CN110647676A - Interest attribute mining method and device based on big data and computer equipment - Google Patents
Interest attribute mining method and device based on big data and computer equipment Download PDFInfo
- Publication number
- CN110647676A CN110647676A CN201910748904.5A CN201910748904A CN110647676A CN 110647676 A CN110647676 A CN 110647676A CN 201910748904 A CN201910748904 A CN 201910748904A CN 110647676 A CN110647676 A CN 110647676A
- Authority
- CN
- China
- Prior art keywords
- interest
- attribute
- node
- nodes
- determined
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/958—Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application relates to an interest attribute mining method and device based on big data and computer equipment. The method comprises the following steps: acquiring a fully-connected sub-network graph of an object to be determined; the fully connected sub-network graph comprises undetermined object nodes and at least one reference object node; calculating the comprehensive association degree of each reference object node and each undetermined object node; obtaining interest attribute values corresponding to the reference object nodes, and determining reference weights of the interest attribute values according to the comprehensive association degree; calculating to obtain a first interest reference value according to the interest attribute values and the reference weights respectively corresponding to the interest attribute values; acquiring initial attribute information of an object to be determined, and determining a second interest reference value of an interest attribute according to the initial attribute information; and calculating to obtain an interest attribute value corresponding to the object to be determined based on the first interest reference value and the second interest reference value. By adopting the method, the user interest attribute information can be efficiently and accurately mined.
Description
Technical Field
The application relates to the technical field of computers, in particular to an interest attribute mining method and device based on big data and computer equipment.
Background
Fully understanding user interest needs is a prerequisite for potential customer mining. Most enterprises currently use information questionnaires to obtain the interest data of customers on their products. With the faster and faster life rhythm, people are lack of time to pay attention to the information, and even if corresponding information questionnaires are filled, the authenticity of the information is unreliable, namely, the interest attribute information of the users is difficult to obtain efficiently and accurately.
Disclosure of Invention
In view of the foregoing, there is a need to provide a big data-based interest attribute mining method, device and computer equipment capable of efficiently and accurately mining user interest attribute information.
A big data-based interest attribute mining method, the method comprising: acquiring a fully-connected sub-network graph of an object to be determined; the fully connected subnetwork graph comprises pending object nodes and at least one reference object node; calculating the comprehensive association degree of each reference object node and the undetermined object node; obtaining interest attribute values corresponding to the reference object nodes, and determining reference weights of the interest attribute values according to the comprehensive association degree; calculating to obtain a first interest reference value according to the interest attribute values and the reference weights respectively corresponding to the interest attribute values; acquiring initial attribute information of the object to be determined, and determining a second interest reference value of an interest attribute according to the initial attribute information; and calculating to obtain an interest attribute value corresponding to the object to be determined based on the first interest reference value and the second interest reference value.
In one embodiment, the acquiring a fully connected subnet graph of the pending object includes: acquiring a relation network map; the relational network graph comprises a plurality of object nodes and attribute nodes connected with each object node; identifying whether the attribute value of the interest attribute corresponding to each object node is missing; distinguishing a plurality of object nodes in the relational network graph into determined object nodes and undetermined object nodes according to the recognition result; drawing a fully connected sub-network graph of each node to be determined in the relational network graph; and marking the object nodes which have target association relation with the object nodes to be determined in the fully-connected sub-network graph as reference object nodes.
In one embodiment, the calculating the comprehensive association degree of each reference object node and the pending object node includes: acquiring social network information corresponding to the node to be determined; identifying the relationship type between each reference object node and the undetermined object node according to the social network information, and counting the event type and the occurrence frequency of the associated events occurring in the specified time period; acquiring a preset basic association coefficient corresponding to the relationship type; calculating the shortest social distance from each reference object node to the pending object node based on the fully connected sub-network graph; adjusting the basic association coefficient according to the shortest social distance and the event type and occurrence frequency of the associated event to obtain the unilateral association degree of the node to be determined based on different associated nodes; and superposing the single-side association degrees of a plurality of association nodes between each reference object node and the node to be determined to obtain the comprehensive association degree of the reference object node and the node to be determined.
In one embodiment, the determining a second interest reference value of the interest attribute according to the initial attribute information includes: acquiring initial attribute information of the object to be determined, and constructing a user portrait of the object to be determined based on the initial attribute information; monitoring product reference records generated by the target website browsed by the object to be determined; generating an interest characteristic matrix of the object to be determined according to the user portrait and a product reference record; and calculating to obtain the second interest reference value based on the interest feature matrix.
In one embodiment, the method further comprises: supplementing the initial attribute information of the undetermined object based on the interest attribute value to obtain target attribute information; determining the client grade of the undetermined target object according to the target attribute information; screening matched salesmen according to the customer grade, and pushing the target attribute information to a terminal corresponding to the screened salesmen; receiving product recommendation information returned by the terminal based on the target attribute information, verifying the product recommendation information, and generating a product transaction link based on the verified product recommendation information; and pushing the product transaction link to a terminal corresponding to the pending object.
In one embodiment, the supplementing the initial attribute information of the pending object based on the interest attribute value to obtain target attribute information includes: identifying whether a risk attribute is missing in the initial attribute information; if yes, determining a first risk reference value of the risk attribute based on the fully connected sub-network graph; determining a second risk reference value for the pending object based on the initial attribute information; performing preset logical operation on the first risk reference value and the second risk reference value, and taking a calculation result as a risk attribute value of the object to be determined; and performing completion processing on the initial attribute information based on the interest attribute value and the risk attribute value to obtain target attribute information.
An interest attribute mining apparatus based on big data, the apparatus comprising: the first interest mining module is used for acquiring a fully-connected sub-network graph of an object to be determined; the fully connected subnetwork graph comprises pending object nodes and at least one reference object node; calculating the comprehensive association degree of each reference object node and the undetermined object node; obtaining interest attribute values corresponding to the reference object nodes, and determining reference weights of the interest attribute values according to the comprehensive association degree; calculating to obtain a first interest reference value according to the interest attribute values and the reference weights respectively corresponding to the interest attribute values; the second interest mining module is used for acquiring initial attribute information of the object to be determined and determining a second interest reference value of the interest attribute according to the initial attribute information; and the interest attribute value calculation module is used for calculating and obtaining an interest attribute value corresponding to the object to be determined based on the first interest reference value and the second interest reference value.
