WO2022126982A1 - 聊天群组创建方法、装置、设备及存储介质 - Google Patents

聊天群组创建方法、装置、设备及存储介质 Download PDF

Info

Publication number
WO2022126982A1
WO2022126982A1 PCT/CN2021/091310 CN2021091310W WO2022126982A1 WO 2022126982 A1 WO2022126982 A1 WO 2022126982A1 CN 2021091310 W CN2021091310 W CN 2021091310W WO 2022126982 A1 WO2022126982 A1 WO 2022126982A1
Authority
WO
WIPO (PCT)
Prior art keywords
user
target
cluster
contact
contacts
Prior art date
Application number
PCT/CN2021/091310
Other languages
English (en)
French (fr)
Inventor
郑昊敏
李昊彦
Original Assignee
平安科技(深圳)有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 平安科技(深圳)有限公司 filed Critical 平安科技(深圳)有限公司
Publication of WO2022126982A1 publication Critical patent/WO2022126982A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90Details of database functions independent of the retrieved data types
    • G06F16/95Retrieval from the web
    • G06F16/953Querying, e.g. by the use of web search engines
    • G06F16/9536Search customisation based on social or collaborative filtering
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24Querying
    • G06F16/245Query processing
    • G06F16/2458Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
    • G06F16/2462Approximate or statistical queries
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24Querying
    • G06F16/245Query processing
    • G06F16/2458Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
    • G06F16/2465Query processing support for facilitating data mining operations in structured databases
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/27Replication, distribution or synchronisation of data between databases or within a distributed database system; Distributed database system architectures therefor
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90Details of database functions independent of the retrieved data types
    • G06F16/906Clustering; Classification
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION 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
    • G06Q50/00Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/01Social networking
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L51/00User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
    • H04L51/52User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail for supporting social networking services

Definitions

  • the present application relates to the technical field of data processing, and in particular, to a method, apparatus, computer device and storage medium for creating a chat group.
  • chat group has the function of gathering and organizing users who have a certain relationship in the same social network.
  • the user's social circle is relatively fixed, so that the contacts of the group chat often cover each other. Users need to repeat many operations to create and maintain groups.
  • the inventor realizes that under the background of high frequency of users initiating group chats, the current method of adding contacts to group chats is mechanical and cumbersome. Therefore, based on the real social habits and communication behaviors of users, recommend and assist users to add target contacts. Entering the grouping can provide users with an intelligent and precise user experience.
  • the present application provides a method, device, electronic device, and computer-readable storage medium for creating a chat group, the main purpose of which is to solve the problem that users need to pay repetitive operations to create a chat group in a social client, and create a group in a high frequency of users.
  • chat behavior the way to add contacts is mechanical and cumbersome.
  • a first aspect of the present application provides a method for creating a chat group, including:
  • target standard data of the user within a preset statistical period, wherein the target standard data is behavioral feature data of the user characterized by vectorization within the preset statistical period;
  • a second aspect of the present application provides an apparatus for creating a chat group, including:
  • the request receiving module is used to receive the group creation request initiated by the user on the social client;
  • a standard data acquisition module configured to acquire, according to the group creation request, the target standard data of the user within a preset statistical period, wherein the target standard data is the vector of the user in the preset statistical period Behavioural characteristic data of chemical representation;
  • a cluster analysis module configured to analyze the target standard data by clustering, and determine the intimacy level between the user and other contacts in the social client;
  • a recommendation module configured to determine and recommend a target contact to the user according to the intimacy level
  • a group creation module is configured to receive a selection instruction from the user, add the target contact according to the selection instruction, and complete the operation of creating a chat group.
  • a third aspect of the present application provides a chat group creation device, comprising a memory and at least one processor, wherein instructions are stored in the memory, and the memory and the at least one processor are interconnected through a line; the at least one processor The controller invokes the instructions in the memory, so that the chat group creation device performs the following steps:
  • target standard data of the user within a preset statistical period, wherein the target standard data is behavioral feature data of the user characterized by vectorization within the preset statistical period;
  • a fourth aspect of the present application provides a computer-readable storage medium, where instructions are stored in the computer-readable storage medium, which, when executed on a computer, cause the computer to perform the following operations:
  • target standard data of the user within a preset statistical period, wherein the target standard data is behavioral feature data of the user characterized by vectorization within the preset statistical period;
  • a group creation request initiated by a user on a social client is received; according to the group creation request, the target standard data of the user within a preset statistical period is obtained, wherein the target The standard data is the behavioral feature data of the user that is characterized by vectorization within the preset statistical period; the target standard data is analyzed by clustering to determine the intimacy level between the user and other contacts in the social client ; determine to recommend a target contact to the user according to the intimacy level; receive a selection instruction from the user, add the target contact according to the selection instruction, and complete the operation of creating a chat group.
  • the embodiment of the present application uses the hierarchical clustering analysis method to finely divide the user's contacts, so that the divided groups are more accurate, the accuracy of recommending target contacts is greatly improved, and matching contacts can be intelligently recommended in the process of creating a chat group.
  • Target contacts providing users with an intelligent and precise user experience.
  • FIG. 1 is a schematic process diagram of an embodiment of a method for creating a chat group in an embodiment of the present application
  • FIG. 2 is a schematic diagram of an embodiment of an apparatus for creating a chat group in an embodiment of the present application
  • FIG. 3 is a schematic diagram of an embodiment of a chat group creation device in an embodiment of the present application.
  • the embodiments of the present application provide a method, apparatus, device and storage medium for creating a chat group, which are used for intelligently recommending matching target contacts during the creation of a chat group, so as to provide users with an intelligent and precise user experience .
  • the method for creating a chat group provided by the present application can solve the problem that the user needs to pay repeated operations to create a chat group in the social client, and when the user creates group chat behaviors frequently, the method of adding contacts is mechanical and cumbersome. Each of them will be described in detail below.
  • the embodiment of the present application provides a method for creating a chat group.
  • the execution body of the method for creating a chat group includes, but is not limited to, at least one of electronic devices that can be configured to execute the method provided by the embodiments of the present application, such as a server and a terminal.
  • the chat group creation method can be executed by software or hardware installed in a terminal device or a server device, and the software can be a blockchain platform.
  • the server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like.
  • the method for creating a chat group includes:
  • Step 101 Receive a group creation request initiated by a user on a social client.
  • the social client can be the current popular social software, which is not limited here.
  • the above social client is installed in smart terminals such as mobile phones, desktop computers, and tablet computers, and is used to provide users with social services, information and other services.
  • the client can add contacts in a way of adding friends, and create groups according to user requirements, and can add contacts who have a friend relationship with the user into the group. Therefore, during specific implementation, the server receives a group creation request initiated by a user according to a group creation requirement.
  • the method before receiving a group creation request initiated by a user on a social client, the method further includes: acquiring user attributes and historical behavior data of the user within a preset statistical period; Behavior data, determine the behavior feature data of the user, and the behavior feature of the user includes the behavior attributes of each contact who has a friend relationship with the user; the behavior feature data of the user is vectorized and converted into standard data, and the standard data can be Stored to the blockchain node.
  • the blockchain referred to in this example is a new application mode of computer technology such as distributed data storage, point-to-point transmission, consensus mechanism, and encryption algorithm.
  • Blockchain essentially a decentralized database, is a series of data blocks associated with cryptographic methods. Each data block contains a batch of network transaction information to verify its Validity of information and generation of the next block.
  • the blockchain can include the underlying platform of the blockchain, the platform product service layer, and the application service layer.
  • the server can determine the user's behavior characteristic data by acquiring the user attributes and historical behavior data in the current statistical period, wherein the user's behavior characteristics include the behavior attributes of each contact who has a friendship with the user, and the Behavior data such as the user's friend relationship, group relationship, and frequency of being added as a group contact in the past.
  • the text vectorization processing is performed on the behavior characteristic data of the user, preferably the one-hot encoding algorithm is used to convert the text into a vector, and the implementation process of converting the text into a vector through one-hot encoding is the prior art, which will not be repeated here.
  • the vector obtained by text conversion is preferably a three-dimensional array. By converting the text code into a vector represented by a three-dimensional array, the subsequent clustering analysis process can analyze the intimacy between the various contacts of the user by calculating the Euclidean distance or similarity. grade.
  • the above-mentioned user attributes include information such as the user's friend relationship, group relationship, etc.
  • its historical behavior data includes information such as the frequency of initiating group chats in the past to add contacts and other information
  • the user attributes can be used to know the social relationship of the user and all contacts thereof, From the historical behavior data, various contacts who have a friend relationship with the user can be known.
  • the present application can perform cluster analysis based on the user's social relationship and historical behavior data, can effectively determine the intimacy level between the user and each contact with whom he has a friend relationship, and can reasonably divide groups and step by step according to the strength of the correlation Make contact recommendations.
  • Step 102 Acquire target standard data of the user within a preset statistical period according to the group creation request; wherein, the target standard data is the behavior characteristic data of the user that is characterized by vectorization within the preset statistical period.
  • the server obtains the target standard data of the user in the preset statistical period, that is, the above-mentioned standard data in the current statistical period can be obtained according to the requirements, that is, the behavior characteristics obtained by text conversion in a certain statistical period
  • the 3D array vector corresponding to the data is the target standard data of the user in the preset statistical period.
  • Step 103 Determine the intimacy level between the user and other contacts in the social client through cluster analysis of the target standard data.
  • the server obtains the three-dimensional array vector corresponding to the behavior characteristic data through cluster analysis, and performs cluster analysis on the above behavior characteristic data in the form of a vector, so as to determine the user and other contacts in the social client. level of intimacy.
  • the above-mentioned determining the intimacy level between the user and other contacts in the social client by analyzing the target standard data by clustering specifically includes: combining the target standard data according to the behavior attributes of each contact Divide into corresponding cluster sub-categories; calculate the first distance between multiple target cluster sub-categories and other cluster sub-categories according to the preset Euclidean distance formula, and obtain a distance matrix; The two cluster sub-categories corresponding to the first distance are combined into a new cluster sub-category; the second distance between the new cluster sub-category and other cluster sub-categories is calculated according to the Euclidean distance formula, and the smallest distance is calculated.
  • the two cluster sub-categories corresponding to the second distance are merged into a new cluster sub-category; according to the distance matrix, the two cluster sub-categories corresponding to the smallest first distance are merged into a new cluster sub-category category, until the number of cluster subcategories obtained by merging reaches the preset number of categories.
  • the server can divide the corresponding target standard data, that is, the corresponding three-dimensional array vector, into corresponding clustering sub-clusters according to the behavior attributes of each contact during cluster analysis.
  • the first distance between each target clustering subcategory and other clustering subcategories can be calculated through the above Euclidean distance.
  • a distance is the representation of similarity, then all target cluster sub-categories are calculated to obtain a distance matrix.
  • the two cluster sub-categories corresponding to the smallest first distance are merged into a new cluster sub-category, so that contacts can be initially merged according to similarity. And further calculate the second distance between the new cluster sub-category and other cluster sub-categories according to the Euclidean distance formula, and also merge the two cluster sub-categories corresponding to the smallest second distance into a new cluster sub-category.
  • Cluster subcategories and so on, return the steps of merging the two cluster subcategories corresponding to the smallest first distance into a new cluster subcategory according to the distance matrix, until the merged cluster subcategories reach Presetting the number of categories, that is, merging all the contacts of the user according to the cluster analysis method to obtain the merged group according to the preset number of categories, by merging the contacts with high similarity to each other into the target number of clusters
  • the sub-category can realize the fine division of contacts, so that the divided groups are more accurate, thereby greatly improving the accuracy of subsequent recommended contacts to create groups.
  • the method further includes: calculating the relationship between the user and each clustered subcategory of the preset number of categories according to user attributes.
  • the correlation coefficient of The intimacy relationship is divided; according to the sorting result of the intimacy level, the intimacy level between the user and each contact in each cluster sub-category of the preset number of categories is determined.
  • the server calculates the correlation coefficient between the user and the merged group obtained after merging according to the above-mentioned user attributes, that is, the correlation coefficient between each cluster sub-category.
  • the calculation method of the correlation system here is the prior art, which will not be repeated here.
  • the intimacy levels of the merged groups are sorted according to the obtained correlation coefficients, so as to determine the intimacy level of the user and each contact in each cluster sub-category of the preset number of categories. Among them, the intimacy level is positively correlated with the correlation coefficient, and the intimacy level divides the intimacy relationship between the user and other contacts.
  • the preset intimacy level has five levels: very good, good, average, poor, and poor; then According to the intimacy level, the intimacy relationship between the several merged groups obtained above and the user can be divided into intimacy levels, so that each contact in each merged group also has a corresponding intimacy level division with the intimacy relationship of the user.
  • the present application analyzes the target standard data of the user in the current statistical period by means of cluster analysis, so as to determine the intimacy level between the user and other contacts in the social client, through which the intimacy level can effectively distinguish each contact in a group manner The intimacy level of the person, so that the target contact can be preferentially recommended to the user according to the intimacy level.
  • Step 104 Determine and recommend the target contact to the user according to the intimacy level.
  • determining to recommend the target contact to the user according to the intimacy level specifically includes: according to the intimacy level between the user and each contact, taking the contact with the highest intimacy level as the target contact; Select the recommendation information for recommending the target contact to join the group; if so, present the target contact to the user in the recommendation list to facilitate the user to select; otherwise, close the recommendation information.
  • the contact with the highest intimacy level is used as the target contact to send recommendation information for joining the group to the user, which can help the user to add contacts more conveniently to initiate group chats.
  • the target contact is presented to the user in the recommendation list so as to facilitate the user to select, so that the operation of adding a contact when initiating a group chat is more flexible, and has both intelligence and speed. Further, if the user does not select the recommended target contact to join the group, the recommendation information is closed, so that the user has more flexibility in adding contacts.
  • the method further includes: if the user's selection to add the target contact is not received, cancel the recommendation and use the custom contact list to send the target contact to the user.
  • the user presents other contacts; the receiving user selects to add contacts in the custom contact list, and completes the operation of creating a chat group.
  • the recommendation is canceled and other contacts are presented to the user in a custom contact list, so that the user can add a contact to join the group through the custom selection, so as to complete the creation of the chat group group operations.
  • Step 105 Receive a selection instruction from the user, add a target contact according to the selection instruction, and complete the operation of creating a chat group.
  • the server After recommending the target contact to the user, the server creates a chat group according to the received operation instruction of the user selecting to add the target contact, so that the user can further add one or more contacts from the recommended list to form a chat group.
  • Group chat makes the operation of adding contacts more flexible, intelligent and fast when initiating a group chat.
  • This application implements hierarchical clustering analysis on user attributes such as user friend relationship, group relationship and other behavioral data such as the frequency of adding contacts in group chats in the past, and sorts their intimacy relationships, so as to achieve intelligent recommendation matching
  • user attributes such as user friend relationship, group relationship and other behavioral data such as the frequency of adding contacts in group chats in the past, and sorts their intimacy relationships, so as to achieve intelligent recommendation matching
  • a fixed model of group division can be obtained during the actual operation of creating a group. In the subsequent statistical period, it is only necessary to apply user attributes and behavior data to the model, which can be quickly and conveniently to realize the division of user groups.
  • the method for creating a chat group is to receive a group creation request initiated by a user on a social client; and obtain the target of the user within a preset statistical period according to the group creation request.
  • standard data wherein the target standard data is the behavioral feature data of the user that is characterized by vectorization within the preset statistical period; through clustering analysis of the target standard data, it is determined that the The intimacy level between the user and other contacts; according to the intimacy level, it is determined to recommend a target contact to the user; receiving a selection instruction from the user, adding the target contact according to the selection instruction, and completing the operation of creating a chat group .
  • the embodiment of the present application uses the hierarchical clustering analysis method to finely divide the user's contacts, so that the divided groups are more accurate, the accuracy of recommending target contacts is greatly improved, and matching contacts can be intelligently recommended in the process of creating a chat group.
  • Target contacts providing users with an intelligent and precise user experience.
  • an embodiment of the apparatus for creating a chat group in the embodiment of the present application includes:
  • a request receiving module 21 configured to receive a group creation request initiated by a user on a social client
  • the standard data acquisition module 22 is configured to acquire, according to the group creation request, the target standard data of the user within the preset statistical period, wherein the target standard data is the user's data obtained within the preset statistical period.
  • Behavioral feature data of vectorized representation
  • a cluster analysis module 23 configured to analyze the target standard data by clustering, and determine the intimacy level between the user and other contacts in the social client;
  • a recommendation module 24 configured to determine and recommend a target contact to the user according to the intimacy level
  • the group creation module 25 is configured to receive a selection instruction from the user, add the target contact according to the selection instruction, and complete the operation of creating a chat group.
  • the apparatus further includes:
  • a historical data acquisition module used for acquiring user attributes and historical behavior data of the user within a preset statistical period
  • a behavioral feature data determination module configured to determine the behavioral feature data of the user according to the historical behavioral data, where the behavioral feature of the user includes the behavioral attributes of each contact who has a friend relationship with the user;
  • the data vectorization module is used to perform vectorization processing on the behavior characteristic data of the user and convert it into standard data, and the standard data can be stored in the blockchain node.
  • the cluster analysis module 23 specifically includes:
  • a clustering sub-category dividing module configured to divide the target standard data into corresponding clustering sub-categories according to the behavior attributes of each of the contacts;
  • the calculation and distance matrix acquisition module is used to calculate the first distance between the multiple target cluster sub-categories and each other cluster sub-categories according to the preset Euclidean distance formula, and obtain the distance matrix;
  • a first merging module for merging two clustering subcategories corresponding to the smallest first distance into a new clustering subcategory according to the distance matrix
  • the second merging module is configured to calculate the second distance between the new cluster sub-category and the other cluster sub-categories according to the Euclidean distance formula, and calculate the two distances corresponding to the smallest second distance
  • the cluster subcategories are merged into a new cluster subcategory
  • the returning and stopping merging module is used to return the step of merging the two cluster sub-categories corresponding to the smallest first distance into a new cluster sub-category according to the distance matrix, until the merged The number of clustered subcategories reaches the preset number of categories.
  • the Euclidean distance formula is:
  • the cluster analysis module 23 further includes:
  • a correlation coefficient calculation module configured to calculate the correlation coefficient between the user and each clustering sub-category of the preset number of categories according to the user attribute
  • an intimacy level sorting module configured to perform intimacy level sorting on each cluster sub-category of the preset number of categories according to each of the obtained correlation coefficients, wherein the intimacy level has a positive correlation with the correlation coefficient, and the intimacy level divides the intimacy between the user and other contacts;
  • An intimacy level determination module configured to determine the intimacy level between the user and each contact in each cluster sub-category of the preset number of categories according to the sorting result of the intimacy level.
  • the recommending module 24 specifically includes:
  • a target contact acquisition module configured to use the contact with the highest intimacy level as the target contact according to the intimacy level between the user and each contact;
  • a recommendation information sending module configured to send recommendation information to the user whether to choose to recommend the target contact to join the group
  • a recommendation list presentation module configured to present the target contact to the user with a recommendation list to facilitate selection by the user
  • the recommendation information closing module is used to close the recommendation information otherwise.
  • the apparatus further includes:
  • Cancellation recommendation and customization module for not receiving the user's selection to add the target contact, canceling the recommendation and presenting other contacts to the user with a custom contact list;
  • the custom adding and group creating module is used to receive the user's selection to add contacts in the custom contact list, and complete the operation of creating a chat group.
  • chat group creation apparatus in the embodiment of the present application is described in detail above from the perspective of modular functional entities, and the chat group creation device in the embodiment of the present application is described in detail below from the perspective of hardware processing.
  • the chat group creation device 300 may vary greatly due to different configurations or performances, and may include one or more processors (central processing units, CPU) 301 (eg, one or more processors) and memory 309, one or more storage media 308 (eg, one or more mass storage devices) that store application programs 307 or data 306.
  • processors central processing units, CPU
  • storage media 308 eg, one or more mass storage devices
  • the memory 309 and the storage medium 308 may be short-term storage or persistent storage.
  • the program stored in the storage medium 308 may include one or more modules (not shown), and each module may include a series of instruction operations in Boolean variable storage for graph computation.
  • the processor 301 may be configured to communicate with the storage medium 308 to execute a series of instruction operations in the storage medium 308 on the chat group creation device 300 .
  • Chat group creation device 300 may also include one or more power supplies 302, one or more wired or wireless network interfaces 303, one or more input and output interfaces 304, and/or, one or more operating systems 305, such as Windows Serve, Mac OS X, Unix, Linux, FreeBSD, and more.
  • operating systems 305 such as Windows Serve, Mac OS X, Unix, Linux, FreeBSD, and more.
  • FIG. 3 does not constitute a limitation on the chat group creation device, and may include more or less components than those shown in the figure, or combine some components, Or a different component arrangement.
  • the disclosed system, apparatus and method may be implemented in other manners.
  • the apparatus embodiments described above are only illustrative.
  • the division of the units is only a logical function division. In actual implementation, there may be other division methods.
  • multiple units or components may be combined or Can be integrated into another system, or some features can be ignored, or not implemented.
  • the shown or discussed mutual coupling or direct coupling or communication connection may be through some interfaces, indirect coupling or communication connection of devices or units, and may be in electrical, mechanical or other forms.
  • the units described as separate components may or may not be physically separated, and components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution in this embodiment.
  • each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit.
  • the above-mentioned integrated units may be implemented in the form of hardware, or may be implemented in the form of software functional units.
  • the integrated unit may be stored in a computer-readable storage medium, which may be non-volatile or is volatile.
  • a computer-readable storage medium which may be non-volatile or is volatile.
  • the technical solutions of the present application can be embodied in the form of software products in essence, or the parts that contribute to the prior art, or all or part of the technical solutions, and the computer software products are stored in a storage medium , including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application.
  • the aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), magnetic disk or optical disk and other media that can store program codes .

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Computing Systems (AREA)
  • Probability & Statistics with Applications (AREA)
  • Fuzzy Systems (AREA)
  • Business, Economics & Management (AREA)
  • Software Systems (AREA)
  • Mathematical Physics (AREA)
  • Computational Linguistics (AREA)
  • General Health & Medical Sciences (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Health & Medical Sciences (AREA)
  • Economics (AREA)
  • Signal Processing (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

一种聊天群组创建方法、装置、设备及存储介质,涉及数据处理技术领域,用于在聊天群组创建过程中智能推荐相匹配的目标联系人,为用户提供智能化、精准化的用户体验。方法包括:接收用户在社交客户端发起的群组创建请求(101);根据所述群组创建请求,获取所述用户在预设统计周期内的目标标准数据,所述目标标准数据为所述用户在所述预设统计周期内经向量化表征的行为特征数据(102);通过聚类分析所述目标标准数据,确定在所述社交客户端中所述用户与其它联系人的亲密等级(103);根据所述亲密等级确定向所述用户推荐目标联系人(104);接收所述用户的选择指令,根据所述选择指令添加所述目标联系人,完成创建聊天群组操作(105)。还涉及区块链技术。

Description

聊天群组创建方法、装置、设备及存储介质
本申请要求于2020年12月16日提交中国专利局、申请号为202011483775.0,发明名称为“聊天群组创建方法、装置、设备及存储介质”的中国专利申请的优先权,其全部内容通过引用结合在本申请中。
技术领域
本申请涉及数据处理技术领域,特别是涉及一种聊天群组创建方法、装置、计算机设备和存储介质。
背景技术
社交软件作为一种的现代生活方式下的沟通平台,通过提供发送语音、文字、图片等功能,成为人们必不可少的联络工具。其中,聊天群组具有把同一个社交网络中具有某种关系的用户聚集组织在一起的功能,通常情况下,用户的社交圈是相对固定的,导致群聊的联系人经常是相互覆盖的,用户建立和维护群组需要重复多次操作。并且,发明人意识到在用户发起群聊行为的高频次背景下,目前添加联系人群聊的方式机械而繁琐,因此,面向用户真实的社交习惯和沟通行为,推荐并协助用户添加目标联系人进入分组,才能为用户提供智能化、精准化的用户体验。
发明内容
本申请提供一种聊天群组创建方法、装置、电子设备及计算机可读存储介质,其主要目的在于解决在社交客户端中用户创建聊天群组需要付出重复操作,并且在用户高频次创建群聊行为时,添加联系人的方式机械而繁琐的问题。
为实现上述目的,本申请第一方面提供了一种聊天群组创建方法,包括:
接收用户在社交客户端发起的群组创建请求;
根据所述群组创建请求,获取所述用户在预设统计周期内的目标标准数据,其中,所述目标标准数据为所述用户在所述预设统计周期内经向量化表征的行为特征数据;
通过聚类分析所述目标标准数据,确定在所述社交客户端中所述用户与其它联系人的亲密等级;
根据所述亲密等级确定向所述用户推荐目标联系人;
接收所述用户的选择指令,根据所述选择指令添加所述目标联系人,完成创建聊天群组操作。
本申请第二方面提供了一种聊天群组创建装置,包括:
请求接收模块,用于接收用户在社交客户端发起的群组创建请求;
标准数据获取模块,用于根据所述群组创建请求,获取所述用户在预设统计周期内的目标标准数据,其中,所述目标标准数据为所述用户在所述预设统计周期内经向量化表征的行为特征数据;
聚类分析模块,用于通过聚类分析所述目标标准数据,确定在所述社交客户端中所述用户与其它联系人的亲密等级;
推荐模块,用于根据所述亲密等级确定向所述用户推荐目标联系人;
群组创建模块,用于接收所述用户的选择指令,根据所述选择指令添加所述目标联系人,完成创建聊天群组操作。
本申请第三方面提供了一种聊天群组创建设备,包括存储器和至少一个处理器,所述存储器中存储有指令,所述存储器和所述至少一个处理器通过线路互联;所述至少一个处理器调用所述存储器中的所述指令,以使得所述聊天群组创建设备执行以下步骤:
接收用户在社交客户端发起的群组创建请求;
根据所述群组创建请求,获取所述用户在预设统计周期内的目标标准数据,其中,所述目标标准数据为所述用户在所述预设统计周期内经向量化表征的行为特征数据;
通过聚类分析所述目标标准数据,确定在所述社交客户端中所述用户与其它联系人的亲密等级;
根据所述亲密等级确定向所述用户推荐目标联系人;
接收所述用户的选择指令,根据所述选择指令添加所述目标联系人,完成创建聊天群组操作。
本申请的第四方面提供了一种计算机可读存储介质,所述计算机可读存储介质中存储有指令,当其在计算机上运行时,使得计算机执行以下操作:
接收用户在社交客户端发起的群组创建请求;
根据所述群组创建请求,获取所述用户在预设统计周期内的目标标准数据,其中,所述目标标准数据为所述用户在所述预设统计周期内经向量化表征的行为特征数据;
通过聚类分析所述目标标准数据,确定在所述社交客户端中所述用户与其它联系人的亲密等级;
根据所述亲密等级确定向所述用户推荐目标联系人;
接收所述用户的选择指令,根据所述选择指令添加所述目标联系人,完成创建聊天群组操作。
本申请提供的技术方案中,通过接收用户在社交客户端发起的群组创建请求;根据所述群组创建请求,获取所述用户在预设统计周期内的目标标准数据,其中,所述目标标准数据为所述用户在所述预设统计周期内经向量化表征的行为特征数据;通过聚类分析所述目标标准数据,确定在所述社交客户端中所述用户与其它联系人的亲密等级;根据所述亲密等级确定向所述用户推荐目标联系人;接收所述用户的选择指令,根据所述选择指令添加所述目标联系人,完成创建聊天群组操作。本申请实施例利用层次聚类分析方法将用户的联系人进行精细划分,使划分后的群组更加准确,推荐目标联系人的精度大大提高,在聊天群组创建过程中能够智能推荐相匹配的目标联系人,为用户提供智能化、精准化的用户体验。
附图说明
为了更清楚地说明本申请实施例或现有技术中的技术方案,下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍,显而易见地,下面描述中的附图仅仅是本申请的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动的前提下,还可以根据这些附图获得其他附图。
图1为本申请实施例中聊天群组创建方法的一个实施例过程示意图;
图2为本申请实施例中聊天群组创建装置的一个实施例示意图;
图3为本申请实施例中聊天群组创建设备的一个实施例示意图。
具体实施方式
本申请实施例提供了一种聊天群组创建方法、装置、设备及存储介质,用于在聊天群组创建过程中智能推荐相匹配的目标联系人,为用户提供智能化、精准化的用户体验。
为了使本技术领域的人员更好地理解本申请方案,下面将结合本申请实施例中的附图,对本申请实施例进行描述。
本申请的说明书和权利要求书及上述附图中的术语“第一”、“第二”、“第三”、“第四”等(如果存在)是用于区别类似的对象,而不必用于描述特定的顺序或先后次序。应该理解这样使用的数据在适当情况下可以互换,以便这里描述的实施例能够以除了在这里图示或描述的内容以外的顺序实施。此外,术语“包括”或“具有”及其任何变形,意 图在于覆盖不排他的包含,例如,包含了一系列步骤或单元的过程、方法、系统、产品或设备不必限于清楚地列出的那些步骤或单元,而是可包括没有清楚地列出的或对于这些过程、方法、产品或设备固有的其它步骤或单元。
在现有技术中同一个社交网络中具有某种关系的用户聚集组织在一起的功能,通常情况下,用户的社交圈是相对固定的,导致群聊的联系人经常是相互覆盖的,用户建立和维护群组需要重复多次操作。并且,在用户发起群聊行为的高频次背景下,目前添加联系人群聊的方式机械而繁琐,因此,面向用户真实的社交习惯和沟通行为,推荐并协助用户添加目标联系人进入分组,才能为用户提供智能化、精准化的用户体验。
本申请提供的聊天群组创建方法能解决目前在社交客户端中用户创建聊天群组需要付出重复操作,并且在用户高频次创建群聊行为时,添加联系人的方式机械而繁琐的问题,以下分别进行详细的说明。
本申请实施例提供一种聊天群组创建方法。所述聊天群组创建方法的执行主体包括但不限于服务端、终端等能够被配置为执行本申请实施例提供的该方法的电子设备中的至少一种。换言之,所述聊天群组创建方法可以由安装在终端设备或服务端设备的软件或硬件来执行,所述软件可以是区块链平台。所述服务端包括但不限于:单台服务器、服务器集群、云端服务器或云端服务器集群等。
参照图1所示的本申请一实施例提供的聊天群组创建方法的流程示意图,在本申请实施例中,所述聊天群组创建方法包括:
步骤101、接收用户在社交客户端发起的群组创建请求。
社交客户端可以为目前热门的社交软件,在此不作限定,上述社交客户端安装于手机、台式电脑、平板电脑等智能终端中、用于给使用用户提供社交、资讯等服务项目,用户通过社交客户端可以以添加好友的方式添加联系人、并且根据用户需求创建群组、可以添加与用户具有好友关系的联系人进入群组中。因此,具体实施时,服务器接收到用户根据群组创建需求发起的群组创建请求。
进一步地,在本申请的另一个方法实施例中,在接收用户在社交客户端发起的群组创建请求之前,还包括:获取用户在预设统计周期内的用户属性及历史行为数据;根据历史行为数据,确定出用户的行为特征数据,用户的行为特征包括与用户具有好友关系的各个联系人的行为属性;将用户的行为特征数据进行向量化处理,转化为标准数据,所述标准数据可以存储至区块链节点。本示例所指区块链是分布式数据存储、点对点传输、共识机制、加密算法等计算机技术的新型应用模式。区块链(Blockchain),本质上是一个去中心化的数据库,是一串使用密码学方法相关联产生的数据块,每一个数据块中包含了一批次网络交易的信息,用于验证其信息的有效性和生成下一个区块。区块链可以包括区块链底层平台、平台产品服务层以及应用服务层等。
服务器通过获取当前统计周期内的用户属性及历史行为数据,可以确定出用户的行为特征数据,其中用户的行为特征包括与用户具有好友关系的各个联系人的行为属性,联系人的行为属性包括与用户的好友关系、群组关系以及过往被添加为群组联系人的频次等行为数据。通过将用户的行为特征数据进行文本向量化处理,优选为通过one-hot编码算法将文本转化为向量,通过one-hot编码实现文本转化为向量的实现过程为现有技术,在此不作赘述,此处文本转化得到的向量优选为三维数组,通过将文本编码转换为三维数组表示的向量,使后续在聚类分析过程可以通过计算欧式距离或相似度以分析用户的各个联系人之间的亲密等级。
进一步地,上述用户属性包括用户的好友关系、群组关系等信息,其历史行为数据包括过往发起群聊添加联系人的频次等信息,通过用户属性可以得知该用户与其所有联系的社交关系,从历史行为数据可以得知与该用户具有好友关系的各个联系人。本申请可以基于用户的社交关系和历史行为数据进行聚类分析,能够有效的判别用户与其具有好友关系 的各个联系人之间的亲密等级,可以合理划分群组并按照相关性的强弱逐级进行联系人推荐。
步骤102、根据群组创建请求,获取用户在预设统计周期内的目标标准数据;其中,所述目标标准数据为所述用户在所述预设统计周期内经向量化表征的行为特征数据。具体地,根据上述群组创建请求,服务器获取用户在预设统计周期内的目标标准数据,即可以根据需求获取当前统计周期内的上述标准数据,即在一定统计周期内经文本转化得到的行为特征数据对应的三维数组向量。
步骤103、通过聚类分析目标标准数据,确定在社交客户端中用户与其它联系人的亲密等级。
本实施例具体实施时,服务器通过聚类分析获取得到的行为特征数据对应的三维数组向量,以对上述行为特征数据按向量形式进行聚类分析,以确定在社交客户端中用户与其它联系人的亲密等级。
具体地,在本申请的另一个实施例中,上述通过聚类分析目标标准数据,确定在社交客户端中用户与其它联系人的亲密等级具体包括:根据各个联系人的行为属性将目标标准数据划分为对应的各个聚类子类别;根据预设的欧式距离公式计算多个目标聚类子类别与其它各个聚类子类别之间的第一距离,得到距离矩阵;根据距离矩阵,将最小的第一距离所对应的两个聚类子类别合并为一个新的聚类子类别;根据欧式距离公式计算新的聚类子类别与其它聚类子类别之间的第二距离,并将最小的第二距离所对应的两个聚类子类别合并为一个新的聚类子类别;返回根据距离矩阵,将最小的第一距离所对应的两个聚类子类别合并为一个新的聚类子类别的步骤,直至合并得到的聚类子类别达到预设类别数目。
具体实施时,由于各个联系人的行为属性不同,因此服务器在聚类分析时可以据各个联系人的行为属性将对应的目标标准数据、即对应的三维数组向量,划分为对应的各个聚类子类别,进一步根据预设的欧式距离公式,其中,欧式距离公式为:距离d=sqrt((x1-x2)^+(y1-y2)^+(z1-z2)^),其中,x1、y1、z1,x2、y2、z2分别为每两个聚类子类别的三维向量,通过上述欧式距离可以计算每个目标聚类子类别与其它各个聚类子类别之间的第一距离,该第一距离即为相似度的表示,则将所有目标聚类子类别进行计算,即可得到距离矩阵。
根据得到的距离矩阵,将其中最小的第一距离所对应的两个聚类子类别合并为一个新的聚类子类别,则可以实现初步根据相似度将联系人进行合并。并进一步地根据欧式距离公式计算新的聚类子类别与其它聚类子类别之间的第二距离,并同样将其中最小的第二距离所对应的两个聚类子类别合并为一个新的聚类子类别;以此类推,返回根据距离矩阵,将最小的第一距离所对应的两个聚类子类别合并为一个新的聚类子类别的步骤,直至合并得到的聚类子类别达到预设类别数目,即将用户的所有联系人按聚类分析方式合并、以得到按预设的类别数目的合并群,通过将相互间具有较高相似度的联系人合并为目标个数的聚类子类别,可以实现将联系人进行精细划分,使划分后的群组更加准确,进而使后续推荐联系人创建群组的精度大大提高。
进一步地,在本申请另一个实施例中,在上述直至合并得到的聚类子类别达到预设类别数目之后,还包括:根据用户属性计算用户与预设类别数目的各个聚类子类别之间的相关性系数;根据得到的各个相关性系数,对预设类别数目的各个聚类子类别进行亲密等级排序,其中亲密等级与相关性系数呈正相关关系,且亲密等级将用户与其它联系人的亲密关系进行划分;根据亲密等级的排序结果,确定用户与预设类别数目的各个聚类子类别中的每个联系人的亲密等级。
具体实施时,服务器根据上述用户属性计算用户与合并后得到的合并群,即各个聚类子类别之间的相关性系数,此处相关性系统的计算方式为现有技术,在此不作赘述,从而根据得到的各个相关性系数对合并得到的几个合并群进行亲密等级排序,以确定用户与预 设类别数目的各个聚类子类别中的每个联系人的亲密等级。其中,亲密等级与相关性系数呈正相关关系,且亲密等级将用户与其它联系人的亲密关系进行划分,譬如预设亲密等级有五个等级:非常好,好,一般,差,较差;则根据亲密等级可以将上述得到的几个合并群与用户的亲密关系进行亲密等级划分,从而每个合并群里的每位联系人也相应地与用户的亲密关系作出一致的亲密等级划分。
本申请通过聚类分析方式,分析用户在当前统计周期内的目标标准数据,以确定在社交客户端中用户与其它联系人的亲密等级,通过该亲密等级可以有效地以群组方式区分各个联系人的亲密等级,以便于按亲密等级向用户优先推荐目标联系人。
步骤104、根据亲密等级确定向用户推荐目标联系人。
具体地,在另一个实施例中,根据亲密等级确定向用户推荐目标联系人具体包括:根据用户与每个联系人的亲密等级,将亲密等级最高的联系人作为目标联系人;向用户发送是否选择推荐目标联系人加入分组的推荐信息;若是则以推荐列表向用户呈现目标联系人以便于用户进行挑选;若否则关闭推荐信息。
具体实施时,以用户跟每个联系人的亲密等级,将亲密等级最高的联系人作为目标联系人向用户发送加入分组的推荐信息,可以帮助用户更便捷地添加联系人发起群聊。并且,以推荐列表向用户呈现目标联系人以便于用户进行挑选,使得发起群聊时添加联系人的操作更加灵活,兼具智能性和快速性。进一步地,若用户不选择推荐的目标联系人加入分组则关闭推荐信息,使得用户添加联系人更具有灵活性。
进一步地,在本申请方法的另一个实施例中,根据亲密等级确定向用户推荐目标联系人之后,还包括:未接收到用户选择添加目标联系人,则取消推荐并以自定义联系人列表向用户呈现其它联系人;接收用户选择添加自定义联系人列表中的联系人,完成创建聊天群组操作。具体地,当未接收到用户选择添加目标联系人时,则取消推荐并以自定义联系人列表向用户呈现其它联系人,使得用户可以通过自定义选择添加联系人加入分组,以完成创建聊天群组操作。
步骤105、接收用户的选择指令,根据选择指令添加目标联系人,完成创建聊天群组操作。
具体地,服务器在向用户推荐目标联系人之后,根据接收到的用户选择添加目标联系人的操作指令后,创建聊天群组,从而使用户可以从推荐列表中进一步添加一个或多个联系人组成群聊,使得发起群聊时添加联系人的操作更加灵活,兼具智能性和快速性。
本申请实现了通过对用户的好友关系、群组关系等用户属性以及过往发起群聊添加联系人的频次等行为数据进行层次聚类分析,并对其亲疏关系进行排序,从而实现智能推荐相匹配的联系人,进一步地,可以在创建群组的实操过程中获得一个群组划分的固定模型,在后续统计周期内,只需要将用户属性和行为数据套用到该模型当中,即可快速便捷地实现用户群组的划分。
综上可知,本申请提供的一种聊天群组创建方法,通过接收用户在社交客户端发起的群组创建请求;根据所述群组创建请求,获取所述用户在预设统计周期内的目标标准数据,其中,所述目标标准数据为所述用户在所述预设统计周期内经向量化表征的行为特征数据;通过聚类分析所述目标标准数据,确定在所述社交客户端中所述用户与其它联系人的亲密等级;根据所述亲密等级确定向所述用户推荐目标联系人;接收所述用户的选择指令,根据所述选择指令添加所述目标联系人,完成创建聊天群组操作。本申请实施例利用层次聚类分析方法将用户的联系人进行精细划分,使划分后的群组更加准确,推荐目标联系人的精度大大提高,在聊天群组创建过程中能够智能推荐相匹配的目标联系人,为用户提供智能化、精准化的用户体验。
上面对本申请实施例中聊天群组创建方法进行了描述,下面对本申请实施例中聊天群组创建装置进行描述,请参阅图2,本申请实施例中聊天群组创建装置的一个实施例包括:
请求接收模块21,用于接收用户在社交客户端发起的群组创建请求;
标准数据获取模块22,用于根据所述群组创建请求,获取所述用户在预设统计周期内的目标标准数据,其中,所述目标标准数据为所述用户在所述预设统计周期内经向量化表征的行为特征数据;
聚类分析模块23,用于通过聚类分析所述目标标准数据,确定在所述社交客户端中所述用户与其它联系人的亲密等级;
推荐模块24,用于根据所述亲密等级确定向所述用户推荐目标联系人;
群组创建模块25,用于接收所述用户的选择指令,根据所述选择指令添加所述目标联系人,完成创建聊天群组操作。
可选的,在本申请聊天群组创建装置的另一个实施例中,所述装置还包括:
历史数据获取模块,用于获取所述用户在预设统计周期内的用户属性及历史行为数据;
行为特征数据确定模块,用于根据所述历史行为数据,确定出用户的行为特征数据,所述用户的行为特征包括与所述用户具有好友关系的各个联系人的行为属性;
数据向量化模块,用于将所述用户的行为特征数据进行向量化处理,转化为标准数据,所述标准数据可以存储至区块链节点。
可选的,在本申请聊天群组创建装置的另一个实施例中,所述聚类分析模块23具体包括:
聚类子类别划分模块,用于根据各个所述联系人的行为属性将所述目标标准数据划分为对应的各个聚类子类别;
计算与距离矩阵获取模块,用于根据预设的欧式距离公式计算多个目标聚类子类别与其它各个聚类子类别之间的第一距离,得到距离矩阵;
第一合并模块,用于根据所述距离矩阵,将最小的所述第一距离所对应的两个聚类子类别合并为一个新的聚类子类别;
第二合并模块,用于根据所述欧式距离公式计算所述新的聚类子类别与其它所述聚类子类别之间的第二距离,并将最小的所述第二距离所对应的两个聚类子类别合并为一个新的聚类子类别;
返回与停止合并模块,用于返回所述根据所述距离矩阵,将最小的所述第一距离所对应的两个聚类子类别合并为一个新的聚类子类别的步骤,直至合并得到的聚类子类别达到预设类别数目。
可选的,在本申请聊天群组创建装置的另一个实施例中,所述欧式距离公式为:
距离d=sqrt((x1-x2)^+(y1-y2)^+(z1-z2)^),其中,所述x1、y1、z1,x2、y2、z2分别为每两个所述聚类子类别的三维向量。
可选的,在本申请聊天群组创建装置的另一个实施例中,所述聚类分析模块23还包括:
相关性系数计算模块,用于根据所述用户属性计算所述用户与所述预设类别数目的各个聚类子类别之间的相关性系数;
亲密等级排序模块,用于根据得到的各个所述相关性系数,对所述预设类别数目的各个聚类子类别进行亲密等级排序,其中所述亲密等级与所述相关性系数呈正相关关系,且所述亲密等级将所述用户与其它联系人的亲密关系进行划分;
亲密等级确定模块,用于根据所述亲密等级的排序结果,确定所述用户与所述预设类别数目的各个聚类子类别中的每个联系人的亲密等级。
可选的,在本申请聊天群组创建装置的另一个实施例中,所述推荐模块24具体包括:
目标联系人获取模块,用于根据所述用户与每个联系人的亲密等级,将亲密等级最高的联系人作为目标联系人;
推荐信息发送模块,用于向所述用户发送是否选择推荐所述目标联系人加入分组的推荐信息;
推荐列表呈现模块,用于若是则以推荐列表向所述用户呈现所述目标联系人以便于所述用户进行挑选;
推荐信息关闭模块,用于若否则关闭所述推荐信息。
可选的,在本申请聊天群组创建装置的另一个实施例中,所述装置还包括:
取消推荐与自定义模块,用于未接收到所述用户选择添加所述目标联系人,则取消推荐并以自定义联系人列表向所述用户呈现其它联系人;
自定义添加与群组创建模块,用于接收用户选择添加所述自定义联系人列表中的联系人,完成创建聊天群组操作。
需要说明的是,本申请实施例中的装置可以用于实现上述方法实施例中的全部技术方案,其各个功能模块的功能可以根据上述方法实施例中的方法具体实现,其具体实现过程可参照上述实例中的相关描述,此处不再赘述。
上面从模块化功能实体的角度对本申请实施例中的聊天群组创建装置进行详细描述,下面从硬件处理的角度对本申请实施例中聊天群组创建设备进行详细描述。
图3是本申请实施例提供的一种聊天群组创建设备的结构示意图,该聊天群组创建设备300可因配置或性能不同而产生比较大的差异,可以包括一个或一个以上处理器(central processing units,CPU)301(例如,一个或一个以上处理器)和存储器309,一个或一个以上存储应用程序307或数据306的存储介质308(例如一个或一个以上海量存储设备)。其中,存储器309和存储介质308可以是短暂存储或持久存储。存储在存储介质308的程序可以包括一个或一个以上模块(图示没标出),每个模块可以包括对图计算的布尔型变量存储中的一系列指令操作。更进一步地,处理器301可以设置为与存储介质308通信,在聊天群组创建设备300上执行存储介质308中的一系列指令操作。
聊天群组创建设备300还可以包括一个或一个以上电源302,一个或一个以上有线或无线网络接口303,一个或一个以上输入输出接口304,和/或,一个或一个以上操作系统305,例如Windows Serve,Mac OS X,Unix,Linux,FreeBSD等等。本领域技术人员可以理解,图3中示出的聊天群组创建设备结构并不构成对聊天群组创建设备的限定,可以包括比图示更多或更少的部件,或者组合某些部件,或者不同的部件布置。
所属领域的技术人员可以清楚地了解到,为描述的方便和简洁,上述描述的系统,装置和单元的具体工作过程,可以参考前述方法实施例中的对应过程,在此不再赘述。
在本申请所提供的几个实施例中,应该理解到,所揭露的系统,装置和方法,可以通过其它的方式实现。例如,以上所描述的装置实施例仅仅是示意性的,例如,所述单元的划分,仅仅为一种逻辑功能划分,实际实现时可以有另外的划分方式,例如多个单元或组件可以结合或者可以集成到另一个系统,或一些特征可以忽略,或不执行。另一点,所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口,装置或单元的间接耦合或通信连接,可以是电性,机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的,作为单元显示的部件可以是或者也可以不是物理单元,即可以位于一个地方,或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外,在本申请各个实施例中的各功能单元可以集成在一个处理单元中,也可以是各个单元单独物理存在,也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现,也可以采用软件功能单元的形式实现。
所述集成的单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时,可以存储在一个计算机可读取存储介质中,该计算机可读存储介质可以是非易失性的,也可以是易失性的。基于这样的理解,本申请的技术方案本质上或者说对现有技术做出贡献的 部分或者该技术方案的全部或部分可以以软件产品的形式体现出来,该计算机软件产品存储在一个存储介质中,包括若干指令用以使得一台计算机设备(可以是个人计算机,服务器,或者网络设备等)执行本申请各个实施例所述方法的全部或部分步骤。而前述的存储介质包括:U盘、移动硬盘、只读存储器(read-only memory,ROM)、随机存取存储器(random access memory,RAM)、磁碟或者光盘等各种可以存储程序代码的介质。
以上所述,以上实施例仅用以说明本申请的技术方案,而非对其限制;尽管参照前述实施例对本申请进行了详细的说明,本领域的普通技术人员应当理解:其依然可以对前述各实施例所记载的技术方案进行修改,或者对其中部分技术特征进行等同替换;而这些修改或者替换,并不使对应技术方案的本质脱离本申请各实施例技术方案的精神和范围。

Claims (20)

  1. 一种聊天群组创建方法,其中,包括:
    接收用户在社交客户端发起的群组创建请求;
    根据所述群组创建请求,获取所述用户在预设统计周期内的目标标准数据,其中,所述目标标准数据为所述用户在所述预设统计周期内经向量化表征的行为特征数据;
    通过聚类分析所述目标标准数据,确定在所述社交客户端中所述用户与其它联系人的亲密等级;
    根据所述亲密等级确定向所述用户推荐目标联系人;
    接收所述用户的选择指令,根据所述选择指令添加所述目标联系人,完成创建聊天群组操作。
  2. 根据权利要求1所述的聊天群组创建方法,其中,所述接收用户在社交客户端发起的群组创建请求之前,所述方法还包括:
    获取所述用户在预设统计周期内的用户属性及历史行为数据;
    根据所述历史行为数据,确定出用户的行为特征数据,所述用户的行为特征包括与所述用户具有好友关系的各个联系人的行为属性;
    将所述用户的行为特征数据进行向量化处理,转化为标准数据,所述标准数据可以存储至区块链节点。
  3. 如权利要求2所述聊天群组创建方法,其中,所述通过聚类分析所述目标标准数据,确定在所述社交客户端中所述用户与其它联系人的亲密等级具体包括:
    根据各个所述联系人的行为属性将所述目标标准数据划分为对应的各个聚类子类别;
    根据预设的欧式距离公式计算多个目标聚类子类别与其它各个聚类子类别之间的第一距离,得到距离矩阵;
    根据所述距离矩阵,将最小的所述第一距离所对应的两个聚类子类别合并为一个新的聚类子类别;
    根据所述欧式距离公式计算所述新的聚类子类别与其它所述聚类子类别之间的第二距离,并将最小的所述第二距离所对应的两个聚类子类别合并为一个新的聚类子类别;
    返回所述根据所述距离矩阵,将最小的所述第一距离所对应的两个聚类子类别合并为一个新的聚类子类别的步骤,直至合并得到的聚类子类别达到预设类别数目。
  4. 如权利要求3所述聊天群组创建方法,其中,所述欧式距离公式为:
    距离d=sqrt((x1-x2)^+(y1-y2)^+(z1-z2)^),其中,所述x1、y1、z1,x2、y2、z2分别为每两个所述聚类子类别的三维向量。
  5. 如权利要求4所述聊天群组创建方法,其中,所述直至合并得到的聚类子类别达到预设类别数目之后,还包括:
    根据所述用户属性计算所述用户与所述预设类别数目的各个聚类子类别之间的相关性系数;
    根据得到的各个所述相关性系数,对所述预设类别数目的各个聚类子类别进行亲密等级排序,其中所述亲密等级与所述相关性系数呈正相关关系,且所述亲密等级将所述用户与其它联系人的亲密关系进行划分;
    根据所述亲密等级的排序结果,确定所述用户与所述预设类别数目的各个聚类子类别中的每个联系人的亲密等级。
  6. 如权利要求5所述聊天群组创建方法,其中,所述根据所述亲密等级确定向所述用户推荐目标联系人具体包括:
    根据所述用户与每个联系人的亲密等级,将亲密等级最高的联系人作为目标联系人;
    向所述用户发送是否选择推荐所述目标联系人加入分组的推荐信息;
    若是则以推荐列表向所述用户呈现所述目标联系人以便于所述用户进行挑选;
    若否则关闭所述推荐信息。
  7. 如权利要求6所述聊天群组创建方法,其中,所述根据所述亲密等级确定向所述用户推荐目标联系人之后,所述方法还包括:
    未接收到所述用户选择添加所述目标联系人,则取消推荐并以自定义联系人列表向所述用户呈现其它联系人;
    接收用户选择添加所述自定义联系人列表中的联系人,完成创建聊天群组操作。
  8. 如权利要求2所述聊天群组创建方法,其中,所述用户属性包括用户的好友关系、群组关系,历史行为数据包括过往发起群聊添加联系人的频次,用户属性用于得知该用户与其所有联系的社交关系,历史行为数据用于得知与该用户具有好友关系的各个联系人。
  9. 一种聊天群组创建装置,其中,包括:
    请求接收模块,用于接收用户在社交客户端发起的群组创建请求;
    标准数据获取模块,用于根据所述群组创建请求,获取所述用户在预设统计周期内的目标标准数据,其中,所述目标标准数据为所述用户在所述预设统计周期内经向量化表征的行为特征数据;
    聚类分析模块,用于通过聚类分析所述目标标准数据,确定在所述社交客户端中所述用户与其它联系人的亲密等级;
    推荐模块,用于根据所述亲密等级确定向所述用户推荐目标联系人;
    群组创建模块,用于接收所述用户的选择指令,根据所述选择指令添加所述目标联系人,完成创建聊天群组操作。
  10. 一种聊天群组创建设备,其中,所述聊天群组创建设备包括存储器和至少一个处理器,所述存储器中存储有指令,所述存储器和所述至少一个处理器通过线路互联;所述至少一个处理器调用所述存储器中的所述指令,以使得所述聊天群组创建设备执行以下步骤:
    接收用户在社交客户端发起的群组创建请求;
    根据所述群组创建请求,获取所述用户在预设统计周期内的目标标准数据,其中,所述目标标准数据为所述用户在所述预设统计周期内经向量化表征的行为特征数据;
    通过聚类分析所述目标标准数据,确定在所述社交客户端中所述用户与其它联系人的亲密等级;
    根据所述亲密等级确定向所述用户推荐目标联系人;
    接收所述用户的选择指令,根据所述选择指令添加所述目标联系人,完成创建聊天群组操作。
  11. 根据权利要求10所述的聊天群组创建设备,其中,所述接收用户在社交客户端发起的群组创建请求之前,所述方法还包括:
    获取所述用户在预设统计周期内的用户属性及历史行为数据;
    根据所述历史行为数据,确定出用户的行为特征数据,所述用户的行为特征包括与所述用户具有好友关系的各个联系人的行为属性;
    将所述用户的行为特征数据进行向量化处理,转化为标准数据,所述标准数据可以存储至区块链节点。
  12. 如权利要求11所述聊天群组创建设备,其中,所述通过聚类分析所述目标标准数据,确定在所述社交客户端中所述用户与其它联系人的亲密等级具体包括:
    根据各个所述联系人的行为属性将所述目标标准数据划分为对应的各个聚类子类别;
    根据预设的欧式距离公式计算多个目标聚类子类别与其它各个聚类子类别之间的第一距离,得到距离矩阵;
    根据所述距离矩阵,将最小的所述第一距离所对应的两个聚类子类别合并为一个新的 聚类子类别;
    根据所述欧式距离公式计算所述新的聚类子类别与其它所述聚类子类别之间的第二距离,并将最小的所述第二距离所对应的两个聚类子类别合并为一个新的聚类子类别;
    返回所述根据所述距离矩阵,将最小的所述第一距离所对应的两个聚类子类别合并为一个新的聚类子类别的步骤,直至合并得到的聚类子类别达到预设类别数目。
  13. 如权利要求12所述聊天群组创建设备,其中,所述欧式距离公式为:
    距离d=sqrt((x1-x2)^+(y1-y2)^+(z1-z2)^),其中,所述x1、y1、z1,x2、y2、z2分别为每两个所述聚类子类别的三维向量。
  14. 如权利要求13所述聊天群组创建设备,其中,所述直至合并得到的聚类子类别达到预设类别数目之后,还包括:
    根据所述用户属性计算所述用户与所述预设类别数目的各个聚类子类别之间的相关性系数;
    根据得到的各个所述相关性系数,对所述预设类别数目的各个聚类子类别进行亲密等级排序,其中所述亲密等级与所述相关性系数呈正相关关系,且所述亲密等级将所述用户与其它联系人的亲密关系进行划分;
    根据所述亲密等级的排序结果,确定所述用户与所述预设类别数目的各个聚类子类别中的每个联系人的亲密等级。
  15. 如权利要求14所述聊天群组创建设备,其中,所述根据所述亲密等级确定向所述用户推荐目标联系人具体包括:
    根据所述用户与每个联系人的亲密等级,将亲密等级最高的联系人作为目标联系人;
    向所述用户发送是否选择推荐所述目标联系人加入分组的推荐信息;
    若是则以推荐列表向所述用户呈现所述目标联系人以便于所述用户进行挑选;
    若否则关闭所述推荐信息。
  16. 如权利要求15所述聊天群组创建设备,其中,所述根据所述亲密等级确定向所述用户推荐目标联系人之后,所述方法还包括:
    未接收到所述用户选择添加所述目标联系人,则取消推荐并以自定义联系人列表向所述用户呈现其它联系人;
    接收用户选择添加所述自定义联系人列表中的联系人,完成创建聊天群组操作。
  17. 如权利要求11所述聊天群组创建设备,其中,所述用户属性包括用户的好友关系、群组关系,历史行为数据包括过往发起群聊添加联系人的频次,用户属性用于得知该用户与其所有联系的社交关系,历史行为数据用于得知与该用户具有好友关系的各个联系人。
  18. 一种计算机可读存储介质,其上存储有计算机程序,其中,所述计算机程序被处理器执行时实现以下操作:
    接收用户在社交客户端发起的群组创建请求;
    根据所述群组创建请求,获取所述用户在预设统计周期内的目标标准数据,其中,所述目标标准数据为所述用户在所述预设统计周期内经向量化表征的行为特征数据;
    通过聚类分析所述目标标准数据,确定在所述社交客户端中所述用户与其它联系人的亲密等级;
    根据所述亲密等级确定向所述用户推荐目标联系人;
    接收所述用户的选择指令,根据所述选择指令添加所述目标联系人,完成创建聊天群组操作。
  19. 根据权利要求18所述的计算机可读存储介质,其中,所述接收用户在社交客户端发起的群组创建请求之前,所述方法还包括:
    获取所述用户在预设统计周期内的用户属性及历史行为数据;
    根据所述历史行为数据,确定出用户的行为特征数据,所述用户的行为特征包括与所述用户具有好友关系的各个联系人的行为属性;
    将所述用户的行为特征数据进行向量化处理,转化为标准数据,所述标准数据可以存储至区块链节点。
  20. 如权利要求19所述计算机可读存储介质,其中,所述通过聚类分析所述目标标准数据,确定在所述社交客户端中所述用户与其它联系人的亲密等级具体包括:
    根据各个所述联系人的行为属性将所述目标标准数据划分为对应的各个聚类子类别;
    根据预设的欧式距离公式计算多个目标聚类子类别与其它各个聚类子类别之间的第一距离,得到距离矩阵;
    根据所述距离矩阵,将最小的所述第一距离所对应的两个聚类子类别合并为一个新的聚类子类别;
    根据所述欧式距离公式计算所述新的聚类子类别与其它所述聚类子类别之间的第二距离,并将最小的所述第二距离所对应的两个聚类子类别合并为一个新的聚类子类别;
    返回所述根据所述距离矩阵,将最小的所述第一距离所对应的两个聚类子类别合并为一个新的聚类子类别的步骤,直至合并得到的聚类子类别达到预设类别数目。
PCT/CN2021/091310 2020-12-16 2021-04-30 聊天群组创建方法、装置、设备及存储介质 WO2022126982A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202011483775.0 2020-12-16
CN202011483775.0A CN112632402A (zh) 2020-12-16 2020-12-16 聊天群组创建方法、装置、设备及存储介质

Publications (1)

Publication Number Publication Date
WO2022126982A1 true WO2022126982A1 (zh) 2022-06-23

Family

ID=75313530

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/091310 WO2022126982A1 (zh) 2020-12-16 2021-04-30 聊天群组创建方法、装置、设备及存储介质

Country Status (2)

Country Link
CN (1) CN112632402A (zh)
WO (1) WO2022126982A1 (zh)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112632402A (zh) * 2020-12-16 2021-04-09 平安科技(深圳)有限公司 聊天群组创建方法、装置、设备及存储介质
CN113300942B (zh) * 2021-05-24 2022-08-19 中国平安财产保险股份有限公司 聊天群的管理方法、装置、设备及存储介质
CN116932927B (zh) * 2023-09-18 2023-12-15 深圳市爱聊科技有限公司 基于人工智能实现社交匹配推荐的数据处理方法和装置

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103294801A (zh) * 2013-05-29 2013-09-11 中国科学技术大学 基于情境感知的联系人个性化推荐服务器、客户端及方法
CN107835085A (zh) * 2017-09-23 2018-03-23 深圳市金立通信设备有限公司 一种联系人群组处理方法、终端及计算机可读存储介质
CN109951578A (zh) * 2019-01-17 2019-06-28 平安科技(深圳)有限公司 一种查询联系人的方法、装置及存储介质
US20200259779A1 (en) * 2019-02-12 2020-08-13 Global Elmeast Inc. Super chat
CN112632402A (zh) * 2020-12-16 2021-04-09 平安科技(深圳)有限公司 聊天群组创建方法、装置、设备及存储介质

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111324259B (zh) * 2020-03-18 2021-09-28 腾讯科技(成都)有限公司 群组创建方法、装置和存储介质

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103294801A (zh) * 2013-05-29 2013-09-11 中国科学技术大学 基于情境感知的联系人个性化推荐服务器、客户端及方法
CN107835085A (zh) * 2017-09-23 2018-03-23 深圳市金立通信设备有限公司 一种联系人群组处理方法、终端及计算机可读存储介质
CN109951578A (zh) * 2019-01-17 2019-06-28 平安科技(深圳)有限公司 一种查询联系人的方法、装置及存储介质
US20200259779A1 (en) * 2019-02-12 2020-08-13 Global Elmeast Inc. Super chat
CN112632402A (zh) * 2020-12-16 2021-04-09 平安科技(深圳)有限公司 聊天群组创建方法、装置、设备及存储介质

Also Published As

Publication number Publication date
CN112632402A (zh) 2021-04-09

Similar Documents

Publication Publication Date Title
WO2022126982A1 (zh) 聊天群组创建方法、装置、设备及存储介质
CN109241415B (zh) 项目推荐方法、装置、计算机设备及存储介质
Kodinariya et al. Review on determining number of Cluster in K-Means Clustering
JP4906846B2 (ja) ソーシャルネットワークにおける利用者の相性の得点化
US11042946B2 (en) Identity mapping between commerce customers and social media users
CN106484777B (zh) 一种多媒体数据处理方法以及装置
CN110909182B (zh) 多媒体资源搜索方法、装置、计算机设备及存储介质
CN105847127B (zh) 一种用户属性信息确定方法以及服务器
US8909581B2 (en) Factor-graph based matching systems and methods
CN110196904B (zh) 一种获取推荐信息的方法、装置及计算机可读存储介质
US10664929B2 (en) Extracting data for professional event and participant grouping recommendations
CN107808314B (zh) 用户推荐方法及装置
US9824123B2 (en) System and method for finding matches between users in a networked environment
CN105893562A (zh) 会话消息处理方法、装置及终端
KR20210050166A (ko) 그룹 앨범을 이용하는 대화방에서 프로필 사진 기반 사용자 얼굴 인식과 활용 방법
Jagabathula et al. A model-based embedding technique for segmenting customers
CN108401005B (zh) 一种表情推荐方法和装置
CN109977979B (zh) 定位种子用户的方法、装置、电子设备和存储介质
CN114221991A (zh) 基于大数据的会话推荐反馈处理方法及深度学习服务系统
CN112783468A (zh) 目标对象的排序方法和排序装置
CN113934776B (zh) 食材推送方法、装置、介质及设备
CN113327154B (zh) 基于大数据的电商用户讯息推送方法及系统
CN114547480A (zh) 一种基于多平台融合的深度学习推荐方法以及系统
TWI714019B (zh) 諮詢式聊天機械人之執行方法
Liu et al. Minimizing required user effort for cold-start recommendation by identifying the most important latent factors

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21904921

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21904921

Country of ref document: EP

Kind code of ref document: A1