WO2017202208A1 - 征信特征获取方法及其设备 - Google Patents

征信特征获取方法及其设备 Download PDF

Info

Publication number
WO2017202208A1
WO2017202208A1 PCT/CN2017/083944 CN2017083944W WO2017202208A1 WO 2017202208 A1 WO2017202208 A1 WO 2017202208A1 CN 2017083944 W CN2017083944 W CN 2017083944W WO 2017202208 A1 WO2017202208 A1 WO 2017202208A1
Authority
WO
WIPO (PCT)
Prior art keywords
application
interaction
application identifier
identifier
service type
Prior art date
Application number
PCT/CN2017/083944
Other languages
English (en)
French (fr)
Inventor
黎新
陈谦
Original Assignee
腾讯科技（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 腾讯科技（深圳）有限公司 filed Critical 腾讯科技（深圳）有限公司
Publication of WO2017202208A1 publication Critical patent/WO2017202208A1/zh

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L65/00—Network arrangements, protocols or services for supporting real-time applications in data packet communication
    • H04L65/40—Support for services or applications
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/50—Network service management, e.g. ensuring proper service fulfilment according to agreements
    • H04L41/508—Network service management, e.g. ensuring proper service fulfilment according to agreements based on type of value added network service under agreement
    • H04L41/5093—Network service management, e.g. ensuring proper service fulfilment according to agreements based on type of value added network service under agreement wherein the managed service relates to messaging or chat services
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/50—Network services
    • H04L67/51—Discovery or management thereof, e.g. service location protocol [SLP] or web services

