal user emotion analysis method.
Background
The development of modern society gradually separates human beings from natural attributes, environmental pollution, fast pace of life, competitive pressure, complex social relationships, bad work and rest time, consumption orientation difference and the like, so that people who have psychological problems are gradually increased, and emotional disorders caused by loving off, strandboard, emotional fluctuation caused by interpersonal relationship conflict, interest reduction caused by bad mood within a period of time, life law disorder, even behavior abnormality, character deviation and the like are caused. Some people may not find that the emotional disorder exists, and some people may know that the emotional disorder exists, but the emotional disorder is further developed into psychological diseases because the people are not hospitalized in time due to the sensitive pubic feeling or the inadequately attached attention and the like. Social networks have gradually become one of the main ways for people to release emotions and display real self in the network world, and the emotional conditions of users can be often seen through social behaviors of the users on the social networks, however, no related technical means is available at present for processing mass social network data so as to analyze emotions of the users.
Disclosure of Invention
The invention aims to provide a knowledge graph-based multi-mode user emotion analysis method, which adopts the knowledge graph to model social network data of a user and analyzes the emotional condition of the user according to a model, thereby preventing the emotional disorder from developing into a psychological disease and overcoming or at least partially solving the problems in the prior art.
A multimodal user emotion analysis method based on knowledge graph comprises the following steps:
receiving an emotion analysis service request of a user or acquiring authorization of social network data of a monitored user applied to emotion analysis service;
obtaining user social network data, establishing a user graph model based on the user social network data, the user graph model including a data graph DGraphInformation map IGraphAnd knowledge map KGraphSeparately store DDIK、IDIK、KDIKThree types of resources;
extracting interaction relation tuples Inter (user) of the user and others from the user atlas model, calculating an Inter (user) substitution function, and analyzing the emotional tendency of the user according to the calculation result;
and sending the emotional tendency analysis result to a corresponding user.
Further, the establishing a user graph model based on the user social network data specifically includes:
using user-related D in social networksDIKResource construction user feature set Attr (U)a) User feature set Attr (U)a) Comprises a plurality of users U surrounding a central nodeaA set of discrete feature nodes outside, the feature nodes being denoted as Ex(IS(ai))(1<i<n), where x denotes the user, n denotes the number of characteristic nodes defining the user, Attr (U)a) Expressed as:
statistics DDIKFrequency of occurrence of each feature node Attr (U) in a resourcea)freqAnd store it in the data map DGraphUp, Attr (U)a)freqExpressed as:
further, the establishing a user graph model based on the user social network data specifically further includes:
constructing Inter (U) according to social behavior data of usersa) Counting the occurrence frequency Inter (U) of different social behaviors of the usera)freqAnd storing to the information map I of the userGraphWherein Inter (U)a) And Inter (U)a)freqRespectively expressed as:
Inter(Ua)＝{Send；Receive；Post；Reply；Like} (3)
Inter(Ua)freq＝{Sendfreq；Receivefreq；Postfreq；Replyfreq；Likefreq} (4)
wherein Send represents the sending information, Receive represents the receiving information, Post represents the releasing UGC content, Reply represents leaving a message under the UGC content, and Like represents the praise of the UGC content.
Further, the establishing a user graph model based on the user social network data specifically further includes:
based on Inter (U)a) Obtaining user UaWith other users UbSocial relationship data R (U) betweena,Ub)，R(Ua,Ub) Expressed as:
wherein Send (U)a,Ub) Represents UaSending a message to Ub，Receive(Ua,Ub) Represents UaReceive to UbTransmitted message, Reply (U)a,Ub) Represents UaAt UbLeave a message, ReceiveRely (U) under published UGC contenta,Ub) Represents UaPublished UGC content receipt UbLeave a message, Like (U)a,Ub) Represents UaLike UbPublished UGC content, Receivelike (U)a,Ub) Represents UaPublished UGC content receipt UbLeave messages, calculate UaAnd UbFrequency R (U) of different social behaviorsa,Ub)freq，R(Ua,Ub)freqExpressed as:
will Inter (U)a)、R(Ua,Ub) Store to information map IGraphAbove, mixing R (U)a,Ub)freqStore to data map DGraphThe above.
Further, the establishing a user graph model based on the user social network data specifically further includes:
according to R (U)a,Ub) And R (U)a,Ub)freqFor computingHousehold UaWith other users UbThe level of exchange relationship between Rdegree(Ua,Ub)；
Calculating user UaEach level of communication relation contact group Gdegree(Ua) And storing into an information map IGraphThe above.