In one embodiment, the first interest mining module comprises a sub-network graph building module for obtaining a relationship network graph; the relational network graph comprises a plurality of object nodes and attribute nodes connected with each object node; identifying whether the attribute value of the interest attribute corresponding to each object node is missing; distinguishing a plurality of object nodes in the relational network graph into determined object nodes and undetermined object nodes according to the recognition result; drawing a fully connected sub-network graph of each node to be determined in the relational network graph; and marking the object nodes which have target association relation with the object nodes to be determined in the fully-connected sub-network graph as reference object nodes.
A computer device comprising a memory storing a computer program and a processor implementing the steps of a big data based interest property mining method as provided in any of the embodiments of the present application when the computer program is executed.
A computer-readable storage medium, having stored thereon a computer program which, when executed by a processor, performs the steps of the big data based interest property mining method provided in any one of the embodiments of the present application.
According to the interest attribute mining method, device and computer equipment based on big data, the comprehensive association degree of each reference object node and the node of the object to be determined in the fully-connected sub-network graph can be obtained through calculation according to the fully-connected sub-network graph of the object to be determined; according to the comprehensive association degree and the interest attribute value corresponding to the reference object node, the reference weight of the interest attribute value can be determined; according to the interest attribute values and the corresponding reference weights, a first interest reference value can be obtained through calculation; according to the initial attribute information of the object to be determined, a second interest reference value of the interest attribute can be determined; based on the first interest reference value and the second interest reference value, an interest attribute value corresponding to the object to be determined can be calculated. Besides the initial attribute information of the undetermined object, the identity attribute information of the reference object node with strong correlation degree with the undetermined object node is considered, the interest attribute of the undetermined object node is predicted by integrating the factors of multiple dimensions, the information completion efficiency can be improved, and the accuracy of the completion information can also be improved.
Drawings
FIG. 1 is a diagram illustrating an exemplary application of a big data-based interest property mining method;
FIG. 2 is a schematic flow chart diagram illustrating a big data-based interest property mining method according to an embodiment;
FIG. 3 is a diagram of a relationship network graph employed by the interest attribute mining process in one embodiment;
FIG. 4 is a flowchart illustrating the steps of constructing a fully connected subnetwork graph in one embodiment;
FIG. 5 is a block diagram of an apparatus for interest property mining based on big data according to an embodiment;
FIG. 6 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application 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 present application and are not intended to limit the present application.
The interest attribute mining method based on big data can be applied to the application environment shown in fig. 1. Wherein the terminal 102 and the server 104 communicate via a network. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices, and the server 104 may be implemented by an independent server or a server cluster formed by a plurality of servers. The server 104 acquires a fully connected sub-network graph of the object to be determined according to the interest attribute mining request triggered by the user based on the terminal 102. The fully connected subnetwork graph comprises a pending object node and at least one reference object node. The server 104 calculates the comprehensive association degree of each reference object node and the undetermined object node, and determines the reference weight of the interest attribute value according to the comprehensive association degree. The server 104 obtains the interest attribute values corresponding to the reference object nodes, and calculates a first interest reference value according to the interest attribute values and the reference weights respectively corresponding to the interest attribute values. The server 104 obtains initial attribute information of the object to be determined, and determines a second interest reference value of the interest attribute according to the initial attribute information. The server 104 calculates an interest attribute value corresponding to the object to be determined based on the first interest reference value and the second interest reference value. In the interest attribute mining process, the identity attribute information of the reference object node with strong correlation degree with the undetermined object node is considered in combination with the initial attribute information of the undetermined object, and the interest attribute of the undetermined object node is predicted by integrating factors of multiple dimensions, so that the information completion efficiency can be improved, and the accuracy of the completion information can also be improved.
In one embodiment, as shown in fig. 2, there is provided a big data-based interest property mining method, which is described by taking the method as an example applied to the server in fig. 1, and includes the following steps:
The fully connected sub-network graph comprises nodes of the objects to be determined, a plurality of other object nodes and directed edges among the nodes. The fully connected subnetwork graph can be drawn from the relational network graph. The relationship network graph may be pre-constructed by the server according to the identity attribute information and the social network information of the plurality of target objects. The relational network graph comprises a plurality of object nodes, attribute nodes corresponding to the object nodes and directed edges for connecting the object nodes and the attribute nodes. The server identifies whether different object nodes are connected with the same attribute node. If so, the server merges the same attribute nodes, and marks the attribute nodes obtained by merging as the associated nodes corresponding to the object nodes.
Fig. 3 illustrates a relationship network graph. As shown in fig. 3, V1 to V8 are respectively 8 object nodes, and Mij and Mijij are attribute nodes "job units" corresponding to each object node; nij and Nijij are attribute nodes 'transfer ID' corresponding to each object node; oij and Oijijijj are attribute nodes 'policy' corresponding to each object node; the P ij and the P ijijijijj are attribute nodes 'wireless network identifiers' corresponding to the object nodes; qij and Qijij are attribute nodes 'bank card numbers' corresponding to each object node. Wherein i is more than or equal to 1 and less than or equal to 8; j is more than or equal to 1. Directed edges may point from object nodes to property nodes. Mijij, Nijij, Oijijj, P ijijj and Qijij are used as the associated nodes of the object nodes. The node identification of the associated node may be generated from the node identifications of the plurality of attribute nodes that are merged. For example, the node identification of the associated node resulting from the merging of the attribute node Q51 with the attribute node Q83 may be Q5183.
The server also generates a node tag corresponding to each object node according to the identity attribute information, such as a basic information tag, a consumption interest tag, a wealth level tag or a risk rating tag. The server identifies whether each object node lacks a certain node label so as to judge whether the identity attribute information of the corresponding object node has a missing attribute. The server marks the object node table with the missing attribute as an undetermined object node, and marks the object node without the missing attribute as a determined object node.
The server determines the attribute type of the missing attribute corresponding to the object node to be determined, identifies the target association relation corresponding to the attribute type, and marks one or more object nodes in the fully-connected sub-network graph as reference object nodes.
And 204, calculating the comprehensive association degree of each reference object node and the undetermined object node.
Two object nodes to which one or more association nodes are connected are associated. And the server calculates the unilateral association degree of the two associated object nodes based on each associated node according to the social network information. The single-side association degrees of the plurality of association nodes between the two object nodes are superposed, so that the comprehensive association degree of the two object nodes can be obtained.
And step 206, obtaining the interest attribute value corresponding to the reference object node, and determining the reference weight of the interest attribute value according to the comprehensive association degree.
The server acquires identity attribute information corresponding to each reference object node, and extracts an attribute value (denoted as an interest attribute value) of an interest attribute corresponding to the missing attribute from the acquired identity attribute information. It is easy to understand that some attribute values of interest attributes in the identity attribute information corresponding to the reference object node may also be absent. The fully connected subnetwork graph includes at least one determinate object node so that at least one interest attribute value can be extracted.
And 208, calculating to obtain a first interest reference value according to the interest attribute values and the reference weights respectively corresponding to the interest attribute values.
The server carries out preset logic operation on the interest attribute value to obtain a first interest reference value of the interest attribute. The preset logical operation may be a superposition operation based on the reference weight. The reference weight may be determined according to a comprehensive association degree of the corresponding reference object node and the node to be determined. In another embodiment, the preset logical operation may be a median or an average of the plurality of interest attribute values.
Step 210, obtaining initial attribute information of the object to be determined, and determining a second interest reference value of the interest attribute according to the initial attribute information.
And 212, calculating an interest attribute value corresponding to the object to be determined based on the first interest reference value and the second interest reference value.
And the server constructs a user portrait of the object to be determined based on the initial attribute information, and predicts a second interest reference value of the interest attribute corresponding to the object to be determined according to the user portrait. And the server performs superposition operation based on preset weight on the first interest reference value and the second interest reference value to obtain an interest attribute value corresponding to the object to be determined. The preset weight may be a fixed value, or may be dynamically determined according to the confidence of the first interest reference value. And the server trains a corresponding missing attribute completion model in advance aiming at the missing attributes. The server can give the confidence of the calculated first interest reference value according to the model accuracy.
In this embodiment, according to the fully-connected sub-network graph of the undetermined object, the comprehensive association degree between each reference object node and the node of the undetermined object in the fully-connected sub-network graph can be calculated; according to the comprehensive association degree and the interest attribute value corresponding to the reference object node, the reference weight of the interest attribute value can be determined; according to the interest attribute values and the corresponding reference weights, a first interest reference value can be obtained through calculation; according to the initial attribute information of the object to be determined, a second interest reference value of the interest attribute can be determined; based on the first interest reference value and the second interest reference value, an interest attribute value corresponding to the object to be determined can be calculated. Besides the initial attribute information of the undetermined object, the identity attribute information of the reference object node with strong correlation degree with the undetermined object node is considered, the interest attribute of the undetermined object node is predicted by integrating the factors of multiple dimensions, the information completion efficiency can be improved, and the accuracy of the completion information can also be improved.
In one embodiment, as shown in fig. 4, the step of obtaining a fully connected subnet graph of the pending object, that is, building the fully connected subnet graph, includes:
The server acquires identity attribute information and social network information of a plurality of target objects. The target object may be an attrition customer, an existing customer, or a potential customer. Wherein the potential customer may be identified based on customer data of the attrition customer or the existing customer, for example, a guarantor or an emergency contact reserved by the existing customer may be used as the potential customer. The potential customer may also be obtained by monitoring a product review record left by the user browsing the relevant product at the target website by the server, which is not limited in this respect.
The identity attribute information includes an object identification. The object identifier can be an identity card number, a mobile phone number or a mailbox, etc. It is easy to understand that if the target object is an enterprise, the object identifier may also be an organization code or the like. The identity attribute information further includes name, gender, age, academic calendar, contact information, job unit, policy, bank card account number, terminal device information, social network account number, interests, wealth level or risk level, and the like. The social network information comprises wifi connection information, position sharing information, instant messaging information, electronic transfer information or remote call information and the like.
And the server generates an object node corresponding to the target object according to the object identifier and generates one or more attribute nodes corresponding to the target object according to other identity attribute information. For example, an attribute node may be generated with the designation of the discretionary unit, or an attribute node may be generated with the designation of the transfer ID. Each attribute node is associated with a corresponding node description. In this embodiment, the directed edge points from the object node to the property node. A plurality of attribute nodes may be connected to one object node.
The server identifies whether different object nodes are connected with the same attribute node. If so, the server merges the same attribute nodes, and marks the attribute nodes obtained by merging as the associated nodes corresponding to the object nodes. The same object node can be connected with various types of attribute nodes, such as an arbitrary unit type, a bank card account number type, a common network type and the like. By merging the same attribute nodes, multiple object nodes can be associated. In other words, the association between the plurality of target objects can be identified according to the identity attribute information. For example, nodes with the same "incumbent unit" attribute indicate that two target objects may have a co-worker relationship; the nodes have the same attribute of 'academic calendar', and represent that the two target objects possibly have a classmate relationship; the method has the advantages that the same 'bank card account' or 'common network type' attribute nodes are provided, the possible relationship between two target objects is represented, and the like, and each type of incidence relation is analyzed.
Two object nodes to which one or more association nodes are connected are associated. The server calculates the unilateral association degree of two associated object nodes based on each associated node according to the social network information, and adds the unilateral association degree to the directed edge connected with the corresponding associated node to obtain the relationship network map. The single-side association degrees of the plurality of association nodes between the two object nodes are superposed, so that the comprehensive association degree of the two object nodes can be obtained.
And 406, distinguishing a plurality of object nodes in the relational network graph into determined object nodes and undetermined object nodes according to the identification result.
And step 408, drawing a fully connected sub-network graph of each node to be determined in the relational network graph.
And the server draws a fully-connected sub-network graph of each node to be determined in the relationship network graph according to the social network information. Specifically, the server acquires social network information of the undetermined object node, and calculates a comprehensive association degree between the undetermined object node and each object node associated once based on the social network information according to the above manner. One-degree association means that two object nodes are directly connected through a directed edge. And the server compares whether the comprehensive association degree reaches a threshold value, reserves the object node (marked as a first-degree associated object node) of which the comprehensive association degree reaches the threshold value, and deletes the object node of which the comprehensive association degree is less than the threshold value.
The server identifies whether at least one of the reserved one-degree-of-association object nodes is a determination object node. In other words, the server determines whether at least one of the reserved once-associated object nodes is an object node containing complete identity attribute information. If the determined object node exists in the reserved first-degree associated object nodes, the server draws the undetermined object node, the reserved first-degree associated object nodes and directed edges connecting the undetermined object nodes and the first-degree associated object nodes in the relational network graph to obtain a fully-connected sub-network graph corresponding to the undetermined object nodes. If no object node is determined in the reserved first-degree associated object nodes, the server further screens one or more object nodes (marked as second-degree associated object nodes) which are associated with the object nodes to be determined in a second-degree manner according to the method. The second degree association means that two object nodes are connected through two directed edges. It is easily understood that the second degree associated object node is an object node directly connected to the first degree associated object node.
The server further identifies whether at least one of the two-degree-of-relevance object nodes is a determination object node. If not, further screening the three-degree associated object nodes of the nodes to be determined according to the mode, and repeating the steps until at least one determined object node is obtained through screening. The server draws the nodes to be determined, the primary associated object nodes obtained by screening, the secondary associated object nodes and the like in the relational network graph according to the mode to obtain the fully-connected sub-network graph corresponding to the nodes to be determined.
And the server supplements the missing attribute of the corresponding node to be determined according to the identity attribute information of the reference object node in the fully-connected sub-network graph. The server may supplement the missing attributes for the multiple attribute types. The attribute types include basic attributes, interest attributes, asset attributes, risk attributes, and the like. The fully connected sub-network graph of the same node to be determined can be drawn differently according to different missing attributes.
In another embodiment, the fully connected sub-network graph is used for supplementing the missing attribute of the node to be determined, in order to improve the accuracy of the missing attribute supplementation of the throw pillow, the server presets a screening threshold of the associated object node, and stops screening the associated object node if the determined object node does not exist in the associated object node reaching the level of the screening threshold, and generates corresponding prompt information of missing attribute supplementation failure. For example, if the association threshold is 2 and the determined object node does not exist in the two-degree association object nodes, a prompt message of "missing attribute supplementation failure" is returned.
The server presets a plurality of attribute types and corresponding target association relations, and selects the associated object nodes having the target association relations with the nodes to be determined in the corresponding fully-connected sub-network graph as reference object nodes according to the attribute types of the missing attributes. For example, when the attribute type is a basic attribute, an associated object having a classmate relationship, a colleague relationship, or a friend relationship with the pending object may be determined as a reference object; when the attribute type is an interest attribute, determining an associated object which has a friend relationship and a nearby personal relationship with the object to be determined as a reference object; when the attribute type is the asset attribute, determining an associated object which has a relationship with the target object and a friendship as a reference object; when the attribute type is a risk attribute, an associated object node having other object nodes connected in common with the node to be determined may be determined as a reference object node. It is easy to understand that all the associated objects in the fully connected subnetwork graph can also be determined as reference objects, but different reference weights are preset for different reference objects according to different missing attributes, which is not limited to this.
In the embodiment, the association relationship covering large-scale crowds is displayed in a relationship network map in a centralized manner, so that a user can master the association relationship among clients from the whole situation conveniently. And according to the different missing attributes, drawing a fully connected sub-network graph corresponding to the node to be determined from the relational network graph, so that a user can know a certain client in a more targeted manner.
In one embodiment, calculating the comprehensive association degree of each reference object node and the node to be determined comprises: acquiring social network information corresponding to a node to be determined; identifying the relationship type between each reference object node and the undetermined object node according to the social network information, and counting the event type and the occurrence frequency of the associated events occurring in the specified time period; acquiring a basic association coefficient corresponding to a preset relationship type; calculating the shortest social distance from each reference object node to the node to be determined on the basis of the fully connected sub-network graph; adjusting the basic association coefficient according to the shortest social distance and the event type and occurrence frequency of the associated events to obtain the unilateral association degree of the node to be determined based on different associated nodes; and superposing the single-side association degrees of the plurality of association nodes between each reference object node and the node to be determined to obtain the comprehensive association degree of the reference object node and the node to be determined.
The relationship type may be a relationship of relatives, classmates, coworkers, friends, transfer, location proximity, etc. The server can identify the relationship type between the two associated object nodes according to the identity attribute information and the social network information. For example, according to the same family wifi, enterprise wifi or public wifi connected with the target object A and the target objects B, C and D, the possible incidence relations of relatives and friends, co-workers or nearby people can be identified.
Different basic association coefficients may be preset for different relationship types. The two target objects may have various incidence relations, for example, the target objects A and B can be classmates, colleagues or friends. For this case, the server may also preset different basic association coefficients for different relationship types.
In another embodiment, based on different uses of the relationship network map, the mapping relationship between different relationship types and the basic association coefficient, or the mapping relationship between different relationship type combinations and the basic association coefficient may be preset. For example, when the relationship network graph is used to mine the client interest attributes, the direct relationship is set to 1, the co-workers relationship is set to 0.5, etc.; when the relationship network map is used for auditing the risk attributes of the client, the friendship is set to 1, the relativity is set to 0.4, and the like. According to the purpose of the relation network atlas, basic association coefficients corresponding to multiple purposes are preset, multiple unilateral association degree calculation modes are realized, different value meanings of each relation type on the evaluation association degree can be fully considered, and therefore the accuracy of supplementing different missing attributes based on the relation network atlas is improved.
The server determines a shortest social distance between the associated two object nodes based on the relationship network graph. The shortest social distance refers to the number of associated nodes that are to be passed at least from one object node to another object node. For example, in FIG. 3 of the above example, the shortest social distance between object nodes V3 and V5 is 1, and the shortest social distance between object nodes V4 and V8 is 2.
And the server counts the event type and the occurrence frequency of the associated events which occur in the counting period of the two associated object nodes according to the social network information. The related events can be interactive operations such as connecting the same local area network, sending social information based on an instant messaging platform or bank card transfer.
The server is preset with a plurality of event types, a plurality of occurrence frequency intervals corresponding to each event type and a first adjusting coefficient corresponding to each occurrence frequency interval. The server also presets a plurality of second adjustment coefficients corresponding to the shortest social distance. And increasing or reducing the basic correlation coefficient according to the first adjustment coefficient and the second adjustment coefficient to obtain a target correlation coefficient. And the server marks the target association coefficient as the unilateral association degree of the corresponding object node based on the corresponding association node. The directed edges connected to the corresponding object nodes exhibit corresponding single-sided association degrees, for example, in fig. 3 of the above example, the single-sided association degree of the associated node Q5183 with the two connected object nodes V5 and V8 is 3.21, i.e., the single-sided association degree of the object node V5 with the object node V8 based on the associated node Q5183 is 3.21. The single-edge degree of association of the association node M5482 with the two object nodes V5 and V8 connected thereto is 0.89.
The server superposes the single-side association degrees of the plurality of association nodes between the two object nodes, and the comprehensive association degree of the two object nodes can be obtained.
In the embodiment, the basic association coefficient is adjusted by simultaneously combining the shortest social distance and the influence factors of multiple dimensions of the frequency of occurrence of the association events, so that the calculation accuracy of the unilateral association degree can be improved, and the accuracy of the interest attribute value is further improved.
In one embodiment, determining a second interest reference value for the interest attribute based on the initial attribute information comprises: acquiring initial attribute information of the undetermined object, and constructing a user portrait of the undetermined object based on the initial attribute information; monitoring product reference records generated by browsing a target website by an object to be determined; generating an interest characteristic matrix of the object to be determined according to the user portrait and the product reference record; and calculating to obtain a second interest reference value based on the interest characteristic matrix.
The server acquires initial attribute information of the undetermined object, analyzes the initial attribute information and obtains a plurality of node labels corresponding to the nodes of the undetermined object, such as age, gender, occupation, marital status, cultural degree, occupation, property status, health status and the like. And the server forms the acquired node labels into a text vector, and the formed text vector is used as the user portrait of the object to be determined.
The server also captures the visit records of the object to be determined at various target websites, namely product reference records. The product reference record can be a click operation or a query operation of a certain product resource by the object to be determined at the target website.
And the server determines an interest characteristic matrix of the object to be determined according to the user portrait and the product reference record. Specifically, the user portrait and the product lookup record are combined into a long text vector, the text vector is used as an input variable and substituted into the random forest model, and then the interest probability of the object to be determined on various product resources is predicted. For example, assuming that the current resource pool has 100 product resources (A1-a 100), the probability that each product resource is expected to be acquired by the pending object needs to be predicted according to the user representation and the product reference record of the user.
And modeling by taking a target object of the next product resource acquisition behavior as a sample, and predicting the possibility that the current undetermined object expects to acquire each product resource. And the server obtains the interest characteristic matrix of the object to be determined according to the probability of the expected product resources. And the server predicts the possible acquisition probability after the A2 product resources are clicked, and the like until a random forest model of 100 product resources is established, and finally obtains the interest characteristic matrix of each product resource expected to be obtained by the undetermined object according to the established random forest model. The method for predicting the interest characteristic matrix of the undetermined object by adopting the random forest algorithm is characterized in that the undetermined object of the existing next-step acquired behavior is used as a sample to predict the interest characteristic matrix, namely, the method is used for measuring and calculating by combining the probability of the whole crowd, personal attributes and the current state, and the accuracy of measuring and calculating the second interest reference value is improved.
And the server calculates a second interest reference value based on the interest characteristic matrix. The second interest reference value may be one or more product resource identifiers and interest probabilities corresponding to each product resource identifier.
In the embodiment, the interest characteristic matrix corresponding to the undetermined object is determined according to the user portrait and the product reference record, the second interest reference value of the undetermined object is determined according to the interest characteristic matrix, the second interest reference value unique to the user is obtained because each undetermined object corresponds to one unique interest characteristic matrix, the interest attribute mining is carried out according to the second interest reference value, the personalized measurement and calculation can be well carried out according to the condition of each undetermined object, and the accuracy of the interest attribute mining result is improved. Meanwhile, the mining method is based on the user portrait and the product lookup record of the object to be determined for mining, is also suitable for new clients, and well solves the cold start problem of the new clients.
In one embodiment, the method further comprises: supplementing initial attribute information of the object to be determined based on the interest attribute value to obtain target attribute information; determining the client grade of the object to be targeted according to the target attribute information; screening matched salesmen according to the client grade, and pushing the target attribute information to a terminal corresponding to the screened salesmen; the receiving terminal returns product recommendation information based on the target attribute information, verifies the product recommendation information, and generates a product transaction link based on the verified product recommendation information; and pushing the product transaction link to a terminal corresponding to the pending object.
The server collects historical service data of a plurality of salesmen, counts the historical service data, and calculates the service skill value of each salesmen corresponding to different client levels. The historical service data refers to online message records of online business consultation and business handling provided by an operator for a client in historical time. The online message record can be an instant messaging record, a call record and the like. The historical service data comprises the number of follow-up online messages, the client grade of each online message corresponding to a client, corresponding client feedback and the like.
And the server performs classified statistics on the collected historical service data of each salesman according to different client grades of the service, and calculates the service skill value of each salesman corresponding to different client grades. And the server performs classified statistics on the plurality of message records and the client feedback corresponding to each message record according to the client level of the target client corresponding to each message record in the historical service data of the salesman to obtain the skill value of the salesman. The skill value calculated by each operator has a one-to-one correspondence with the customer level.
The server searches the salesmen with the corresponding service technical value one by one according to the client level until the idle salesmen is searched, and sends and pushes the target attribute information of the object to be determined to the terminal (operation service terminal) corresponding to the salesmen obtained by screening. The service staff can recommend the product resources at the service terminal according to the target attribute information and send the product recommendation information to the server.
And the server verifies the product recommendation information, if the product recommendation information passes the verification, a corresponding product transaction link is generated, and the product transaction link is pushed to a terminal (a user terminal) corresponding to the object to be determined. When the pending object confirms the product recommendation information based on the product transaction link, the user terminal displays a transaction payment page and displays a transaction success prompt according to the payment success operation of the customer on the transaction payment page. For example, a customer desires to purchase an insurance product, and the user terminal performs underwriting on product recommendation information based on preset check rules corresponding to different insurance products, such as whether the customer has a purchase right or not. And if the underwriting passes, converting the product recommendation information by the subprogram by using a preset formula to generate an insurance plan book, and pushing the insurance plan book to the user terminal. And when the undetermined object confirms the insurance confirmation book, displaying the premium payment page, and when the payment success operation corresponding to the premium payment page is detected, generating a corresponding insurance policy so as to finish the product transaction.
In the embodiment, based on the supplemented target attribute information, a salesman can more accurately recommend product resources; the salesman carries out product resource recommendation personally, so that the complexity of query operation before transaction can be reduced, the threshold of a client for purchasing products independently is reduced, and the product transaction efficiency is improved.
In one embodiment, supplementing initial attribute information of an object to be determined based on an interest attribute value to obtain target attribute information, including: identifying whether the risk attribute is missing in the initial attribute information; if yes, determining a first risk reference value of the risk attribute based on the fully connected sub-network graph; determining a second risk reference value of the object to be determined based on the initial attribute information; performing preset logical operation on the first risk reference value and the second risk reference value, and taking a calculation result as a risk attribute value of the object to be determined; and performing completion processing on the initial attribute information based on the interest attribute value and the risk attribute value to obtain target attribute information.
The server extracts the attribute value of the risk attribute (noted as the risk attribute value) from the identity attribute information corresponding to each reference object node. It is easy to understand that some attribute values of the risk attribute in the identity attribute information corresponding to the reference object node may be absent. The fully connected subnetwork graph includes at least one determinate object node so that at least one risk attribute value can be extracted.
And the server performs preset logical operation on the risk attribute value to obtain a first risk reference value of the risk attribute. The preset logical operation may be a superposition operation based on the reference weight. The reference weight may be determined according to a comprehensive association degree of the corresponding reference object node and the node to be determined. In another embodiment, the preset logical operation may be a median or an average of the plurality of risk attribute values.
The server acquires the identity attribute information of the target object from the service system. The identity attribute information of each target object can be obtained from different service systems, but the identity attribute information of some target objects may be incomplete and have missing attributes. For different service types, risk factors needing to be considered by risk assessment in a emphasizing manner are different, and the server presets corresponding risk assessment models respectively aiming at service systems for realizing different types of services. The server also presets corresponding risk coefficient weights for each business system. The risk coefficient weights are used for dividing different weight ratios for different importance degrees of each business system when the risk evaluation results output by the risk evaluation models corresponding to the business systems are comprehensively processed, so that the weighted comprehensive evaluation results are obtained. In other words, according to different uses of the relational network graph, different importance degrees of each business system on risk assessment can be represented based on the risk coefficient weight.
And the server calculates a second risk reference value corresponding to the object to be determined when the business system carries out comprehensive risk control according to the business risk coefficient and the inquired risk coefficient weight. The second risk reference value reflects the comprehensive risk evaluation result of the undetermined object in each service system, and the second risk reference value meeting different risk control requirements can be obtained by adjusting the risk coefficient weight according to the comprehensive risk control requirements.
And the server performs superposition operation based on the preset weight on the first risk reference value and the second risk reference value to obtain a risk attribute value corresponding to the object to be determined. The preset weight may be a fixed value. And the server trains a corresponding missing attribute completion model in advance aiming at the missing attributes. The server may give the calculated confidence level of the second risk reference value according to the model accuracy, so that the preset weight may also be dynamically determined according to the confidence level of the second risk reference value.
The product resource information can be accurately pushed to the target object according to the interest attribute value, and risk control can be performed on the corresponding target object according to the risk attribute value. For example, when the risk attribute value is higher than the threshold value, no relevant business service is provided, or further, the responsibility clause of additional business is generated based on the high risk condition, so as to avoid the risk and guarantee the effect of risk control.
In this embodiment, in addition to the identity attribute information of the target object itself, the identity attribute information of the reference object node having a strong association with the target object node is also considered, and the interest attribute and the risk attribute of the target object are predicted by integrating the factors of multiple dimensions, so that not only the information completion efficiency can be improved, but also the accuracy of completion information can be improved.
It should be understood that although the steps in the flowcharts of fig. 2 and 4 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2 and 4 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performing the sub-steps or stages is not necessarily sequential, but may be performed alternately or alternately with other steps or at least some of the sub-steps or stages of other steps.
In one embodiment, as shown in fig. 5, there is provided an interest property mining apparatus based on big data, including: a first interest mining module 502, a second interest mining module 504, and an interest attribute value calculation module 506, wherein:
a first interest mining module 502, configured to obtain a fully connected subnetwork graph of an object to be determined; the fully connected sub-network graph comprises undetermined object nodes and at least one reference object node; calculating the comprehensive association degree of each reference object node and each undetermined object node; obtaining interest attribute values corresponding to the reference object nodes, and determining reference weights of the interest attribute values according to the comprehensive association degree; and calculating to obtain a first interest reference value according to the interest attribute values and the reference weights respectively corresponding to the interest attribute values.
The second interest mining module 504 is configured to obtain initial attribute information of the object to be determined, and determine a second interest reference value of the interest attribute according to the initial attribute information.
An interest attribute value calculating module 506, configured to calculate an interest attribute value corresponding to the object to be determined based on the first interest reference value and the second interest reference value.
In one embodiment, the first interest mining module 502 includes a subnet graph construction module 5022 for obtaining a relationship network graph; the relational network graph comprises a plurality of object nodes and attribute nodes connected with each object node; identifying whether the attribute value of the interest attribute corresponding to each object node is missing; according to the identification result, a plurality of object nodes in the relational network graph are divided into determined object nodes and undetermined object nodes; drawing a fully-connected sub-network graph of each node to be determined in a relational network graph; and marking the object nodes which have target association relation with the object nodes to be determined in the fully-connected sub-network graph as reference object nodes.
In one embodiment, the first interest mining module 502 further includes an association degree calculating module 5024, configured to obtain social network information corresponding to the node to be determined; identifying the relationship type between each reference object node and the undetermined object node according to the social network information, and counting the event type and the occurrence frequency of the associated events occurring in the specified time period; acquiring a basic association coefficient corresponding to a preset relationship type; calculating the shortest social distance from each reference object node to the node to be determined on the basis of the fully connected sub-network graph; adjusting the basic association coefficient according to the shortest social distance and the event type and occurrence frequency of the associated events to obtain the unilateral association degree of the node to be determined based on different associated nodes; and superposing the single-side association degrees of the plurality of association nodes between each reference object node and the node to be determined to obtain the comprehensive association degree of the reference object node and the node to be determined.
In one embodiment, the second interest mining module 504 is further configured to obtain initial attribute information of the object to be determined, and construct a user portrait of the object to be determined based on the initial attribute information; monitoring product reference records generated by browsing a target website by an object to be determined; generating an interest characteristic matrix of the object to be determined according to the user portrait and the product reference record; and calculating to obtain a second interest reference value based on the interest characteristic matrix.
In one embodiment, the apparatus further includes a product resource recommending module 508, configured to supplement the initial attribute information of the object to be determined based on the interest attribute value, to obtain target attribute information; determining the client grade of the object to be targeted according to the target attribute information; screening matched salesmen according to the client grade, and pushing the target attribute information to a terminal corresponding to the screened salesmen; the receiving terminal returns product recommendation information based on the target attribute information, verifies the product recommendation information, and generates a product transaction link based on the verified product recommendation information; and pushing the product transaction link to a terminal corresponding to the pending object.
In one embodiment, the apparatus further comprises a risk attribute mining module 510 for identifying whether a risk attribute is missing from the initial attribute information; if yes, determining a first risk reference value of the risk attribute based on the fully connected sub-network graph; determining a second risk reference value of the object to be determined based on the initial attribute information; performing preset logical operation on the first risk reference value and the second risk reference value, and taking a calculation result as a risk attribute value of the object to be determined; and performing completion processing on the initial attribute information based on the interest attribute value and the risk attribute value to obtain target attribute information.
For specific limitations of the big data based interest attribute mining device, reference may be made to the above limitations of the big data based interest attribute mining method, which are not described herein again. The modules in the big data-based interest property mining device can be wholly or partially implemented by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in fig. 6. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing a relationship network map and identity attribute information and social network information of a plurality of target objects. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a big data based interest property mining method.
Those skilled in the art will appreciate that the architecture shown in fig. 6 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the big data based interest property mining method provided in any one of the embodiments of the present application.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware related to instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above examples only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A big data-based interest attribute mining method, the method comprising:
acquiring a fully-connected sub-network graph of an object to be determined; the fully connected subnetwork graph comprises pending object nodes and at least one reference object node;
calculating the comprehensive association degree of each reference object node and the undetermined object node;
obtaining interest attribute values corresponding to the reference object nodes, and determining reference weights of the interest attribute values according to the comprehensive association degree;
calculating to obtain a first interest reference value according to the interest attribute values and the reference weights respectively corresponding to the interest attribute values;
acquiring initial attribute information of the object to be determined, and determining a second interest reference value of an interest attribute according to the initial attribute information;
and calculating to obtain an interest attribute value corresponding to the object to be determined based on the first interest reference value and the second interest reference value.
2. The method of claim 1, wherein the obtaining a fully connected subnet graph of the pending object comprises:
acquiring a relation network map; the relational network graph comprises a plurality of object nodes and attribute nodes connected with each object node;
identifying whether the attribute value of the interest attribute corresponding to each object node is missing;
distinguishing a plurality of object nodes in the relational network graph into determined object nodes and undetermined object nodes according to the recognition result;
drawing a fully connected sub-network graph of each node to be determined in the relational network graph;
and marking the object nodes which have target association relation with the object nodes to be determined in the fully-connected sub-network graph as reference object nodes.
3. The method of claim 1, wherein the calculating of the integrated association of each reference object node with the pending object node comprises:
acquiring social network information corresponding to the node to be determined;
identifying the relationship type between each reference object node and the undetermined object node according to the social network information, and counting the event type and the occurrence frequency of the associated events occurring in the specified time period;
acquiring a preset basic association coefficient corresponding to the relationship type;
calculating the shortest social distance from each reference object node to the pending object node based on the fully connected sub-network graph;
and adjusting the basic association coefficient according to the shortest social distance and the event type and occurrence frequency of the associated event to obtain the comprehensive association degree of the reference object node and the undetermined object node.
4. The method of claim 1, wherein determining a second interest reference value for an interest attribute based on the initial attribute information comprises:
constructing a user portrait of the pending object based on the initial attribute information;
monitoring product reference records generated by the target website browsed by the object to be determined;
generating an interest characteristic matrix of the object to be determined according to the user portrait and a product reference record;
and calculating to obtain the second interest reference value based on the interest feature matrix.
5. The method of claim 1, further comprising:
supplementing the initial attribute information of the undetermined object based on the interest attribute value to obtain target attribute information;
determining the client grade of the undetermined target object according to the target attribute information;
screening matched salesmen according to the customer grade, and pushing the target attribute information to a terminal corresponding to the screened salesmen;
receiving product recommendation information returned by the terminal based on the target attribute information, verifying the product recommendation information, and generating a product transaction link based on the verified product recommendation information;
and pushing the product transaction link to a terminal corresponding to the pending object.
6. The method of claim 5, wherein supplementing the identity attribute information of the object to be determined based on the interest attribute value to obtain target attribute information comprises:
identifying whether a risk attribute is missing in the initial attribute information;
if yes, determining a first risk reference value of the risk attribute based on the fully connected sub-network graph;
determining a second risk reference value for the pending object based on the initial attribute information;
performing preset logical operation on the first risk reference value and the second risk reference value, and taking a calculation result as a risk attribute value of the object to be determined;
and performing completion processing on the initial attribute information based on the interest attribute value and the risk attribute value to obtain target attribute information.
7. An interest attribute mining apparatus based on big data, the apparatus comprising:
the first interest mining module is used for acquiring a fully-connected sub-network graph of an object to be determined; the fully connected subnetwork graph comprises pending object nodes and at least one reference object node; calculating the comprehensive association degree of each reference object node and the undetermined object node; obtaining interest attribute values corresponding to the reference object nodes, and determining reference weights of the interest attribute values according to the comprehensive association degree; calculating to obtain a first interest reference value according to the interest attribute values and the reference weights respectively corresponding to the interest attribute values;
the second interest mining module is used for acquiring initial attribute information of the object to be determined and determining a second interest reference value of the interest attribute according to the initial attribute information;
and the interest attribute value calculation module is used for calculating and obtaining an interest attribute value corresponding to the object to be determined based on the first interest reference value and the second interest reference value.
8. The apparatus of claim 7, wherein the first interest mining module comprises a sub-network graph building module configured to obtain a relationship network graph; the relational network graph comprises a plurality of object nodes and attribute nodes connected with each object node; identifying whether the attribute value of the interest attribute corresponding to each object node is missing; distinguishing a plurality of object nodes in the relational network graph into determined object nodes and undetermined object nodes according to the recognition result; drawing a fully connected sub-network graph of each node to be determined in the relational network graph; and marking the object nodes which have target association relation with the object nodes to be determined in the fully-connected sub-network graph as reference object nodes.
9. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 6 when executing the computer program.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910748904.5A CN110647676B (en) | 2019-08-14 | 2019-08-14 | Interest attribute mining method and device based on big data and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910748904.5A CN110647676B (en) | 2019-08-14 | 2019-08-14 | Interest attribute mining method and device based on big data and computer equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110647676A true CN110647676A (en) | 2020-01-03 |
| CN110647676B CN110647676B (en) | 2023-04-11 |
Family
ID=69009540
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910748904.5A Active CN110647676B (en) | 2019-08-14 | 2019-08-14 | Interest attribute mining method and device based on big data and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110647676B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111522888A (en) * | 2020-04-22 | 2020-08-11 | 北京百度网讯科技有限公司 | Method and device for mining competitive relationship between interest points |
| CN111860655A (en) * | 2020-07-23 | 2020-10-30 | 中国联合网络通信集团有限公司 | User processing method, device and equipment |
| CN112507220A (en) * | 2020-12-07 | 2021-03-16 | 中国平安人寿保险股份有限公司 | Information pushing method, device and medium |
| CN112749851A (en) * | 2021-01-20 | 2021-05-04 | 陈网芹 | Big data demand prediction method based on artificial intelligence and big data cloud service center |
| CN114398521B (en) * | 2021-02-23 | 2024-08-13 | 杭州云深科技有限公司 | Device type determining method and data processing system for acquiring abnormal device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104268271A (en) * | 2014-10-13 | 2015-01-07 | 北京建筑大学 | Interest and network structure double-cohesion social network community discovering method |
| US20160188704A1 (en) * | 2014-12-31 | 2016-06-30 | Facebook, Inc. | Systems and methods to determine trending topics for a user based on social graph data |
| WO2017036333A1 (en) * | 2015-09-02 | 2017-03-09 | 阿里巴巴集团控股有限公司 | Interaction event-based webpage item recommendation method and device |
| CN108053260A (en) * | 2017-12-27 | 2018-05-18 | 北京奇虎科技有限公司 | A kind of method and system that extending user is determined according to statistics interest-degree |
| CN108829793A (en) * | 2018-06-01 | 2018-11-16 | 杭州电子科技大学 | A kind of organizational member hobby method for digging |
-
2019
- 2019-08-14 CN CN201910748904.5A patent/CN110647676B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104268271A (en) * | 2014-10-13 | 2015-01-07 | 北京建筑大学 | Interest and network structure double-cohesion social network community discovering method |
| US20160188704A1 (en) * | 2014-12-31 | 2016-06-30 | Facebook, Inc. | Systems and methods to determine trending topics for a user based on social graph data |
| WO2017036333A1 (en) * | 2015-09-02 | 2017-03-09 | 阿里巴巴集团控股有限公司 | Interaction event-based webpage item recommendation method and device |
| CN108053260A (en) * | 2017-12-27 | 2018-05-18 | 北京奇虎科技有限公司 | A kind of method and system that extending user is determined according to statistics interest-degree |
| CN108829793A (en) * | 2018-06-01 | 2018-11-16 | 杭州电子科技大学 | A kind of organizational member hobby method for digging |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111522888A (en) * | 2020-04-22 | 2020-08-11 | 北京百度网讯科技有限公司 | Method and device for mining competitive relationship between interest points |
| US20210334278A1 (en) * | 2020-04-22 | 2021-10-28 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Method and apparatus for mining competition relationship pois |
| US11580124B2 (en) * | 2020-04-22 | 2023-02-14 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Method and apparatus for mining competition relationship POIs |
| CN111860655A (en) * | 2020-07-23 | 2020-10-30 | 中国联合网络通信集团有限公司 | User processing method, device and equipment |
| CN111860655B (en) * | 2020-07-23 | 2023-05-30 | 中国联合网络通信集团有限公司 | User processing method, device and equipment |
| CN112507220A (en) * | 2020-12-07 | 2021-03-16 | 中国平安人寿保险股份有限公司 | Information pushing method, device and medium |
| CN112749851A (en) * | 2021-01-20 | 2021-05-04 | 陈网芹 | Big data demand prediction method based on artificial intelligence and big data cloud service center |
| CN112749851B (en) * | 2021-01-20 | 2021-09-07 | 国网江苏省电力有限公司信息通信分公司 | Big data demand prediction method based on artificial intelligence and big data cloud service center |
| CN114398521B (en) * | 2021-02-23 | 2024-08-13 | 杭州云深科技有限公司 | Device type determining method and data processing system for acquiring abnormal device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110647676B (en) | 2023-04-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110659395B (en) | Method, device, computer equipment and storage medium for constructing relational network map | |
| US11985037B2 (en) | Systems and methods for conducting more reliable assessments with connectivity statistics | |
| US11968105B2 (en) | Systems and methods for social graph data analytics to determine connectivity within a community | |
| CN110647676B (en) | Interest attribute mining method and device based on big data and computer equipment | |
| CN110659799A (en) | Attribute information processing method and device based on relational network, computer equipment and storage medium | |
| US11508012B2 (en) | System and method for generating proactive underwriting offers using social media data | |
| US20230275817A1 (en) | Parallel computational framework and application server for determining path connectivity | |
| CN109582876B (en) | Tourist industry user portrait construction method and device and computer equipment | |
| US9922134B2 (en) | Assessing and scoring people, businesses, places, things, and brands | |
| CN110659396B (en) | Missing attribute information complementing method, device, computer equipment and storage medium | |
| CN108334625B (en) | User information processing method and device, computer equipment and storage medium | |
| CN112131277B (en) | Medical data anomaly analysis method and device based on big data and computer equipment | |
| CN111191100A (en) | Government affair information processing method and device and computer readable storage medium | |
| CN110598124B (en) | Numerical attribute mining method, device, computer equipment and storage medium | |
| CN112085566A (en) | Product recommendation method and device based on intelligent decision and computer equipment | |
| US11671432B1 (en) | Portable trust rating method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |