CN110209704B - User matching method and device - Google Patents
User matching method and device Download PDFInfo
- Publication number
- CN110209704B CN110209704B CN201910336147.0A CN201910336147A CN110209704B CN 110209704 B CN110209704 B CN 110209704B CN 201910336147 A CN201910336147 A CN 201910336147A CN 110209704 B CN110209704 B CN 110209704B
- Authority
- CN
- China
- Prior art keywords
- user
- matching
- users
- calling
- gender
- 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.)
- Active
Links
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
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2462—Approximate or statistical queries
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/01—Social networking
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Probability & Statistics with Applications (AREA)
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Human Computer Interaction (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Mathematical Physics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- General Engineering & Computer Science (AREA)
- Fuzzy Systems (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a user matching method and equipment, wherein the method comprises the following steps: acquiring a user who initiates voice matching currently; screening calling users according to a first preset condition from users who currently initiate voice matching; acquiring the circular screening times of a target user when the calling user initiates a calling; selecting a set of users to be matched at least according to the target matching gender of the users in the matching pools corresponding to the circular screening times; sequencing the users to be matched in the user set to be matched according to the similarity with the calling user; and matching according to the sequence of the users to be matched. Both parties of the user who can realize matching have more common characteristics, so that the user can search for the user with similar characteristics without spending a large amount of time, and the possibility of establishing the social contact of strangers is greatly improved. A lot of time can be saved when a user establishes social contact, making it simple and efficient for strangers to establish social contact.
Description
Technical Field
The invention relates to the field of data mining, in particular to a user matching method and device.
Background
Social interaction refers to the interaction between people in the society, and is the consciousness of people in a certain way (tools) for transmitting information and communicating ideas so as to achieve various social activities with a certain purpose. In the modern times, changes in economic and social environments make interpersonal communication more important. Because people can only continuously interact with various personnel and communicate information, people can be enriched, developed and expanded continuously.
With the development of scientific technology and the application of internet resources in life, the communication between people is realized by means of the internet, and strangers can also realize social contact through the internet, so that the purposes of further developing and expanding the strangers are realized. For example, some internet platforms and services have appeared in the prior art that address stranger social services, such as searching for nearby people for online conversations, transmitting network drift bottles, and the like.
However, because the social activities published on the entire platform and the oriented user groups are on the sea level, most of the existing stranger social network platforms recommend strangers capable of performing matching chatting for users based on information such as regions, ages and the like, however, because the users do not know whether interests, hobbies and even three views of the users recommended by the platform are the same as or similar to themselves, the users find the social objects which cannot be accurately positioned to own intentions, even if the social objects of own intentions exist, the users may not be the social objects of opposite intentions, even if the matching is successful, normal social behaviors are difficult to establish due to different intentions or different three views of both parties, and at the moment, the users need to determine whether both parties are proper social objects through a large number of questions and communication, so that the social activities established among the strangers are complicated and inefficient.
Disclosure of Invention
In view of this, the present invention provides a user matching method to improve the probability and efficiency of social establishment of strangers. The matching method can comprise the following steps: acquiring a user who initiates voice matching currently; screening calling users according to a first preset condition from users who currently initiate voice matching; acquiring the circular screening times of a target user circularly screened when the calling user initiates a calling; selecting a set of users to be matched at least according to the target matching gender of the users in the matching pools corresponding to the circular screening times; sequencing the users to be matched in the user set to be matched according to the similarity with the calling user; and matching according to the sequence of the users to be matched.
Optionally, the screening the calling subscriber according to the first preset condition in the current subscriber initiating the voice matching includes: judging the gender of the user who initiates voice matching at present; when the gender of the user initiating voice matching currently is a first gender user, taking the user initiating voice matching currently as the calling user; when the gender of the user who initiates voice matching is a second gender user, acquiring a matching record of the user who initiates voice matching currently, and when the user who initiates voice matching currently does not have a matching successful record, taking the user who initiates voice matching currently as the calling user; or; and when the target matching gender of the user who initiates the voice matching is the second gender, acquiring the target matching gender of the user who initiates the voice matching, and when the target matching gender of the user who initiates the voice matching is the second gender, taking the user who initiates the voice matching as the calling user.