Further, establishing a user graph model based on the user social network data specifically includes:
according to user information map IGraphInter (U) ofa) Judging favorite contents of a user in the social network by the contents;
according to user information map IGraphInter (U) ofa)freqJudging the social behavior habit of the user by the content;
taking the judgment result as KDIKResource storage to knowledge graph KgraphIn (1).
Further, the calculating the inter (user) substitution function, and analyzing the emotional tendency of the user according to the calculation result specifically includes:
inter (U) in information mapa) Calculating a substitution function to obtain a user UaConfidants (U) of the close-relation usera)；
Will Inter (U)a) And Confidants (U)a) And respectively substituting the functions into the functions to calculate the user emotional tendency index, and analyzing and judging the user emotional tendency according to the calculation result.
Further, the Inter (U) in the information mapa) Calculating a substitution function to obtain a user UaThe close-relation user configants specifically comprise:
according to user UaSocial behavior data R (U) among all the highest level communication relation groupsa,Ub) And social behavior frequency R (U)a,Ub)freqCalculating the user UaThe relationship intimacy between each user in the highest level communication relationship group;
screening all users U in highest-level exchange relation populationaUse of relationship intimacy greater than preset thresholdUser U for user compositionaConfidants (U) of the close communication crowda)。
Further, after the sending the emotional tendency analysis result to the corresponding user, the method further includes:
receiving an emotion adjusting service request of a user or acquiring authorization for pushing data to a social network of the user to be applied to the emotion adjusting service;
and selecting a corresponding emotion adjusting strategy according to the emotion tendency analysis result, and pushing corresponding data content to the user social network according to the emotion adjusting strategy.
Compared with the prior art, the invention has the beneficial effects that:
the multi-modal user emotion analysis method based on the knowledge graph provided by the invention comprises the steps of establishing a user graph model by acquiring social data generated when a user moves in a social network, and processing and converting the social data into DDIK、IDIK、KDIKThe three types of resources are used for extracting interactive relation tuples of the user and other people based on the user map model, analyzing the emotional tendency of the user after function calculation, analyzing the emotional tendency of the user based on massive social network data under the condition that the user does not sense, helping the user to know the emotional tendency condition of the user in time and preventing emotional disturbance.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is apparent that the drawings in the following description are only preferred embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained based on these drawings without inventive efforts.
FIG. 1 is a schematic overall flow chart of a knowledge graph-based multi-modal user emotion analysis method provided by the embodiment of the invention.
Detailed Description
The principles and features of this invention are described below in conjunction with the following drawings, the illustrated embodiments are provided to illustrate the invention and not to limit the scope of the invention.
Referring to fig. 1, the invention provides a multimodal user emotion analysis method based on a knowledge graph, which comprises the following steps:
and S1, receiving the emotion analysis service request of the user or acquiring the authorization of the social network data of the monitoring user to be applied to the emotion analysis service.
When the user is aware that the user possibly has or has abnormal emotional tendency, the user can actively initiate an emotion analysis service request to obtain emotion analysis service. When the user thinks that the emotional tendency of the user is abnormal, the user can also authorize the user to allow the monitoring of the social network data and apply the social network data to the emotional analysis service, so that the user can find and take measures in time when the emotional tendency is abnormal. And when receiving the emotion analysis service request of the user, automatically obtaining the social network data of the monitoring user and applying the social network data to the authorization of the emotion analysis service.
S2, obtaining user social network data, and establishing a user graph model based on the user social network data, wherein the user graph model comprises a data graph DGraphInformation map IGraphAnd knowledge map KGraphSeparately store DDIK、IDIK、KDIKThree types of resources.
S3, extracting interaction relation tuples Inter (user) of the user and others from the user atlas model, calculating the Inter (user) substitution function, and analyzing the emotional tendency of the user according to the calculation result.
And S4, sending the emotional tendency analysis result to the corresponding user.
In step S2, establishing a user graph model based on the user social network data specifically includes:
for data map DGraphUsing user-related D in social networksDIKResource construction user feature set Attr (U)a) User feature set Attr (U)a) Comprises a plurality of users U surrounding a central nodeaThe discrete feature node sets outside define the user U togetheraIs characterized byThe token node is denoted as Ex(IS(ai))(1<i<n), where x denotes the user, n denotes the number of characteristic nodes defining the user, Attr (U)a) Expressed as:
a large number of DDIKThere is a certain proportion of data repetition in the resource, statistics DDIKFrequency of occurrence of each feature node Attr (U) in a resourcea)freqAnd store it in the data map DGraphUp, Attr (U)a)freqExpressed as:
for information map IGraphUser UaRecords the behavior record of the user in the social network, and converts the related social behavior data into IDIKResources and constructing Inter (U) on the basis of the resourcesa) Counting the occurrence frequency Inter (U) of different social behaviors of the usera)freqAnd storing to the information map I of the userGraphWherein Inter (U)a) And Inter (U)a)freqRespectively expressed as:
Inter(Ua)＝{Send；Receive；Post；Reply；Like} (3)
Inter(Ua)freq＝{Sendfreq；Receivefreq；Postfreq；Replyfreq；Likefreq} (4)
wherein Send represents the sending information, Receive represents the receiving information, Post represents the releasing UGC content, Reply represents leaving a message under the UGC content, and Like represents the praise of the UGC content. Inter (U) in addition to Post action of publishing UGC contenta) The rest of 4 in (1) occur at the user UaWith other users UbBased on Inter (U)a) Obtaining user UaWith other users UbSocial relationship data R (U) betweena,Ub)，R(Ua,Ub) Expressed as:
wherein Send (U)a,Ub) Represents UaSending a message to Ub，Receive(Ua,Ub) Represents UaReceive to UbTransmitted message, Reply (U)a,Ub) Represents UaAt UbLeave a message, ReceiveRely (U) under published UGC contenta,Ub) Represents UaPublished UGC content receipt UbLeave a message, Like (U)a,Ub) Represents UaLike UbPublished UGC content, Receivelike (U)a,Ub) Represents UaPublished UGC content receipt UbMessage, R (U)a,Ub) Middle Send (U)a,Ub)、Reply(Ua,Ub)、Like(Ua,Ub) Are all user UaActive behavior of (U), Receive (U)a,Ub)、ReceiveReply(Ua,Ub)、ReceiveLike(Ua,Ub) For user UaPassive behavior of (1), Send (U)a,Ub) Is equal to Receive (U)a,Ub) Value of (D), calculating UaAnd UbFrequency R (U) of different social behaviorsa,Ub)freq，R(Ua,Ub)freqExpressed as:
will Inter (U)a)、R(Ua,Ub) Store to information map IGraphAbove, mixing R (U)a,Ub)freqStore to data map DGraphThe above.
According to R (U)a,Ub) And R (U)a,Ub)freqCalculating user UaWith other users UbThe level of exchange relationship between Rdegree(Ua,Ub) If there is direct communication between users, i.e. R (U)a,Ub) If not 0, then user UaAnd UbThe contact persons are in a first-level communication relationship with each other if UaAnd UbAre not connected with each other but are all connected with the user UcIf there is a connection, UaAnd UbBelonging to a second-level contact relation, calculating a user U as shown in formula (7)aEach level of communication relation contact group Gdegree(Ua) And storing into an information map IGraphThe above.
Gdegree(Ua)＝{User|degree(Ua,other)＝n} (7)
For knowledge graph KgraphIt can be constructed in the following way:
according to user information map IGraphInter (U) ofa) The content judges the favorite content of the user in the social network. In particular according to Inter (U)a) The three contents of Post, Reply and Like in (1) can be obtained:
K1:K(Ua,content)::＝"preference"
by K1Can know the user UaFavorite content in a social network.
According to user information map IGraphInter (U) ofa)freqThe content judges the social behavior habit of the user. In particular according to Inter (U)a)freqThe content can be obtained as follows:
K2:K(Ua,behavior)::＝"habit"
by K2Can know the user UaThe social behavior pattern used. Will K1、K2And other judgment results as KDIKResource storage to knowledge graph KgraphIn (1).
In step S3, the calculating the inter (user) substitution function, and analyzing the emotional tendency of the user according to the calculation result specifically includes:
s31, Inter (U) in the information mapa) Calculating a substitution function to obtain a user UaConfidants (U) of the close-relation usera)。
S32, mixing Inter (U)a) And Confidants (U)a) And respectively substituting the functions into the functions to calculate the user emotional tendency index, and analyzing and judging the user emotional tendency according to the calculation result.
The step S31 specifically includes:
according to user UaPeople with highest level of communication relation, namely people with first level of communication relation Gdegree＝1(Ua) Social relationship R (U) betweena,Ub) And social frequency R (U)a,Ub)freqCalculating user and Gdegree＝1(Ua) Each user U inbRelationship intimacy degree I (U) betweena,Ub)，I(Ua,Ub) Expressed as:
I(Ua,Ub)＝Intimacy(Gdegree＝1(Ua),R(Ua,Ub),R(Ua,Ub)freq) (8)
when I (U)a,Ub) If the value is greater than the preset threshold Iw, the user UaAnd UbG is taken as the confidential user of the other partydegree＝1(Ua) And user UaIntimacy value of (U)aOthers) are greater than IwaConfidants (U) of the close communication related populationa)，Confidants(Ua) Expressed as:
Confidants(Ua)＝{Ub∈Gdegree＝1(Ua)|I(Ua,Ub)>Iw} (9)。
in step S32, calculating the Emotion tendency index of the user is implemented by a constructor Emotion, as shown in formula 10.
e＝Emotion(Confidants(Ua),inter(Ua)freq) (10)
Confidants(Ua) Can reflect the social contact of the user to a certain extentHabits and requirements, if Confidants (U)a) Two indexes of (I) (U)aOthers) and the number of close users Cn(Ua) If the numerical value is higher, the emotional tendency of the user is more likely to focus on the relationship with other people; if lower, it is likely that its emotional tendency is more self-focused, if I (U)aOthers) are high and Cn(Ua) A low level indicates that the user has more communication with the stationary population and less communication with strangers. Inter (U)a)freqFor analyzing social habits of users, if Send (U)a,Ub)freq、Receive(Ua,Ub)freqThe ratio of the number to the specific gravity is higher, Reply (U)a,Ub)freq、Like(Ua,Ub)freqIf the numerical value accounts for the bottom of the proportion, the emotion of the user tends to have a communication relation with a plurality of people; if the situation is opposite, the emotional tendency of the user is more likely to be biased to be centered on the user. e represents the emotional tendency index of the user, and the emotional tendency of the user can be judged according to whether e is larger than or smaller than a preset threshold value.
As an example, after sending the emotional tendency analysis result to the corresponding user, the method further includes:
receiving a sentiment adjustment service request of a user or obtaining authorization for pushing data to a social network of the user to be applied to the sentiment adjustment service.
And selecting a corresponding emotion adjusting strategy according to the emotion tendency analysis result, and pushing corresponding data content to the user social network according to the emotion adjusting strategy.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (9)
1. A multimodal user emotion analysis method based on knowledge graph is characterized by comprising the following steps:
receiving an emotion analysis service request of a user or acquiring authorization of social network data of a monitored user applied to emotion analysis service;
obtaining user social network data, establishing a user graph model based on the user social network data, the user graph model including a data graph DGraphInformation map IGraphAnd knowledge map KGraphSeparately store DDIK、IDIK、KDIKThree types of resources;
extracting interaction relation tuples Inter (user) of the user and others from the user atlas model, calculating an Inter (user) substitution function, and analyzing the emotional tendency of the user according to the calculation result;
and sending the emotional tendency analysis result to a corresponding user.
2. The method according to claim 1, wherein the establishing of the user graph model based on the user social network data specifically comprises:
using user-related D in social networksDIKResource construction user feature set Attr (U)a) User feature set Attr (U)a) Comprises a plurality of users U surrounding a central nodeaA set of discrete feature nodes outside, the feature nodes being denoted as Ex(IS(ai))(1<i<n), where x denotes the user, n denotes the number of characteristic nodes defining the user, Attr (U)a) Expressed as:
statistics DDIKFrequency of occurrence of each feature node Attr (U) in a resourcea)freqAnd store it in the data map DGraphUp, Attr (U)a)freqExpressed as:
3. the multimodal user emotion analysis method based on knowledge graph as claimed in claim 2, wherein the establishing a user graph model based on user social network data further comprises:
constructing Inter (U) according to social behavior data of usersa) Counting the occurrence frequency Inter (U) of different social behaviors of the usera)freqAnd storing to the information map I of the userGraphWherein Inter (U)a) And Inter (U)a)freqRespectively expressed as:
Inter(Ua)＝{Send；Receive；Post；Reply；Like} (3)
Inter(Ua)freq＝{Sendfreq；Receivefreq；Postfreq；Replyfreq；Likefreq} (4)
wherein Send represents the sending information, Receive represents the receiving information, Post represents the releasing UGC content, Reply represents leaving a message under the UGC content, and Like represents the praise of the UGC content.
4. The multimodal user emotion analysis method based on knowledge graph as claimed in claim 3, wherein the establishing a user graph model based on user social network data further comprises:
based on Inter (U)a) Obtaining user UaWith other users UbSocial relationship data R (U) betweena,Ub)，R(Ua,Ub) Expressed as:
wherein Send (U)a,Ub) Represents UaSending a message to Ub，Receive(Ua,Ub) Represents UaReceive to UbTransmitted message, Reply (U)a,Ub) Represents UaAt UbContent of published UGCMessage, Receivedreply (U)a,Ub) Represents UaPublished UGC content receipt UbLeave a message, Like (U)a,Ub) Represents UaLike UbPublished UGC content, Receivelike (U)a,Ub) Represents UaPublished UGC content receipt UbLeave messages, calculate UaAnd UbFrequency R (U) of different social behaviorsa,Ub)freq，R(Ua,Ub)freqExpressed as:
will Inter (U)a)、R(Ua,Ub) Store to information map IGraphAbove, mixing R (U)a,Ub)freqStore to data map DGraphThe above.
5. The multimodal user emotion analysis method based on knowledge graph as claimed in claim 4, wherein the establishing a user graph model based on user social network data further comprises:
according to R (U)a,Ub) And R (U)a,Ub)freqCalculating user UaWith other users UbThe level of exchange relationship between Rdegree(Ua,Ub)；
Calculating user UaEach level of communication relation contact group Gdegree(Ua) And storing into an information map IGraphThe above.
6. The multimodal user emotion analysis method based on knowledge graph as claimed in claim 3, wherein the user graph model is established based on user social network data, further comprising:
according to user information map IGraphInter (U) ofa) Content determination of user preferences in a social network；
According to user information map IGraphInter (U) ofa)freqJudging the social behavior habit of the user by the content;
taking the judgment result as KDIKResource storage to knowledge graph KgraphIn (1).
7. The method according to claim 5, wherein an inter (user) substitution function is calculated, and the emotional tendency of the user is analyzed according to the calculation result, and the method specifically comprises the following steps:
inter (U) in information mapa) Calculating a substitution function to obtain a user UaConfidants (U) of the close-relation usera)；
Will Inter (U)a) And Confidants (U)a) And respectively substituting the functions into the functions to calculate the user emotional tendency index, and analyzing and judging the user emotional tendency according to the calculation result.
8. The method according to claim 7, wherein the Inter (U) in the information graph is selected as a knowledge grapha) Calculating a substitution function to obtain a user UaThe close-relation user configants specifically comprise:
according to user UaSocial behavior data R (U) among all the highest level communication relation groupsa,Ub) And social behavior frequency R (U)a,Ub)freqCalculating the user UaThe relationship intimacy between each user in the highest level communication relationship group;
screening all users U in highest-level exchange relation populationaUser U formed by users with relationship intimacy greater than preset thresholdaConfidants (U) of the close communication crowda)。
9. The method of claim 1, wherein after the sending the emotion tendency analysis result to the corresponding user, the method further comprises:
receiving an emotion adjusting service request of a user or acquiring authorization for pushing data to a social network of the user to be applied to the emotion adjusting service;
and selecting a corresponding emotion adjusting strategy according to the emotion tendency analysis result, and pushing corresponding data content to the user social network according to the emotion adjusting strategy.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011055440.9A CN112163169A (en) | 2020-09-29 | 2020-09-29 | Multi-mode user emotion analysis method based on knowledge graph |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011055440.9A CN112163169A (en) | 2020-09-29 | 2020-09-29 | Multi-mode user emotion analysis method based on knowledge graph |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112163169A true CN112163169A (en) | 2021-01-01 |
Family
ID=73861541
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011055440.9A Pending CN112163169A (en) | 2020-09-29 | 2020-09-29 | Multi-mode user emotion analysis method based on knowledge graph |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112163169A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112948554A (en) * | 2021-02-28 | 2021-06-11 | 西北工业大学 | Real-time multi-modal dialogue emotion analysis method based on reinforcement learning and domain knowledge |
| CN115630697A (en) * | 2022-10-26 | 2023-01-20 | 泸州职业技术学院 | Knowledge graph construction method and system capable of distinguishing single-phase and double-phase affective disorder |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9015088B2 (en) * | 2012-10-30 | 2015-04-21 | Palo Alto Research Center Incorported | Method and system for psychological analysis by fusing multiple-view predictions |
| CN105260410A (en) * | 2015-09-22 | 2016-01-20 | 天津大学 | Microblog interestingness circle mining method based on intimacy degree and influence power and microblog interestingness circle mining device based on intimacy degree and influence power |
| CN106528643A (en) * | 2016-10-13 | 2017-03-22 | 上海师范大学 | Social network based multi-dimension comprehensive recommending method |
| CN110569411A (en) * | 2019-09-20 | 2019-12-13 | 海南大学 | Virtual community personnel character classification and character conversion method based on typed knowledge graph |
-
2020
- 2020-09-29 CN CN202011055440.9A patent/CN112163169A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9015088B2 (en) * | 2012-10-30 | 2015-04-21 | Palo Alto Research Center Incorported | Method and system for psychological analysis by fusing multiple-view predictions |
| CN105260410A (en) * | 2015-09-22 | 2016-01-20 | 天津大学 | Microblog interestingness circle mining method based on intimacy degree and influence power and microblog interestingness circle mining device based on intimacy degree and influence power |
| CN106528643A (en) * | 2016-10-13 | 2017-03-22 | 上海师范大学 | Social network based multi-dimension comprehensive recommending method |
| CN110569411A (en) * | 2019-09-20 | 2019-12-13 | 海南大学 | Virtual community personnel character classification and character conversion method based on typed knowledge graph |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112948554A (en) * | 2021-02-28 | 2021-06-11 | 西北工业大学 | Real-time multi-modal dialogue emotion analysis method based on reinforcement learning and domain knowledge |
| CN112948554B (en) * | 2021-02-28 | 2024-03-08 | 西北工业大学 | Real-time multi-mode dialogue emotion analysis method based on reinforcement learning and domain knowledge |
| CN115630697A (en) * | 2022-10-26 | 2023-01-20 | 泸州职业技术学院 | Knowledge graph construction method and system capable of distinguishing single-phase and double-phase affective disorder |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Qiu et al. | Limited individual attention and online virality of low-quality information | |
| Bradford et al. | A leap of faith? Trust in the police among immigrants in England and Wales | |
| Pielot et al. | When attention is not scarce-detecting boredom from mobile phone usage | |
| Halupka | Clicktivism: A systematic heuristic | |
| Liau et al. | Parental awareness and monitoring of adolescent Internet use | |
| CN104484359B (en) | A kind of the analysis of public opinion method and device based on social graph | |
| US8560486B2 (en) | Content recommendation method and system based on psychological factors from a use profile | |
| Lim et al. | Finding twitter communities with common interests using following links of celebrities | |
| Lowe-Calverley et al. | A risky investment? Examining the outcomes of emotional investment in Instagram | |
| Carley et al. | The etiology of social change | |
| Green Jr et al. | Shared risk: who engages in substance use with A merican homeless youth? | |
| Shi et al. | Geographical impacts on social networks from perspectives of space and place: An empirical study using mobile phone data | |
| CN112163169A (en) | Multi-mode user emotion analysis method based on knowledge graph | |
| US20170352044A1 (en) | Method and system for evaluating reliability based on analysis of user activities on social medium | |
| Voutyras et al. | Social monitoring and social analysis in internet of things virtual networks | |
| US20160335405A1 (en) | Method and system for analyzing digital activity | |
| Laumer et al. | Social media stress: A literature review and future research directions | |
| Wang et al. | Transmission of information about consumer product quality and safety: a social media perspective | |
| KR101926620B1 (en) | MBTI-Based Recommendation Method For Resource Collaboration In IoT Environment | |
| Bode et al. | Study designs for quantitative social science research using social media | |
| Tang et al. | CloudRec: A mobile cloud service recommender system based on adaptive QoS management | |
| US20190332637A1 (en) | Method and system for evaluating reliability based on analysis of user activities on social medium | |
| de Oliveira Albuquerque et al. | Gtrust: group extension for trust models in distributed systems | |
| Afshari et al. | QoE assessment of interactive applications in computer networks | |
| Rangnani et al. | Autoregressive model for users’ retweeting profiles |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210101 |
|
| RJ01 | Rejection of invention patent application after publication |