An information information pushing method and device, electronic equipment and storage medium

Abstract

The application discloses an information information pushing method and device, electronic equipment and storage medium, and the method comprises the following steps: acquiring the data record of the access page of the target object; according to the data record, the individual interest graph of the target object is obtained by collating; the individual interest graph comprises the first correlation weight between each access page; based on the union of the access pages of different target objects, the individual interest graph of each target object is fused in combination with the first correlation weight, and a group interest graph is obtained; wherein, the group interest graph comprises the second correlation weight between each access page; based on the page node corresponding to the access page in the group interest graph and the adjacent node of the page node, the importance of the page node is obtained in combination with the corresponding second correlation weight; and the information information of each page node corresponding to the access page is pushed based on the importance. The application can realize accurate pushing of user favorite information information, and can be widely applied to the technical field of data processing.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to an information push method, apparatus, electronic device, and storage medium. Background Technology

[0002] The continuous development of big data technology and the integration of diversified businesses have driven enterprises to develop their products from single to diversified, customized and high-quality. To this end, it is necessary to analyze users' preferences and potential tendencies in order to quickly and accurately understand the information that users care about, thereby increasing retention rates and improving user experience to ensure the company's competitiveness in the market.

[0003] The diversification and rapid increase in the volume of business information sources have led to information redundancy and duplicate pushes, negatively impacting customer experience. To ensure the accuracy of information delivery, user behavior analysis is necessary. However, traditional information delivery methods merely quantify information by linearly weighting relevant metrics, resulting in incomplete understanding of influencing factors, inaccurate quantification of user interests, and inaccurate push results. Summary of the Invention

[0004] This invention aims to at least partially solve one of the technical problems in related technologies. To this end, this invention proposes an information push method, apparatus, electronic device, and storage medium capable of accurately pushing information.

[0005] On one hand, embodiments of the present invention provide an information push method, including:

[0006] Retrieve data records of the target object's accessed pages;

[0007] Based on the data records, an individual interest graph of the target object is obtained; the individual interest graph includes the first association weight between each visited page;

[0008] Based on the union of accessed pages of different target objects, the individual interest graphs of each target object are fused together with the first association weight to obtain a group interest graph; wherein, the group interest graph includes the second association weight between each accessed page;

[0009] The importance of a page node is obtained by combining the page node corresponding to the accessed page in the group interest graph with the adjacent nodes of the page node and the corresponding second association weight.

[0010] Information is pushed to the corresponding access pages based on their importance.

[0011] Optionally, the data records include the tags of the visited pages, the number of visits, and the navigation relationships and number of navigations between the visited pages; based on the data records, an individual interest graph of the target object is obtained, including:

[0012] Based on the tags of all the pages accessed by the target object, we obtain the access tag set of the target object;

[0013] The page weight of the accessed page is determined based on the number of times the accessed page of the target object is accessed, and then the page weights of each accessed page are sorted out to obtain the page weight set of the target object.

[0014] The relationships between accessed pages are determined based on the redirection relationships between them. Then, all the relationships between accessed pages are organized to obtain the set of relationships between the target object. Among them, when there is a redirection relationship between accessed pages, the relationship value is 1; otherwise, the relationship value is 0.

[0015] Multiply the association between the accessed pages by the number of jumps between the corresponding accessed pages to obtain the first association weight between the accessed pages. Then, organize the association relationships between all accessed pages to obtain the association weight set of the target object.

[0016] The individual interest graph of the target object is obtained by organizing the access tag set, page weight set, relationship set, and relationship weight set.

[0017] Optionally, the page weight of a page is determined based on the number of times the target object's access page is accessed, including:

[0018] Add up the number of visits to all the accessed pages to get the total number of visits;

[0019] The page weight of a visited page is calculated based on the ratio of the number of visits to the total number of visits.

[0020] Optionally, based on the union of accessed pages of different target objects, and combined with the first association weight, the individual interest graphs of each target object are fused to obtain a group interest graph, including:

[0021] The matrix size is determined by the union of accessed pages based on different target objects;

[0022] Based on matrix specifications, the individual interest graphs of each target object are converted into adjacency matrices;

[0023] The group interest graph is obtained by combining the adjacency matrix corresponding to each individual interest graph with the first association weight.

[0024] Optionally, based on the adjacency matrix corresponding to each individual's interest graph and combined with the first association weight, a group interest graph is obtained, including:

[0025] Based on the adjacency matrix corresponding to each individual's interest graph, and combined with the first association weight, the group interest graph is calculated using the group interest graph formula; where the group interest graph is in matrix format, and the expression of the group interest graph formula is:

[0026]

[0027] In the formula, V(A)[i,j] represents the value of the element at (i,j) in the group interest graph; N A δ represents the total number of target objects in the group; t represents the t-th target object; t (w i ,w j ) represents the page node w of the t-th target object. i The corresponding access page and page node w j The first association weight between the corresponding accessed pages; A t [i,j] represents the value of the element at (i,j) in the adjacency matrix of the t-th target object; a (i,j) Represents page node w i and page node w j The line connecting them; D t Let W represent the individual interest graph of the t-th target object; let W represent the set of pages accessed by the t-th target object.

[0028] Optionally, the second association weight represents the sum of the first association weights of all target objects on the same accessed page; based on the page node corresponding to the accessed page in the group interest graph and the adjacent nodes of the page node, the importance of the page node is obtained by combining the corresponding second association weight, including:

[0029] The influence of a page node is obtained by adding the second association weights between the visited page corresponding to a page node and the visited page corresponding to the first-order node of the page node, and between the visited page corresponding to the visited page corresponding to the second-order node of the page node, in the group interest graph. Then, the importance of the page node is derived based on its influence. Here, a first-order node represents a node directly connected to the page node, and a second-order node represents a node indirectly connected to the page node through a first-order node. The expression for influence is:

[0030]

[0031] In the formula, T(w) i ) represents page node w i Its influence; Indicates w i The set of first-order nodes, w r Indicates wi First-order nodes; δ(w) i ,w r ) indicates w i and w r The second association weight; Indicates w i The set of second-order nodes, Indicates w r The set of first-order nodes, w v Indicates w i The second-order node and w r First-order nodes; δ(w) r ,w v ) indicates w r and w v The second association weight.

[0032] Optionally, information is pushed to the accessed pages corresponding to each page node based on its importance, including:

[0033] The push factor for the accessed page is obtained by combining the importance with the page weight of the corresponding accessed page; where the page weight is determined by the ratio of the number of times the accessed page is accessed to the total number of times all accessed pages are accessed.

[0034] The push priority of each access page is determined based on the push factor, and information is pushed according to the push priority.

[0035] On the other hand, embodiments of the present invention provide an information push device, including:

[0036] The first module is used to obtain data records of the target object's accessed pages;

[0037] The second module is used to organize the data records to obtain the individual interest graph of the target object; the individual interest graph includes the first association weight between each visited page;

[0038] The third module is used to fuse the individual interest graphs of each target object based on the union of accessed pages of different target objects and the first association weight to obtain a group interest graph; wherein, the group interest graph includes the second association weight between each accessed page.

[0039] The fourth module is used to obtain the importance of a page node based on the page node corresponding to the accessed page in the group interest graph and the adjacent nodes of the page node, combined with the corresponding second association weight.

[0040] The fifth module is used to push information to the accessed pages corresponding to each page node based on its importance.

[0041] On the other hand, embodiments of the present invention provide an electronic device, including: a processor and a memory; the memory is used to store a program; the processor executes the program to implement the above-mentioned information push method.

[0042] On the other hand, embodiments of the present invention provide a computer storage medium storing a processor-executable program, which, when executed by a processor, is used to implement the above-described information push method.

[0043] This invention embodiment obtains data records of accessed pages of a target object; based on the data records, it organizes and obtains an individual interest graph of the target object; wherein, the individual interest graph includes a first association weight between each accessed page; based on the union of accessed pages of different target objects, and combined with the first association weight, the individual interest graphs of each target object are fused to obtain a group interest graph; wherein, the group interest graph includes a second association weight between each accessed page; based on the page node corresponding to the accessed page in the group interest graph and the adjacent nodes of the page node, and combined with the corresponding second association weight, the importance of the page node is obtained; and information is pushed to the accessed page corresponding to each page node based on the importance. This invention embodiment first creates an individual interest graph through user access page data records, which mainly reflects the degree of preference of individual users for information. Second, it effectively merges the interest graphs of different individual users to obtain a group interest graph, and then obtains the importance of the node page based on the association weight between each page node in the group interest graph. Finally, information is pushed based on the importance, thereby achieving accurate delivery of information based on user preferences. Attached Figure Description

[0044] The accompanying drawings are provided to further understand the technical solutions of the present invention and constitute a part of the specification. They are used together with the embodiments of the present invention to explain the technical solutions of the present invention, and do not constitute a limitation on the technical solutions of the present invention.

[0045] Figure 1 This is a schematic diagram of an implementation environment for pushing information provided in an embodiment of the present invention;

[0046] Figure 2 This is a flowchart illustrating an information push method provided in an embodiment of the present invention;

[0047] Figure 3 This is a schematic diagram of the process of organizing individual interest maps provided in an embodiment of the present invention;

[0048] Figure 4 This is a schematic diagram illustrating the overall process principle of information push provided in this embodiment of the invention;

[0049] Figure 5A schematic diagram illustrating an example of an individual interest map provided in an embodiment of the present invention;

[0050] Figure 6 A schematic diagram illustrating another example of an individual interest map provided in an embodiment of the present invention;

[0051] Figure 7 A schematic diagram illustrating an example of a group interest graph provided in an embodiment of the present invention;

[0052] Figure 8 This is a schematic diagram of the structure of an information push device provided in an embodiment of the present invention;

[0053] Figure 9 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention;

[0054] Figure 10 A computer system architecture block diagram suitable for implementing electronic devices according to embodiments of the present invention is provided. Detailed Implementation

[0055] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0056] It should be noted that although functional modules are divided in the system diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the system or the order in the flowchart. The terms "first / S100," "second / S200," etc., in the specification, claims, and the aforementioned figures are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0057] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0058] It is understood that the information push method provided in this embodiment of the invention can be applied to any computer device with data processing and computing capabilities, and this computer device can be various terminals or servers. When the computer device in the embodiment is a server, the server is an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms. Optionally, the terminal can be a smartphone, tablet computer, laptop computer, or desktop computer, but it is not limited to these.

[0059] like Figure 1 The diagram shown is a schematic representation of an implementation environment provided by an embodiment of the invention. (Refer to...) Figure 1 The implementation environment includes at least one terminal 102 and a server 101. The terminal 102 and the server 101 can be connected via a network, either wirelessly or via a wired connection, to complete data transmission and exchange.

[0060] Server 101 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms.

[0061] Additionally, server 101 can also be a node server in a blockchain network. Blockchain is a novel application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and encryption algorithms.

[0062] Terminal 102 can be a smartphone, tablet computer, laptop computer, desktop computer, smart speaker, smartwatch, etc., but is not limited to these. Terminal 102 and server 101 can be directly or indirectly connected via wired or wireless communication, and this embodiment of the invention does not impose any limitations.

[0063] Exemplary based on Figure 1 The implementation environment shown in this embodiment of the invention provides an information push method. The following description uses the application of this information push method in server 101 as an example. It can be understood that this information push method can also be applied in terminal 102 to realize automatic scheduling and processing of business security issues of the monitored network.

[0064] Reference Figure 2 , Figure 2 This is a flowchart illustrating an information push method applied to a server, provided in an embodiment of the present invention. The executing entity of this information push method can be any of the aforementioned computer devices (including servers or terminals). (Refer to...) Figure 2 The method includes the following steps:

[0065] S100: Obtain the data records of the accessed pages of the target object;

[0066] It should be noted that the data records include the tags of the accessed pages, the number of accesses, and the redirection relationships and number of redirects between the accessed pages.

[0067] S200. Based on the data records, we can compile and obtain the individual interest map of the target object;

[0068] The individual interest graph includes the first association weight between each visited page;

[0069] It should be noted that in some embodiments, such as Figure 3 As shown, step S200 may include: S201, compiling a set of access tags for the target object based on the tags of all accessed pages of the target object; S202, determining the page weight of each accessed page based on the number of accesses to the accessed pages of the target object, and then compiling the page weights of each accessed page to obtain a set of page weights for the target object; S203, determining the association relationship between accessed pages based on the jump relationship between accessed pages, and then compiling the association relationship between all accessed pages to obtain a set of association relationships for the target object; wherein, when there is a jump relationship between accessed pages, the association relationship value is 1, otherwise, the association relationship value is 0; S204, multiplying the association relationship between accessed pages by the corresponding number of jumps between accessed pages to obtain the first association weight between accessed pages, and then compiling the association relationships between all accessed pages to obtain a set of association weights for the target object; S205, compiling an individual interest graph of the target object based on the set of access tags, the set of page weights, the set of association relationships, and the set of association weights.

[0070] In some embodiments, determining the page weight of an accessed page based on the number of times the accessed page of the target object is accessed includes: adding up the number of accesses of all accessed pages to obtain the total number of accesses; and calculating the page weight of the accessed page based on the ratio of the number of accesses of the accessed page to the total number of accesses.

[0071] In some specific embodiments, the establishment of an individual interest graph includes the following process: the individual interest graph mainly consists of four parts: user access information page tags, access information page weights, page associations, and page association weights.

[0072] (1) User accesses page tags:

[0073] The pages are categorized according to business functions, and each page is numbered, i.e., a corresponding tag is set for each page. Then, the page access tag set W corresponding to user U is... i It can be represented as:

[0074] W i ={w i |i=1,2,3,…,n} (1)

[0075] Among them, w i This represents the i-th visited page, and n represents the total number of pages visited by the user.

[0076] (2) Page access weight:

[0077] User access page w i The importance is indicated as follows:

[0078]

[0079] In the formula WF i That is, individual users accessing the page w i The weights, N i Let represent the number of times the user visits the i-th page, and let the denominator represent the sum of the number of times all pages are visited. Therefore, the weight set of user page visits can be represented as:

[0080] K(w i )={k(w i )|w i ∈W}, i=1,2,3,…,n (3)

[0081] k(w i ) indicates page w i The weights (i.e., WF) i ), can be calculated using equation (2), where W is the set of pages accessed by the user.

[0082] (3) Page association:

[0083] Each visited page can be viewed as a node, and page relationships are mainly determined by the navigation relationships between each page in the visited page set. Let the Boolean variable θ(w i ,w j If page w i With w j If there is no jump relationship between them, then θ(w) i ,w j If θ(w) is 0, it means there is no relationship between the pages; conversely, if there are redirects between pages, then θ(w) = 0. i ,wj A value of 1 indicates that there is some kind of relationship between the pages. Therefore, the set of relationships between pages can be represented as:

[0084] R i ={(w i ,w j )|θ(w i ,w j )=1}, i,j=(1,2,3,…,n) (4)

[0085] (4) Page association weight:

[0086] Page association weight is mainly derived from the frequency of related pages appearing, so page w i With w j Correlation frequency δ(w) i ,w j )for:

[0087] δ(w i ,w j )=θ(w i ,w j )×P (i,j) (5)

[0088] In the formula P (i,j) This represents the number of jumps between page i and page j. From equations (4) and (5) above, the page association weight set can be derived as follows:

[0089] Q(R i )=}δ(w i ,w j )|w i ,w j ∈W}, i,j=(1,2,3,…,n) (6)

[0090] Therefore, the interest graph of an individual user can be represented as:

[0091] H i ={W i ,K(w i ),R i ,Q(R i )} (7)

[0092] In some specific embodiments, the set S of interest graphs of all users can be further obtained as follows:

[0093] S={H i ,i=1,2,3,…,n} (8)

[0094] Among them, H i Let represent the interest graph of the i-th user, and n represent the number of users.

[0095] S300: Based on the union of accessed pages of different target objects, and combined with the first association weight, the individual interest graphs of each target object are fused to obtain the group interest graph;

[0096] Among them, the group interest graph includes the second association weight between each visited page;

[0097] It should be noted that in some embodiments, step S300 may include: determining the matrix size based on the union of the access pages of different target objects; converting the individual interest graphs of each target object into adjacency matrices based on the matrix size; and obtaining the group interest graph by combining the adjacency matrices corresponding to each individual interest graph with the first association weight. For example, if the number of unions of the access pages of two target objects is 7, then the determined matrix size is 7×7.

[0098] In some embodiments, the group interest graph is obtained by combining the adjacency matrix corresponding to each individual interest graph with a first association weight. This includes: calculating the group interest graph using the group interest graph formula based on the adjacency matrix corresponding to each individual interest graph and the first association weight; wherein the group interest graph is in matrix format, and the expression of the group interest graph formula is:

[0099]

[0100] In the formula, V(A)[i,j] represents the value of the element at (i,j) in the group interest graph; N A δ represents the total number of target objects in the group; t represents the t-th target object; t (w i ,w j ) represents the page node w of the t-th target object. i The corresponding access page and page node w f The first association weight between the corresponding accessed pages; A t [i,j] represents the value of the element at (i,j) in the adjacency matrix of the t-th target object; a (i,j) Represents page node w i and page node w j The line connecting them; D t Let W represent the individual interest graph of the t-th target object; let W represent the set of pages accessed by the t-th target object.

[0101] In some specific embodiments, the establishment of a group interest graph includes the following process:

[0102] By combining the collection of all user-accessed pages with the interest graphs of individual users, a group interest graph containing all accessed pages and their relationships is created.

[0103] (1) Individual interest graph modeling:

[0104] Treating each visited page as a node in a graph, the individual interest graph can be represented by an adjacency matrix:

[0105]

[0106] In the formula a (i,j) Represents page node w i and page node w j The line connecting them, D t Let W represent the interest graph of the t-th user, and W be the set of all pages visited by the t-th user. If the interest graph of the t-th user contains a connecting line a... (i,j) Then matrix A t The value of [i,j] is 1, otherwise the matrix value is 0.

[0107] (2) Group interest graph modeling:

[0108] First, the union of the pages visited by individual users in the group is calculated. Then, the group interest graph matrix model is derived by using the page association weights and the adjacency matrix of the individual interest graphs.

[0109]

[0110] In the formula δ t (w i ,w j Let N be the association weight of the page visited by the t-th user. A A represents the total number of individual users in the group. t [i,j] represents the adjacency matrix of the t-th user.

[0111] (3) Group interest graph weights:

[0112] According to formula (2), the weight value of an individual user's page can be obtained. The weight values ​​of each user's page are added together to obtain the weight of the group interest graph:

[0113]

[0114] In the formula K t (w i ) represents the page accessed by the t-th user. i The weights, N A This represents the total number of individual users in the group.

[0115] S400. Based on the page node corresponding to the accessed page in the group interest graph and the adjacent nodes of the page node, the importance of the page node is obtained by combining the corresponding second association weight.

[0116] It should be noted that the second association weight represents the sum of the first association weights of all target objects on the same accessed page; in some embodiments, step S400 may include: based on the second association weight between the accessed page corresponding to the page node and the accessed page corresponding to the first-order node of the page node in the group interest graph, and the second association weight between the accessed page corresponding to the first-order node and the accessed page corresponding to the second-order node of the page node, the influence of the page node is obtained by adding them together; and then the importance of the page node is obtained based on the influence; wherein, the first-order node represents the node directly connected to the page node, and the second-order node represents the node indirectly connected to the page node through the first-order node; the expression for influence is:

[0117]

[0118] In the formula, T(w) i ) represents page node w i Its influence; Indicates w i The set of first-order nodes, w r Indicates w i First-order nodes; δ(w) i ,w r ) indicates w i and w r The second association weight; Indicates w i The set of second-order nodes, Indicates w r The set of first-order nodes, w v Indicates w i The second-order node and w r First-order nodes; δ(w) r ,w v ) indicates w r and w v The second association weight.

[0119] In some specific embodiments, the calculation process for the importance of nodes in the group interest graph is as follows:

[0120] In a group interest graph, each node has its own importance. The importance of the current node is not only related to the adjacent first-level nodes, but also affected by the second-level nodes connected to the first-level nodes, while also taking into account the role of the association weight between nodes.

[0121]

[0122] In formula (12) For node w i The set of first-order nodes, δ(w) i ,w r ) is node w i With node w r Association weights Represents node w v Not only w i The second-level node and also w r The first-level node, and w r ≠w v .

[0123]

[0124] In formula (13) Represents node w r Belongs to node w i The set of first-order nodes, T(w) r The value can be calculated from equation (12). From equations (12) and (13), the node w can be obtained. i Importance is:

[0125]

[0126] In equation (14) Represents node w t Belongs to node w i The set of first-order nodes, N(w) t It can be calculated from equation (13).

[0127] S500 pushes information to the accessed pages corresponding to each page node based on importance.

[0128] It should be noted that step S500 may include: obtaining the push factor of the accessed page based on its importance and the page weight of the corresponding accessed page; wherein, the page weight is determined based on the ratio of the number of times the accessed page is accessed to the total number of times all accessed pages are accessed; determining the push priority of each accessed page based on the push factor, and pushing information according to the push priority.

[0129] In some specific embodiments, the information push process based on node importance is as follows:

[0130] In an interest graph, the importance of a node is not only related to the weight of the associations between nodes, but also influenced by the node's own weight. Therefore, the product of node importance and node's own weight is used as the basis for node recommendation.

[0131] E(w i )= I(w i )×K(wi (15)

[0132] In the above formula, E(w) i ) is node w i The push factor, I(w) i ) is node w i The importance of K(w) can be calculated using equation (14). i ) is node w i The weights can be obtained from equation (3).

[0133] Finally, by arranging the push factors of each node in the calculated group interest graph from largest to smallest, the push priority of the target business information can be obtained. The larger the push factor, the higher the push priority.

[0134] To explain in detail the principle of the technical solution of the present invention, the overall process of the present invention will be described below with reference to some specific embodiments. It is easy to understand that the following is an explanation of the technical principle of the present invention and should not be regarded as a limitation of the present invention.

[0135] In some specific embodiments, such as Figure 4 As shown, the specific implementation steps mainly include the following four steps:

[0136] 1. Initialize user interest data:

[0137] First, data statistics are performed through the monitoring platform. For example, Table 1 shows the data on user U1 and user U2 browsing tab pages within a certain time period.

[0138] Table 1

[0139]

[0140] The pages visited by users are numbered as follows: w1: Education, w2: Healthcare, w3: Smart City, w4: Entertainment, w5: Big Data, w6: Finance, w7: Food.

[0141] 2. Establishment of individual interest maps:

[0142] First, according to equation (1), we can determine that the set of pages accessed by user U1 is W1 = {w1, w2, w3, w4, w5}, and the set of pages accessed by user U2 is W2 = {w2, w3, w5, w6, w7}.

[0143] Secondly, the page weight sets for the two users can be calculated using equations (2) and (3), respectively: Page weight for user U1: K1 = {0.08, 0.26, 0.34, 0.12, 0.2}, Page weight for user U2: K2 = {0.31, 0.1, 0.28, 0.14, 0.17}.

[0144] Furthermore, according to formula (4), the page association sets are R1={(w1,w3),(w1,w5),(w2,w3),(w3,w5),(w2,w4)} and R2={(w2,w3),(w2,w7),(w3,w5),(w3,w7),(w5,w6)}.

[0145] Finally, from equations (5) and (6), the set of page association weights for user U1 is Q(R1) = {5|(w1,w3),4|(w1,w5),7|(w2,w3),4|(w3,w5),2|(w2,w4)}, and the set of page association weights for user U2 is Q(R2) = {7|(w2,w3),4|(w2,w7),8|(w3,w5),5|(w3,w7),6|(w5,w6)}.

[0146] Therefore, the individual interest map of user U1 can be obtained as follows: Figure 5 As shown, and as user U2's... Figure 6 As shown.

[0147] 3. Integration of individual interest maps:

[0148] First, since it is necessary to fuse the individual interest graphs, it is necessary to find the union of the access pages of the two users, that is, W = W1UW2 = {w1, w2, w3, w4, w5, w6, w7}. Therefore, two 7×7 matrices can be obtained according to equation (9), where A1 and A2 represent the matrix form of the individual interest graphs of users U1 and U2, respectively, and their expressions are as follows:

[0149]

[0150] Then, according to equation (10), the matrix form V(A) of the group interest map can be calculated:

[0151]

[0152] The weights of the group interest graph are calculated according to formula (11):

[0153] Q(W) = [0.08, 0.57, 0.44, 0.12, 0.48, 0.14, 0.17], corresponding to w1, w2, w3, w4, w5, w6, w7 respectively.

[0154] The matrix V(A) of the group interest map is obtained by normalizing it.

[0155]

[0156] The above method can be used to merge the interest graphs of individual users U1 and U2, resulting in a merged group interest graph as follows: Figure 7 As shown, this includes all users' accessed pages, page weights, page association information, and association weights.

[0157] 4. Calculation of node page importance and push factor:

[0158] The importance of each page node can be calculated from the group interest graph obtained in step 3. Taking page w1 as an example, the following explanation is provided:

[0159] like Figure 7 Taking node w1 as an example, the first-level node set of w1 is {w3, w5}, and the second-level node set is {w2, w3, w5, w6, w7}. Therefore, according to equations (12), (13), (14), and (15), we can obtain:

[0160] T(w1)=δ(w1,w3)+δ(w1,w5)+δ(w3,w2)+δ(w3,w5)+δ(w3,w7)+δ(w5,w3)+δ(w5,w6)=4.16

[0161] N(w1) = T(w3) + T(w5) = 7.65

[0162] I(w1)=N(w3)+N(w5)=24.93

[0163] The push factor for node w1 is: E(w1) = I(w1) × K(w1) = 1.99.

[0164] The calculation process for the push factors of the remaining nodes is the same as that of node w1, and will not be repeated here. The calculation results for all node pages in the group interest graph are shown in Table 2 below:

[0165] Table 2

[0166] <![CDATA[w1]]> <![CDATA[{w3,w5}]]> <![CDATA[{w2,w3,w5,w6,w7}]]> 4.16 7.65 24.93 1.99 <![CDATA[w2]]> <![CDATA[{w3,w4,w7}]]> <![CDATA[{w1,w3,w5,w7}]]> 3.37 9.45 25.93 14.78 <![CDATA[w3]]> <![CDATA[{w1,w2,w5,w7}]]> <![CDATA[{w1,w2,w4,w5,w6,w7}]]> 4.02 15.17 34.25 15.07 <![CDATA[w4]]> <![CDATA[{w2}]]> <![CDATA[{w3,w7}]]> 1.43 3.37 9.45 1.13 <![CDATA[w5]]> <![CDATA[{w1,w3,w6}]]> <![CDATA[{w1,w2,w3,w7}]]> 3.63 9.76 26.45 12.78 <![CDATA[w6]]> <![CDATA[{w5}]]> <![CDATA[{w1,w3}]]> 1.58 3.63 9.76 1.37 <![CDATA[w7]]> <![CDATA[{w2,w3}]]> <![CDATA[{w1,w2,w3,w4,w5}]]> 4.01 7.39 24.62 4.19

[0167] Finally, the push factors of each node page are sorted from largest to smallest as follows: E(w3)>E(w2)>E(w5)>E(w7)>E(w1)>E(w6)>E(w4), which means that the priority of pushing target business information from high to low is smart city, medical care, big data, food, education, finance, and entertainment.

[0168] Specifically, the information push method for target businesses based on user behavior analysis mentioned in the embodiments of the present invention can be applied to the information push module. By statistically analyzing user behavior data, user access pages are classified, numbered, and initialized. Interest graphs of different users are established, and the interest graphs of different users are effectively integrated to obtain a group interest graph. The priority of pushed information is obtained from high to low by calculating the inference factor: smart city, medical care, big data, food, education, finance, and entertainment.

[0169] In summary, this invention creates an individual user interest graph by considering user access to information page tags, the page's own weight, the relationships between pages, and the page association weights. This individual user interest graph primarily reflects an individual user's preference for information. Secondly, different individual user interest graphs are effectively merged to obtain a group interest graph. Then, the importance of each node page is determined based on the association weights between page nodes in the group interest graph. Finally, the importance of each node page is combined with its own weight to obtain an information push factor. Sorting the information according to the push factor ranking yields the information push priority, thus enabling rapid and accurate delivery of user-preferred information. Compared with existing technologies, this invention offers at least the following advantages: 1. Interest graph modeling is unrestricted and can be applied to business scenarios with complex user behaviors and mutual influences; 2. Interest graphs can be merged to expand the interest group and can be applied to cross-business information platforms; 3. Pushed information is more accurate, providing more options for industries such as e-commerce, news, and marketing.

[0170] On the other hand, such as Figure 8 As shown, this embodiment of the invention provides an information push device 800, comprising: a first module 810 for acquiring data records of accessed pages of a target object; a second module 820 for organizing the data records to obtain an individual interest graph of the target object; wherein the individual interest graph includes a first association weight between each accessed page; a third module 830 for fusing the individual interest graphs of each target object based on the union of accessed pages of different target objects and the first association weight to obtain a group interest graph; wherein the group interest graph includes a second association weight between each accessed page; a fourth module 840 for obtaining the importance of a page node based on the page node corresponding to the accessed page in the group interest graph and the adjacent nodes of the page node, and the corresponding second association weight; and a fifth module 850 for pushing information to the accessed pages corresponding to each page node based on the importance.

[0171] The content of the method embodiments of the present invention is applicable to the device embodiments. The specific functions implemented by the device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above methods.

[0172] On the other hand, such as Figure 9 As shown, this embodiment of the invention also provides an electronic device 900, which includes at least one processor 910 and at least one memory 920 for storing at least one program; taking one processor 910 and one memory 920 as an example.

[0173] The processor 910 and memory 920 can be connected via a bus or other means.

[0174] Memory 920, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory 920 may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory 920 may optionally include memory remotely located relative to the processor, and this remote memory can be connected to the device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0175] The electronic device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0176] Specifically, Figure 10 A schematic block diagram of a computer system architecture for implementing an electronic device according to embodiments of the present invention is shown.

[0177] It should be noted that, Figure 10 The computer system 1000 of the electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of the present invention.

[0178] like Figure 10As shown, the computer system 1000 includes a central processing unit (CPU) 1001, which can perform various appropriate actions and processes based on programs stored in read-only memory (ROM) 1002 or programs loaded from storage section 1008 into random access memory (RAM). The RAM 1003 also stores various programs and data required for system operation. The CPU 1001, ROM 1002, and RAM 1003 are interconnected via a bus 1004. An input / output interface 1005 (I / O interface) is also connected to the bus 1004.

[0179] The following components are connected to the input / output interface 1005: an input section 1006 including a keyboard, mouse, etc.; an output section 1007 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 1008 including a hard disk, etc.; and a communication section 1009 including a network interface card such as a local area network card, modem, etc. The communication section 1009 performs communication processing via a network such as the Internet. A drive 1010 is also connected to the input / output interface 1005 as needed. A removable medium 1011, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on the drive 1010 as needed so that computer programs read from it can be installed into the storage section 1008 as needed.

[0180] In particular, according to embodiments of the present invention, the processes described in the various method flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 1009, and / or installed from removable medium 1011. When the computer program is executed by central processing unit 1001, it performs various functions defined in the system of the present invention.

[0181] It should be noted that the computer-readable medium shown in the embodiments of the present invention can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present invention, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, wherein computer-readable program code is carried. Such transmitted data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wired, etc., or any suitable combination thereof.

[0182] The content of the method embodiments of the present invention is applicable to the system embodiments. The specific functions implemented in the system embodiments are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above methods.

[0183] Another aspect of this invention provides a computer-readable storage medium storing a program that is executed by a processor to implement the aforementioned method.

[0184] The content of the method embodiments of the present invention is applicable to the computer-readable storage medium embodiments. The specific functions implemented by the computer-readable storage medium embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above methods.

[0185] This invention also discloses a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device can read the computer instructions from the computer-readable storage medium and execute the computer instructions, causing the computer device to perform the aforementioned method.

[0186] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0187] It should be noted that although several modules for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to embodiments of the present invention, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0188] Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, portable hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, touch terminal, or network device, etc.) to execute the method according to the embodiments of the present invention.

[0189] In some alternative embodiments, the functions / operations mentioned in the block diagrams may not occur in the order shown in the operation diagrams. For example, depending on the functions / operations involved, two consecutively shown blocks may actually be executed substantially simultaneously, or the blocks may sometimes be executed in reverse order. Furthermore, the embodiments presented and described in the flowcharts of this invention are provided by way of example to provide a more comprehensive understanding of the technology. The disclosed methods are not limited to the operations and logic flows presented herein. Alternative embodiments are contemplated in which the order of various operations is changed and sub-operations described as part of a larger operation are executed independently.

[0190] Furthermore, although the invention has been described in the context of functional modules, it should be understood that, unless otherwise stated, one or more of the functions and / or features may be integrated into a single physical device and / or software module, or one or more functions and / or features may be implemented in a separate physical device or software module. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding the invention. Rather, given the properties, functions, and internal relationships of the various functional modules in the apparatus disclosed herein, the actual implementation of the module will be understood within the scope of conventional skill of an engineer. Therefore, those skilled in the art can implement the invention as set forth in the claims using ordinary techniques without excessive experimentation. It is also understood that the specific concepts disclosed are merely illustrative and not intended to limit the scope of the invention, which is determined by the full scope of the appended claims and their equivalents.

[0191] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0192] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution means, apparatus, or device (such as a computer-based device, a processor-including device, or other means that can fetch and execute instructions from, or in conjunction with, an instruction execution means, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution means, apparatus, or device.

[0193] More specific examples of computer-readable media (a non-exhaustive list) include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which programs can be printed, because programs can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0194] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution device. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0195] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0196] Although embodiments of the invention have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.

[0197] The above is a detailed description of the preferred embodiments of the present invention. However, the present invention is not limited to the embodiments. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of the present invention. All such equivalent modifications or substitutions are included within the scope defined by the claims of the present invention.

Claims

1. A method for pushing information, characterized in that, include: Retrieve data records of the target object's accessed pages; Based on the data records, an individual interest graph of the target object is obtained; wherein, the individual interest graph includes a first association weight between each of the accessed pages; Based on the union of the accessed pages of different target objects, the individual interest graphs of each target object are fused together with the first association weight to obtain a group interest graph; wherein, the group interest graph includes the second association weight between each accessed page; Based on the page node corresponding to the accessed page in the group interest graph and the adjacent nodes of the page node, the importance of the page node is obtained by combining the corresponding second association weight; Information is pushed to the accessed page corresponding to each of the page nodes based on the importance level. The data records include the tags of the accessed pages, the number of accesses, and the jump relationships and jump counts between the accessed pages; the step of organizing the individual interest map of the target object based on the data records includes: Based on the tags of all the accessed pages of the target object, the access tag set of the target object is obtained; The page weight of the accessed page is determined based on the number of times the accessed page of the target object is accessed, and then the page weights of each accessed page are sorted out to obtain the page weight set of the target object; The association relationships between the accessed pages are determined based on the jump relationships between the accessed pages, and then all the association relationships between the accessed pages are sorted out to obtain the association relationship set of the target object; wherein, when there is a jump relationship between the accessed pages, the association relationship value is 1, otherwise, the association relationship value is 0. The association between the accessed pages is multiplied by the number of jumps between the corresponding accessed pages to obtain the first association weight between the accessed pages. Then, the association between all the accessed pages is sorted out to obtain the association weight set of the target object. The individual interest graph of the target object is obtained by organizing the access tag set, the page weight set, the association relationship set, and the association weight set. Wherein, the second association weight represents the sum of the first association weights of all the target objects on the same accessed page; the step of obtaining the importance of the page node based on the page node corresponding to the accessed page in the group interest graph and the adjacent nodes of the page node, combined with the corresponding second association weight, includes: Based on the second association weight between the visited page corresponding to the page node and the visited page corresponding to the first-order node of the page node in the group interest graph, and the second association weight between the visited page corresponding to the first-order node and the visited page corresponding to the second-order node of the page node, the influence of the page node is obtained by adding them together; then, the importance of the page node is obtained based on the influence; wherein, the first-order node represents the node directly connected to the page node, and the second-order node represents the node indirectly connected to the page node through the first-order node; the expression for the influence is: ； In the formula, Represents page nodes Its influence; express The set of first-order nodes, express First-order nodes; express and The second association weight; express The set of second-order nodes, express The set of first-order nodes, express Second-order nodes and First-order nodes; express and The second association weight.

2. The information push method according to claim 1, characterized in that, The step of determining the page weight of the accessed page based on the number of accesses to the accessed page of the target object includes: Add up the number of visits to all the accessed pages to get the total number of visits; The page weight of the accessed page is calculated based on the ratio of the number of times the accessed page is accessed to the total number of accesses.

3. The information push method according to claim 1, characterized in that, The process of fusing the individual interest graphs of each target object based on the union of the accessed pages of different target objects and the first association weight to obtain a group interest graph includes: The matrix specification is determined based on the union of the accessed pages of different target objects; Based on the matrix specifications, the individual interest graphs of each target object are converted into adjacency matrices; The group interest map is obtained by combining the adjacency matrix corresponding to each individual interest map with the first association weight.

4. The information push method according to claim 3, characterized in that, The step of obtaining the group interest map based on the adjacency matrix corresponding to each individual interest map and the first association weight includes: Based on the adjacency matrix corresponding to each individual interest graph, and combined with the first association weight, the group interest graph is calculated using the group interest graph formula; wherein, the group interest graph is in matrix format, and the expression of the group interest graph formula is: ； In the formula, Representing group interest graphs in The value of the element at that position; This indicates the total number of target objects in the group; Indicates the first One target object; Indicates the first Page nodes of the target object The corresponding access page and page node The first association weight between the corresponding accessed pages; Indicates the first The adjacency matrix of the target objects is in The value of the element at that position. ; Represents page nodes and page nodes The lines connecting them; Indicates the first Individual interest profiles of each target group; Indicates the first A collection of access pages for a target object.

5. The information push method according to claim 1, characterized in that, The process of pushing information to the accessed page corresponding to each page node based on the importance includes: The push factor of the accessed page is obtained by combining the importance with the page weight of the corresponding accessed page; wherein, the page weight is determined based on the ratio of the number of times the accessed page is accessed to the total number of times all accessed pages are accessed. The push priority of each accessed page is determined based on the push factor, and information is pushed according to the push priority.

6. An information push device, characterized in that, include: The first module is used to obtain data records of the target object's accessed pages; The second module is used to organize the data records to obtain the individual interest graph of the target object; wherein, the individual interest graph includes a first association weight between each of the accessed pages; The third module is used to fuse the individual interest graphs of each target object based on the union of the accessed pages of different target objects and the first association weight, to obtain a group interest graph; wherein, the group interest graph includes the second association weight between each accessed page. The fourth module is used to obtain the importance of the page node based on the page node corresponding to the accessed page in the group interest graph and the adjacent nodes of the page node, combined with the corresponding second association weight. The fifth module is used to push information to the accessed page corresponding to each page node based on the importance. The data records include the tags of the accessed pages, the number of accesses, and the jump relationships and jump counts between the accessed pages; the step of organizing the individual interest map of the target object based on the data records includes: Based on the tags of all the accessed pages of the target object, the access tag set of the target object is obtained; The page weight of the accessed page is determined based on the number of times the accessed page of the target object is accessed, and then the page weights of each accessed page are sorted out to obtain the page weight set of the target object; The association relationships between the accessed pages are determined based on the jump relationships between the accessed pages, and then all the association relationships between the accessed pages are sorted out to obtain the association relationship set of the target object; wherein, when there is a jump relationship between the accessed pages, the association relationship value is 1, otherwise, the association relationship value is 0. The association between the accessed pages is multiplied by the number of jumps between the corresponding accessed pages to obtain the first association weight between the accessed pages. Then, the association between all the accessed pages is sorted out to obtain the association weight set of the target object. The individual interest graph of the target object is obtained by organizing the access tag set, the page weight set, the association relationship set, and the association weight set. Wherein, the second association weight represents the sum of the first association weights of all the target objects on the same accessed page; the step of obtaining the importance of the page node based on the page node corresponding to the accessed page in the group interest graph and the adjacent nodes of the page node, combined with the corresponding second association weight, includes: Based on the second association weight between the visited page corresponding to the page node and the visited page corresponding to the first-order node of the page node in the group interest graph, and the second association weight between the visited page corresponding to the first-order node and the visited page corresponding to the second-order node of the page node, the influence of the page node is obtained by adding them together; then, the importance of the page node is obtained based on the influence; wherein, the first-order node represents the node directly connected to the page node, and the second-order node represents the node indirectly connected to the page node through the first-order node; the expression for the influence is: In the formula, Represents page nodes Its influence; express The set of first-order nodes, express First-order nodes; express and The second association weight; express The set of second-order nodes, express The set of first-order nodes, express Second-order nodes and First-order nodes; express and The second association weight.

7. An electronic device, characterized in that, Including the processor and memory; The memory is used to store programs; The processor executes the program to implement the method as described in any one of claims 1 to 5.

8. A computer storage medium storing a processor-executable program, characterized in that, The processor-executable program, when executed by the processor, is used to implement the method as described in any one of claims 1 to 5.

Images