Optionally, the matching pool includes: the system comprises an active voice matching pool and a non-body matching pool, wherein the active voice matching pool is used for all users who are initiating voice matching, the non-body matching pool is used for initiating voice matching, and the historical matching times exceed the preset times; selecting a set of users to be matched at least according to the target matching gender of the users in the matching pools corresponding to the historical matching times respectively comprises: and judging whether the circular screening times are within a first preset range, and when the circular screening times are within the first preset range, selecting the target matching gender of the calling user from the active voice matching pool and selecting a user as the to-be-matched user set, wherein the user is a target shell with the calling user, and the shell is used for representing groups divided according to the relevance of user features.
Optionally, when the number of times of circular screening is within a second preset range, selecting a target gender-matched user of the calling user as the user set to be matched in the non-trunk matching pool, where a small value within the second preset range is greater than or equal to a maximum value within the first preset range.
Optionally, when the number of circular screening times is within a second preset range, the calling user is placed in the non-trunk matching pool.
Optionally, the obtaining of the current user initiating voice matching and the screening of the calling user according to the first preset condition in the current user initiating voice matching include: judging whether the user initiating the voice matching currently meets a preset matching condition or not; and when the user request meets the preset matching condition, performing matching timing.
Optionally, the matching according to the ranking of the users to be matched includes: searching for valid users in sequence; when the effective user is obtained, a calling party is initiated; and when the effective user is not obtained, repeatedly obtaining the circular screening times of the calling user, respectively selecting a set of users to be matched in a matching pool corresponding to the circular screening times at least according to the target matching gender of the users, and sequencing the users to be matched in the set of users to be matched according to the similarity with the calling user until the effective user is obtained or the matching timing reaches the preset time.
Optionally, before the obtaining the user currently initiating voice matching, the method further includes: acquiring user characteristic information, wherein the user characteristic information comprises at least one attribute characteristic information of a user, and the user attribute characteristic comprises a plurality of hierarchies; determining the hull of the user according to the user attribute and the hierarchy of the user attribute; respectively calculating the similar values of each category on different levels; calculating the association degree with other users according to the similarity; and selecting the user with the relevance larger than a preset value as the target hull of the current user.
Optionally, the user characteristic information comprises at least one behavior characteristic information of the user; the calculating the similarity between the users according to the characteristic information comprises the following steps: obtaining a user attribute vector according to the user attribute characteristics; obtaining a user behavior vector according to the user behavior characteristics; calculating a first distance between user attribute vectors and/or a second distance between user behavior vectors; and determining the similarity between the users according to the first distance and/or the second distance.
The present invention also provides a user matching device, including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the one processor to cause the at least one processor to perform the user matching method.
According to the user matching method and the user matching device, the calling user is screened from the users who initiate the voice matching according to a first preset condition; selecting a set of users to be matched in a matching pool corresponding to the circulating screening times at least according to the target matching gender of the users; sorting the users to be matched in the user set to be matched according to the similarity with the calling user; and matching according to the sequence of the users to be matched. The calling user can be screened firstly, the set to be matched is determined according to the matching times, the more determined target is used as the matching target of the current user, and the probability and the efficiency of social establishment of strangers can be improved.
According to the user matching method and the user matching device, the user characteristics are grouped according to the user characteristic association degree through the user characteristic information, the similarity between the users is calculated, and the target user which can be matched with the current user is searched in the group according to the user similarity to match the current user. The method comprises the steps of firstly determining a body set to which a target user belongs according to user characteristics, determining a user with higher relevance with a current user, matching the users according to the similarity of the user characteristics, and searching the user with higher similarity in the target body set of the current user as a matching target user of the current user by using the user characteristics because the relevance and the similarity are determined by both the users to be matched, so that the users with higher similarity in the target body set of the current user can be searched by using the user characteristics, the matched users have more common characteristics, the users can search the users with similar characteristics without spending a large amount of time, and the possibility of establishing strangers in a social contact mode is greatly improved. A lot of time can be saved when a user establishes social contact, making it simple and efficient for strangers to establish social contact. And better experience is brought to the user.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flow chart of a user matching method in an embodiment of the present invention;
FIG. 2 is a flowchart of another user matching method in an embodiment of the present invention
FIG. 3 is a diagram illustrating a virtual device structure of a user matching device according to an embodiment of the present invention;
fig. 4 is a schematic diagram of a user matching device in an embodiment of the present invention.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the accompanying drawings, and it should be understood that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In addition, the technical features involved in the different embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
The social network comprises a plurality of user sides and at least one server, and the user sides interact with each other through the server, wherein the interaction comprises instant messaging and non-instant messaging. For example, users can not only communicate with each other in real time through the server, but also view the published contents, such as user's personal homepage, published pictures, published text contents.
The invention provides a user matching method, wherein a plurality of user sides exist in a social network, each user side aims to search strangers meeting the intention of the user and meeting the intention of others to establish social contact. The method may be performed by a server or a cluster of servers in a social network, as shown in fig. 1, the method comprising the steps of:
s1, obtaining a user who initiates voice matching currently.
S2, screening calling users in the users who currently initiate voice matching according to a first preset condition. In this embodiment, the calling user is a user who can actively initiate matching, and in this embodiment, a user who is initiating voice matching may be first screened, for example, the user may be screened according to gender, specifically, the gender of the user who is currently initiating voice matching is determined; when the gender of the user who initiates voice matching is a first gender user, taking the user who initiates voice matching as a calling user; in this embodiment, the first gender may be determined according to the gender ratio of the online user, and in this embodiment, the first gender may be a female. When the gender of the user initiating the voice matching is a second gender user, acquiring a matching record of the user initiating the voice matching currently, and when the user initiating the voice matching currently has no matching success record, taking the user initiating the voice matching currently as a calling user; in this embodiment, the second gender is taken as a male as an example, when the user initiating the voice matching is a male and the user does not have a record of successful matching, in order to increase the matching success probability of the current user, in this embodiment, the male user may be taken as a calling user. In an optional embodiment, it may be further determined whether the user who is initiating voice matching is the calling user according to the target gender of the user who is initiating voice matching, specifically, when the gender of the user who is currently initiating voice matching is the second gender user, the target matching gender of the user who is currently initiating voice matching is obtained, and when the target matching gender of the user who is currently initiating voice matching is the second gender, that is, when the target matching gender of the male user is male, the user who is currently initiating voice matching may also be used as the calling user, so as to increase the matching success probability.
And S3, acquiring the circular screening times of the target user when the calling user of the calling user initiates the calling. In this embodiment, the number of times of circular screening for circularly screening the target user when the calling user initiates the calling may be one voice matching request initiated by each person, and may be at most circularly screened to a predetermined time.
And S4, selecting a set of users to be matched at least according to the target matching gender of the users in the matching pools corresponding to the circulating screening times. In a particular embodiment, the matching pool includes: the method comprises an active voice matching pool and a non-body matching pool, wherein the active voice matching pool is all users who are initiating voice matching, the non-body matching pool is all users who are initiating voice matching, the history matching times exceed preset times, specifically, whether the circular screening times are within a first preset range can be judged, when the circular screening times are within the first preset range, a target matching gender of a calling user is selected from the active voice matching pool, and a user who selects a body which is a target body with the calling user as a set of users to be matched is selected, the body is used for representing groups divided according to the relevance of user characteristics, and specifically, the definition of the body and the target body is introduced in detail in the following embodiments. In this embodiment, the first predetermined range may be 0 to 15 times. And when the matching times are less than or equal to 15 times, screening out users which are consistent with the target gender of the user and are mutually shells from the voice matching pool as a matching set.
And when the circular screening times are within a second preset range, selecting the target gender-matched users of the calling users as a user set to be matched in the non-shell matching pool, wherein the small value within the second preset range is greater than or equal to the maximum value within the first preset range. The second preset range may be more than 15 times. Namely, when the matching times are more than 15, acquiring a non-hull matching pool, and performing gender screening to serve as a user set to be matched. Meanwhile, the calling user is placed in the non-body matching pool to wait for the matching of other users, so that the matching probability of the user can be increased.
And S5, sequencing the users to be matched in the user set to be matched according to the similarity with the calling user.
And S6, matching according to the sequence of the users to be matched. Specifically, effective users are searched in sequence; when an effective user is obtained, a calling party is initiated; and when the valid user is not acquired, repeating S3-S6. And finishing the matching until the effective user is obtained or the matching timing reaches the preset time, and clearing the user matching state data after the matching is finished.
Screening calling users according to a first preset condition from users who currently initiate voice matching; selecting a set of users to be matched at least according to the target matching gender of the users in a matching pool corresponding to the circular screening times; sorting the users to be matched in the user set to be matched according to the similarity with the calling user; and matching according to the sequence of the users to be matched. The calling user can be screened firstly, the set to be matched is determined according to the matching times, the more determined target is used as the matching target of the current user, and the probability and the efficiency of social establishment of strangers can be improved.
Before performing voice matching, in this embodiment, the similarity between the user's body and the user may be calculated, so that accurate and fast matching can be performed. Specifically, as shown in fig. 2, before step S1, the method may further include:
and S10, acquiring user characteristic information. In this embodiment, the user characteristic information may include user attribute characteristic information and may also include user behavior characteristic information, where the user attribute characteristic may include a quantitative characteristic of the user, for example: the location, age, height, weight, income status of the user, the brand, price, etc. of the terminal used; user attribute features may also include virtual features of the user, such as the user's education, learning ability, social ability, wisdom, valentine, etc. Different features may each be attributed to one user. The behavior characteristics of the user may be referred to as including: the time period when the user is active, the time period when the user is frequently moving and the time period when the user is frequently doing, whether the user likes tourism, the place of the tourism and the like, and the behavior habits of the user. In this embodiment, the feature information of the user may be obtained by obtaining the information of the user written on the platform, or by obtaining the test questions performed by the user through psychological analysis, or by learning the habits of the user using the platform through machine learning. For example, the behavior characteristics of the user may be collected as a training sample of the machine learning model, the machine learning model is trained, and finally the behavior characteristics of the user are obtained according to the use habit of the user.
And S20, calculating the similarity among the users and the current user target hull set according to the characteristic information. In this embodiment, the body shell is used for representing groups of the user features divided according to the association degree. In this embodiment, the user attribute features may include a plurality of features, and the features may be divided into different groups according to a certain rule, where each group may represent a body shell. The division of the body case is described by way of example, for example, the attributes of the user may include an X attribute, a Y attribute, and a Z attribute, for example, information (brand, price, and the like) that may respectively represent a city, an age, and a mobile phone used, the X attribute may be, for example, the city of the user, and the city of the user may be divided into X levels according to a city level, for example, a first-line city, a second-line city, a third-line city, and the like. The Y attribute may be an age, and for example, the age may be divided into Y levels according to age group pairs, for example, it may be a teenager, a middle year, and the like. For convenience of description, in this embodiment, the X attribute may be denoted as D, the Y attribute may be denoted as a, and the Z attribute may be denoted as C, where the hull species expression may be: s = D | a | C, the number of types of the trunk may be: and x y z. In this embodiment, the users may be classified into which type of body shells the users belong to according to the attribute characteristics of the users, that is, the external characteristics of the users are more visually classified, so that the users may be primarily screened, for example, the grades of cities in which the two users are located are relatively different, the user a is in a first-line city, the user B is in a five-line city, the living habits or consumption appearances of the two users may be different, the body shells of the two users may be relatively different, or other attribute characteristics may be added, for example, the prices of the mobile phones of the user a and the user B may be relatively different, the habits of the two users using the mobile phones may be considered to be different, it may be determined that the differences of some characters are relatively large, and the body shells of the users may be relatively different. How to determine the target user's torso is described in detail below:
two users are taken as an example for explanation, wherein the body case of the user A is as follows: s 1 ＝D 1 |A 1 |C 1 (ii) a The body of the user B is S 2 ＝D 2 |A 2 |C 2 Calculating the similar values among the attribute features based on the hierarchy of the attribute features of the users, and calculating the association degree with other users according to the similar values; and selecting the user with the relevance degree larger than a preset value as a current user target body shell set. For convenience of description, in the present embodiment, a specific example is taken as an example for description, for example: the approximate values of the X attribute may be: d is a radical of s1s2 Wherein d is s1s2 Being a close value of the X attribute, D 1 Is the quantized value of the X attribute of user A, D 2 Taking the X attribute as the mobile phone used by the user, the price of the mobile phone used by the user A is higher or is a hot brand, and the price of the mobile phone used by the user B is higher or is a hot brand, so that the difference between the X attribute of the user A and the X attribute of the user B is smaller, and the similar value is higher; if the price of the mobile phone used by the user B is lower than that of the mobile phone of the user A or the brand popularity is poor, the attribute difference between the user A and the user B in X is considered to be moderate, and the similarity value is moderate. If all the mobile phones of the user B are low in price or the brand is cold, the attribute difference of the user A and the attribute of the user B on X is large, and the similarity value is small. In the embodiment, the price of the mobile phone can be graded according to the actual condition, and the brand popularity of the mobile phone can be graded according to the actual condition according to the sales volume of the mobile phone. The specific grading rule can be freely selected, and is not limited in this embodiment. In this embodiment, for a user with a large similarity, the association degree between two users can be considered to be large, and specific reference may be made to the following equation:
wherein d is s1s2 For the similar values of the X attribute, 9, 6, and 0 may respectively represent the similar value scores of the two users, which is only illustrated in this embodiment, and other values may also be used to represent different relevancy scores.
Similarly, the similarity value between the attribute features may be calculated based on the hierarchy of the attribute features of the users according to the category of the Y attribute, for example, the Y attribute may be the age of the user, the similarity value between the ages of the two users may be greater for the user a and the user B, and the similarity value outside the preset age may be smaller, and specifically, the following formula may be referred to:
a s1s2 being a close value of the X attribute, A 1 Is a quantified value of the Y attribute (which may be age) of user A, A 2 The quantized value of the Y attribute (which may be age) of user B, 6, 0 may represent the approximate value scores of two users, respectively, | A 1 -A 2 | is the age difference of the user, which is only illustrated in this embodiment, and other numerical values may also be used to represent different relevancy scores. That is, the user may be considered to have a large similarity value for the age difference of 3 years or less, and the user may have a small similarity value for 3 years or more.
Similarly, the similarity value between the attribute features may be calculated based on the hierarchy of the attribute features of the user according to the category of the Z attribute, for example, the Z attribute may be a city where the user is located, the city level between two users is the same, the similarity value may be larger for the user a and the user B, and the similarity value may be smaller if the city level has a larger difference, specifically, the following formula may be entered:
c s1s2 being a close value of the X attribute, C 1 Is the Z attribute of user A (can)At the city level), C 2 The quantized value of the Z attribute (which may be the level of the city) of the user B, 9, 6, and 0 may represent the similar value scores of the two users, respectively. For example, the user a and the user B are in the same city, which is only illustrated in this embodiment, and other numerical values may also be used to represent different relevancy scores. .
After the quantized values of the similarity values of the features of each user are calculated, the similarity value quantized values of the attribute features of the user may be integrated to calculate the association degree of the current user with respect to other users, for example, the similarity value quantized values of the attribute features may be added to obtain the association degree value between users, which may be specifically described in the following formula:
wherein v is s1s2 The quantized value of the association degree between the current user and other users is obtained, in this embodiment, after the association degree of the current user to other users is determined, whether the association degree is greater than a preset value is judged, and when the association degree is greater than the preset value, the other users are determined to be target hulls of the current user, the association degrees between the current user and multiple users can be respectively calculated, and a target hull set of the current user is determined.
In this embodiment, the similarity between users may also be calculated according to the feature information. In this embodiment, the user feature information may further include at least one behavior feature credit of the user, and in this embodiment, a user attribute vector is obtained according to the user attribute feature; obtaining a user behavior vector according to the user behavior characteristics; calculating a first distance between user attribute vectors and/or a second distance between user behavior vectors; and determining the similarity between the users according to the first distance and/or the second distance. Specifically, the attribute features of the user may include a plurality of attribute features, the behavior of the user may also include a plurality of attribute features, and the quantization of the attribute features of the user may obtain an n-dimensional attribute vector, which may be written as: p = (P) 1 ,p 2 ,…,p n ). Wherein p is 1 …p n Dimensions characterised by the user's attributes respectivelyThe degree, such as the city, age, mobile phone information, etc. of the user can be used as the dimension of the attribute vector. Quantifying the user behavior features can obtain an m-dimensional attribute vector, which can be written as: q = (Q) 1 ,q 2 ,…,q m ). P1 \8230pnis the dimension of the attribute characteristics of the user, for example, the favorite movement of the user, the activity period of the user, the favorite trip mode of the user, and the like can be used as the dimension of the row vector of the user.
In this embodiment, a first distance between the attribute vectors of the users and/or a second distance between the behavior vectors of the users may be calculated by using the attribute vectors and/or the behavior vectors, and specifically, the first distance and the second distance may be euclidean distances or cosine values of included angles between the vectors. In this embodiment, a cosine value of a vector angle may be taken as an example for explanation, and specifically, the vector angle may be represented by the following formula:
wherein Pi and Pj are different vectors.
Specifically, the above formula is adopted to calculate the attribute vector angle of two users as cos (P) A P B ) Wherein, PA is the attribute vector of user a, and PB is the attribute vector of user B. Calculating the action vector included angle between two users by adopting the formula can be cos (P) A P B ) Wherein QA is the behavior vector of user A, and QB is the behavior vector of user B. The attribute values are taken as first distances between the user attribute vectors. And taking the cosine value of the included angle of the behavior vectors as a second distance between the behavior vectors of the user.
In this embodiment, the similarity of the user may be represented by the first distance or the second distance alone, or the similarity of the user may be represented by the first distance and the second distance together, specifically, a value range of a cosine value of a vector included angle is [ 1,1 ], when the cosine value of the vector included angle is 1, the two vectors are considered to be the same, and when the cosine value of the vector included angle is-1, the two vectors are considered to be completely opposite. Whereby the user's similarity can be defined.
In this embodiment, in order to prevent a user from occupying resources by malicious matching or prevent an illegal user from interfering with other users, in this embodiment, before executing a matching thread, it may be determined whether a user currently initiating voice matching meets a preset matching condition; and when the user request meets the preset matching condition, performing matching timing, and entering the step S1. The matching conditions may include: the complaint times of the user exceed the preset times, or the user has the behavior of violating the preset rules. In the present embodiment, the two cases are not limited to the above, and other matching conditions are also applicable to the present embodiment.
According to the matching method in the embodiment, the user features are utilized to find the user with higher similarity in the current user target body case set as the matching target user of the current user, so that more common features exist in both matched users, the user can find the user with the similar features without spending a large amount of time, and the possibility of establishing strangers in a social contact mode is greatly improved. A lot of time can be saved when a user establishes social contact, making it simple and efficient for strangers to establish social contact. And better experience is brought to the user.
The present invention also provides a user matching apparatus, as shown in fig. 3, the apparatus including:
a first obtaining unit 10, configured to obtain a user currently initiating voice matching; the first screening unit 20 is configured to screen a calling subscriber according to a first preset condition among users currently initiating voice matching; a second obtaining unit 30, configured to obtain the number of circular screening times of the calling subscriber; the second screening unit 40 is configured to select a set of users to be matched in the matching pool corresponding to the number of times of the circular screening at least according to the target matching gender of the user; the sorting unit 50 is configured to sort the users to be matched in the set of users to be matched according to the similarity with the calling user; and the matching unit 60 is used for matching according to the sequence of the users to be matched.
The present invention also provides a user interaction monitoring device, as shown in fig. 4, including one or more processors 41 and a memory 42, and one processor 43 is taken as an example in fig. 4.
The control unit may further include: an input device 43 and an output device 44.
The processor 41, the memory 42, the input device 43 and the output device 44 may be connected by a bus or other means, and fig. 4 illustrates the connection by a bus as an example.
The processor 41 may be a Central Processing Unit (CPU). The Processor 41 may also be other general purpose processors, digital Signal Processors (DSPs), application Specific Integrated Circuits (ASICs), field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, or combinations thereof. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 42, which is a non-transitory computer readable storage medium, may be used to store non-transitory software programs, non-transitory computer executable programs, and modules, such as the user matching corresponding program instructions/modules in the embodiments of the present application. The processor 41 executes various functional applications of the server and data processing, i.e., implements the user matching method of the above-described method embodiment, by running non-transitory software programs, instructions, and modules stored in the memory 42.
The memory 42 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to use of a processing apparatus operated by the server, and the like. Further, the memory 42 may include high speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, memory 42 may optionally include memory located remotely from processor 41, which may be connected to a network connection device via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input means 43 may receive input numeric or character information and generate key signal inputs related to user settings and function control of the processing means of the server. The output device 44 may include a display device such as a display screen.
One or more modules are stored in the memory 42, which when executed by the one or more processors 41 perform the method as shown in FIG. 1.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention has been described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It should be understood that the above examples are only for clarity of illustration and are not intended to limit the embodiments. Other variations and modifications will be apparent to persons skilled in the art in light of the above description. This need not be, nor should it be exhaustive of all embodiments. And obvious variations or modifications derived therefrom are intended to be within the scope of the invention.
Claims (10)
1. A user matching method, comprising:
acquiring a user who initiates voice matching currently;
screening calling users according to a first preset condition from users who currently initiate voice matching;
acquiring the circular screening times of a target user circularly screened when the calling user initiates a calling;
selecting a set of users to be matched at least according to the target matching gender of the users in the matching pools corresponding to the circular screening times;
sequencing the users to be matched in the user set to be matched according to the similarity with the calling user;
and matching according to the sequence of the users to be matched.
2. The method as claimed in claim 1, wherein said screening calling subscribers according to a first preset condition among subscribers currently initiating voice matching comprises:
judging the gender of the user who initiates voice matching at present;
when the gender of the user who initiates voice matching is a first gender user, taking the user who initiates voice matching as the calling user;
when the gender of the user currently initiating voice matching is a second gender user,
acquiring a matching record of the user currently initiating voice matching, and taking the user currently initiating voice matching as the calling user when the user currently initiating voice matching does not have a matching successful record; or;
and when the target matching gender of the current voice matching initiating user is the second gender, the target matching gender of the current voice matching initiating user is acquired, and when the target matching gender of the current voice matching initiating user is the second gender, the current voice matching initiating user is taken as the calling user.
3. The method of claim 1, wherein the matching pool comprises: the system comprises an active voice matching pool and a non-body matching pool, wherein the active voice matching pool is all users who are initiating voice matching, the non-body matching pool is the users who are initiating voice matching, and the historical matching times exceed the preset times;
selecting a set of users to be matched at least according to the target matching gender of the users in the matching pools corresponding to the historical matching times respectively comprises:
judging whether the circulating screening times are within a first preset range,
and when the circular screening times are within a first preset range, selecting the target matching gender of the calling user from the active voice matching pool, and selecting a user as the to-be-matched user set, wherein the user is a target body shell with the calling user, and the body shell is used for representing groups divided according to the relevance of user features.
4. The method according to claim 3, wherein when the circular screening times are within a second preset range, the target gender-matching user of the calling user is selected as the set of users to be matched in the non-trunk matching pool, and a small value within the second preset range is greater than or equal to a maximum value within the first preset range.
5. The method of claim 4, wherein the calling subscriber is placed in the non-trunk match pool when the round robin filtering times are within a second predetermined range.
6. The method of claim 1, wherein the step of filtering the calling subscriber according to the first preset condition between the step of obtaining the subscriber who currently initiates voice matching and the step of filtering the calling subscriber according to the first preset condition among the subscribers who currently initiate voice matching comprises:
judging whether the user who initiates the voice matching currently meets a preset matching condition;
and when the user request meets the preset matching condition, performing matching timing.
7. The method of claim 6, wherein the matching according to the ranking of the users to be matched comprises:
searching for valid users in sequence;
when the effective user is obtained, initiating a calling party;
and when the effective user is not obtained, repeatedly obtaining the circular screening times of the calling user, respectively selecting a set of users to be matched in a matching pool corresponding to the circular screening times at least according to the target matching gender of the user, and sequencing the users to be matched in the set of users to be matched according to the similarity of the users to the calling user until the effective user is obtained or the matching timing reaches the preset time.
8. The method of claim 1, wherein prior to said obtaining a user currently initiating a voice match, further comprising:
acquiring user characteristic information, wherein the user characteristic information comprises at least one attribute characteristic information of a user, and the user attribute characteristic comprises a plurality of hierarchies;
determining the hull of the user according to the user attribute and the hierarchy of the user attribute;
respectively calculating the similar values of each category on different levels;
calculating the association degree with other users according to the similarity;
and selecting the user with the relevance degree larger than a preset value as the current user target body shell.
9. The method of claim 8, wherein the user characteristic information is at least one behavior characteristic information of a user; the calculating the similarity between the users according to the characteristic information comprises the following steps:
obtaining a user attribute vector according to the user attribute characteristics;
obtaining a user behavior vector according to the user behavior characteristics;
calculating a first distance between user attribute vectors and/or a second distance between user behavior vectors;
and determining the similarity between the users according to the first distance and/or the second distance.
10. A user matching device, comprising: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the one processor to cause the at least one processor to perform the user matching method of any one of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910336147.0A CN110209704B (en) | 2019-04-24 | 2019-04-24 | User matching method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910336147.0A CN110209704B (en) | 2019-04-24 | 2019-04-24 | User matching method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110209704A CN110209704A (en) | 2019-09-06 |
| CN110209704B true CN110209704B (en) | 2023-02-07 |
Family
ID=67786255
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910336147.0A Active CN110209704B (en) | 2019-04-24 | 2019-04-24 | User matching method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110209704B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112559893A (en) * | 2021-01-11 | 2021-03-26 | 引粒网络科技(上海)有限公司 | User recommendation method in internet matching social scene |
| CN113014564B (en) * | 2021-02-19 | 2022-10-21 | 提亚有限公司 | User matching method and device, computer equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105468443A (en) * | 2015-11-19 | 2016-04-06 | 北京乐动卓越科技有限公司 | User matching method and device for social application software |
| CN106790738A (en) * | 2016-11-17 | 2017-05-31 | 维沃移动通信有限公司 | The querying method and server of a kind of user contact details |
| CN107111651A (en) * | 2016-07-29 | 2017-08-29 | 深圳越界创新科技有限公司 | A kind of matching degree computational methods, device and user equipment |
| CN109582700A (en) * | 2018-11-28 | 2019-04-05 | 广州华多网络科技有限公司 | A kind of voice room user matching method, device and equipment |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120265703A1 (en) * | 2011-04-13 | 2012-10-18 | Verizon Patent And Licensing Inc. | Ad hoc social networking |
-
2019
- 2019-04-24 CN CN201910336147.0A patent/CN110209704B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105468443A (en) * | 2015-11-19 | 2016-04-06 | 北京乐动卓越科技有限公司 | User matching method and device for social application software |
| CN107111651A (en) * | 2016-07-29 | 2017-08-29 | 深圳越界创新科技有限公司 | A kind of matching degree computational methods, device and user equipment |
| WO2018018610A1 (en) * | 2016-07-29 | 2018-02-01 | 深圳越界创新科技有限公司 | Method and device for computing degree of match, and user equipment |
| CN106790738A (en) * | 2016-11-17 | 2017-05-31 | 维沃移动通信有限公司 | The querying method and server of a kind of user contact details |
| CN109582700A (en) * | 2018-11-28 | 2019-04-05 | 广州华多网络科技有限公司 | A kind of voice room user matching method, device and equipment |
Non-Patent Citations (2)
| Title |
|---|
| 基于NLP的社交问答网站用户兴趣能力分析方法的研究;何婷;《中国优秀硕士学位论文全文数据库信息科技辑》;20190215(第02期);I138-2581 * |
| 基于推文与属性的社交网络用户重识别方法;高伟等;《计算机系统应用》;20171215(第12期);96-105 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110209704A (en) | 2019-09-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108763314B (en) | Interest recommendation method, device, server and storage medium | |
| WO2022041979A1 (en) | Information recommendation model training method and related device | |
| US20230259566A1 (en) | Recommending an item based on attention of user group to item | |
| WO2017186054A1 (en) | Emoticon recommendation method and apparatus | |
| CN106302085B (en) | Recommendation method and system for instant messaging group | |
| WO2017084362A1 (en) | Model generation method, recommendation method and corresponding apparatuses, device and storage medium | |
| CN111602147A (en) | Machine learning model based on non-local neural network | |
| CN107835113A (en) | Abnormal user detection method in a kind of social networks based on network mapping | |
| Wang et al. | Exploiting social influence for context-aware event recommendation in event-based social networks | |
| CN108647800B (en) | Online social network user missing attribute prediction method based on node embedding | |
| CN110807207A (en) | Data processing method and device, electronic equipment and storage medium | |
| CN112104642B (en) | Abnormal account number determination method and related device | |
| CN108629010B (en) | Web service recommendation method based on theme and service combination information | |
| CN108287875B (en) | Character co-occurrence relation determining method, expert recommending method, device and equipment | |
| CN103761254A (en) | Method for matching and recommending service themes in various fields | |
| US20200210506A1 (en) | Systems and methods for matching a query | |
| Kotzias et al. | Home is where your friends are: Utilizing the social graph to locate twitter users in a city | |
| CN110209704B (en) | User matching method and device | |
| CN113988314A (en) | Cluster federal learning method and system for selecting client | |
| CN106803092B (en) | Method and device for determining standard problem data | |
| CN110188123A (en) | User matching method and equipment | |
| CN110196951A (en) | User matching method and equipment | |
| CN110609958A (en) | Data pushing method and device, electronic equipment and storage medium | |
| JP2024507338A (en) | Automatic detection of prohibited gaming content | |
| Caso et al. | Users Ranking in Online Social Networks to Support POIs Selection in Small Groups. |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |