CN111160977A - Method, device, device and medium for acquiring user relationship interest feature map - Google Patents
Method, device, device and medium for acquiring user relationship interest feature map Download PDFInfo
- Publication number
- CN111160977A CN111160977A CN201911402394.2A CN201911402394A CN111160977A CN 111160977 A CN111160977 A CN 111160977A CN 201911402394 A CN201911402394 A CN 201911402394A CN 111160977 A CN111160977 A CN 111160977A
- Authority
- CN
- China
- Prior art keywords
- user
- communication
- interest
- relationship
- users
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Accounting & Taxation (AREA)
- Data Mining & Analysis (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Game Theory and Decision Science (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
本发明实施例提供一种用户关系兴趣特征图的获取方法、装置、设备及介质。该方法包括：获取目标区域中多个用户的通信数据；根据多个用户的通信数据、多个用户中每个用户的兴趣区域集合、每个用户的每个通信对象的兴趣区域集合，生成用户关系图，其中，兴趣区域集合包括至少一个兴趣区域，兴趣区域为具有语义信息的时空位置区域；根据每个用户的兴趣特征向量与每个用户的每个通信对象的兴趣特征向量，生成用户兴趣特征图，其中，兴趣特征向量基于兴趣区域获得；根据用户关系图与用户兴趣特征图，生成用户关系兴趣特征图。通过本发明的识别方法能够精准地反映出用户间的关系以及用户间的兴趣特征的相似性。
Embodiments of the present invention provide a method, apparatus, device, and medium for acquiring a user relationship interest feature map. The method includes: acquiring communication data of multiple users in a target area; generating a user according to the communication data of the multiple users, the set of interest areas of each user in the multiple users, and the set of interest areas of each communication object of each user A relationship diagram, wherein the set of interest areas includes at least one interest area, and the interest area is a spatiotemporal location area with semantic information; according to the interest feature vector of each user and the interest feature vector of each communication object of each user, the user interest is generated. feature map, wherein, the interest feature vector is obtained based on the area of interest; according to the user relationship map and the user interest feature map, the user relationship interest feature map is generated. The identification method of the present invention can accurately reflect the relationship between users and the similarity of interest features between users.
Description
Technical Field
The present invention relates to the field of business support technologies, and in particular, to a method, an apparatus, a device, and a computer-readable storage medium for obtaining a user relationship interest feature map.
Background
In the big data era, operators face business transformation pressure, and gradually change from single communication service providers to diversified information service providers, so that the industry chain and the value chain of the operators also need to be richer, and customers become the core of a new value chain.
In the process of building a client label system, besides the client basic characteristic labels of the consumption ability, social attributes, social behaviors, terminal characteristics, position characteristics, internet behaviors, temperament and the like of a client need to be described, the space-time position track information of a user actually records the objective activity behaviors of the user, important information such as the intention, activity rules and potential interests and hobbies of the user can be continuously mined from the behavior activities, and the method has important significance in the aspects of client behavior insights and value change.
In the prior art, because the newly added user has less interaction relationship, the phenomenon of cold start can be generated, and the relationship between the newly added user and other users cannot be identified.
Disclosure of Invention
The embodiment of the invention provides a method, a device and equipment for acquiring a user relationship interest characteristic diagram and a computer readable storage medium, which can accurately reflect the relationship among users and the similarity of interest characteristics among users.
In a first aspect, an embodiment of the present invention provides a method for obtaining a user relationship interest feature map, where the method includes: acquiring communication data of a plurality of users in a target area; generating a user relation graph according to communication data of a plurality of users, an interest area set of each user in the plurality of users and an interest area set of each communication object of each user, wherein the interest area set comprises at least one interest area, and the interest area is a space-time position area with semantic information; generating a user interest feature map according to the interest feature vector of each user and the interest feature vector of each communication object of each user, wherein the interest feature vectors are obtained based on the interest areas; and generating a user relation interest characteristic diagram according to the user relation diagram and the user interest characteristic diagram.
In some implementations of the first aspect, generating the user relationship graph from the communication data of the plurality of users, the set of interest areas of each of the plurality of users, and the set of interest areas of each of the communication objects of each of the users includes: determining the communication relation of each user in the plurality of users according to the communication data of the plurality of users; determining interest area overlap ratio between each user and each corresponding communication object according to the interest area set of each user and the interest area set of each communication object of each user; and obtaining a user relation graph according to the communication relation of each user and the interest area contact ratio between each user and each corresponding communication object.
In some implementations of the first aspect, determining the communication relationship for each of the plurality of users from the communication data of the plurality of users includes: determining the communication frequency, the communication time length and the communication times between each user in the plurality of users and each corresponding communication object according to the communication data of the plurality of users; determining a communication index between each user and each corresponding communication object according to the communication frequency, the communication time length and the communication frequency between each user and each corresponding communication object; and determining the communication relation of each user according to the communication index between each user and each corresponding communication object.
In some implementations of the first aspect, determining the communication relationship of each user according to the communication index between each user and each corresponding communication object includes: determining the communication relation between each user and each corresponding communication object according to the communication index between each user and each corresponding communication object; and eliminating a temporary relation in the communication relation between each user and each corresponding communication object to obtain the communication relation of each user, wherein the temporary relation is determined based on the communication time length, the communication frequency and the calling communication ratio between each user and each corresponding communication object.
In some implementations of the first aspect, generating the user interest feature map according to the interest feature vector of each user and the interest feature vector of each communication object of each user includes: and determining the interest feature similarity between each user and each corresponding communication object according to the interest feature vector of each user and the interest feature vector of each communication object of each user to obtain a user interest feature map.
In some implementations of the first aspect, generating the user relationship interest feature map according to the user relationship map and the user interest feature map includes: and combining the user relation graph and the user interest characteristic graph based on a preset rule to obtain the user relation interest characteristic graph.
In some implementation manners of the first aspect, merging the user relationship graph and the user interest feature graph based on a preset rule to obtain the user relationship interest feature graph includes: and determining the weight of the relation interest characteristic edge in the user relation interest characteristic graph according to the weight of the relation edge in the user relation graph and the weight of the interest characteristic edge in the user interest characteristic graph to obtain the user relation interest characteristic graph.
In a second aspect, an embodiment of the present invention provides an apparatus for obtaining a user relationship interest feature map, where the apparatus includes: the acquisition module is used for acquiring communication data of a plurality of users in a target area; the generating module is used for generating a user relation graph according to communication data of a plurality of users, an interest area set of each user in the plurality of users and an interest area set of each communication object of each user, wherein the interest area set comprises at least one interest area, and the interest area is a space-time position area with semantic information; the generating module is further used for generating a user interest feature map according to the interest feature vector of each user and the interest feature vector of each communication object of each user, wherein the interest feature vectors are obtained based on the interest areas; the generating module is further used for generating a user relation interest characteristic diagram according to the user relation diagram and the user interest characteristic diagram.
In some implementations of the second aspect, the generating module is specifically configured to: determining the communication relation of each user in the plurality of users according to the communication data of the plurality of users; determining interest area overlap ratio between each user and each corresponding communication object according to the interest area set of each user and the interest area set of each communication object of each user; and obtaining a user relation graph according to the communication relation of each user and the interest area contact ratio between each user and each corresponding communication object.
In some implementations of the second aspect, the generating module is specifically configured to: determining the communication frequency, the communication time length and the communication times between each user in the plurality of users and each corresponding communication object according to the communication data of the plurality of users; determining a communication index between each user and each corresponding communication object according to the communication frequency, the communication time length and the communication frequency between each user and each corresponding communication object; and determining the communication relation of each user according to the communication index between each user and each corresponding communication object.
In some implementations of the second aspect, the generating module is specifically configured to: determining the communication relation between each user and each corresponding communication object according to the communication index between each user and each corresponding communication object; and eliminating a temporary relation in the communication relation between each user and each corresponding communication object to obtain the communication relation of each user, wherein the temporary relation is determined based on the communication time length, the communication frequency and the calling communication ratio between each user and each corresponding communication object.
In some implementations of the second aspect, the generating module is specifically configured to: and determining the interest feature similarity between each user and each corresponding communication object according to the interest feature vector of each user and the interest feature vector of each communication object of each user to obtain a user interest feature map.
In some implementations of the second aspect, the generating module is specifically configured to: and combining the user relation graph and the user interest characteristic graph based on a preset rule to obtain the user relation interest characteristic graph.
In some implementations of the second aspect, the generating module is specifically configured to: and determining the weight of the relation interest characteristic edge in the user relation interest characteristic graph according to the weight of the relation edge in the user relation graph and the weight of the interest characteristic edge in the user interest characteristic graph to obtain the user relation interest characteristic graph.
In a third aspect, an embodiment of the present invention provides an apparatus for acquiring a user relationship interest feature map, where the apparatus includes: a processor and a memory storing computer program instructions; the processor, when executing the computer program instructions, implements the method for obtaining a user relationship interest feature map described in the first aspect or any of the realizable manners of the first aspect.
In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, where computer program instructions are stored on the computer-readable storage medium, and when the computer program instructions are executed by a processor, the method for acquiring a user relationship interest feature map in the first aspect or any of the realizable manners of the first aspect is implemented.
According to the method, the device, the equipment and the computer readable storage medium for acquiring the user relation interest characteristic graph, provided by the embodiment of the invention, the user relation graph is generated according to the communication data of the user and the interest area sets of the user and the communication object, the user interest characteristic graph is generated according to the interest characteristic vectors of the user and the communication object, and the user relation interest characteristic graph is generated according to the user relation graph and the user interest characteristic graph, so that the relation among users and the similarity of interest characteristics among users can be accurately reflected, the cold start phenomenon is avoided, and accurate data basis is provided for subsequent operations such as user group division, marketing and the like.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required to be used in the embodiments of the present invention will be briefly described below, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic flowchart of a method for acquiring a user relationship interest characteristic diagram according to an embodiment of the present invention;
fig. 2 is a schematic flowchart of another method for acquiring a user relationship interest characteristic diagram according to an embodiment of the present invention;
FIG. 3 is a user relationship diagram provided by an embodiment of the present invention;
FIG. 4 is a user interest feature diagram provided by an embodiment of the present invention;
FIG. 5 is a user relationship interest characteristic diagram provided in an embodiment of the present invention;
FIG. 6 is a schematic diagram of a user relationship interest feature matrix according to an embodiment of the present invention;
fig. 7 is a schematic structural diagram of an apparatus for obtaining a user relationship interest characteristic diagram according to an embodiment of the present invention;
fig. 8 is a schematic structural diagram of an apparatus for acquiring a user relationship interest characteristic diagram according to an embodiment of the present invention.
Detailed Description
Features and exemplary embodiments of various aspects of the present invention will be described in detail below, and in order to make objects, technical solutions and advantages of the present invention more apparent, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not to be construed as limiting the invention. It will be apparent to one skilled in the art that the present invention may be practiced without some of these specific details. The following description of the embodiments is merely intended to provide a better understanding of the present invention by illustrating examples of the present invention.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The term "and/or" herein is merely an association describing an associated object, meaning that three relationships may exist, e.g., a and/or B, may mean: a exists alone, A and B exist simultaneously, and B exists alone.
With the development of mobile internet and big data technology, data of operators are gradually complicated, customer requirements are diversified, traditional operation ideas cannot meet competitive requirements, the business is required to be centered, the operation is turned to the customer, the customer characteristics are accurately described by constructing a mature and complete customer label system, all-round analysis and understanding of the customer requirements are achieved, differentiated information service is provided for the customers, and customer insight value is improved.
However, in the current scheme, because the newly added user has fewer interaction relationships, a cold start phenomenon occurs, and the relationship between the newly added user and other users cannot be identified.
In view of the above, embodiments of the present invention provide a method, an apparatus, a device, and a computer-readable storage medium for obtaining a user relationship interest feature map, where a user relationship interest feature map is generated according to communication data of a user and interest region sets of the user and a communication object, a user interest feature map is generated according to interest feature vectors of the user and the communication object, and a user relationship interest feature map is generated according to the user relationship map and the user interest feature map, so that a relationship between users and similarity of interest features between users can be accurately reflected, a cold start phenomenon is avoided, and an accurate data basis is provided for subsequent operations such as user group division and marketing.
The following describes a method for acquiring a user relationship interest characteristic diagram according to an embodiment of the present invention with reference to the accompanying drawings.
Fig. 1 is a schematic flowchart of a method for acquiring a user relationship interest characteristic diagram according to an embodiment of the present invention. As shown in fig. 1, the method 100 for obtaining a user relationship interest feature map may include S110 to S140.
S110, communication data of a plurality of users in the target area are obtained.
Specifically, the call data of the user with different opposite end users every day can be collected from the voice lists of the users in the target area as the communication data of the users. Alternatively, the target area may be flexibly adjusted according to actual conditions, for example, it may be province, city, county, etc.
A subscriber may be identified by an international Mobile Station Integrated Service Digital Network (MSISDN), where the MSISDN is a number that uniquely identifies the Mobile subscriber in a public telephone Network (pstn) numbering plan, and in some embodiments, is also referred to as the Mobile subscriber number.
As an example, the MSISDN may include the following components: CC + NDC + SN, wherein CC (country) is a country code, NDC (national Destination code) is a domestic Destination address code, which can also be a network access number, and SN is a user number.
As a specific example, the MSISDN is "86 +134+ 11111111", where 86 denotes the country code of china, 134 denotes the domestic destination address code, and 11111111 denotes the subscriber number, and the country code CC is removed from the MSISDN, so that the domestic identity number, i.e., the mobile phone number, of the mobile station can be obtained.
And S120, generating a user relation graph according to the communication data of the plurality of users, the interest area set of each user in the plurality of users and the interest area set of each communication object of each user.
First, the communication relationship of each of the plurality of users may be determined from the communication data of the plurality of users. Specifically, the communication frequency, the communication duration and the communication frequency between each of the plurality of users and each of the corresponding communication objects may be determined according to the communication data of the plurality of users, the communication index between each of the users and each of the corresponding communication objects may be determined according to the communication frequency, the communication duration and the communication frequency between each of the users and each of the corresponding communication objects, and further, the communication relationship between each of the users may be determined according to the communication index between each of the users and each of the corresponding communication objects. Communication relation can be generated when communication behaviors exist among users, and the communication index can measure the strength of the communication relation. It can be understood that the communication objects refer to other users who have communication behaviors with the user, and each communication object corresponding to the user refers to all other users who communicate with the user.
Secondly, the interest region overlap ratio between each user and each corresponding communication object can be determined according to the interest region set of each user and the interest region set of each communication object of each user. The interest area set comprises at least one interest area, the interest area is a space-time position area with semantic information, and the interest area is provided with start time, end time, longitude and latitude information and the like. Alternatively, the start time and the end time of the interest area may be the start time and the end time of the user entering the interest area, respectively.
As an example, when the start time, the end time, and the latitude and longitude information of the region of interest in the region of interest set of each user and the region of interest in the region of interest set of each communication object corresponding to each user coincide with each other, a region of interest coincidence between each user and each corresponding communication object may be calculated.
As an example, the position data of the user may be preprocessed according to a preset time threshold and a preset distance threshold to obtain quasi-stop points, and the "noise points" in the stop point set may be eliminated by using the acceleration rate, the stop rate, and the angle conversion rate as the quasi-stop point purification conditions to obtain the stop point set. According to the dwell point set, performing density clustering on the historical dwell point set of the user, extracting the interest region of the user by using the density value of the unit region of the dwell point and the limitation of reachable density, and simultaneously performing interest region abnormal point removing operation on the interest region by using the local reachable density and the local noise point of the interest region to obtain the interest region of the user accurately, thereby obtaining the interest region set of the user.
Then, a user relationship graph can be obtained according to the communication relationship of each user and the interest area overlap ratio between each user and each corresponding communication object. That is to say, the user relationship graph can be obtained according to the communication index in the communication relationship of each user and the interest area overlap ratio between each user and each corresponding communication object. The communication index and the interest area contact degree can be used for measuring the strength of the user relationship.
S130, generating a user interest feature map according to the interest feature vector of each user and the interest feature vector of each communication object of each user.
Specifically, the interest feature similarity between each user and each corresponding communication object may be determined according to the interest feature vector of each user and the interest feature vector of each communication object of each user, so as to obtain a user interest feature map. The interest feature vector is obtained based on the interest region, and the similarity of the interest features can be used for measuring the similarity of the interest features among users.
As one example, semantic mining of user location may be performed using a user's region of interest. The interest area is firstly divided into different topics including food, shopping, rest, medical treatment, sports, entertainment, scenic spots, traffic and the like, and all places of daily life of the user are covered. Secondly, extracting the topic places of the stop points through an Application Programming Interface (API) of the map and forming interest feature vectors of the user to the topics. And finally, normalizing the interest value of the user on the theme to be between [0 and 1], wherein the larger the value is, the stronger the interest on the theme is, and finally obtaining the interest characteristic vector of the user.
And S140, generating a user relation interest characteristic diagram according to the user relation diagram and the user interest characteristic diagram.
Specifically, the user relationship graph and the user interest characteristic graph are combined based on a preset rule to obtain the user relationship interest characteristic graph. Optionally, the weight of the relation interest feature edge in the user relation interest feature map may be determined according to the weight of the relation edge in the user relation map and the weight of the interest feature edge in the user interest feature map, so as to obtain the user relation interest feature map.
The weight of the relationship edge in the user relationship graph may be determined by the communication index in the communication relationship of each user and the interest region overlap ratio between each user and each corresponding communication object, and the weight of the interest feature edge in the user interest feature graph may be the interest feature similarity between each user and each corresponding communication object.
According to the method for acquiring the user relation interest characteristic diagram, the communication data of the user is acquired, the user relation diagram is generated according to the communication data of the user and the interest area sets of the user and the communication object, the user interest characteristic diagram is generated according to the interest characteristic vectors of the user and the communication object, and the user relation interest characteristic diagram is generated according to the user relation diagram and the user interest characteristic diagram, so that the relation among users and the similarity of interest characteristics among users can be accurately reflected, the cold start phenomenon is avoided, and accurate data basis is provided for subsequent operations such as user group division, marketing and the like.
In some embodiments, the communication relationship between each user and each corresponding communication object may be determined according to a communication index between each user and each corresponding communication object. And eliminating the temporary relation in the communication relation between each user and each corresponding communication object to obtain the communication relation of each user. The temporary relationship is determined based on the communication time length, the communication frequency and the calling communication ratio between each user and each corresponding communication object. As an example, the temporary relationship is mostly a temporary relationship between users that is not stable and tight, such as take-out, express delivery, marketing, and the like.
As a specific embodiment, based on the voice lists of the multiple users, the communication frequency, the communication duration, the communication times, the calling communication duty ratio, and the like between each of the multiple users and each corresponding communication object may be obtained, the communication index between each of the multiple users and each corresponding communication object may be calculated, and the size of the effective interaction circle may be determined according to the voice consumption hierarchy between each of the multiple users and each corresponding communication object, so as to extract the effective interaction circle of the user, that is, the final basic interaction circle of the user. It is understood that the basic circle of interaction refers to the communication relationship between each user and each corresponding communication object.
At this time, a provisional relationship among the communication relationships between each user and each corresponding communication object may be eliminated. The reason is that two objects with frequent calls at the same time may be a couple or a relativity or a temporary working relationship (such as take-away meal), and the meanings of the relativity and the sparseness of the two relations between the objects are completely different, and the temporary relation should be eliminated to avoid influencing the clustering precision, and should be eliminated to avoid influencing the clustering precision.
Fig. 2 is a schematic flow chart of another method for acquiring a user relationship interest characteristic diagram according to an embodiment of the present invention, which is specifically described below with reference to fig. 2.
First, the voice lists of a plurality of users in the target area can be extracted, the communication information between each user and different opposite-end users every day is collected from the voice lists of the plurality of users to serve as the communication data of the plurality of users, and the communication frequency between each user and each corresponding communication object is calculated. Here, the communication frequency between each user and each corresponding communication partner can be calculated according to formula (1).
call_freq＝x_1*Dn/C+y_1*Wn/W+z_1*Pn/P (1)
Wherein call _ freq represents the communication frequency between the user and the communication object, C represents the number of days of the statistic month between the user and the communication object, and Dn represents the number of communication days of the statistic month between the user and the communication object; w represents the maximum number of weeks of the statistical month between the user and the communication object, and Wn represents the number of communication weeks of the statistical month between the user and the communication object; p represents 3 days, Pn represents the number of communication days of the statistical month between the user and the communication object, x _1, y _1, z _1 are weight indexes, and x _1+ y _1+ z _1 is 1. Here, the statistical month indicates a statistical month in which call information between the user and the communication destination is counted in a month cycle. As can be seen, C, Dn, W, Wn, Pn can be obtained based on the voice list.
Next, a communication index between each user and each corresponding communication object is calculated. Here, the communication index between each user and each corresponding communication object may be calculated according to formula (2).
Call_Exp＝x_2*(call_freq-min(call_freq))/(max(call_freq)-min(call_freq))+y_2*(call_duar-min(call_dura))/(max(call_dura)-min(call_duar))+z_2*(call_counts-min(call_counts))/(max(call_counts)-min(call_counts)) (2)
Wherein, Call _ Exp represents a communication index between a user and a communication object, Call _ freq is a communication frequency between the user and the communication object, Call _ counts is a communication frequency between the user and the communication object, Call _ bear is a communication time length between the user and the communication object, x _2, y _2, z _2 are weight indexes, and x _2+ y _2+ z _2 is 1. It is understood that, here, the month is taken as a statistical period, and the statistical term may be only within one month or may span multiple months. It is known that call _ counts, call _ bear may be obtained based on the voice list.
Then, the communication relation between each user and each corresponding communication object is determined according to the communication index between each user and each corresponding communication object. And further eliminating the temporary relation in the communication relation between each user and each corresponding communication object to obtain the communication relation of each user. The temporary relationship is characterized by long communication time, high communication frequency, high calling communication proportion and the like, so that the temporary relationship can be determined based on the communication time, the communication frequency and the calling communication proportion between each user and each corresponding communication object, and is eliminated.
And then, obtaining a user relation graph according to the communication relation of each user and the interest area overlap ratio between each user and each corresponding communication object. Specifically, when a user has both a stable communication relationship and appears at the same location at a certain time, it is illustrated that the user has a very stable and tight relationship. The start time, the end time, the latitude and longitude information of the interest area in the interest area set of each user and the interest area in the interest area set of each communication object corresponding to each user can be judged, if the information is overlapped, calculation can be carried out according to a formula (3), and the interest area overlap ratio between each user and each corresponding communication object is obtained.
Wherein, ContactRatio (V)i，Vj) Representing a user ViWith user VjRegion of interest overlap ratio IOP (V)i) Representing a user ViThe set of interest areas of IOP (V)j) Representing a user VjThe interest area set.
Then, a user-user relationship graph can be generated according to the communication relationship of each user and the interest area overlap ratio between each user and each corresponding communication object, where calculation can be performed according to formula (4) to obtain the weight of the relationship edge in the user relationship graph, so as to generate the user relationship graph.
E(Vi，Vj)＝a*CallExp(Vi，Vj)+b*ContactRatio(Vi，Vj) (4)
Wherein, E (V)i，Vj) Representing a user ViAnd VjThe value of the relationship between them. CallExp(Vi，Vj) Representing a user ViAnd VjIndex of communication between. and a + b is 1, and b is 0 if no communication action exists between users. For example, the generated user relationship diagram may be as shown in fig. 3, where fig. 3 is a user relationship diagram provided by an embodiment of the present invention. E (V)i，Vj) Can represent the user V in the user relation graphiAnd VjThe weight of the relationship edge between them, such as the weight of the line between two points in fig. 3.
Meanwhile, the interest feature similarity between each user and each corresponding communication object can be determined according to the interest feature vector of each user and the interest feature vector of each communication object of each user, and then a user interest feature map can be obtained. Wherein the interest feature vector can be utilizedVU＝＜Deu，Shu，...，Enu，ScuThe expression, each tuple in the interest feature vector represents the interest degree label of the user to a subject, and the interest feature vector can be expressed as<Food, shopping, …, entertainment and scenic spot>I.e. formally expressed as < De, Sh. Therefore, most of the subject places closely related to the life of people in the real world can be covered by the processing, most of representative behaviors in the daily life of people can be mapped, and the interest and hobby characteristics of the users can be objectively reflected. Here, the cosine theorem, that is, the formula (5), may be used to perform calculation to obtain the weight of the interest feature edge in the user interest feature map, that is, the similarity of the interest feature, so as to generate the user relationship map.
Wherein VU_iAnd VU_jFor user Vi、VjIs given by the interest feature vector, | VU_iI and I VU_j| represents user Vi、VjThe number of interest features of the feature vector of (1), S (V)i，Vj) Representing a user Vi、VjThe similarity of the interest features is in the range of [0,1]]Wherein S (V)i，Vj) Closer to 1 indicates user ViWith user VjThe higher the similarity of the interest features, the closer to 0, the lower the similarity of the user and the user interest features. For example, the generated user interest feature map may be as shown in fig. 4, where fig. 4 is a user interest feature map provided by an embodiment of the present invention. S (V)i，Vj) Can represent a user V in a user interest characteristic diagramiAnd VjThe weight of the interest feature edge in between, such as the weight of the line between two points in fig. 4.
And then, combining the user relation graph and the user interest characteristic graph based on a preset rule to obtain the user relation interest characteristic graph. The graph clustering operation of the user needs to measure the relationship graph and the interest characteristic graph of the user in a unified way, and the edges in the relationship graph and the interest characteristic graph of the user need to be combined based on a preset rule. The preset rule is as follows:
if, two users ViAnd VjThere are both relationship edges and interesting characteristic edges, and the weight of the relationship edge is E (V)i，Vj) The weight of the interest feature edge is S (V)i，Vj) Then, the weight C (V) of the combined relation interest feature edgei，Vj)＝a_2*S(Vi，Vj)+b_2*E(Vi，Vj) Wherein C (V)i，Vj) For user ViAnd VjThe relationship between them is the weight of the feature edge of interest. Wherein a _2+ b _2 is 1.
If, two users ViAnd VjThere is only a relation edge between them, and the weight of the relation edge is E (V)i，Vj) Then the combined relationship-weight C (V) of the interest feature edgei，Vj)＝b_2*E(Vi，Vj)。
If, two users ViAnd VjOnly interest feature edges exist between the relation edges, and the weight of the relation edges is S (V)i，Vj) Then the combined relationship-weight C (V) of the interest feature edgei，Vj)＝a_2*S(Vi，Vj)。
In this way, the user relationship graph and the user interest feature graph may be merged to obtain the user relationship interest feature graph, for example, the generated user interest feature graph may be as shown in fig. 5, where fig. 5 is a user relationship interest feature graph provided in the embodiment of the present invention. As shown in fig. 5, the dotted line may represent interest feature similarity between users, the solid line represents a relationship value between users, and the parameters a and b may be used to adjust the final weight of the relationship interest feature edge according to different scenarios, where the value a is higher if the relationship is emphasized, and the value b is higher otherwise. The user relationship interest feature map is converted into fig. 6, where fig. 6 is a schematic diagram of a user relationship interest feature matrix provided in an embodiment of the present invention, a value in the matrix represents a standard value of user interaction and interest, and a larger value indicates a tighter relationship between users, and vice versa.
Fig. 7 is a schematic structural diagram of an apparatus for obtaining a user relationship interest feature map according to an embodiment of the present invention, where the apparatus is applied to a monitoring system, and as shown in fig. 7, the apparatus 200 for obtaining a user relationship interest feature map may include: an obtaining module 210 and a generating module 220.
The obtaining module 210 is configured to obtain communication data of a plurality of users in a target area.
The generating module 220 is configured to generate a user relationship graph according to the communication data of the multiple users, the interest region set of each user in the multiple users, and the interest region set of each communication object of each user. The interest region set comprises at least one interest region, and the interest region is a space-time position region with semantic information.
The generating module 220 is further configured to generate a user interest feature map according to the interest feature vector of each user and the interest feature vector of each communication object of each user. Wherein the interest feature vector is obtained based on the region of interest.
The generating module 220 is further configured to generate a user relationship interest feature map according to the user relationship map and the user interest feature map.
In some embodiments, the generating module 220 is specifically configured to determine the communication relationship of each of the plurality of users according to the communication data of the plurality of users. And determining the interest area overlap ratio between each user and each corresponding communication object according to the interest area set of each user and the interest area set of each communication object of each user. And obtaining a user relation graph according to the communication relation of each user and the interest area contact ratio between each user and each corresponding communication object.
In some embodiments, the generating module 220 is specifically configured to determine, according to the communication data of the multiple users, a communication frequency, a communication duration, and a communication frequency between each of the multiple users and each of the corresponding communication objects. And determining the communication index between each user and each corresponding communication object according to the communication frequency, the communication time length and the communication frequency between each user and each corresponding communication object. And determining the communication relation of each user according to the communication index between each user and each corresponding communication object.
In some embodiments, the generating module 220 is specifically configured to determine the communication relationship between each user and each corresponding communication object according to the communication index between each user and each corresponding communication object. And eliminating a temporary relation in the communication relation between each user and each corresponding communication object to obtain the communication relation of each user, wherein the temporary relation is determined based on the communication time length, the communication frequency and the calling communication ratio between each user and each corresponding communication object.
In some embodiments, the generating module 220 is specifically configured to determine, according to the interest feature vector of each user and the interest feature vector of each communication object of each user, an interest feature similarity between each user and each corresponding communication object, so as to obtain a user interest feature map.
In some embodiments, the generating module 220 is specifically configured to combine the user relationship graph and the user interest feature graph based on a preset rule to obtain the user relationship interest feature graph.
In some embodiments, the generating module 220 is specifically configured to determine the weight of the relationship interest feature edge in the user relationship interest feature map according to the weight of the relationship edge in the user relationship map and the weight of the interest feature edge in the user interest feature map, so as to obtain the user relationship interest feature map.
According to the device for acquiring the user relation interest characteristic diagram, the user relation diagram is generated according to the communication data of the user and the interest area set of the user and the communication object, the user interest characteristic diagram is generated according to the interest characteristic vectors of the user and the communication object, and the user relation interest characteristic diagram is generated according to the user relation diagram and the user interest characteristic diagram, so that the relation among users and the similarity of interest characteristics among users can be accurately reflected, the cold start phenomenon is avoided, and accurate data basis is provided for subsequent operations such as user group division, marketing and the like.
It can be understood that the apparatus 200 for obtaining a user relationship interest feature map according to the embodiment of the present invention may correspond to an execution main body of the method for obtaining a user relationship interest feature map in fig. 1 according to the embodiment of the present invention, and specific details of operations and/or functions of each module/unit of the apparatus 200 for obtaining a user relationship interest feature map may refer to the description of the corresponding part in the method for obtaining a user relationship interest feature map in fig. 1 according to the embodiment of the present invention, and are not described herein again for brevity.
Fig. 8 is a schematic diagram of a hardware structure of an apparatus for acquiring a user relationship interest characteristic diagram according to an embodiment of the present invention.
As shown in fig. 8, the acquiring device 300 of the user relationship interest feature map in the present embodiment includes an input device 301, an input interface 302, a central processor 303, a memory 304, an output interface 305, and an output device 306. The input interface 302, the central processing unit 303, the memory 304, and the output interface 305 are connected to each other through a bus 310, and the input device 301 and the output device 306 are connected to the bus 310 through the input interface 302 and the output interface 305, respectively, and further connected to other components of the device 300 for acquiring a user relationship interest characteristic diagram.
Specifically, the input device 301 receives input information from the outside and transmits the input information to the central processor 303 through the input interface 302; central processor 303 processes the input information based on computer-executable instructions stored in memory 304 to generate output information, stores the output information temporarily or permanently in memory 304, and then transmits the output information to output device 306 through output interface 305; the output device 306 outputs the output information to the outside of the user relation interest feature map obtaining device 300 for use by the user.
In one embodiment, the apparatus 300 for obtaining a user relationship interest feature map shown in fig. 8 includes: a memory 304 for storing programs; the processor 303 is configured to execute a program stored in the memory to execute the method for obtaining the user relationship interest characteristic diagram according to the embodiment shown in fig. 1.
An embodiment of the present invention further provides a computer-readable storage medium, where the computer-readable storage medium has computer program instructions stored thereon; the computer program instructions, when executed by a processor, implement the method for obtaining a user relationship interest feature map provided by the embodiment shown in fig. 1.
It is to be understood that the invention is not limited to the specific arrangements and instrumentality described above and shown in the drawings. A detailed description of known methods is omitted herein for the sake of brevity. In the above embodiments, several specific steps are described and shown as examples. However, the method processes of the present invention are not limited to the specific steps described and illustrated, and those skilled in the art can make various changes, modifications and additions or change the order between the steps after comprehending the spirit of the present invention.
The functional blocks shown in the above-described structural block diagrams may be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, it may be, for example, an electronic Circuit, an Application Specific Integrated Circuit (ASIC), suitable firmware, plug-in, function card, or the like. When implemented in software, the elements of the invention are the programs or code segments used to perform the required tasks. The program or code segments may be stored in a machine-readable medium or transmitted by a data signal carried in a carrier wave over a transmission medium or a communication link. A "machine-readable medium" may include any medium that can store or transfer information. Examples of machine-readable media include electronic circuits, semiconductor Memory devices, Read-Only memories (ROMs), flash memories, erasable ROMs (eroms), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, Radio Frequency (RF) links, and so forth. The code segments may be downloaded via computer networks such as the internet, intranet, etc.
It should also be noted that the exemplary embodiments mentioned in this patent describe some methods or systems based on a series of steps or devices. However, the present invention is not limited to the order of the above-described steps, that is, the steps may be performed in the order mentioned in the embodiments, may be performed in an order different from the order in the embodiments, or may be performed simultaneously.
As described above, only the specific embodiments of the present invention are provided, and it can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the system, the module and the unit described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again. It should be understood that the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive various equivalent modifications or substitutions within the technical scope of the present invention, and these modifications or substitutions should be covered within the scope of the present invention.
Claims (13)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911402394.2A CN111160977A (en) | 2019-12-31 | 2019-12-31 | Method, device, device and medium for acquiring user relationship interest feature map |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911402394.2A CN111160977A (en) | 2019-12-31 | 2019-12-31 | Method, device, device and medium for acquiring user relationship interest feature map |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111160977A true CN111160977A (en) | 2020-05-15 |
Family
ID=70559402
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911402394.2A Pending CN111160977A (en) | 2019-12-31 | 2019-12-31 | Method, device, device and medium for acquiring user relationship interest feature map |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111160977A (en) |
Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090176509A1 (en) * | 2008-01-04 | 2009-07-09 | Davis Marc E | Interest mapping system |
| JP2010218376A (en) * | 2009-03-18 | 2010-09-30 | Nomura Research Institute Ltd | User interest genre analysis system |
| CN103198480A (en) * | 2013-04-02 | 2013-07-10 | 西安电子科技大学 | Remote sensing image change detection method based on area and Kmeans clustering |
| JP2013186809A (en) * | 2012-03-09 | 2013-09-19 | Kddi Corp | Recommend device, recommend method and program |
| US20160179598A1 (en) * | 2014-12-17 | 2016-06-23 | Alcatel-Lucent Usa, Inc. | System and method of visualizing historical event correlations in a data center |
| CN106228371A (en) * | 2016-07-18 | 2016-12-14 | 南京坦道信息科技有限公司 | A kind of social network analysis based on the ultra-large user associating frequency and associate index and family relation recognizer |
| CN106875276A (en) * | 2016-12-30 | 2017-06-20 | 广州市申迪计算机系统有限公司 | A kind of communication user social circle generation method and system |
| WO2017133007A1 (en) * | 2016-02-05 | 2017-08-10 | Hewlett Packard Enterprise Development Lp | User interest and relationship determination |
| US20170249325A1 (en) * | 2016-02-26 | 2017-08-31 | Microsoft Technology Licensing, Llc | Proactive favorite leisure interest identification for personalized experiences |
| CN107220316A (en) * | 2017-05-17 | 2017-09-29 | 华为机器有限公司 | Communication data analysis method and device |
| CN108268877A (en) * | 2016-12-30 | 2018-07-10 | 中国移动通信集团黑龙江有限公司 | A kind of method and apparatus for identifying target terminal |
| CN108319628A (en) * | 2017-02-22 | 2018-07-24 | 腾讯科技（深圳）有限公司 | A kind of user interest determines method and device |
| US20190197427A1 (en) * | 2017-12-22 | 2019-06-27 | Samsung Electronics Co., Ltd. | Device and method for recommending contact information |
| CN110020178A (en) * | 2017-12-30 | 2019-07-16 | 中国移动通信集团辽宁有限公司 | Point of interest recognition methods, device, equipment and storage medium |
| CN110515981A (en) * | 2018-05-21 | 2019-11-29 | 国家计算机网络与信息安全管理中心 | A kind of user identification method and device based on space-time trajectory |
| CN110555164A (en) * | 2019-07-23 | 2019-12-10 | 平安科技（深圳）有限公司 | generation method and device of group interest tag, computer equipment and storage medium |
-
2019
- 2019-12-31 CN CN201911402394.2A patent/CN111160977A/en active Pending
Patent Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090176509A1 (en) * | 2008-01-04 | 2009-07-09 | Davis Marc E | Interest mapping system |
| JP2010218376A (en) * | 2009-03-18 | 2010-09-30 | Nomura Research Institute Ltd | User interest genre analysis system |
| JP2013186809A (en) * | 2012-03-09 | 2013-09-19 | Kddi Corp | Recommend device, recommend method and program |
| CN103198480A (en) * | 2013-04-02 | 2013-07-10 | 西安电子科技大学 | Remote sensing image change detection method based on area and Kmeans clustering |
| US20160179598A1 (en) * | 2014-12-17 | 2016-06-23 | Alcatel-Lucent Usa, Inc. | System and method of visualizing historical event correlations in a data center |
| WO2017133007A1 (en) * | 2016-02-05 | 2017-08-10 | Hewlett Packard Enterprise Development Lp | User interest and relationship determination |
| US20170249325A1 (en) * | 2016-02-26 | 2017-08-31 | Microsoft Technology Licensing, Llc | Proactive favorite leisure interest identification for personalized experiences |
| CN106228371A (en) * | 2016-07-18 | 2016-12-14 | 南京坦道信息科技有限公司 | A kind of social network analysis based on the ultra-large user associating frequency and associate index and family relation recognizer |
| CN106875276A (en) * | 2016-12-30 | 2017-06-20 | 广州市申迪计算机系统有限公司 | A kind of communication user social circle generation method and system |
| CN108268877A (en) * | 2016-12-30 | 2018-07-10 | 中国移动通信集团黑龙江有限公司 | A kind of method and apparatus for identifying target terminal |
| CN108319628A (en) * | 2017-02-22 | 2018-07-24 | 腾讯科技（深圳）有限公司 | A kind of user interest determines method and device |
| CN107220316A (en) * | 2017-05-17 | 2017-09-29 | 华为机器有限公司 | Communication data analysis method and device |
| US20190197427A1 (en) * | 2017-12-22 | 2019-06-27 | Samsung Electronics Co., Ltd. | Device and method for recommending contact information |
| CN110020178A (en) * | 2017-12-30 | 2019-07-16 | 中国移动通信集团辽宁有限公司 | Point of interest recognition methods, device, equipment and storage medium |
| CN110515981A (en) * | 2018-05-21 | 2019-11-29 | 国家计算机网络与信息安全管理中心 | A kind of user identification method and device based on space-time trajectory |
| CN110555164A (en) * | 2019-07-23 | 2019-12-10 | 平安科技（深圳）有限公司 | generation method and device of group interest tag, computer equipment and storage medium |
Non-Patent Citations (5)
| Title |
|---|
| YING LI ET AL.: "Seed selection for data offloading based on socaal and interest graphs", 《CMC》 * |
| YU QIN ET AL.: "Approaches to Detect Micro-Blog User Interest Communities Through the Integration of Explicit User Relationship and Implicit Topic Relations", 《SOCIAL MEDIA PROCESSING》 * |
| 张红玉: "基于社交网络的好友推荐方法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 文哥的学习日记: "利用社交网络数据进行推荐", 《HTTP://EVENTS.JIANSHU.IO/P/6D5CBC329AF0》 * |
| 曾瑞: "移动定位社交服务中相似用户发现方法的研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110337059B (en) | Analysis algorithm, server and network system for family relationship of user | |
| CN107948928B (en) | Empirical expert determination and problem routing system and method | |
| CN104636439B (en) | A kind of method and device for analyzing user's social relationships | |
| US20150278546A1 (en) | Information disclosure system, information disclosure server, communication terminal, information disclosing method, and non-transitory computer-readable medium | |
| CN108833453A (en) | A kind of method and apparatus determined using account | |
| CN105898085B (en) | Harass recognition methods and the device of communications account | |
| US20200019994A1 (en) | Systems and methods for using spatial and temporal analysis to associate data sources with mobile devices | |
| CN109543734A (en) | User portrait method and device, storage medium | |
| US20240334159A1 (en) | Systems and methods for using spatial and temporal analysis to associate data sources with mobile devices | |
| CN112752256A (en) | Client portrait label determination method, device, equipment and storage medium | |
| CN111400520B (en) | Face recognition library construction method, face payment method, device and system | |
| CN111132027A (en) | Scene recognition network graph drawing method, scene recognition method and device | |
| CN112307075B (en) | User relationship identification method and device | |
| EP2015101A2 (en) | System and process for enabling location queries for locating a user of a mobile terminal for mobile networks which adds dimensions of time, are, probability and distance beween users | |
| CN110677269B (en) | Method and device for determining communication user relationship and computer readable storage medium | |
| CN113163324A (en) | Household user identification method and module | |
| CN114390550B (en) | Network type identification method, related device, equipment and storage medium | |
| CN108513303A (en) | The abnormality monitoring method and device of jack per line terminal | |
| CN111160977A (en) | Method, device, device and medium for acquiring user relationship interest feature map | |
| CN112235778B (en) | Group Member Determination Method and Server | |
| CN115348544B (en) | Different network user positioning method, terminal equipment and storage medium | |
| KR101928822B1 (en) | System and method for computing a user's trust value of unknown device in IoT | |
| Landau et al. | Reversing Privacy Risks: Strict Limitations on the Use of Communications Metadata and Telemetry Information | |
| CN113378073B (en) | User relationship identification method and device | |
| KR101612797B1 (en) | Providing Method of Personal Connection Information Using Smart Phone Address Book |
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: 20200515 |