Definitions

  • the present application relates to the field of computer technology, and in particular, to a method for acquiring a credit feature and a device thereof.
  • users can communicate through interactive platforms provided by interactive applications, such as instant messaging applications, microblog applications, etc., and can also be based on the public identification of services under the interactive application to the associated user groups. Sending subscription information, etc., improves interactivity between users.
  • the embodiment of the present invention provides a method for acquiring a credit information feature and a device thereof, which can be combined with a service type of a service public identifier and a user's personal information to increase the available credit information feature resources under the interaction application.
  • the first aspect of the embodiment of the present application provides a method for acquiring a credit feature, which may include:
  • the interaction application Recording, according to the interaction application, the interaction information between the first application identifier and each of the at least one second application identifier, where the first application identifier is a personal interaction identifier under the interaction application, the at least one The second application identifier is the at least one service public identifier associated with the first application identifier in the interaction application;
  • the service type pointing data is determined as a credit characteristic parameter corresponding to the first application identifier.
  • the second aspect of the embodiment of the present application provides a credit feature acquiring device, which may include:
  • An information recording unit configured to record, according to the interaction application, interaction operation information between the first application identifier and each second application identifier of the at least one second application identifier, where the first application identifier is a personal interaction identifier of the interaction application
  • the at least one second application identifier is related to the first application identifier in the interaction application At least one business public identity of the association;
  • a data obtaining unit configured to acquire, according to the interaction operation information between the first application identifier and each second application identifier, and the service type corresponding to each second application identifier, the service type corresponding to the first application identifier Point to data;
  • the parameter determining unit is configured to determine the service type pointing data as the credit characteristic parameter corresponding to the first application identifier.
  • the interaction information between the personal interaction identifier and the service public identifier in the interaction application is recorded, and the individual is obtained according to the interaction operation information between the personal interaction identifier and the service public identifier and the service type corresponding to the service public identifier.
  • the service type corresponding to the interaction identifier points to the data, and the combination of the service type of the service public identifier and the user's personal information is realized, and the resource of the interaction application is avoided, and the service type corresponding to the personal interaction identifier can be determined as the corresponding levy.
  • the characteristic parameters of the trust increase the available credit characteristic resources under the interactive application.
  • FIG. 1 is a schematic flowchart of a method for acquiring a credit feature provided by an embodiment of the present application
  • FIG. 2 is a schematic flowchart of another method for acquiring a credit feature provided by an embodiment of the present application
  • FIG. 3 is a schematic structural diagram of a credit information acquisition device according to an embodiment of the present application.
  • FIG. 4 is a schematic structural diagram of another method for acquiring a credit feature provided by an embodiment of the present application.
  • FIG. 5 is a schematic structural diagram of a data acquiring unit according to an embodiment of the present application.
  • FIG. 6 is a schematic structural diagram of a parameter determining unit provided by an embodiment of the present application.
  • FIG. 7 is a schematic structural diagram of still another method for acquiring a credit feature provided by an embodiment of the present application.
  • the subscription information sent by the same service has information relevance, that is, the service type (for example, sports, music, etc.), and the user's personal interaction identifier and service public identifier are only
  • the service type for example, sports, music, etc.
  • the user's personal interaction identifier and service public identifier are only
  • the binding is performed in an associated manner, and there is no other personal information record. Therefore, the service type of the service public identifier cannot be combined with the user's personal information, which causes waste of resources of the interactive application, thereby reducing the possibility of interaction under the application.
  • the acquired credit feature resource is based on the same service public identity, the subscription information sent by the same service has information relevance, that is, the service type (for example, sports, music, etc.), and the user's personal interaction identifier and service public identifier are only
  • the binding is performed in an associated manner, and there is no other personal information record. Therefore, the service type of the service public identifier cannot be combined with the user's personal information, which causes
  • the method for acquiring the credit information provided by the embodiment of the present application can be applied to a scenario of an interactive application such as an instant messaging application or a social application.
  • the credit information acquiring device records the first application identifier and each of the at least one second application identifier based on the interaction application.
  • the information about the interaction between the personal interaction identifier and the service public identifier is recorded, and the service type corresponding to the personal interaction identifier is obtained according to the interaction information between the personal interaction identifier and the service public identifier and the service type corresponding to the service public identifier.
  • the data realizes the combination of the service type of the service public identity and the user's personal information, avoids waste of resources of the interactive application, and can determine the service type corresponding to the personal interaction identifier as the corresponding credit characteristic parameter, and increases the interaction.
  • the available credit characteristic resources under application is recorded, and the service type corresponding to the personal interaction identifier is obtained according to the interaction information between the personal interaction identifier and the service public identifier and the service type corresponding to the service public identifier.
  • the information collection device of the present invention may be a background service device corresponding to the interaction application; the interaction application may include an instant communication application, a social application, and the like, and the function of establishing a public service group to provide public service services.
  • the first application identifier is a personal interaction identifier in the interaction application
  • the at least one second application identifier is at least one service public identifier associated with the first application identifier in the interaction application
  • the service public identity may be based on the interaction platform provided by the interaction application to perform certain business type interaction information on a text, a picture, a voice, a video, and the like to a specific personal interaction application.
  • the personal interaction identifier may be an account registered by the user in the interactive application for using the interactive application to interact with other users.
  • the user can log in to the interactive application using the personal interaction identifier.
  • an add request containing the personal interaction identifier is generated. Can take advantage of this personal interaction
  • the identity and another personal interaction identity establish a session that contains two personal interaction identities.
  • the business public identity is a type of account that provides a public platform for public services, including: service number, subscription number, and enterprise number. Different from the personal interaction identifier, the user holding the service public identity cannot actively add a friend, and can only be added as a friend by other people. Other users can use the service public identity to search and pay attention to the public service, and the public can be established. The association between the identity and the personal interaction identity used by the user. Alternatively, other users may scan a two-dimensional code including the public identifier of the service, link to the page of the public service, and establish an association relationship between the public identifier of the service and the personal interaction identifier used by the user by paying attention to the public service.
  • the service public identity may be utilized as other personal interaction identification push information with which the sending direction is associated, such as subscription information, advertisement information, notification information, and the like.
  • the user holding the service public identity such as the enterprise administrator, may display the information sent by the user in the message list.
  • the automatic reply function is set in advance, the automatic reply function is configured to send the response information corresponding to the keyword to the personal interaction identifier when the received information sent by the user includes a preset keyword. Only the user holding the public identity of the service can receive the information sent by the user, and other users who hold the personal interaction identifier associated with the public identifier of the service cannot receive the information sent by the user.
  • a session established using a service public identity and a personal interaction identity is different from a group session established using multiple personal interaction identities.
  • the information sent by the users joining the group session using their personal interaction identity is forwarded to all other personal interaction identities in the group, and can also receive information sent by any other personal interaction identities in the group session.
  • FIG. 1 a flow chart of a method for acquiring a credit feature is provided in an embodiment of the present application. As shown in FIG. 1 , the method in this embodiment of the present application may include the following steps S101 to S103.
  • the credit feature acquiring device may record the interaction operation information between the first application identifier and each of the at least one second application identifier based on the interaction application.
  • the interaction information between the first application identifier and each of the at least one second application identifier may be based on the interaction application between the first application identifier and each of the at least one second application identifier.
  • the information generated by the platform when interacting may include one or more of a variety of information types.
  • the type of interaction information can include: subscription class operations Information, uplink and downlink message type operation information, menu click type operation information, graphic reading operation information, and forwarding type operation information.
  • a first application identifier may be associated with a plurality of second application identifiers, and a second application identifier may be associated with a plurality of first application identifiers.
  • the information collection device may record the interaction information between the first application identifier and each of the at least one second application identifier in the preset time period based on the interaction application.
  • the information collection device may obtain the first application according to the interaction operation information between the first application identifier and each second application identifier and the service type corresponding to each second application identifier.
  • the corresponding business type of the identifier points to the data.
  • the credit feature acquiring device may preconfigure a corresponding service type for each of the second application identifiers based on the interaction application.
  • the type of business may be an industry classification, such as: food and beverage, physical fitness, financial management, tourism, transportation, and the like.
  • the service type corresponding to the first application identifier is used to represent an interest index vector of the user-to-business type of the first application identifier.
  • the credit information acquiring device may determine the service type pointing data as a credit characteristic parameter corresponding to the first application identifier, and apply the service type pointing data to a preset credit model. As an input parameter of the credit model.
  • the interaction information between the personal interaction identifier and the service public identifier in the interaction application is recorded, and the individual is obtained according to the interaction operation information between the personal interaction identifier and the service public identifier and the service type corresponding to the service public identifier.
  • the service type corresponding to the interaction identifier points to the data, and the combination of the service type of the service public identifier and the user's personal information is realized, and the resource of the interaction application is avoided, and the service type corresponding to the personal interaction identifier can be determined as the corresponding levy.
  • the characteristic parameters of the trust increase the available credit characteristic resources under the interactive application.
  • FIG. 2 is a schematic flowchart of another method for acquiring a credit feature according to an embodiment of the present application. As shown in FIG. 2, the method in this embodiment of the present application may include the following steps S201 to S208.
  • the credit feature acquiring device may configure, according to the interaction application, a corresponding service type for each of the second application identifiers, where the service type corresponding to each second application identifier configuration may be in the When the application identifier is registered, it is filled in by the user, or may be calculated by the credit information feature obtaining device according to the statistics of the content of the message published by the second application identifier in a period of time.
  • the type of business may be an industry classification, such as: food and beverage, physical fitness, financial management, tourism, transportation, and the like.
  • the information collection device may record the interaction operation information between the first application identifier and each of the at least one second application identifier based on the interaction application, where the interaction operation information may include subscription operation information.
  • the interaction operation information may include subscription operation information.
  • a first application identifier may be associated with a plurality of second application identifiers
  • a second application identifier may be associated with a plurality of first application identifiers.
  • the information collection device may record the interaction information between the first application identifier and each of the at least one second application identifier in the preset time period based on the interaction application.
  • the credit feature acquiring device may perform categorization processing on the at least one second application identifier based on the service type, and generate at least one application identifier set after the categorization processing.
  • the at least one application identifier set is used to represent at least one service type associated with the first application identifier, that is, each application identifier set represents a service type.
  • S204 Perform classification and statistics on the interaction operation information of each application identifier set in the at least one application identifier set, and obtain the number of each type of interaction operation information in each application identifier set.
  • the information collection device may perform classification and statistics on the interaction operation information of each application identifier set in the at least one application identifier set, and obtain the number of each type of interaction operation information in each application identifier set. For example, it is counted within one month that the first application identifier has five times of subscription operation information for the second application identifier in the application identifier set of the food and beverage category.
  • S205 Calculate at least one industry according to the number of each type of interaction operation information in each application identification set.
  • the information collection device may calculate the interaction weight data corresponding to each service type in the at least one service type according to the number of each type of interaction operation information in each application identification set, and the interaction weight data Biz ( u i , t j ) can be calculated using the following formula 1:
  • u i represents the first application identifier of the i-th user
  • t j represents the j-th service type
  • cn(i, j) represents the first application identifier of the i-th user and the associated j-th service type
  • the action (k, j) indicates that the first application identifier of the i-th user has the number of k-type interaction operation information for the second application identifier of the j-th service type, and ⁇ k represents the k-type interaction operation.
  • the weighting factor of the information indicates that the first application identifier of the i-th user has the number of k-type interaction operation information for the second application identifier of the j-th service type, and ⁇ k represents the k-type interaction operation.
  • S206 Perform normalization processing on the interaction weight data corresponding to each service type to generate an interaction weight vector corresponding to each service type, and generate the first according to the interaction weight vector corresponding to each service type.
  • the service type corresponding to an application identifier points to data.
  • the credit feature acquiring device performs normalization processing on the interaction weight data corresponding to each service type to generate an interaction weight vector corresponding to each service type, and corresponding to each service type according to the service type
  • the service type mapping data corresponding to the first application identifier is to perform statistics and processing on the number of each interaction operation information in each service type associated with the first application identifier, and obtain corresponding to each service type. Interact weight data.
  • the credit information acquiring device may obtain, in the service type pointing data, a first service type in which the interaction weight vector satisfies a preset weight threshold, and determine an interaction weight vector corresponding to the first service type as The credit characteristic parameter corresponding to the first application identifier may be applied to the preset credit information model as an input parameter of the credit information model.
  • the at least one second application identifier may be a service public identifier.
  • the information about the interaction between the personal interaction identifier and the service public identifier is recorded, and the service type corresponding to the personal interaction identifier is obtained according to the interaction information between the personal interaction identifier and the service public identifier and the service type corresponding to the service public identifier.
  • Data which realizes the combination of the service type of the service public identification and the user's personal information, can store the corresponding business type of the personal interaction identifier as data to be stored as big data, fully utilize the interaction data generated in the interaction, and avoid receiving a large number of users.
  • the service type corresponding to the personal interaction identifier can be determined as the corresponding credit characteristic parameter, and the available credit characteristic resource under the interaction application is added.
  • the service characteristics of the service public identity can be further embodied, and the performance form of the service public identity is enriched.
  • the interaction weight data to represent the relationship between the personal interaction identifier and the service public identity, the user's interest in the public number can be accurately reflected, and the mining accuracy of the user's business interest orientation is improved.
  • the credit information acquisition device provided by the embodiment of the present application will be described in detail below with reference to FIG. 3 to FIG. It should be noted that the method for acquiring the feature of the present invention shown in FIG. 3 and FIG. 6 is for performing the method of the embodiment shown in FIG. 1 and FIG. 2, and for the convenience of description, only the implementation of the present application is shown. For the relevant parts of the example, the specific technical details are not disclosed, please refer to the embodiment shown in FIG. 1 and FIG. 2 of the present application.
  • FIG. 3 is a schematic structural diagram of a method for acquiring a credit feature according to an embodiment of the present application.
  • the communication connection device 1 of the embodiment of the present application may include an information recording unit 11, a data acquisition unit 12, and a parameter determination unit 13.
  • the information recording unit 11 is configured to record, according to the interaction application, interaction operation information between the first application identifier and each second application identifier of the at least one second application identifier;
  • the information recording unit 11 may record, according to the interaction application, interaction operation information between the first application identifier and each second application identifier of the at least one second application identifier, where the interaction operation information may be Including one or more of the subscription class operation information, the uplink and downlink message class operation information, the menu click class operation information, the graphic reading class operation information, and the forwarding class operation information, it can be understood that in the interactive application, a first The application identifier may be associated with a plurality of second application identifiers, and the second application identifier may be associated with the plurality of first application identifiers. Further, the information recording unit 11 may record the interaction operation information between the first application identifier and each of the at least one second application identifier in the preset time period based on the interaction application.
  • the data obtaining unit 12 is configured to acquire, according to the interaction operation information between the first application identifier and each second application identifier, and the service type corresponding to each second application identifier, the service corresponding to the first application identifier.
  • Type points to data
  • the data acquiring unit 12 may obtain the first application according to the interaction operation information between the first application identifier and each second application identifier, and the service type corresponding to each second application identifier.
  • the identification of the corresponding service type is directed to the data.
  • the credit information acquisition device 1 can pre-configure the corresponding service type for each of the second application identifiers based on the interaction application.
  • the type of business may be an industry classification, such as: food and beverage, physical fitness, financial management, tourism, transportation, and the like.
  • the service type corresponding to the first application identifier is used to represent an interest index vector of the user-to-business type of the first application identifier.
  • the parameter determining unit 13 is configured to determine the service type pointing data as the crediting feature parameter corresponding to the first application identifier
  • the parameter determining unit 13 may determine the service type pointing data as a credit characteristic parameter corresponding to the first application identifier, and apply the service type pointing data to a preset credit model. As an input parameter of the credit model.
  • the interaction information between the personal interaction identifier and the service public identifier in the interaction application is recorded, and the individual is obtained according to the interaction operation information between the personal interaction identifier and the service public identifier and the service type corresponding to the service public identifier.
  • the service type corresponding to the interaction identifier points to the data, and the combination of the service type of the service public identifier and the user's personal information is realized, and the resource of the interaction application is avoided, and the service type corresponding to the personal interaction identifier can be determined as the corresponding levy.
  • the characteristic parameters of the trust increase the available credit characteristic resources under the interactive application.
  • FIG. 4 is a schematic structural diagram of another method for acquiring a credit feature according to an embodiment of the present application.
  • the communication connection device 1 of the embodiment of the present application may include an information recording unit 11, a data acquisition unit 12, a parameter determination unit 13, and a type configuration unit 14.
  • the type configuration unit 14 is configured to configure, according to the interaction application, a service type corresponding to each second application identifier of the at least one second application identifier;
  • the type configuration unit 14 may configure, according to the interaction application, a corresponding service type for each of the second application identifiers, where the service type corresponding to each second application identifier configuration may be in the When the second application identifier is registered, it is filled in by the user, or may be calculated by the type configuration unit 14 according to the statistics of the content of the message published by the second application identifier in a period of time.
  • the type of business may be an industry classification, such as: food and beverage, physical fitness, financial management, tourism, transportation, and the like.
  • the information recording unit 11 is configured to record, according to the interaction application, interaction operation information between the first application identifier and each second application identifier of the at least one second application identifier;
  • the information recording unit 11 may record, according to the interaction application, interaction operation information between the first application identifier and each of the at least one second application identifier, where the interaction operation information may include subscription operation information.
  • the interaction operation information may include subscription operation information.
  • a first application identifier can be associated with the binding.
  • a plurality of second application identifiers are defined, and a second application identifier may be associated with the plurality of first application identifiers.
  • the information recording unit 11 may record the interaction operation information between the first application identifier and each of the at least one second application identifier in the preset time period based on the interaction application.
  • the data obtaining unit 12 is configured to acquire, according to the interaction operation information between the first application identifier and each second application identifier, and the service type corresponding to each second application identifier, the service corresponding to the first application identifier.
  • Type points to data
  • the data acquiring unit 12 may obtain the first application according to the interaction operation information between the first application identifier and each second application identifier, and the service type corresponding to each second application identifier.
  • the identification of the corresponding service type is directed to the data.
  • the credit information acquisition device 1 can pre-configure the corresponding service type for each of the second application identifiers based on the interaction application.
  • the type of business may be an industry classification, such as: food and beverage, physical fitness, financial management, tourism, transportation, and the like.
  • the service type corresponding to the first application identifier is used to represent the user of the first application identifier to the service class. Type of interest index vector.
  • FIG. 5 is a schematic structural diagram of a data acquiring unit according to an embodiment of the present application.
  • the data obtaining unit 12 may include:
  • a set generation sub-unit 121 configured to perform categorization processing on the at least one second application identifier based on a service type, and generate at least one application identifier set after the categorization process;
  • the set generation sub-unit 121 may perform categorization processing on the at least one second application identifier based on the service type, and generate at least one application identifier set after the categorization process, it being understood that the at least An application identifier set is used to represent at least one service type associated with the first application identifier, that is, each application identifier set represents a service type.
  • the information acquisition sub-unit 122 is configured to perform classification and statistics on the interaction operation information of each application identifier set in the at least one application identifier set, and obtain the number of each type of interaction operation information in each application identifier set.
  • the information collection sub-unit 122 may perform classification and statistics on the interaction operation information of each application identifier set in the at least one application identifier set, and acquire each type of interaction operation information in each application identifier set. For example, it is counted that within 1 month, the first application identifier has five times of subscription operation information for the second application identifier in the application identifier set of the food and beverage category.
  • the data calculation sub-unit 123 is configured to calculate interaction weight data corresponding to each service type in the at least one service type according to the number of each type of interaction operation information in each application identification set;
  • the data calculation sub-unit 123 may calculate the interaction weight data corresponding to each service type in the at least one service type according to the number of each type of interaction operation information in each application identification set, and the interaction weight data Biz (u i , t j ) can be calculated using Equation 1 below:
  • u i represents the first application identifier of the i-th user
  • t j represents the j-th service type
  • cn(i, j) represents the first application identifier of the i-th user and the associated j-th service type
  • the action (k, j) indicates that the first application identifier of the i-th user has the number of k-type interaction operation information of the second application identifier under the j-th service type, and ⁇ k represents the k-type interaction operation.
  • the weighting factor of the information indicates that the first application identifier of the i-th user has the number of k-type interaction operation information of the second application identifier under the j-th service type, and ⁇ k represents the k-type interaction operation.
  • the data generation sub-unit 124 is configured to perform normalization processing on the interaction weight data corresponding to each service type to generate an interaction weight vector corresponding to each service type, and according to the interaction corresponding to each service type The weight vector generates the service type corresponding to the first application identifier to point to the data;
  • the data generation sub-unit 124 performs normalization processing on the interaction weight data corresponding to each service type to generate an interaction weight vector corresponding to each service type, and according to each service type.
  • the parameter determining unit 13 is configured to determine the service type pointing data as the crediting feature parameter corresponding to the first application identifier
  • the parameter determining unit 13 may determine the service type pointing data as a credit characteristic parameter corresponding to the first application identifier, and apply the service type pointing data to a preset credit model. As an input parameter of the credit model.
  • FIG. 6 is a schematic structural diagram of a parameter determining unit according to an embodiment of the present application.
  • the parameter determining unit 13 may include:
  • a type obtaining sub-unit 131 configured to acquire, in the service type pointing data, a first service type that the interaction weight vector satisfies a preset weight threshold
  • a parameter determining sub-unit 132 configured to determine an interaction weight vector corresponding to the first service type as a credit feature parameter corresponding to the first application identifier
  • the type obtaining sub-unit 131 may obtain, in the service type pointing data, a first service type in which the interaction weight vector satisfies a preset weight threshold, and the parameter determining sub-unit 132 corresponds the first service type.
  • the interaction weight vector is determined as the credit characteristic parameter corresponding to the first application identifier, and the credit characteristic parameter corresponding to the first application identifier may be applied to the preset credit model as a kind of the credit model. Input parameters.
  • the interoperability information is obtained according to the interaction information between the personal interaction identifier and the service public identifier and the service type corresponding to the service public identifier, and the service type corresponding to the personal interaction identifier is obtained, and the service type of the service public identifier and the user's individual are realized.
  • the combination of information avoids the waste of resources of the interactive application, and at the same time, the service type corresponding to the personal interaction identifier can be determined as the corresponding credit characteristic parameter, and the available credit characteristic resource under the interactive application is added;
  • the public identification configuration service type can further reflect the service characteristics of the service public identity and enrich the performance form of the service public identity; by using the interaction weight data to represent the relationship between the personal interaction identifier and the service public identity, the user can accurately reflect the public number of the user. Interests have improved the accuracy of the user's business interest.
  • FIG. 7 is a schematic structural diagram of another method for acquiring a credit feature according to an embodiment of the present application.
  • the credit information acquiring apparatus 1000 may include at least one processor 1001, such as a CPU, at least one network interface 1004, a user interface 1003, a memory 1005, and at least one communication bus 1002.
  • the communication bus 1002 is used to implement connection communication between these components.
  • the user interface 1003 can include a display and a keyboard.
  • the optional user interface 1003 can also include a standard wired interface and a wireless interface.
  • the network interface 1004 can optionally include a standard wired interface, a wireless interface (such as a WI-FI interface).
  • the memory 1005 may be a high speed RAM memory or a non-volatile memory such as at least one disk memory.
  • the memory 1005 can also optionally be at least one storage device located remotely from the aforementioned processor 1001. As shown in FIG. 7, an operating system, a network communication module, a user interface module, and a feature acquisition application may be included in the memory 1005 as a computer storage medium.
  • the user interface 1003 is mainly used to provide an input interface for the user to acquire data input by the user;
  • the network interface 1004 is configured to connect with the user terminal to acquire data sent by the user terminal.
  • the processor 1001 can be used to call the feature acquisition application stored in the memory 1005, and specifically perform the following operations:
  • the interaction application Recording, according to the interaction application, the interaction information between the first application identifier and each of the at least one second application identifier, where the first application identifier is a personal interaction identifier under the interaction application, the at least one The second application identifier is the at least one service public identifier associated with the first application identifier in the interaction application;
  • the service type pointing data is determined as a credit characteristic parameter corresponding to the first application identifier.
  • the processor 1001 further performs the following operations before performing the interaction operation between the first application identifier and each of the at least one second application identifier based on the interaction application:
  • the processor 1001 performs the following operations when performing interaction operation information between the first application identifier and each of the at least one second application identifier based on the interaction application:
  • the interaction operation information between the first application identifier and each of the at least one second application identifier is recorded in the preset time period based on the interaction application.
  • the processor 1001 is configured to acquire, according to the interaction operation information between the first application identifier and each second application identifier, and the service type corresponding to each of the second application identifiers.
  • the service type corresponding to an application identifier points to data, perform the following operations:
  • the processor 1001 when the processor 1001 determines to determine the service type pointing data as the credit characteristic parameter corresponding to the first application identifier, the processor 1001 performs the following operations:
  • the interaction weight vector corresponding to the first service type is determined as the credit feature parameter corresponding to the first application identifier.
  • the interoperability information is obtained according to the interaction information between the personal interaction identifier and the service public identifier and the service type corresponding to the service public identifier, and the service type corresponding to the personal interaction identifier is obtained, and the service type of the service public identifier and the user's individual are realized.
  • the combination of information avoids the waste of resources of the interactive application, and at the same time, the service type corresponding to the personal interaction identifier can be determined as the corresponding credit characteristic parameter, and the available credit characteristic resource under the interactive application is added;
  • the public identification configuration service type can further reflect the service characteristics of the service public identity and enrich the performance form of the service public identity; by using the interaction weight data to represent the relationship between the personal interaction identifier and the service public identity, the user can accurately reflect the public number of the user. Interests have improved the accuracy of the user's business interest.
  • the storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).
  • the present application therefore also provides a storage medium having stored therein computer readable instructions that are executed by at least one processor for performing any of the above-described embodiments of the present application.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Multimedia (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • User Interface Of Digital Computer (AREA)

Abstract

本申请实施例公开一种征信特征获取方法及其设备，其中方法包括如下步骤：基于交互应用记录第一应用标识与至少一个第二应用标识中每个第二应用标识间的交互操作信息，所述第一应用标识为所述交互应用下的个人交互标识，所述至少一个第二应用标识为所述交互应用下所述第一应用标识所关联的至少一个业务公众标识；根据所述第一应用标识与每个第二应用标识间的交互操作信息以及所述每个第二应用标识对应的业务类型，获取所述第一应用标识对应的业务类型指向数据；将所述业务类型指向数据确定为所述第一应用标识对应的征信特征参数。采用本申请，可以结合业务公众标识的业务类型与用户的个人信息，增加交互应用下的可获取的征信特征资源。

Description

征信特征获取方法及其设备
本申请要求于2016年5月24日提交中国专利局、申请号为201610347923.3、发明名称为“一种征信特征获取方法及其设备”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
本申请涉及计算机技术领域，尤其涉及一种征信特征获取方法及其设备。
背景技术
随着计算机技术不断的开发和完善，用户间可以通过交互应用提供的交互平台进行通讯、例如：即时通讯应用、微博应用等，同时还可以基于交互应用下的业务公众标识向关联的用户群体发送订阅信息等，提升了用户间的交互性。
发明内容
本申请实施例提供一种征信特征获取方法及其设备，可以结合业务公众标识的业务类型与用户的个人信息，增加交互应用下的可获取的征信特征资源。
本申请实施例第一方面提供了一种征信特征获取方法，可包括：
基于交互应用记录第一应用标识与至少一个第二应用标识中每个第二应用标识间的交互操作信息，所述第一应用标识为所述交互应用下的个人交互标识，所述至少一个第二应用标识为所述交互应用下所述第一应用标识所关联的至少一个业务公众标识；
根据所述第一应用标识与每个第二应用标识间的交互操作信息以及所述每个第二应用标识对应的业务类型，获取所述第一应用标识对应的业务类型指向数据；
将所述业务类型指向数据确定为所述第一应用标识对应的征信特征参数。
本申请实施例第二方面提供了一种征信特征获取设备，可包括：
信息记录单元，用于基于交互应用记录第一应用标识与至少一个第二应用标识中每个第二应用标识间的交互操作信息，所述第一应用标识为所述交互应用下的个人交互标识，所述至少一个第二应用标识为所述交互应用下所述第一应用标识所关 联的至少一个业务公众标识；
数据获取单元，用于根据所述第一应用标识与每个第二应用标识间的交互操作信息以及所述每个第二应用标识对应的业务类型，获取所述第一应用标识对应的业务类型指向数据；
参数确定单元，用于将所述业务类型指向数据确定为所述第一应用标识对应的征信特征参数。
在本申请实施例中，通过记录交互应用下个人交互标识与业务公众标识间的交互操作信息，并根据个人交互标识与业务公众标识间的交互操作信息以及业务公众标识对应的业务类型，获取个人交互标识对应的业务类型指向数据，实现了业务公众标识的业务类型与用户的个人信息的结合，避免了交互应用的资源浪费，同时可以将个人交互标识对应的业务类型指向数据确定为对应的征信特征参数，增加了交互应用下的可获取的征信特征资源。
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的附图。
图1是本申请实施例提供的一种征信特征获取方法的流程示意图；
图2是本申请实施例提供的另一种征信特征获取方法的流程示意图；
图3是本申请实施例提供的一种征信特征获取设备的结构示意图；
图4是本申请实施例提供的另一种征信特征获取设备的结构示意图；
图5是本申请实施例提供的数据获取单元的结构示意图；
图6是本申请实施例提供的参数确定单元的结构示意图；
图7是本申请实施例提供的又一种征信特征获取设备的结构示意图。
具体实施方式
下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本申请一部分实施例，而不是全部的实 施例。基于本申请中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本申请保护的范围。
在一种交互应用下，基于同一个业务公众标识，其发送的订阅信息存在信息相关性，即业务类型(例如：体育类、音乐类等)，而用户的个人交互标识与业务公众标识仅仅是通过关联的方式进行绑定，并不存在其它的个人信息记录，因此无法将业务公众标识的业务类型与用户的个人信息进行结合，造成了交互应用的资源浪费，进而减少了交互应用下的可获取的征信特征资源。
本申请实施例提供的征信特征获取方法可以应用于即时通讯应用、社交应用等交互应用的场景，例如：征信特征获取设备基于交互应用记录第一应用标识与至少一个第二应用标识中每个第二应用标识间的交互操作信息，所述征信特征获取设备根据所述第一应用标识与每个第二应用标识间的交互操作信息以及所述每个第二应用标识对应的业务类型，获取所述第一应用标识对应的业务类型指向数据，所述征信特征获取设备将所述业务类型指向数据确定为所述第一应用标识对应的征信特征参数的场景等。通过记录交互应用下个人交互标识与业务公众标识间的交互操作信息，并根据个人交互标识与业务公众标识间的交互操作信息以及业务公众标识对应的业务类型，获取个人交互标识对应的业务类型指向数据，实现了业务公众标识的业务类型与用户的个人信息的结合，避免了交互应用的资源浪费，同时可以将个人交互标识对应的业务类型指向数据确定为对应的征信特征参数，增加了交互应用下的可获取的征信特征资源。
本申请实施例涉及的征信特征获取设备具体可以为交互应用对应的后台服务设备；所述交互应用可以包括即时通信应用、社交应用等具备建立公众业务群组以提供公众业务服务的功能在内的应用；所述第一应用标识为所述交互应用下的个人交互标识，所述至少一个第二应用标识为所述交互应用下所述第一应用标识所关联的至少一个业务公众标识，通过所述业务公众标识，可以基于所述交互应用提供的交互平台向特定的个人交互应用进行文字、图片、语音、视频等具备一定业务类型交互信息。
该个人交互标识可以为用户在该交互应用中注册的用于使用该交互应用以与其他用户进行交互的账号。用户可以使用该个人交互标识登录该交互应用。当请求添加另一用户为好友时，生成包含该个人交互标识的添加请求。可以利用该个人交互 标识与另外一个个人交互标识建立包含两个个人交互标识的会话。
业务公众标识是一种提供公众业务的公众平台的帐号类型，包括：服务号、订阅号和企业号。与个人交互标识不同的是，持业务公众标识的用户无法主动去添加好友，只能被其他人添加为好友，其他用户可以利用该业务公众标识搜索并关注该公众业务，即可建立该业务公众标识和该用户使用的个人交互标识之间关联关系。或者，其他用户可以扫描包含该业务公众标识的二维码，链接到该公众业务的页面，通过关注该公众业务，建立该业务公众标识和该用户使用的个人交互标识之间关联关系。可以利用该业务公众标识作为发送方向与之建立关联关系的其他个人交互标识推送信息，例如订阅信息，广告信息、通知信息等。当一用户使用一个人交互标识做为发送方向作为接收方的该业务公众标识发送信息时，持有该业务公众标识的用户，例如企业的管理人员可以在其消息列表中显示该用户发送的信息。如果预先设置自动回复功能，该自动回复功能用于当接收到的用户发送的信息包含预设关键词时，将与该关键词对应的回复信息发送给该个人交互标识。只有持有该业务公众标识的用户可以接收到该用户发送的信息，其他持有与该业务公众标识相关联的个人交互标识的用户并不能接收到该用户发送的信息。所以，利用业务公众标识和个人交互标识建立的会话与利用多个个人交互标识建立的群组会话不同。加入到该群组会话的用户利用其个人交互标识发送的信息均被转发到该群组中所有其他个人交互标识，也能接收到群组会话中任何其他个人交互标识发送的信息。
下面将结合附图1-附图3，对本申请实施例提供的征信特征获取方法进行详细介绍。
请参见图1，为本申请实施例提供了一种征信特征获取方法的流程示意图。如图1所示，本申请实施例的所述方法可以包括以下步骤S101-步骤S103。
S101，基于交互应用记录第一应用标识与至少一个第二应用标识中每个第二应用标识间的交互操作信息。
具体的，征信特征获取设备可以基于交互应用记录第一应用标识与至少一个第二应用标识中每个第二应用标识间的交互操作信息。第一应用标识与至少一个第二应用标识中每个第二应用标识间的交互操作信息可以为该第一应用标识与至少一个第二应用标识中每个第二应用标识间在基于该交互应用平台进行交互时而产生的信息，可包括多种信息类型中的一种或多种。交互操作信息类型可包括：订阅类操作 信息、上下行消息类操作信息、菜单点击类操作信息、图文阅读类操作信息以及转发类操作信息等。在交互应用中，一个第一应用标识可以关联绑定多个第二应用标识，一个第二应用标识可以关联绑定多个第一应用标识。进一步的，所述征信特征获取设备可以基于交互应用在预设时间段内记录第一应用标识与至少一个第二应用标识中每个第二应用标识间的交互操作信息。
S102，根据所述第一应用标识与每个第二应用标识间的交互操作信息以及所述每个第二应用标识对应的业务类型，获取所述第一应用标识对应的业务类型指向数据。
具体的，所述征信特征获取设备可以根据所述第一应用标识与每个第二应用标识间的交互操作信息以及所述每个第二应用标识对应的业务类型，获取所述第一应用标识对应的业务类型指向数据。所述征信特征获取设备可以基于交互应用预先为所述每个第二应用标识配置对应的业务类型。所述业务类型可以为行业分类，例如：餐饮美食、体育健身、金融理财、旅游、交通等。所述第一应用标识对应的业务类型指向数据用于表示所述第一应用标识的持有用户对业务类型的兴趣指数向量。
S103，将所述业务类型指向数据确定为所述第一应用标识对应的征信特征参数。
具体的，所述征信特征获取设备可以将所述业务类型指向数据确定为所述第一应用标识对应的征信特征参数，可以将所述业务类型指向数据应用到预设的征信模型中，作为所述征信模型的一种输入参数。
在本申请实施例中，通过记录交互应用下个人交互标识与业务公众标识间的交互操作信息，并根据个人交互标识与业务公众标识间的交互操作信息以及业务公众标识对应的业务类型，获取个人交互标识对应的业务类型指向数据，实现了业务公众标识的业务类型与用户的个人信息的结合，避免了交互应用的资源浪费，同时可以将个人交互标识对应的业务类型指向数据确定为对应的征信特征参数，增加了交互应用下的可获取的征信特征资源。
请参见图2，为本申请实施例提供了另一种征信特征获取方法的流程示意图。如图2所示，本申请实施例的所述方法可以包括以下步骤S201-步骤S208。
S201，基于交互应用配置至少一个第二应用标识中每个第二应用标识对应的业务类型。
具体的，征信特征获取设备可以基于交互应用预先为所述每个第二应用标识配置对应的业务类型，所述每个第二应用标识配置对应的业务类型可以是在对所述每个第二应用标识进行注册时，由用户自行填写，或者也可以为所述征信特征获取设备根据统计的所述每个第二应用标识在一段时间内发布的消息内容等计算生成的。所述业务类型可以为行业分类，例如：餐饮美食、体育健身、金融理财、旅游、交通等。
S202，基于交互应用记录第一应用标识与至少一个第二应用标识中每个第二应用标识间的交互操作信息。
具体的，所述征信特征获取设备可以基于交互应用记录第一应用标识与至少一个第二应用标识中每个第二应用标识间的交互操作信息，所述交互操作信息可以包括订阅类操作信息、上下行消息类操作信息、菜单点击类操作信息、图文阅读类操作信息以及转发类操作信息等一种或多种。可以理解的是，在交互应用中，一个第一应用标识可以关联绑定多个第二应用标识，一个第二应用标识可以关联绑定多个第一应用标识。进一步的，所述征信特征获取设备可以基于交互应用在预设时间段内记录第一应用标识与至少一个第二应用标识中每个第二应用标识间的交互操作信息。
S203，基于业务类型对所述至少一个第二应用标识进行归类处理，并在归类处理后生成至少一个应用标识集合。
具体的，所述征信特征获取设备可以基于业务类型对所述至少一个第二应用标识进行归类处理，并在归类处理后生成至少一个应用标识集合。所述至少一个应用标识集合用于表示所述第一应用标识关联的至少一种业务类型，即每个应用标识集合表示一种业务类型。
S204，对所述至少一个应用标识集合中每个应用标识集合的交互操作信息进行分类统计，获取所述每个应用标识集合中每类交互操作信息的个数。
具体的，所述征信特征获取设备可以对所述至少一个应用标识集合中每个应用标识集合的交互操作信息进行分类统计，获取所述每个应用标识集合中每类交互操作信息的个数，例如：在1个月内统计到第一应用标识存在对餐饮美食类的应用标识集合中的第二应用标识的订阅类操作信息有5次等。
S205，根据所述每个应用标识集合中每类交互操作信息的个数计算至少一个业 务类型中每个业务类型对应的交互权重数据。
具体的，所述征信特征获取设备可以根据所述每个应用标识集合中每类交互操作信息的个数，计算至少一个业务类型中每个业务类型对应的交互权重数据，交互权重数据Biz(ui，tj)可以采用以下公式1进行计算：
Biz(ui,tj)＝1/(1+exp(-cn(i,j))
其中，ui表示第i个用户的第一应用标识，tj表示第j个业务类型，cn(i,j)表示第i个用户的第一应用标识与关联的第j个业务类型下的第二应用标识间的关系数据，关系数据具体的可以采用以下公式2进行计算：
Figure PCTCN2017083944-appb-000001
其中，Action(k,j)表示第i个用户的第一应用标识存在对第j个业务类型下的第二应用标识的第k类交互操作信息的个数，αk表示第k类交互操作信息的权重系数。
S206，对所述每个业务类型对应的交互权重数据进行归一化处理以生成所述每个业务类型对应的交互权重向量，并根据所述每个业务类型对应的交互权重向量生成所述第一应用标识对应的业务类型指向数据。
具体的，所述征信特征获取设备对所述每个业务类型对应的交互权重数据进行归一化处理以生成所述每个业务类型对应的交互权重向量，并根据所述每个业务类型对应的交互权重向量生成所述第一应用标识对应的业务类型指向数据，依据上述举例，将第一应用标识对应的每个业务类型对应的交互权重数据生成数据矩阵X＝[x1，x2，…，xm]T，其中，m表示业务类型的个数，可以采用softmax函数对X中的各个分量进行归一化处理，得到所述第一应用标识对应的业务类型指向数据Xnorm＝[softmax(x1)，softmax(x2)，…softmax(xm)]T。
从上述描述可见，第一应用标识对应的业务类型指向数据是对与所述第一应用标识关联的每种业务类型中每种交互操作信息的个数进行统计和处理得到每种业务类型对应的交互权重数据。
S207，从所述业务类型指向数据中获取交互权重向量满足预设权重阈值的第一业务类型。
S208，将所述第一业务类型对应的交互权重向量确定为所述第一应用标识对应的征信特征参数。
具体的，所述征信特征获取设备可以在所述业务类型指向数据中获取交互权重向量满足预设权重阈值的第一业务类型，并将所述第一业务类型对应的交互权重向量确定为所述第一应用标识对应的征信特征参数，可以将第一应用标识对应的征信特征参数应用到预设的征信模型中，作为所述征信模型的一种输入参数。
在本申请实施例中，上述至少一个第二应用标识可以为业务公众标识。通过记录交互应用下个人交互标识与业务公众标识间的交互操作信息，并根据个人交互标识与业务公众标识间的交互操作信息以及业务公众标识对应的业务类型，获取个人交互标识对应的业务类型指向数据，实现了业务公众标识的业务类型与用户的个人信息的结合，可以将获取的个人交互标识对应的业务类型指向数据存储为大数据，充分利用交互中产生的交互数据，避免接收用户大量的手动输入而产生的交互。同时可以将个人交互标识对应的业务类型指向数据确定为对应的征信特征参数，增加了交互应用下的可获取的征信特征资源。通过对业务公众标识配置业务类型，可以进一步体现业务公众标识的业务特性，丰富了业务公众标识的表现形式。通过采用交互权重数据表示个人交互标识与业务公众标识的关系边，可以准确反映用户对公众号的兴趣，提升了对用户的业务兴趣指向的挖掘准确度。
下面将结合附图3-附图6，对本申请实施例提供的征信特征获取设备进行详细介绍。需要说明的是，附图3-附图6所示的征信特征获取设备，用于执行本申请图1和图2所示实施例的方法，为了便于说明，仅示出了与本申请实施例相关的部分，具体技术细节未揭示的，请参照本申请图1和图2所示的实施例。
请参见图3，为本申请实施例提供了一种征信特征获取设备的结构示意图。如图3所示，本申请实施例的所述通信连接设备1可以包括：信息记录单元11、数据获取单元12和参数确定单元13。
信息记录单元11，用于基于交互应用记录第一应用标识与至少一个第二应用标识中每个第二应用标识间的交互操作信息；
具体实现中，所述信息记录单元11可以基于交互应用记录第一应用标识与至少一个第二应用标识中每个第二应用标识间的交互操作信息，所述交互操作信息可以 包括订阅类操作信息、上下行消息类操作信息、菜单点击类操作信息、图文阅读类操作信息以及转发类操作信息等一种或多种，可以理解的是，在交互应用中，一个第一应用标识可以关联绑定多个第二应用标识，一个第二应用标识可以关联绑定多个第一应用标识。进一步的，所述信息记录单元11可以基于交互应用在预设时间段内记录第一应用标识与至少一个第二应用标识中每个第二应用标识间的交互操作信息。
数据获取单元12，用于根据所述第一应用标识与每个第二应用标识间的交互操作信息以及所述每个第二应用标识对应的业务类型，获取所述第一应用标识对应的业务类型指向数据；
具体实现中，所述数据获取单元12可以根据所述第一应用标识与每个第二应用标识间的交互操作信息以及所述每个第二应用标识对应的业务类型，获取所述第一应用标识对应的业务类型指向数据，可以理解的是，所述征信特征获取设备1可以基于交互应用预先为所述每个第二应用标识配置对应的业务类型。所述业务类型可以为行业分类，例如：餐饮美食、体育健身、金融理财、旅游、交通等。所述第一应用标识对应的业务类型指向数据用于表示所述第一应用标识的持有用户对业务类型的兴趣指数向量。
参数确定单元13，用于将所述业务类型指向数据确定为所述第一应用标识对应的征信特征参数；
具体实现中，所述参数确定单元13可以将所述业务类型指向数据确定为所述第一应用标识对应的征信特征参数，可以将所述业务类型指向数据应用到预设的征信模型中，作为所述征信模型的一种输入参数。
在本申请实施例中，通过记录交互应用下个人交互标识与业务公众标识间的交互操作信息，并根据个人交互标识与业务公众标识间的交互操作信息以及业务公众标识对应的业务类型，获取个人交互标识对应的业务类型指向数据，实现了业务公众标识的业务类型与用户的个人信息的结合，避免了交互应用的资源浪费，同时可以将个人交互标识对应的业务类型指向数据确定为对应的征信特征参数，增加了交互应用下的可获取的征信特征资源。
请参见图4，为本申请实施例提供了另一种征信特征获取设备的结构示意图。 如图4所示，本申请实施例的所述通信连接设备1可以包括：信息记录单元11、数据获取单元12、参数确定单元13和类型配置单元14。
类型配置单元14，用于基于交互应用配置至少一个第二应用标识中每个第二应用标识对应的业务类型；
具体实现中，所述类型配置单元14可以基于交互应用预先为所述每个第二应用标识配置对应的业务类型，所述每个第二应用标识配置对应的业务类型可以是在对所述每个第二应用标识进行注册时，由用户自行填写，或者也可以为所述类型配置单元14根据统计的所述每个第二应用标识在一段时间内发布的消息内容等计算生成的。所述业务类型可以为行业分类，例如：餐饮美食、体育健身、金融理财、旅游、交通等。
信息记录单元11，用于基于交互应用记录第一应用标识与至少一个第二应用标识中每个第二应用标识间的交互操作信息；
具体实现中，所述信息记录单元11可以基于交互应用记录第一应用标识与至少一个第二应用标识中每个第二应用标识间的交互操作信息，所述交互操作信息可以包括订阅类操作信息、上下行消息类操作信息、菜单点击类操作信息、图文阅读类操作信息以及转发类操作信息等一种或多种，可以理解的是，在交互应用中，一个第一应用标识可以关联绑定多个第二应用标识，一个第二应用标识可以关联绑定多个第一应用标识。进一步的，所述信息记录单元11可以基于交互应用在预设时间段内记录第一应用标识与至少一个第二应用标识中每个第二应用标识间的交互操作信息。
数据获取单元12，用于根据所述第一应用标识与每个第二应用标识间的交互操作信息以及所述每个第二应用标识对应的业务类型，获取所述第一应用标识对应的业务类型指向数据；
具体实现中，所述数据获取单元12可以根据所述第一应用标识与每个第二应用标识间的交互操作信息以及所述每个第二应用标识对应的业务类型，获取所述第一应用标识对应的业务类型指向数据，可以理解的是，所述征信特征获取设备1可以基于交互应用预先为所述每个第二应用标识配置对应的业务类型。所述业务类型可以为行业分类，例如：餐饮美食、体育健身、金融理财、旅游、交通等。所述第一应用标识对应的业务类型指向数据用于表示所述第一应用标识的持有用户对业务类 型的兴趣指数向量。
具体的，请一并参见图5，为本申请实施例提供了数据获取单元的结构示意图。如图5所示，所述数据获取单元12可以包括：
集合生成子单元121，用于基于业务类型对所述至少一个第二应用标识进行归类处理，并在归类处理后生成至少一个应用标识集合；
具体实现中，所述集合生成子单元121可以基于业务类型对所述至少一个第二应用标识进行归类处理，并在归类处理后生成至少一个应用标识集合，可以理解的是，所述至少一个应用标识集合用于表示所述第一应用标识关联的至少一种业务类型，即每个应用标识集合表示一种业务类型。
信息个数获取子单元122，用于对所述至少一个应用标识集合中每个应用标识集合的交互操作信息进行分类统计，获取所述每个应用标识集合中每类交互操作信息的个数；
具体实现中，所述信息个数获取子单元122可以对所述至少一个应用标识集合中每个应用标识集合的交互操作信息进行分类统计，获取所述每个应用标识集合中每类交互操作信息的个数，例如：在1个月内统计到第一应用标识存在对餐饮美食类的应用标识集合中的第二应用标识的订阅类操作信息有5次等。
数据计算子单元123，用于根据所述每个应用标识集合中每类交互操作信息的个数，计算至少一个业务类型中每个业务类型对应的交互权重数据；
具体实现中，所述数据计算子单元123可以根据所述每个应用标识集合中每类交互操作信息的个数，计算至少一个业务类型中每个业务类型对应的交互权重数据，交互权重数据Biz(ui，tj)可以采用以下公式1进行计算：
Biz(ui,tj)＝1/(1+exp(-cn(i,j))
其中，ui表示第i个用户的第一应用标识，tj表示第j个业务类型，cn(i,j)表示第i个用户的第一应用标识与关联的第j个业务类型下的第二应用标识间的关系数据，关系数据具体的可以采用以下公式2进行计算：
Figure PCTCN2017083944-appb-000002
其中，Action(k,j)表示第i个用户的第一应用标识存在对第j个业务类型下的 第二应用标识的第k类交互操作信息的个数，αk表示第k类交互操作信息的权重系数。
数据生成子单元124，用于对所述每个业务类型对应的交互权重数据进行归一化处理以生成所述每个业务类型对应的交互权重向量，并根据所述每个业务类型对应的交互权重向量生成所述第一应用标识对应的业务类型指向数据；
具体实现中，所述数据生成子单元124对所述每个业务类型对应的交互权重数据进行归一化处理以生成所述每个业务类型对应的交互权重向量，并根据所述每个业务类型对应的交互权重向量生成所述第一应用标识对应的业务类型指向数据，依据上述举例，将第一应用标识对应的每个业务类型对应的交互权重数据生成数据矩阵X＝[x1，x2，…，xm]T，其中，m表示业务类型的个数，可以采用softmax函数对X中的各个分量进行归一化处理，得到所述第一应用标识对应的业务类型指向数据Xnorm＝[softmax(x1)，softmax(x2)，…softmax(xm)]T。
参数确定单元13，用于将所述业务类型指向数据确定为所述第一应用标识对应的征信特征参数；
具体实现中，所述参数确定单元13可以将所述业务类型指向数据确定为所述第一应用标识对应的征信特征参数，可以将所述业务类型指向数据应用到预设的征信模型中，作为所述征信模型的一种输入参数。
具体的，请一并参见图6，为本申请实施例提供了参数确定单元的结构示意图。如图6所示，所述参数确定单元13可以包括：
类型获取子单元131，用于在所述业务类型指向数据中获取交互权重向量满足预设权重阈值的第一业务类型；
参数确定子单元132，用于将所述第一业务类型对应的交互权重向量确定为所述第一应用标识对应的征信特征参数；
具体实现中，所述类型获取子单元131可以在所述业务类型指向数据中获取交互权重向量满足预设权重阈值的第一业务类型，所述参数确定子单元132将所述第一业务类型对应的交互权重向量确定为所述第一应用标识对应的征信特征参数，可以将第一应用标识对应的征信特征参数应用到预设的征信模型中，作为所述征信模型的一种输入参数。
在本申请实施例中，通过记录交互应用下个人交互标识与业务公众标识间的交 互操作信息，并根据个人交互标识与业务公众标识间的交互操作信息以及业务公众标识对应的业务类型，获取个人交互标识对应的业务类型指向数据，实现了业务公众标识的业务类型与用户的个人信息的结合，避免了交互应用的资源浪费，同时可以将个人交互标识对应的业务类型指向数据确定为对应的征信特征参数，增加了交互应用下的可获取的征信特征资源；通过对业务公众标识配置业务类型，可以进一步体现业务公众标识的业务特性，丰富了业务公众标识的表现形式；通过采用交互权重数据表示个人交互标识与业务公众标识的关系边，可以准确反映用户对公众号的兴趣，提升了对用户的业务兴趣指向的挖掘准确度。
请参见图7，为本申请实施例提供了又一种征信特征获取设备的结构示意图。如图7所示，所述征信特征获取设备1000可以包括：至少一个处理器1001，例如CPU，至少一个网络接口1004，用户接口1003，存储器1005，至少一个通信总线1002。其中，通信总线1002用于实现这些组件之间的连接通信。其中，用户接口1003可以包括显示屏(Display)、键盘(Keyboard)，可选用户接口1003还可以包括标准的有线接口、无线接口。网络接口1004可选的可以包括标准的有线接口、无线接口(如WI-FI接口)。存储器1005可以是高速RAM存储器，也可以是非不稳定的存储器(non-volatile memory)，例如至少一个磁盘存储器。存储器1005可选的还可以是至少一个位于远离前述处理器1001的存储装置。如图7所示，作为一种计算机存储介质的存储器1005中可以包括操作系统、网络通信模块、用户接口模块以及特征获取应用程序。
在图7所示的征信特征获取设备1000中，用户接口1003主要用于为用户提供输入的接口，获取用户输入的数据；网络接口1004用于与用户终端相连接，获取用户终端发送的数据；而处理器1001可以用于调用存储器1005中存储的特征获取应用程序，并具体执行以下操作：
基于交互应用记录第一应用标识与至少一个第二应用标识中每个第二应用标识间的交互操作信息，所述第一应用标识为所述交互应用下的个人交互标识，所述至少一个第二应用标识为所述交互应用下所述第一应用标识所关联的至少一个业务公众标识；
根据所述第一应用标识与每个第二应用标识间的交互操作信息以及所述每个第 二应用标识对应的业务类型，获取所述第一应用标识对应的业务类型指向数据；
将所述业务类型指向数据确定为所述第一应用标识对应的征信特征参数。
在一个实施例中，所述处理器1001在执行基于交互应用记录第一应用标识和至少一个第二应用标识中每个第二应用标识间的交互操作信息之前，还执行以下操作：
基于交互应用配置至少一个第二应用标识中每个第二应用标识对应的业务类型。
在一个实施例中，所述处理器1001在执行基于交互应用记录第一应用标识与至少一个第二应用标识中每个第二应用标识间的交互操作信息时，具体执行以下操作：
基于交互应用在预设时间段内记录第一应用标识与至少一个第二应用标识中每个第二应用标识间的交互操作信息。
在一个实施例中，所述处理器1001在执行根据所述第一应用标识与每个第二应用标识间的交互操作信息以及所述每个第二应用标识对应的业务类型，获取所述第一应用标识对应的业务类型指向数据时，具体执行以下操作：
基于业务类型对所述至少一个第二应用标识进行归类处理，并在归类处理后生成至少一个应用标识集合；
对所述至少一个应用标识集合中每个应用标识集合的交互操作信息进行分类统计，获取所述每个应用标识集合中每类交互操作信息的个数；
根据所述每个应用标识集合中每类交互操作信息的个数计算至少一个业务类型中每个业务类型对应的交互权重数据；
对所述每个业务类型对应的交互权重数据进行归一化处理以生成所述每个业务类型对应的交互权重向量，并根据所述每个业务类型对应的交互权重向量生成所述第一应用标识对应的业务类型指向数据。
在一个实施例中，所述处理器1001在执行将所述业务类型指向数据确定为所述第一应用标识对应的征信特征参数时，具体执行以下操作：
在所述业务类型指向数据中获取交互权重向量满足预设权重阈值的第一业务类型；
将所述第一业务类型对应的交互权重向量确定为所述第一应用标识对应的征信特征参数。
在本申请实施例中，通过记录交互应用下个人交互标识与业务公众标识间的交 互操作信息，并根据个人交互标识与业务公众标识间的交互操作信息以及业务公众标识对应的业务类型，获取个人交互标识对应的业务类型指向数据，实现了业务公众标识的业务类型与用户的个人信息的结合，避免了交互应用的资源浪费，同时可以将个人交互标识对应的业务类型指向数据确定为对应的征信特征参数，增加了交互应用下的可获取的征信特征资源；通过对业务公众标识配置业务类型，可以进一步体现业务公众标识的业务特性，丰富了业务公众标识的表现形式；通过采用交互权重数据表示个人交互标识与业务公众标识的关系边，可以准确反映用户对公众号的兴趣，提升了对用户的业务兴趣指向的挖掘准确度。
本领域普通技术人员可以理解实现上述实施例方法中的全部或部分流程，是可以通过计算机程序来指令相关的硬件来完成，所述的程序可存储于一计算机可读取存储介质中，该程序在执行时，可包括如上述各方法的实施例的流程。其中，所述的存储介质可为磁碟、光盘、只读存储记忆体(Read-Only Memory，ROM)或随机存储记忆体(Random Access Memory，RAM)等。
因此本申请还提供了一种存储介质，其中存储有计算机可读指令，被至少一个处理器执行用于执行本申请上述方法的任何一种实施例。
以上所揭露的仅为本申请较佳实施例而已，当然不能以此来限定本申请之权利范围，因此依本申请权利要求所作的等同变化，仍属本申请所涵盖的范围。

Claims (11)

  1. 一种征信特征获取方法，其特征在于，包括：
    基于交互应用记录第一应用标识与至少一个第二应用标识中每个第二应用标识间的交互操作信息，所述第一应用标识为所述交互应用下的个人交互标识，所述至少一个第二应用标识为所述交互应用下所述第一应用标识所关联的至少一个业务公众标识；
    根据所述第一应用标识与每个第二应用标识间的交互操作信息以及所述每个第二应用标识对应的业务类型，获取所述第一应用标识对应的业务类型指向数据；
    将所述业务类型指向数据确定为所述第一应用标识对应的征信特征参数。
  2. 根据权利要求1所述的方法，其特征在于，所述基于交互应用记录第一应用标识和至少一个第二应用标识中每个第二应用标识间的交互操作信息之前，还包括：
    基于交互应用配置至少一个第二应用标识中每个第二应用标识对应的业务类型。
  3. 根据权利要求1所述的方法，其特征在于，所述基于交互应用记录第一应用标识与至少一个第二应用标识中每个第二应用标识间的交互操作信息，包括：
    基于交互应用在预设时间段内记录第一应用标识与至少一个第二应用标识中每个第二应用标识间的交互操作信息。
  4. 根据权利要求2所述的方法，其特征在于，所述根据所述第一应用标识与每个第二应用标识间的交互操作信息以及所述每个第二应用标识对应的业务类型，获取所述第一应用标识对应的业务类型指向数据，包括：
    基于业务类型对所述至少一个第二应用标识进行归类处理，并在归类处理后生成至少一个应用标识集合；
    对所述至少一个应用标识集合中每个应用标识集合的交互操作信息进行分类统计，获取所述每个应用标识集合中每类交互操作信息的个数；
    根据所述每个应用标识集合中每类交互操作信息的个数计算至少一个业务类型 中每个业务类型对应的交互权重数据；
    对所述每个业务类型对应的交互权重数据进行归一化处理以生成所述每个业务类型对应的交互权重向量，并根据所述每个业务类型对应的交互权重向量生成所述第一应用标识对应的业务类型指向数据。
  5. 根据权利要求4所述的方法，其特征在于，所述将所述业务类型指向数据确定为所述第一应用标识对应的征信特征参数，包括：
    在所述业务类型指向数据中获取交互权重向量满足预设权重阈值的第一业务类型；
    将所述第一业务类型对应的交互权重向量确定为所述第一应用标识对应的征信特征参数。
  6. 一种征信特征获取设备，其特征在于，包括：
    信息记录单元，用于基于交互应用记录第一应用标识与至少一个第二应用标识中每个第二应用标识间的交互操作信息，所述第一应用标识为所述交互应用下的个人交互标识，所述至少一个第二应用标识为所述交互应用下所述第一应用标识所关联的至少一个业务公众标识；
    数据获取单元，用于根据所述第一应用标识与每个第二应用标识间的交互操作信息以及所述每个第二应用标识对应的业务类型，获取所述第一应用标识对应的业务类型指向数据；
    参数确定单元，用于将所述业务类型指向数据确定为所述第一应用标识对应的征信特征参数。
  7. 根据权利要求6所述的设备，其特征在于，还包括：
    类型配置单元，用于基于交互应用配置至少一个第二应用标识中每个第二应用标识对应的业务类型。
  8. 根据权利要求6所述的设备，其特征在于，所述信息记录单元具体用于基于交互应用在预设时间段内记录第一应用标识与至少一个第二应用标识中每个第二应 用标识间的交互操作信息。
  9. 根据权利要求7所述的设备，其特征在于，所述数据获取单元包括：
    集合生成子单元，用于基于业务类型对所述至少一个第二应用标识进行归类处理，并在归类处理后生成至少一个应用标识集合；
    信息个数获取子单元，用于对所述至少一个应用标识集合中每个应用标识集合的交互操作信息进行分类统计，获取所述每个应用标识集合中每类交互操作信息的个数；
    数据计算子单元，用于根据所述每个应用标识集合中每类交互操作信息的个数，计算至少一个业务类型中每个业务类型对应的交互权重数据；
    数据生成子单元，用于对所述每个业务类型对应的交互权重数据进行归一化处理以生成所述每个业务类型对应的交互权重向量，并根据所述每个业务类型对应的交互权重向量生成所述第一应用标识对应的业务类型指向数据。
  10. 根据权利要求9所述的设备，其特征在于，所述参数确定单元包括：
    类型获取子单元，用于在所述业务类型指向数据中获取交互权重向量满足预设权重阈值的第一业务类型；
    参数确定子单元，用于将所述第一业务类型对应的交互权重向量确定为所述第一应用标识对应的征信特征参数。
  11. 一种计算机可读存储介质，存储有计算机可读指令，被至少一个处理器执行以
    执行权利要求1至5任一项所述的征信特征获取方法。
PCT/CN2017/083944 2016-05-24 2017-05-11 征信特征获取方法及其设备 WO2017202208A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201610347923.3 2016-05-24
CN201610347923.3A CN106027303B (zh) 2016-05-24 2016-05-24 一种征信特征获取方法及其设备

Publications (1)

Publication Number Publication Date
WO2017202208A1 true WO2017202208A1 (zh) 2017-11-30

Family

ID=57093115

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/083944 WO2017202208A1 (zh) 2016-05-24 2017-05-11 征信特征获取方法及其设备

Country Status (2)

Country Link
CN (1) CN106027303B (zh)
WO (1) WO2017202208A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108595579A (zh) * 2018-04-17 2018-09-28 平安普惠企业管理有限公司 联系人亲密度估算方法、装置、计算机设备和存储介质
CN111309614A (zh) * 2020-02-17 2020-06-19 支付宝(杭州)信息技术有限公司 A/b测试方法、装置及电子设备

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106027303B (zh) * 2016-05-24 2019-07-16 腾讯科技（深圳）有限公司 一种征信特征获取方法及其设备

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101572606A (zh) * 2009-06-12 2009-11-04 阿里巴巴集团控股有限公司 一种社会化网络中认证请求消息发送方法及装置
CN102855582A (zh) * 2011-06-29 2013-01-02 联想(北京)有限公司 一种获取数据的方法、装置及服务器
CN103532937A (zh) * 2013-09-29 2014-01-22 北京星网锐捷网络技术有限公司 应用识别验证方法及装置
CN106027303A (zh) * 2016-05-24 2016-10-12 腾讯科技（深圳）有限公司 一种征信特征获取方法及其设备

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102141986A (zh) * 2010-01-28 2011-08-03 北京邮电大学 基于用户行为的个性化信息提供方法及系统
CN103246670B (zh) * 2012-02-09 2016-02-17 深圳市腾讯计算机系统有限公司 微博排序、搜索、展示方法和系统
JP6282960B2 (ja) * 2014-09-02 2018-02-21 Kddi株式会社 情報プッシュ方法および装置
CN105069172B (zh) * 2015-09-09 2018-10-30 中国人民大学 兴趣标签生成方法

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101572606A (zh) * 2009-06-12 2009-11-04 阿里巴巴集团控股有限公司 一种社会化网络中认证请求消息发送方法及装置
CN102855582A (zh) * 2011-06-29 2013-01-02 联想(北京)有限公司 一种获取数据的方法、装置及服务器
CN103532937A (zh) * 2013-09-29 2014-01-22 北京星网锐捷网络技术有限公司 应用识别验证方法及装置
CN106027303A (zh) * 2016-05-24 2016-10-12 腾讯科技（深圳）有限公司 一种征信特征获取方法及其设备

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108595579A (zh) * 2018-04-17 2018-09-28 平安普惠企业管理有限公司 联系人亲密度估算方法、装置、计算机设备和存储介质
CN111309614A (zh) * 2020-02-17 2020-06-19 支付宝(杭州)信息技术有限公司 A/b测试方法、装置及电子设备
CN111309614B (zh) * 2020-02-17 2022-10-18 支付宝(杭州)信息技术有限公司 A/b测试方法、装置及电子设备

Also Published As

Publication number Publication date
CN106027303B (zh) 2019-07-16
CN106027303A (zh) 2016-10-12

Similar Documents

Publication Publication Date Title
US9948583B2 (en) Channel based communication and transaction system
US10187337B2 (en) Systems and methods for invoking chatbots in a channel based communication system
US8332476B2 (en) Social network virtual private network
US11677878B2 (en) Methods and systems for notifications in communications networks
US9515967B2 (en) Systems and methods for sharing data among multiple end user devices
JP2012504905A (ja) 相互にスレッド構成された異なるタイプの伝達情報表示
US20060294189A1 (en) Instant messaging with search
US20140201292A1 (en) Digital business card system performing social networking commonality comparisions, professional profile curation and personal brand management
US11902326B1 (en) Secure messaging integration with messaging applications
CA2915049A1 (en) Methods and systems relating to visual communications
WO2015085917A1 (en) Method, apparatus and system for processing information
US10944701B2 (en) Systems and methods for channel based communication and engagement through advertising units
US11017416B2 (en) Distributing electronic surveys to parties of an electronic communication
US11947547B1 (en) Contextual search using database indexes
WO2017045548A1 (zh) 一种功能界面显示方法及装置
WO2019100986A1 (zh) 一种信息发送方法及装置
US20180189017A1 (en) Synchronized, morphing user interface for multiple devices with dynamic interaction controls
WO2017202208A1 (zh) 征信特征获取方法及其设备
WO2022078397A1 (zh) 通信的方法、装置、设备及存储介质
US8738628B2 (en) Community profiling for social media
US10645053B2 (en) Generating a new user base using attractive e-mail addresses
US20130254331A1 (en) Information processing apparatus, information processing method, program, and information processing system
US9129025B2 (en) Automatically granting access to content in a microblog
US20220329545A1 (en) Intelligent Assistant Content Generation
KR102529213B1 (ko) 사용자에게 인터넷 홈페이지를 이용한 메시지 발송 서비스를 제공하기 위한 장치 및 방법

Legal Events

Date Code Title Description
NENP Non-entry into the national phase

Ref country code: DE

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

Ref document number: 17802054

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 17802054

Country of ref document: EP

Kind code of ref document: A1