CN111475540A

CN111475540A - Method and equipment for generating user relationship network

Info

Publication number: CN111475540A
Application number: CN202010165049.8A
Authority: CN
Inventors: 沈楚杰
Original assignee: Ping An Technology Shenzhen Co Ltd
Current assignee: Ping An Technology Shenzhen Co Ltd
Priority date: 2020-03-11
Filing date: 2020-03-11
Publication date: 2020-07-31

Abstract

The invention is suitable for the technical field of information processing, and provides a method and equipment for generating a user relationship network, wherein the method comprises the following steps: acquiring a historical interaction record of a target object, and generating a reference relation tree of the target object according to the historical interaction record; the reference relation tree comprises a plurality of interactive object nodes; respectively identifying the associated interactive objects of each interactive object node according to the first object information of each interactive object node on the reference relation tree and the second object information of all candidate interactive objects in the object library; generating an expanded relation tree of the reference relation tree based on the associated interactive objects; and constructing a user relationship network according to the expanded relationship trees of all the target objects. The invention can improve the coverage of the user relationship network, and determines the unrecorded incidence relation through the matching degree between the object information, thereby increasing the acquisition mode of the user relationship, and improving the accuracy and the processing quality of the subsequent operation executed based on the user relationship network.

Description

Method and equipment for generating user relationship network

Technical Field

The invention belongs to the technical field of information processing, and particularly relates to a method and equipment for generating a user relationship network.

Background

The user relationship network is often applied to scenes such as credit rating of users, potential customer mining and the like, and the accuracy and the coverage range of the user relationship network directly influence the processing quality of the tasks. The existing user relationship network establishing technology generally establishes a user relationship network based on the user relationship recorded by the existing interaction records, for example, the existence of the association relationship between two users is determined through information such as an applicant and an insured person on a policy, however, the user relationship network has a single establishing mode and a small coverage range, so that the accuracy and the processing quality of subsequent operations executed based on the user relationship network are reduced.

Disclosure of Invention

In view of this, embodiments of the present invention provide a method and an apparatus for generating a user relationship network, so as to solve the problems that, in the existing user relationship network generation technology, based on a user relationship recorded in an existing interaction record, a user relationship network is constructed in a single construction manner and with a small coverage, so that accuracy of subsequent association operations and processing quality are reduced.

A first aspect of an embodiment of the present invention provides a method for generating a user relationship network, including:

acquiring a historical interaction record of a target object, and generating a reference relation tree of the target object according to the historical interaction record; the reference relation tree comprises a plurality of interactive object nodes;

respectively identifying the associated interactive objects of the interactive object nodes according to the first object information of the interactive object nodes on the reference relation tree and the second object information of all candidate interactive objects in the object library;

generating an expanded relation tree of the reference relation tree based on the associated interactive object;

and constructing a user relationship network according to the expanded relationship trees of all the target objects.

A second aspect of the embodiments of the present invention provides a device for generating a user relationship network, including:

the reference relation tree establishing unit is used for acquiring a historical interaction record of a target object and generating a reference relation tree of the target object according to the historical interaction record; the reference relation tree comprises a plurality of interactive object nodes;

the associated interactive object identification unit is used for respectively identifying the associated interactive objects of the interactive object nodes according to the first object information of the interactive object nodes on the reference relation tree and the second object information of all candidate interactive objects in the object library;

the expansion relation tree establishing unit is used for generating an expansion relation tree of the reference relation tree based on the associated interactive object;

and the user relationship network construction unit is used for constructing a user relationship network according to the expanded relationship trees of all the target objects.

A third aspect of embodiments of the present invention provides a terminal device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the first aspect when executing the computer program.

A fourth aspect of embodiments of the present invention provides a computer-readable storage medium storing a computer program which, when executed by a processor, performs the steps of the first aspect.

The embodiment of the invention provides a method and equipment for generating a user relationship network, which has the following beneficial effects:

according to the embodiment of the invention, the reference relation tree of the target object is generated through the incidence relation between the history interactive object recorded in the history interactive record and the target object, the object information of each interactive object node on the reference relation tree is obtained to be matched with the object information of all candidate interactive objects in the object library, the associated interactive object of each interactive object node is determined according to the matching result, each associated interactive object is added to the reference relation tree, the expanded relation tree is generated, the user relation network of the whole object library is obtained according to the expanded relation trees of all the target objects, and the user relation network of the object library is automatically created. Compared with the existing method for generating the user relationship network, the embodiment of the invention does not only construct the user relationship network based on the interactive objects which are directly contacted with the target object, obtains the associated interactive objects which are indirectly associated with the target object on the basis of generating the reference relationship tree of the target object, expands the reference relationship tree to obtain the expanded relationship tree, thereby improving the coverage area of the user relationship network, determining the unrecorded associated relationship through the matching degree of the object information, increasing the obtaining mode of the user relationship, and improving the accuracy and the processing quality of the subsequent operation executed based on the user relationship network.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.

Fig. 1 is a flowchart illustrating an implementation of a method for generating a user relationship network according to a first embodiment of the present invention;

fig. 2 is a flowchart of a specific implementation of a method for generating a user relationship network according to a second embodiment of the present invention;

fig. 3 is a flowchart of a specific implementation of a method S102 for generating a user relationship network according to a third embodiment of the present invention;

fig. 4 is a flowchart illustrating an implementation details of a method S1021 for generating a user relationship network according to a fourth embodiment of the present invention;

fig. 5 is a flowchart of a detailed implementation of a method S102 for generating a user relationship network according to a fifth embodiment of the present invention;

fig. 6 is a flowchart of a specific implementation of a method S101 for generating a user relationship network according to a sixth embodiment of the present invention;

fig. 7 is a flowchart of a detailed implementation of a method S101 for generating a user relationship network according to a seventh embodiment of the present invention;

fig. 8 is a block diagram illustrating a structure of a device for generating a user relationship network according to an embodiment of the present invention;

fig. 9 is a schematic diagram of a terminal device according to another embodiment of the present invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

The embodiment of the invention generates the reference relation tree of the target object through the incidence relation between the history interactive object and the target object recorded in the history interactive record, and the object information of each interactive object node on the reference relation tree is obtained to be matched with the object information of all candidate interactive objects in the object library, determining the associated interactive objects of each interactive object node according to the matching result, adding each associated interactive object to the reference relation tree to generate an expanded relation tree, and the user relationship network of the whole object library is obtained according to the expanded relationship trees of all the target objects, so that the user relationship network of the object library is automatically created, the problems of single construction mode and small coverage range of the existing user relationship network generation technology are solved, and the problems of accuracy and processing quality of subsequent association operation are reduced.

In the embodiment of the invention, the execution subject of the process is the terminal equipment. The terminal devices include but are not limited to: the device comprises a server, a computer, a smart phone, a tablet computer and the like, and can execute the task of generating the user relationship network. Fig. 1 shows a flowchart of an implementation of a method for generating a user relationship network according to a first embodiment of the present invention, which is detailed as follows:

in S101, acquiring a history interaction record of a target object, and generating a reference relation tree of the target object according to the history interaction record; the reference relationship tree includes a plurality of interactive object nodes.

In this embodiment, the terminal device may be configured with a trigger condition for generating a user relationship network, where the trigger condition of the user relationship network includes time trigger or event trigger, and if the terminal device detects that any preset trigger condition is currently satisfied, the terminal device obtains a network operation parameter of an interaction database storing an interaction record, and if the network operation parameter is within a preset rated operation parameter range, it indicates that the current interaction database is not in an overload state or in a busy state, and at this time, downloads a historical interaction record of the target object from the interaction database; otherwise, if the network operation parameter is out of the preset rated operation parameter range, the current interactive database is in an overload state or in a network busy state, the current interactive database is added into the list to be executed, the network operation parameter where the interactive database is located is obtained according to the preset detection period, and if the network operation parameter is detected to be in the rated operation parameter range, the historical interactive record is downloaded from the interactive database.

In this embodiment, the terminal device may extract, according to the object identifier of the target object, the historical interaction record matched with the object identifier from the user database, and identify the extracted historical interaction record as the historical interaction record of the target object. The historical interaction record can be a record generated in the interaction process between a target object and other objects on an application with an interaction function, such as a preset social platform or a mailbox, for example, a chat record, a message, an email and the like; the historical interactive record can also be purchased product information of the target object, the purchased product information contains associated object information, and the associated object information is identified as a historical interactive object having an interactive relationship with the target object, for example, if the product information requires a user to fill an emergency contact or other contacts, the emergency contact and other contacts can be identified as the historical interactive object having an interactive relationship with the target object; for another example, the historical interaction record is purchased insurance policy information of the user, the purchased insurance policy information may include relevant user information such as an applicant, an insured person, an emergency contact person, and the like, and the relevant user is identified as the historical interaction object having an interaction relationship with the target object.

Optionally, in this embodiment, if the object type of the target object is a user account, the object type of the history interaction object carried in the history interaction record may also be the user account. And the same entity user can correspond to a plurality of different user accounts, in this case, the terminal device can identify the registration information of each user account, identify a plurality of different user accounts belonging to the same entity user according to the matching degree between the registration information of each user account, and if one user account of a certain entity user is detected to exist in the history interaction record of the target object, all user accounts associated with the entity user can be identified as the history interaction object of the target object.

In this embodiment, the terminal device may use the target object as a reference node, create an interaction object node for each history interaction object recorded in each history interaction record, and connect the reference node and each interaction object node, thereby generating a reference relationship tree of the target object. It should be noted that the terminal device may further record objects having direct association relationships of each history interactive object, and the method for identifying the direct association objects of the history interactive objects may determine, by referring to the above description, the downlink interactive nodes of the history interactive objects by using the history interactive records of the history interactive objects, and so on, thereby continuously downlink extending the reference relationship tree by using the target object as the reference node. Optionally, the terminal device may be configured with a maximum number of associated nodes, that is, the number of nodes between the nth-layer lower-link interaction node and the reference node of the target object is not greater than the maximum number of associated nodes. The reference relation tree is generated through historical interaction records, namely interaction operations exist between the target object and each interaction object node, and the reference relation tree is a reliable and recorded interaction relation.

In S102, the associated interactive objects of each interactive object node are respectively identified according to the first object information of each interactive object node on the reference relationship tree and the second object information of all candidate interactive objects in the object library.

In this embodiment, in order to improve the coverage of the user relationship network, the terminal device may identify the interaction relationship that is not recorded in the manner of S102, in addition to determining the recorded interaction relationship, that is, based on each interaction object node on the reference relationship tree, extend and expand the reference relationship tree, so as to mine more interaction relationships regarding the target object. The terminal equipment can extract first object information of each interactive object node from the user database, and the first object information can comprise object address, enterprise where the object is located, object enterprise address and other information related to object attributes. Similarly, the second object information may also include one or more of the above listed information related to the object property. The terminal equipment respectively calculates the matching degree between the first object information of the interactive object node and the second object information of the candidate interactive object, and selects the associated interactive object of the interactive object node based on the numerical value of the matching degree.

Optionally, in this embodiment, the first object information includes a region identifier, and when identifying the associated interactive object of the interactive object node, the terminal device may extract a candidate interactive object matched with the region identifier from the object library to perform matching degree calculation operation. Because the terminal equipment cannot determine the interaction relationship between the two objects from the historical interaction records, namely, no online interaction operation exists, offline interaction operation needs to be determined; however, if the interaction operation needs to be performed under the departure line, the geographic positions of the two objects should be close to each other, so that the two objects have a larger interaction probability, that is, belong to the same geographic area. Based on this, in order to reduce a large number of invalid matching degree calculations and improve the identification efficiency of the interactive objects, the terminal device may perform preliminary screening on all objects in the object library according to the area identifiers, select an object belonging to the same area as the interactive object node as a candidate interactive object, and determine the associated interactive object according to the second object information and the first object information of the extracted candidate interactive object.

In this embodiment, the way for the terminal device to identify the associated interaction object node may specifically be: and detecting whether one or more information items in the second object information of any candidate interaction object in the object library are matched with the information items of the first object information, and judging whether the candidate object is an association object of the interaction object node according to the number of the matched information items.

Preferably, in this embodiment, the terminal device may configure corresponding weighting coefficients for different information items, and the terminal device may calculate a matching degree between the interaction object node and the candidate interaction object according to the number of information items matched between the interaction object node and the candidate interaction object and a weight value corresponding to each information item, and select the candidate interaction object whose matching degree is greater than a preset threshold value as the associated interaction object. By configuring different weighting coefficients, the credibility contribution of each information item to interactive operation can be matched, and the accuracy of the matching degree is improved.

In S103, an expanded relationship tree of the reference relationship tree is generated based on the associated interaction object.

In this embodiment, after identifying the associated interactive object of each interactive object node, the terminal device may create a corresponding node for each associated interactive object on a preset reference relationship tree, connect the associated interactive object and the corresponding interactive object node, and perform the above operations on all interactive object nodes, thereby generating an extended relationship tree of the target object.

Optionally, in this embodiment, in order to improve readability of the expanded relationship tree, the terminal device may mark, according to an identification manner of the association relationship, a corresponding color for the interaction connection line between the interaction nodes, for example, the association relationship directly determined from the historical interaction records may be marked by red, and a potential association relationship indirectly determined from the object information is marked by green, specifically, if the terminal device selects based on the matching degree when identifying the associated interaction object, the shade of the marked color may be determined according to a magnitude of the matching degree value, and if the matching degree value is larger, the color of the corresponding interaction connection line is darker, that is, the pixel value is smaller; conversely, if the value of the matching degree is smaller, the color of the corresponding cross connecting line is lighter, that is, the pixel value is larger.

In S104, a user relationship network is constructed according to the expanded relationship trees of all the target objects.

In this embodiment, the terminal device may perform operations from S101 to S103 on each target object, generate an extended relationship tree of each target object, and merge multiple extended relationship trees according to an association relationship between each target object, thereby constructing and obtaining a user relationship network.

In this embodiment, if the terminal device needs to send the target information to a certain object in the user relationship network and does not record the communication address of the object, the terminal device may extract the propagation path of the object based on the user relationship network, send the target information to be sent to the target object corresponding to the head node of the propagation path, and then transfer the target information to the object through the interaction relationship between the target object and the object, so that the target information can be sent without determining the communication address of the object.

As can be seen from the above, in the method for generating a user relationship network according to the embodiment of the present invention, the reference relationship tree of the target object is generated according to the association relationship between the historical interaction object recorded in the historical interaction record and the target object, the object information of each interaction object node on the reference relationship tree is obtained and matched with the object information of all candidate interaction objects in the object library, the association interaction object of each interaction object node is determined according to the matching result, each association interaction object is added to the reference relationship tree, the extended relationship tree is generated, the user relationship network of the entire object library is obtained according to the extended relationship trees of all target objects, and the user relationship network of the object library is automatically created. Compared with the existing method for generating the user relationship network, the embodiment of the invention does not only construct the user relationship network based on the interactive objects which are directly contacted with the target object, obtains the associated interactive objects which are indirectly associated with the target object on the basis of generating the reference relationship tree of the target object, expands the reference relationship tree to obtain the expanded relationship tree, thereby improving the coverage area of the user relationship network, determining the unrecorded associated relationship through the matching degree of the object information, increasing the obtaining mode of the user relationship, and improving the accuracy and the processing quality of the subsequent operation executed based on the user relationship network.

Fig. 2 is a flowchart illustrating a specific implementation of a method for generating a user relationship network according to a second embodiment of the present invention. Referring to fig. 2, in the embodiment described with reference to fig. 1, after constructing a user relationship network according to the extended relationship trees of all the target objects in the method for generating a user relationship network provided in this embodiment, the method further includes: s201 to S203 are detailed as follows:

further, before the starting the video playing application and loading the video playing plug-in to the video playing application based on the plug-in identifier, the method further includes:

in S201, if a preset information transmission condition is satisfied, the radiation level of the target information associated with the information transmission condition is determined.

In this embodiment, after the user relationship network is generated, the terminal device may select the target user based on the user relationship network, and because an interaction relationship exists between two users, that is, a commonality exists between two users, if a certain user has a certain behavior tendency, the probability that another user having an interaction relationship with the certain user has the behavior tendency is higher, so that the target user can be selected through the user relationship network, and the accuracy of selecting the target user can be improved. For example, the terminal device may perform potential user mining according to the user relationship network, and if the user a purchases the target product, the other users having an association relationship with the user a may also have a purchase intention on the target product, that is, the other users having an association relationship with the user a are potential users of the target product, and the potential user mining is completed.

In this embodiment, when detecting that a preset information sending condition is currently met, the terminal device performs an operation of S201, where the information sending condition may be a time trigger condition, for example, a certain target product has a specific promotion period, and a plurality of promotion time points are configured based on the promotion period, and if detecting that the current time reaches the preset promotion time point, it identifies that the information sending condition is met; of course, the information sending condition may be an event triggering condition, for example, if release information of a certain target product is received, it is identified that the target product needs to be promoted, and at this time, the operation of S201 is executed.

In this embodiment, each information sending condition may be associated with at least one piece of target information, and if it is detected that the information sending condition is satisfied, the target information associated with the information sending condition is queried, and the radiation level pre-configured for the target information is determined.

In S202, extracting a radiation network centered on the target object according to the radiation level and the user relationship network; the maximum number of nodes between a last object node in the radiating network to a center node of the target object matches the radiation level.

In this embodiment, the terminal device may locate a node where the target object is located in the user relationship network, determine the maximum number of nodes according to the radiation level, and extract the radiation network with the target object as a center node from the user relationship network, where the number of nodes from the center node to the boundary node in the radiation network is not greater than the maximum number of nodes. It should be noted that the target object is an object associated with the target information, and if the target information is a network article of the social network, the target object is a user who has read the network article; if the target information is product information, the target object is a user who purchased the product or other products similar to the product.

For example, if the radiation level is 3, the corresponding maximum number of nodes is 3, and the terminal device may extract, from the user relationship network, a radiation network that takes the target object as a central node and extends 3 nodes outward, that is, the maximum level is 3, and the number of nodes between the last node of the radiation network, which may also be referred to as a boundary node, and the central node where the target object is located is not greater than 3.

In S203, the communication address of each object node in the radiation network is queried from the user database, and the target information is sent to the user terminal corresponding to each communication address.

In this embodiment, after determining the radiation network, the terminal device may query, according to the object identifiers of all object nodes included in the network, the communication address of each object identifier from the user database, generate a data packet according to the communication address and the target information, send the data packet through the gateway interface, analyze the communication address in the data packet through each router in the internet, and forward the data packet to the user terminal corresponding to the communication address, thereby completing information push.

In the embodiment of the invention, the target user is selected through the user relationship network, so that the accuracy of information pushing can be improved, particularly, the potential user can be mined in the mode, and the popularization efficiency of the product is improved.

Fig. 3 shows a flowchart of a specific implementation of the method S102 for generating a user relationship network according to a third embodiment of the present invention. Referring to fig. 3, with respect to the embodiment described in fig. 1, S102 in the method for generating a user relationship network according to this embodiment includes: s1021 to S1024 are described in detail as follows:

further, the identifying the associated interactive object of each interactive object node according to the first object information of each interactive object node on the reference relationship tree and the second object information of all candidate interactive objects in the object library respectively includes:

in S1021, the first object information is matched with each keyword in a preset keyword dictionary to obtain a first keyword sequence of the interactive object node.

In this embodiment, the terminal device stores a keyword dictionary, where the keyword dictionary includes a plurality of keywords, and each keyword is sequentially arranged in a fixed order, that is, each keyword has a fixed dictionary number in the keyword dictionary. Therefore, different first object information is matched with the keyword dictionary, and the keywords corresponding to the elements at the same position in the obtained keyword sequence are the same.

In this embodiment, the terminal device matches the first object information with each keyword in the keyword dictionary, and determines whether the user information includes the keyword. If the keyword is contained, the keyword is filled in the element at the corresponding position in the keyword sequence, so that the output first keyword sequence represents the keyword contained in the first object information. Compared with the matching of the first object information, the keyword matching has higher accuracy, so that the key information contained in the first object information can be determined, the number of the key information contained in the two interactive objects is compared, whether the two interactive objects are related or not is determined, and whether the two interactive objects are related interactive objects or not is determined. For example, the first object information of the interactive object node is "Shenzhen south mountain coast group mansion 16 building", and the keyword sequence identified by the keyword dictionary is: { Shenzhen, Nanshan, coast, group, 16 }; and the second object information of a certain candidate interactive object is 'Shenzhen Shentian district coast group building 5 th', and the keyword sequence obtained after keyword matching is as follows: { Shenzhen, Futian, coast, clique, and 5}, it can be seen that the number of keywords having the same two object information is 3, and the two object information can be identified as associated object information.

Optionally, the keyword dictionary may be obtained from an upper server, and the upper server may update the keyword dictionary at regular time. With the continuous development of society, emerging words often appear, so that the keyword dictionary needs to be updated regularly, and the accuracy of identifying keywords in user information is improved.

In S1022, the second object information is matched with each keyword in the keyword dictionary to obtain a second keyword sequence of the candidate interactive object.

In this embodiment, since the implementation manner of S1022 is completely the same as that of S1021, reference may be made to the detailed description of S1021, and details are not repeated here.

In S1023, a matching degree between the first keyword sequence and the second keyword sequence is calculated.

In S1024, if the matching degree is greater than a preset matching degree threshold, identifying the candidate interactive object as the associated interactive object of the interactive object node.

In this embodiment, after determining the first keyword sequence of the interaction object node and the second keyword sequence corresponding to the candidate interaction object, the matching degree between the two keyword sequences may be calculated, and then whether the two users are related users is determined according to the matching degree between the users.

In this embodiment, the matching degree threshold may be a threshold of the number of the same keywords in the keyword sequence, in this case, the terminal device may count the number of the same keywords in the first keyword sequence and the second keyword sequence, and use the number as the matching degree between the interaction object node and the candidate interaction node, and if the number of the same keywords between the interaction object node and the candidate interaction node is greater than a preset threshold of the matching degree, identify the candidate interaction object as an associated interaction object of the interaction object node; otherwise, if the number of the same keywords is smaller than the preset matching degree threshold, identifying that the candidate interactive object is not the associated interactive object of the interactive object node. The association threshold may also be a similarity threshold, in which case the terminal device may calculate the similarity of the two keyword sequences, that is, whether the elements at the same position are the same, and the calculation formula may be

And S is the number of the same elements, Q is the total number of the elements, so that the similarity between the two keyword sequences is obtained, and the similarity is compared with a similarity threshold value to determine whether the two interactive objects are related interactive objects. Preferably, when determining whether the two keyword sequences are similar, in addition to determining whether the elements at the same positions are the same, it may also be determined whether the elements at the same positions are similar, the terminal device records fuzzy keywords associated with the respective keywords, for example, because the two keywords "sun" and "day" are the same as the real object, it may identify that the two keywords have a relationship therebetween, and identify the keywords having a key relationship at the same positions as similar keywords, in calculating the similarity, in addition to the number of the same keywords, the number of the similar keywords may also be considered, in this case, the formula for calculating the similarity may be:

wherein, a₁、a₂Is a weighting coefficient, and Y is the similarity between two keyword sequences; s is the same number of elements at the same position; sl is the number of similar elements at the same position; q is the total number of elements in the keyword sequence.

In the embodiment of the invention, the first keyword sequence corresponding to the first object information and the second keyword sequence corresponding to the second object information are generated through the keyword dictionary, the keyword sequences are standardized, and the accuracy of matching degree calculation is improved, so that the accuracy of identification of the associated interactive object is improved.

Fig. 4 shows a flowchart of a specific implementation of a method S1021 for generating a user relationship network according to a fourth embodiment of the present invention. Referring to fig. 4, with respect to the embodiment described in fig. 3, a method S1021 for generating a user relationship network according to this embodiment includes: s401 to S405 are described in detail as follows:

further, the matching the first object information with each keyword in a preset keyword dictionary to obtain a first keyword sequence of the interactive object node includes:

in S401, a first sequence template is created, where each element in the first sequence template sequentially corresponds to a keyword in the keyword dictionary.

In this embodiment, before determining the first keyword sequence, the terminal device may create a keyword sequence template, that is, the first sequence template, so that the number of elements in the generated first keyword sequence is the same as the number of the keyword dictionaries, and each element in the first keyword sequence corresponds to one keyword in the keyword dictionary respectively. Specifically, the nth element in the first sequence template corresponds to the nth keyword in the keyword dictionary, that is, the sequence number of any element and the corresponding keyword in the keyword dictionary is the same.

In this embodiment, the process of creating the first sequence template by the terminal device specifically includes: reading the number of keywords in the keyword dictionary, creating a sequence containing the same number of elements, assigning no value to each element in the sequence, and after matching is completed, determining the assigned bit value of the element corresponding to the keyword according to whether the keyword exists in the user information.

In S402, whether each keyword is included in the first object information is sequentially determined according to the order of each keyword in the keyword dictionary.

In this embodiment, the terminal device may sequentially identify whether each keyword is included in the first object information according to an order of each keyword in the keyword dictionary, and if the first object information includes the keyword, perform the operation of S403; on the contrary, if the first object information does not include the keyword, the operation of S404 is performed.

In S403, if the keyword in the keyword dictionary is included in the first object information, setting an element of the keyword in the keyword sequence as a first place value.

In this embodiment, the terminal device determines that the first object information includes a certain keyword in the keyword dictionary, obtains a sequence number corresponding to the keyword, determines an element corresponding to the sequence number in the keyword sequence based on the sequence number, and sets the element as a first bit value, for example, a bit value "1" indicates that the keyword is included.

In S404, if the keyword in the keyword dictionary is not included in the first object information, the element of the keyword in the keyword sequence is set as a second place value.

In this embodiment, the terminal device determines that the first object information does not include a certain keyword in the keyword dictionary, obtains a sequence number corresponding to the keyword, determines an element corresponding to the sequence number in the keyword sequence based on the sequence number, and sets the element to a second bit value, for example, a bit value "0" indicates that the keyword is included.

In S405, a first keyword sequence of the interaction object node is generated based on the bit value of each of the elements.

In this embodiment, after the terminal device identifies each keyword in the keyword dictionary, the terminal device may generate a first keyword sequence corresponding to the first object information according to a bit value corresponding to each element and an element serial number corresponding to the element.

For example, the keyword dictionary includes 6 keywords { shenzhen, futian, coast, 6, bank, male }, and if a certain keyword is included, the keyword is represented by a place value "1", and if a certain keyword is not included, the keyword is represented by a place "0", the first object information of the interaction object node a is "shenzhen city south mountain coast mansion 9 building chinese bank female", the second object information of the candidate interaction object B is "guangzhou city mountain coast mansion 6 building transportation bank male", and for the first object information of the interaction object node a, the first keyword sequence obtained by matching is: 101010, after the second object information of the candidate interactive object B is matched, the obtained second keyword sequence is: 001111. based on the two keyword sequences, the matching degree between the two object information can be determined, so that whether the two users are related interactive objects or not can be judged. It should be noted that the second keyword sequence can also be implemented in the above manner.

In the embodiment of the invention, the keyword sequence consisting of the first bit value and the second bit value is obtained by carrying out inclusiveness recognition on each keyword in the keyword dictionary and the object information, so that the data size of the keyword sequence can be reduced, the matching degree between two users can be quickly determined, and the efficiency of related object recognition is improved.

Fig. 5 shows a flowchart of a specific implementation of the method S102 for generating a user relationship network according to a fifth embodiment of the present invention. Referring to fig. 5, with respect to the embodiment described in fig. 1, a method S102 for generating a user relationship network provided in this embodiment includes: S501-S506 are detailed as follows:

in S501, a social network account of the interaction object node is extracted from the first object information.

In this embodiment, the terminal device may determine, except for determining the associated interaction object by constructing the keyword sequence and calculating the similarity between the two keyword sequences, whether an interaction relationship exists between the two interaction objects may be determined based on an interaction behavior on the social network if the first object information and the second object information include an account identifier of the social network account. Based on this, the terminal device obtains a social network account related to the interaction object node from the first object information, where the social network account may be an account identifier, such as an account name or an account number.

In S502, a database interface associated with the social network account is called, and the browsing record and the release information of the social network account are downloaded.

In this embodiment, in order to obtain an interaction record of a social network account, a terminal device needs to determine a network address of a database associated with the social network account, and send a link request to the network address, where the database returns a link confirmation request, where the link confirmation request carries an interface identifier and an interface type of a database interface that establishes a communication link with the terminal device, the terminal device may locally create a virtual interface that matches the interface type, and establish a communication connection with the database interface corresponding to the interface identifier through the virtual interface, and because the interface types of the two interfaces are consistent, interaction information of the social network account of an interaction object node may be downloaded through the database interface, and the interaction information includes a browsing record and release information released on a social network platform.

In S503, counting the browsing times of each candidate interactive object according to the browsing accounts corresponding to all the browsing records; the browsing account is a network account of a certain candidate interaction object.

In this embodiment, the browsing record is specifically a record generated by the interactive object node accessing a homepage of another account or a distribution network. Therefore, each browsing record contains the browsing account of the browsed opposite terminal, and the candidate interactive object corresponding to each browsing account is determined according to the second object information of each candidate interactive object. Therefore, the number of times that the interaction object node accesses the candidate interaction object, that is, the browsing number corresponding to the candidate interaction object, can be determined.

In S504, counting the number of interactions of each candidate interaction object according to the interaction accounts corresponding to all the release information; the interaction account is a network account of a certain candidate interaction object.

In this embodiment, an account of the social network platform publishes information, and other users may perform interactive operations based on the published information, such as performing interactive behaviors such as comment, forwarding, and like. The terminal equipment can determine the interaction times between each candidate interaction object and the interaction object node according to the interaction account corresponding to the release information.

In S505, according to the browsing times and the interaction times, calculating a degree of association between the candidate interaction object and the interaction object node.

In this embodiment, the terminal device may determine the account adhesion degree between the interaction object node and the candidate interaction object, that is, the association degree according to the browsing frequency and the interaction frequency, and if the browsing frequency and the interaction frequency are greater, it indicates that the association degree between the two is higher and the probability of the association between the two is higher, so that the association between the two may be identified according to the value of the association degree.

In S506, the associated interactive object of the interactive object node is identified based on the association degree.

In this embodiment, the terminal device may identify a candidate interactive node having a greater association degree than the association with which the terminal device is associated as an associated interactive node having an association relationship with the interactive object node.

In the embodiment of the invention, the association degree between the interaction object node and the candidate interaction object is determined by acquiring the publishing information and the browsing record of the social network account, so that the association interaction object is identified, the accuracy of association identification is improved, the identification channel is expanded, and the purpose of determining the association in multiple modes is realized.

Fig. 6 shows a flowchart of a specific implementation of a method S101 for generating a user relationship network according to a sixth embodiment of the present invention. Referring to fig. 6, with respect to any one of the embodiments in fig. 1 to fig. 5, in the method for generating a user relationship network provided in this embodiment, S101 includes: s1011 to S1013 are specifically described as follows:

further, the obtaining a history interaction record of the target object and generating a reference relationship tree of the target object according to the history interaction record includes:

in S1011, valid time ranges of the historical interaction records are respectively identified.

In this embodiment, if the history interaction records have a valid time range, that is, a valid period, valid history interaction records can be filtered out according to the valid time range, and invalid history interaction records are filtered out. Based on this, the terminal device will respectively determine the valid time range of each historical interaction record. If the current time is detected to be out of the valid time range, identifying the historical interaction record as an invalid transaction record, wherein the recorded association is invalid and is not used as a basis for establishing a reference relationship tree; if the current time is detected to be within the valid time range, the operation of S1012 is performed.

In S1012, if the current time is within the valid time range, the historical interaction object in the historical interaction record is identified as a valid interaction object.

In this embodiment, if it is detected that the current time is within the valid time range, the historical interaction record is identified as a valid interaction record, and the historical interaction object in the valid interaction record is identified as a valid interaction object.

In S1013, the reference relationship tree is generated based on the valid interaction object.

In this embodiment, the terminal device may establish the reference relationship tree according to all the identified effective interactive objects, thereby determining that the interactive object nodes in the reference relationship tree are all effective nodes.

In the embodiment of the invention, the invalid historical interaction records are filtered by determining the valid time range of each historical interaction record, so that the accuracy and the timeliness of the reference relation tree are improved.

Fig. 7 shows a flowchart of a specific implementation of a method S101 for generating a user relationship network according to a seventh embodiment of the present invention. Referring to fig. 7, with respect to any one of the embodiments in fig. 1 to fig. 5, in the method for generating a user relationship network provided in this embodiment, S101 includes: S1014-S1015, detailed as follows:

in S1014, the number of databases associated with the target object is identified, and multiple concurrent threads matching the number of databases are created.

In this embodiment, since the target object may interact on a plurality of different platforms, the historical interaction records may be stored in a plurality of different databases, and in order to improve the acquisition efficiency, the terminal device may identify the number of databases associated with the target object, create a plurality of concurrent threads matching the number of databases, and control the plurality of different concurrent threads to establish communication connections with the interaction databases associated with the target object, respectively.

In S1015, each of the concurrent threads is invoked to download the historical interaction records of the target object from each of the interaction databases.

In this embodiment, the history interaction records associated with the target object are downloaded from each interaction database through each concurrent thread, so that multilink concurrent downloading is realized.

In the embodiment of the invention, the historical interaction records are downloaded by a plurality of concurrent threads by identifying the number of the interaction databases associated with the target object, so that the downloading efficiency of the historical interaction records is improved, and the construction efficiency of the user relationship network is improved.

It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

Fig. 8 is a block diagram illustrating a structure of a user relationship network generating device according to an embodiment of the present invention, where the user relationship network generating device includes units for executing steps in the embodiment corresponding to fig. 1. Please refer to fig. 1 and fig. 1 for the corresponding description of the embodiment. For convenience of explanation, only the portions related to the present embodiment are shown.

Referring to fig. 8, the apparatus for generating a user relationship network includes:

a reference relationship tree establishing unit 81, configured to obtain a history interaction record of a target object, and generate a reference relationship tree of the target object according to the history interaction record; the reference relation tree comprises a plurality of interactive object nodes;

an associated interactive object identifying unit 82, configured to identify, according to the first object information of each interactive object node in the reference relationship tree and the second object information of all candidate interactive objects in the object library, an associated interactive object of each interactive object node respectively;

an extended relationship tree establishing unit 83, configured to generate an extended relationship tree of the reference relationship tree based on the associated interaction object;

and a user relationship network constructing unit 84, configured to construct a user relationship network according to the extended relationship trees of all the target objects.

Optionally, the apparatus for generating a user relationship network further includes:

the radiation level determining unit is used for determining the radiation level of the target information associated with the information sending condition if the preset information sending condition is met;

the radiation network extraction unit is used for extracting a radiation network taking the target object as a center according to the radiation level and the user relation network; the maximum node number between the end object node in the radiation network to the central node of the target object is matched with the radiation level;

and the target information sending unit is used for inquiring the communication address of each object node in the radiation network from a user database and sending the target information to the user terminal corresponding to each communication address.

Optionally, the associated interaction object recognition unit 82 includes:

the first keyword sequence output unit is used for matching the first object information with each keyword in a preset keyword dictionary to obtain a first keyword sequence of the interactive object node;

a second keyword sequence output unit, configured to match the second object information with each keyword in the keyword dictionary, to obtain a second keyword sequence of the candidate interactive object;

a matching degree calculation unit, configured to calculate a matching degree between the first keyword sequence and the second keyword sequence;

and the first associated interactive object identification unit is used for identifying the candidate interactive object as the associated interactive object of the interactive object node if the matching degree is greater than a preset matching degree threshold value.

Optionally, the first keyword sequence output unit includes:

the first sequence template creating unit is used for creating a first sequence template, and each element in the first sequence template sequentially corresponds to one keyword in the keyword dictionary respectively;

the inclusion relation identification unit is used for sequentially judging whether the first object information contains each keyword according to the sequence of each keyword in the keyword dictionary;

a first bit value setting unit configured to set an element of the keyword in the keyword sequence as a first bit value if the keyword in the keyword dictionary is included in the first object information;

a second bit value setting unit, configured to set an element of the keyword in the keyword sequence as a second bit value if the keyword in the keyword dictionary is not included in the first object information;

and the first keyword sequence generating unit is used for generating the first keyword sequence of the interactive object node based on the bit value of each element.

Optionally, the associated interaction object recognition unit 82 includes:

the social network account extracting unit is used for extracting the social network account of the interaction object node from the first object information;

the interaction record acquisition unit is used for calling a database interface associated with the social network account, downloading the browsing record and the release information of the social network account;

the browsing frequency counting unit is used for counting the browsing frequency of each candidate interactive object according to the browsing accounts corresponding to all the browsing records; the browsing account is a network account of a certain candidate interaction object;

the interaction frequency counting unit is used for counting the interaction frequency of each candidate interaction object according to the interaction accounts corresponding to all the release information; the interaction account is a network account of a certain candidate interaction object;

the association degree calculation unit is used for calculating the association degree between the candidate interactive object and the interactive object node according to the browsing times and the interaction times;

and the second association interactive object identification unit is used for identifying the association interactive object of the interactive object node based on the association degree.

Optionally, the reference relationship tree establishing unit 81 includes:

the effective time range identification unit is used for respectively identifying the effective time range of each historical interaction record;

the effective interactive object determining unit is used for identifying the historical interactive object in the historical interactive record as an effective interactive object if the current time is within the effective time range;

and the effective interactive object integration unit is used for generating the reference relation tree based on the effective interactive object.

Optionally, the reference relationship tree establishing unit 81 includes:

the concurrent thread creating unit is used for identifying the number of databases related to the target object and creating a plurality of concurrent threads matched with the number of the databases;

and the concurrent downloading unit is used for calling each concurrent thread to download the historical interaction records of the target object from each interaction database respectively.

Therefore, the generation device of the user relationship network provided in the embodiment of the present invention does not just construct the user relationship network based on the interaction object directly linked to the target object, and on the basis of generating the reference relationship tree of the target object, obtains the association interaction object indirectly linked to the target object, expands the reference relationship tree, and obtains the expanded relationship tree, so as to improve the coverage of the user relationship network, and determine the unrecorded association relationship according to the matching degree between the object information, thereby increasing the obtaining manner of the user relationship, and improving the accuracy and the processing quality of the subsequent operations performed based on the user relationship network.

Fig. 9 is a schematic diagram of a terminal device according to another embodiment of the present invention. As shown in fig. 9, the terminal device 9 of this embodiment includes: a processor 90, a memory 91 and a computer program 92, such as a user relationship network generating program, stored in said memory 91 and executable on said processor 90. The processor 90 executes the computer program 92 to implement the steps in the above-mentioned embodiments of the method for generating a user relationship network, for example, S101 to S104 shown in fig. 1. Alternatively, the processor 90, when executing the computer program 92, implements the functions of the units in the device embodiments, such as the functions of the modules 81 to 84 shown in fig. 8.

Illustratively, the computer program 92 may be divided into one or more units, which are stored in the memory 91 and executed by the processor 90 to carry out the invention. The one or more units may be a series of computer program instruction segments capable of performing specific functions, which are used to describe the execution process of the computer program 92 in the terminal device 9. For example, the computer program 92 may be divided into a reference relationship tree building unit, an associated interaction object identification unit, an extended relationship tree building unit, and a user relationship network building unit, and the specific functions of each unit are as described above.

The terminal device 9 may be a desktop computer, a notebook, a palm computer, a cloud server, or other computing devices. The terminal device may include, but is not limited to, a processor 90, a memory 91. Those skilled in the art will appreciate that fig. 9 is only an example of a terminal device 9, and does not constitute a limitation to the terminal device 9, and may include more or less components than those shown, or combine some components, or different components, for example, the terminal device may also include an input-output device, a network access device, a bus, etc.

The Processor 90 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

The memory 91 may be an internal storage unit of the terminal device 9, such as a hard disk or a memory of the terminal device 9. The memory 91 may also be an external storage device of the terminal device 9, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the terminal device 9. Further, the memory 91 may also include both an internal storage unit and an external storage device of the terminal device 9. The memory 91 is used for storing the computer program and other programs and data required by the terminal device. The memory 91 may also be used to temporarily store data that has been output or is to be output.

In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.

The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present invention, and are intended to be included within the scope of the present invention.

Claims

1. A method for generating a user relationship network is characterized by comprising the following steps:

2. The method according to claim 1, further comprising, after constructing a user relationship network from the expanded relationship trees of all the target objects:

if the preset information sending condition is met, determining the radiation level of the target information associated with the information sending condition;

extracting a radiation network taking the target object as a center according to the radiation level and the user relation network; the maximum node number between the end object node in the radiation network to the central node of the target object is matched with the radiation level;

and inquiring the communication address of each object node in the radiation network from a user database, and sending target information to a user terminal corresponding to each communication address.

3. The method according to claim 1, wherein the identifying the associated objects of each node of the interactive object according to the first object information of each node of the interactive object on the reference relationship tree and the second object information of all candidate objects in the object library respectively comprises:

matching the first object information with each keyword in a preset keyword dictionary to obtain a first keyword sequence of the interactive object node;

matching the second object information with each keyword in the keyword dictionary to obtain a second keyword sequence of the candidate interactive object;

calculating the matching degree between the first keyword sequence and the second keyword sequence;

and if the matching degree is greater than a preset matching degree threshold value, identifying the candidate interactive object as the associated interactive object of the interactive object node.

4. The generation method of claim 3, wherein the matching the first object information with each keyword in a preset keyword dictionary to obtain the first keyword sequence of the interactive object node comprises:

creating a first sequence template, wherein each element in the first sequence template sequentially corresponds to one keyword in the keyword dictionary respectively;

sequentially judging whether the first object information contains each keyword according to the sequence of each keyword in the keyword dictionary;

if the keyword in the keyword dictionary is contained in the first object information, setting an element of the keyword in the keyword sequence as a first place value;

if the keyword in the keyword dictionary is not contained in the first object information, setting an element of the keyword in the keyword sequence as a second place value;

generating a first keyword sequence of the interaction object node based on bit values of the respective elements.

5. The method according to claim 1, wherein the identifying the associated objects of each node of the interactive object according to the first object information of each node of the interactive object on the reference relationship tree and the second object information of all candidate objects in the object library respectively comprises:

extracting a social network account of the interaction object node from the first object information;

calling a database interface associated with the social network account, and downloading the browsing record and the release information of the social network account;

counting the browsing times of each candidate interaction object according to the browsing accounts corresponding to all the browsing records; the browsing account is a network account of a certain candidate interaction object;

counting the interaction times of each candidate interaction object according to the interaction accounts corresponding to all the release information; the interaction account is a network account of a certain candidate interaction object;

calculating the association degree between the candidate interactive object and the interactive object node according to the browsing times and the interactive times;

identifying the associated interactive object of the interactive object node based on the association degree.

6. The method according to any one of claims 1 to 5, wherein the obtaining a history interaction record of the target object and generating the reference relationship tree of the target object according to the history interaction record comprises:

respectively identifying the effective time range of each historical interaction record;

if the current time is within the effective time range, identifying the historical interaction object in the historical interaction record as an effective interaction object;

generating the reference relationship tree based on the effective interaction object.

7. The method according to any one of claims 1 to 5, wherein the obtaining a history interaction record of the target object and generating the reference relationship tree of the target object according to the history interaction record comprises:

identifying the number of databases associated with the target object, and creating a plurality of concurrent threads matched with the number of the databases;

and calling each concurrent thread to download the historical interaction records of the target object from each interaction database respectively.

8. A device for generating a user relationship network, comprising:

9. A terminal device, characterized in that the terminal device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, the processor executing the computer program with the steps of the method according to any of claims 1 to 7.

10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 7.