WO2022152061A1 - 资源推荐方法及装置、设备、存储介质 - Google Patents

资源推荐方法及装置、设备、存储介质 Download PDF

Info

Publication number
WO2022152061A1
WO2022152061A1 PCT/CN2022/070845 CN2022070845W WO2022152061A1 WO 2022152061 A1 WO2022152061 A1 WO 2022152061A1 CN 2022070845 W CN2022070845 W CN 2022070845W WO 2022152061 A1 WO2022152061 A1 WO 2022152061A1
Authority
WO
WIPO (PCT)
Prior art keywords
node
resource
attribute
target
requirements
Prior art date
Application number
PCT/CN2022/070845
Other languages
English (en)
French (fr)
Other versions
WO2022152061A9 (zh
Inventor
王苑青
黄栋
沈俊杰
Original Assignee
北京沃东天骏信息技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 北京沃东天骏信息技术有限公司 filed Critical 北京沃东天骏信息技术有限公司
Publication of WO2022152061A1 publication Critical patent/WO2022152061A1/zh
Publication of WO2022152061A9 publication Critical patent/WO2022152061A9/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0251—Targeted advertisements
    • G06Q30/0269—Targeted advertisements based on user profile or attribute
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G06F16/2455—Query execution
    • G06F16/24553—Query execution of query operations
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0277—Online advertisement

Definitions

  • the present application relates to the field of information processing, and relates to, but is not limited to, a resource recommendation method and apparatus, device, and storage medium.
  • Internet websites generally place advertisements to increase the operating income of the website.
  • advertisements such as banners, floating animations, slideshows, etc.
  • the advertising materials also have various expressions such as pictures, videos and animations.
  • creatives will be dynamically adjusted based on schedules, client requests, or event schedules.
  • the present application provides a resource recommendation method, device, device, and storage medium, which can recommend advertisement spaces suitable for materials to users and improve the work efficiency of users.
  • an embodiment of the present application provides a resource recommendation method, the method includes:
  • the resource is used as the resource to be recommended, and the resource identifier of the resource to be recommended is output.
  • an embodiment of the present application provides a resource recommendation device, where the device includes:
  • an obtaining unit configured to obtain the elements included in the material, obtain the first set of elements, and obtain the elements included in the resource, and obtain the second set of elements;
  • mapping unit configured to map each first element in the first element set to a first node, and map each second element in the second element set to a second node;
  • a building unit configured to connect an edge between the first node and the second node to build a node relationship graph
  • a matching unit configured to search for a match in the node relationship graph
  • the output unit is configured to, when a match is found, take the resource as the resource to be recommended, and output the resource identifier of the resource to be recommended.
  • an embodiment of the present application provides a computer device, including a memory, a processor, and a computer program stored in the memory and running on the processor, where the processor implements the above resource recommendation method when executing the computer program steps in .
  • an embodiment of the present application provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, implements the steps in the above resource recommendation method.
  • a resource recommendation method which obtains elements included in a material to obtain a first set of elements, and obtains elements included in a resource to obtain a second set of elements;
  • the first element is mapped to a first node, and each second element in the second element set is mapped to a second node; an edge is connected between the first node and the second node, and a node relationship graph is constructed;
  • find a match in the case of finding a match, take the resource as the resource to be recommended, and output the resource identifier of the resource to be recommended; in this way, before the user uploads the material, it is possible to effectively determine the relationship between the material and the resource.
  • FIG. 1 is an optional structural schematic diagram of an information processing system provided by an embodiment of the present application.
  • FIG. 2 is an optional structural schematic diagram of an information processing system provided by an embodiment of the present application.
  • FIG. 3 is an optional schematic flowchart of a resource recommendation method provided by an embodiment of the present application.
  • FIG. 4 is an optional structural schematic diagram of a node relationship diagram provided by an embodiment of the present application.
  • FIG. 5 is an optional schematic flowchart of a resource recommendation method provided by an embodiment of the present application.
  • FIG. 6 is an optional schematic flowchart of a resource recommendation method provided by an embodiment of the present application.
  • FIG. 7 is an optional structural schematic diagram of a node relationship diagram provided by an embodiment of the present application.
  • FIG. 8 is an optional schematic flowchart of a resource recommendation method provided by an embodiment of the present application.
  • FIG. 9 is an optional schematic structural diagram of a resource recommendation apparatus provided by an embodiment of the present application.
  • FIG. 10 is an optional schematic structural diagram of an electronic device provided by an embodiment of the present application.
  • Resource the page display area that can carry the material, such as: advertising space.
  • Element a single content of the content included in the material, or a single content of the content that the resource can carry. Based on the type, elements can include text, pictures, video, audio, etc.
  • Attributes which can represent the requirements of the elements included in the material, including: type, size, size, etc.
  • Attribute requirements which can represent the capabilities of elements that the resource can carry, including: type requirements, size requirements, size requirements, etc.
  • a node relationship graph which is a graph with an element as a node, and an edge is connected between the first node corresponding to the element of the material and the second node corresponding to the element of the resource.
  • an edge When an edge is connected between the first node and the second node, it indicates that the element corresponding to the first node is adapted to the element corresponding to the second node, that is, the element corresponding to the second node can carry the element corresponding to the first node.
  • bipartite graph bipartite graph.
  • the two nodes associated with each edge in the graph belong to two different sets of nodes.
  • the embodiments of the present application can be provided as a resource recommendation method and apparatus, device, and storage medium.
  • the resource recommendation method can be implemented by a resource recommendation device, and each functional entity in the resource recommendation device can be implemented by hardware resources of computer equipment (such as terminal equipment, servers or server clusters), such as computing resources such as processors, communication resources (such as It is used to support the realization of communication in various ways such as optical cable, cellular, etc.) collaborative realization.
  • the resource recommendation method of the embodiment of the present application can be applied to the information processing system shown in FIG. 1 , and the resource recommendation device in the information processing system can determine whether a resource is a resource to be recommended.
  • the information processing system includes a client 10 and a server 20; wherein, the client 10 is installed with an input application program APP capable of receiving user input operations or a browser providing an input page, The user can receive the material input by the user through the input application APP or the input page.
  • the server 20 is a service of the client 10, the server 20 includes resources, and can receive the materials sent by the client 10, determine whether a resource is a resource to be recommended for the received material, and output the resource to be recommended to the client end 10.
  • the client 10 and the server 20 interact through the network 30 .
  • the server 20 may be implemented as a resource recommendation device implementing the resource recommendation method.
  • the server 20 obtains the elements included in the material, obtains the first element set, and obtains the elements included in the resource, and obtains the second element set; maps each first element in the first element set to the first node, and maps each first element in the first element set to the first node, and maps the first element to the first node.
  • Each second element in the second element set is mapped to a second node; an edge is connected between the first node and the second node to construct a node relationship graph; in the node relationship graph, a match is found; when a match is found
  • the resource is taken as the resource to be recommended, the resource identifier of the resource is output, and the resource identifier of the resource is output to the client 10 .
  • the client 10 may present the resource identifier of the resource to be recommended to the user through the display.
  • the information processing system includes only the client 40, and the client 40 is implemented as a resource recommendation device implementing the resource recommendation method.
  • the client receives the material input by the user through the input application program APP or the input page, and obtains the elements included in the material to obtain the first set of elements, and obtains the elements included in the resource to obtain the second set of elements;
  • Each first element in the set is mapped to a first node, and each second element in the second element set is mapped to a second node; an edge is connected between the first node and the second node, and a node relationship graph is constructed; In the node relationship graph, a match is searched; when a match is found, the resource is taken as the resource to be recommended, and the resource identifier of the resource to be recommended is presented to the user through the display.
  • the present embodiment proposes a resource recommendation method, which can recommend an advertisement space adapted to the material to the user, thereby improving the work efficiency of the user.
  • This embodiment provides a resource recommendation method, which is applied to a resource recommendation device, where the resource recommendation device may be a computer device or a distributed network composed of computer devices.
  • the functions implemented by the method can be implemented by a processor in a computer device calling program codes, and of course the program codes can be stored in a computer storage medium.
  • the computer device includes at least a processor and a storage medium.
  • FIG. 3 is a schematic diagram of an implementation flowchart of a resource recommendation method according to an embodiment of the present application. As shown in FIG. 3 , the method may include the following steps:
  • the resource recommendation device obtains the elements included in the material to obtain a first set of elements, and obtains the elements included in the resource to obtain a second set of elements.
  • the resource recommendation device receives the material input by the user, parses the elements in the material, and obtains the elements included in the material.
  • the element in the material is called the first element
  • the set formed by the first element is called the first element gather.
  • one material corresponds to one first element set.
  • the type of the first element included in the material includes a combination of one or more of the following types: text, picture, audio, video, and the like.
  • the first element set corresponding to material 1 is: text 1 , text 2 and video 2 .
  • the first element set corresponding to the material 2 is: text 1 , text 2 , picture 1 , picture 2 , picture 3 , video 1 , and video 2 .
  • the resource recommendation device obtains the elements that the resource can carry and analyzes, and obtains the elements included in the resource.
  • the elements in the resource are called second elements, and the set formed by the second elements is called the second element set.
  • one resource corresponds to one second element set.
  • the second set of elements corresponding to resource 1 is: title 1 , main image, sub-image, and video 1 .
  • the type of title is text
  • the type of main image is image
  • the type of sub image is image
  • the type of video 1 is video.
  • the first element set corresponding to the material 2 is: text 1 , text 2 , picture 1 , picture 2 , picture 3 , video 1 , and video 2 .
  • the resource recommendation device maps each first element in the first element set to a first node, and maps each second element in the second element set to a second node.
  • the first element set includes: element 11, element 12, and element 13.
  • Element 11, element 12, and element 13 are mapped to the first node in one-to-one correspondence: node s11, node s12, and node s13, where node s11, node s12, and node constitute a first node set.
  • the second element set includes: element 21, element 22, element 23, element 24 and element 25, and the element 21, element 22, element 23, element 24 and element 25 are mapped to the second node in one-to-one correspondence: node s21 , node s22, node s23, node s24, and node s25, where, node s21, node s22, node s23, node s24, and node s25 constitute a second node set.
  • the resource recommendation device connects an edge between the first node and the second node to construct a node relationship graph.
  • An edge is connected between the first node of the first node set and the second node of the second node set, and the formed node relationship graph is a bipartite graph. At this time, there is no edge between the first node and any other first node. , there is no edge between the second node and any other second node.
  • an edge is connected between the first node and the second node according to the relationship between the attribute of the element corresponding to the first node and the attribute requirement of the element corresponding to the second node.
  • an edge is connected between the first node and the second node; when the attribute of the element corresponding to the first node is the same as that of the second node If the attribute requirements of the corresponding elements do not match, no edge is connected between the first node and the second node.
  • the constructed node relationship diagram is shown in FIG. 4 , the node s11, the node s12 and the node 13 constitute the first node set, and the node s21, the node s22, the node s23, the node s24 and the node s25 constitute the second node set,
  • the connected edges include: the edge between node s11 and node s21, node s23, node s24 and node s25, the edge between node s12 and node s21, node s22, node s24 and node s25, node s13 and node s21, Edges between node s22, node s23, node s24, and node s25.
  • the resource recommendation device searches for a match in the node relationship graph.
  • the subgraph is searched in the node relation graph based on the matching algorithm, so that any two edges in the searched subgraph are not attached to the same node, then the subgraph is called a match.
  • the matching algorithm used for searching for matching may include: Maximal Flow (Maximal Flow) or Hungarian Algorithm (Hungarian Algorithm).
  • the first element set includes: element 11, element 12, and element 13, and the second element set includes: element 21, element 22, element 23, element 24, and element 25
  • the first node in the first node set includes: node s11, node s12 and node 13
  • the second node in the second node set includes: node s21, node s22, node s23, node s24 and node s25
  • the matches found include: node s11-node s23, node S12-node S25, node S13-node S21.
  • the first set of elements includes: element 11 , element 12 , and element 13 .
  • the second element set includes: element 21, element 22, element 23, element 24, and element 25.
  • the first node in the first node set includes: node s11, node s12, and node 13.
  • the second node includes: node s21, node s22, node s23, node s24 and node s25, and the matching based on the node relationship graph search formed by the first node in the first node set and the second node in the second node set includes: Node s11-node s23, node s13-node s25.
  • the resource recommendation device takes the resource as the resource to be recommended, and outputs the resource identifier of the resource to be recommended.
  • the resource recommendation device determines that the resource is the resource to be recommended, obtains the resource identifier of the resource, and outputs the resource identifier of the resource to be recommended for presentation to the user, so that the user can Being able to know that the rendered resource is capable of carrying the material.
  • the resource recommendation device may perform the above steps S301 to S304 for a material and multiple resources, respectively, determine a recommendable resource from the multiple resources, and output the determined resource identifier of the recommendable resource to the user.
  • each resource corresponds to a node relationship graph.
  • the resource corresponding to the node relationship graph is considered to be the resource to be recommended, and the resource can carry the current material; If no match is found, it is considered that the resource corresponding to the node relationship graph is not the resource to be recommended, and the resource cannot carry the current material.
  • the material uploaded by the user is material 1, and the resources provided by the resource provider include: resource 1, resource 2, and resource 3.
  • the node relationship diagram 1 is obtained, and a match is found in the node relationship diagram 1: match 1; according to the element of material 1 and the element of resource 2, the node relationship diagram 2 is obtained, and in No match is found in node relationship diagram 2; according to the element of material 1 and the element of resource 3, node relationship diagram 3 is obtained, and a match is found in node relationship diagram 3: match 2, then resource 1 and resource 3 are considered to be able to carry Material 1, resource 1 and resource 3 can be recommended to users.
  • the user can select the target resource for the user to display the material from the multiple resources according to the resource information such as the billing and location of each resource.
  • the resource information such as the billing and location of each resource to be recommended can be obtained, the recommendation degree of each resource can be calculated according to the resource information, and after outputting the resource to be recommended At the same time as the resource identification of the resource, the recommendation degree of each resource to be recommended is output.
  • the elements included in the material are obtained to obtain a first set of elements, and the elements included in the resource are obtained to obtain a second set of elements; each first element in the first set of elements is mapped is the first node, and each second element in the second element set is mapped to a second node; an edge is connected between the first node and the second node, and a node relationship graph is constructed; in the node relationship graph, Find a match; in the case of finding a match, take the resource as the resource to be recommended, and output the resource identifier of the resource to be recommended; in this way, before the user uploads the material, it is possible to effectively determine whether the material and the resource are compatible , and recommend the adapted resource to the user as the resource to be recommended, so as to prevent the user from blindly selecting the resource, thereby avoiding the occurrence of the problem of material modification or resource re-selection caused by the incompatibility of the selected resource with the material to be uploaded.
  • the implementation of S303 includes:
  • the attributes of the first element include: type and element parameter, wherein the type includes: text, picture, video, etc., representing the style of the element, and the element parameter representing the size of the element, and the like.
  • the element parameter includes: length; when the type is image, the element parameter includes: one or a combination of size, size, and resolution.
  • the element parameters include one or a combination of one or more of aspect ratio, size, bit rate, and duration.
  • the attribute requirements of the second element include: type requirements and parameter requirements, wherein the type requirements include: styles of elements that can be carried by resources such as books, pictures, and videos, and the parameter requirements represent specific requirements for the style of the carried elements.
  • the type requirement includes: length; when the type requirement is image, the parameter requirement includes: one or more combinations of size, size, and resolution.
  • the type requirement is video, the parameter requirement includes one or a combination of one or more of aspect ratio, size, bit rate, and duration.
  • the implementation of S3032 includes: traversing the attributes of each first element and the attribute requirements of each second element, and determining an element pair whose attribute requirements match the attributes; the first element and the second element in the element pair An edge is connected between the first node corresponding to the element and the corresponding second node respectively, and a node relationship graph is obtained.
  • the first element set includes: element 11, element 12, and element 13, and the second element set includes: element 21, element 22, element 23, element 24, and element 25
  • the first node in the first node set includes: node s11, node s12 and node 13
  • the second node in the second node set includes: node s21, node s22, node s23, node s24 and node s25
  • Determine the attribute requirements by comparing the attributes of element 11, the attributes of element 12, and the attributes of element 13 with the attribute requirements of element 21, the attribute requirements of element 22, the attribute requirements of element 23, the attribute requirements of element 24, and the attribute requirements of element 25, respectively.
  • the element pair that matches the attribute wherein the determined element pair includes: element 11 and element 21, element 11 and element 23, element 11 and element 24, element 11 and element 25, element 12 and element 21, element 12 and element 22 , element 12 and element 24, element 12 and element 25, element 13 and element 21, element 13 and element 22, element 13 and element 23, element 13 and element 24, element 13 and element 25; then the connected edges include: node Edges between s11 and node s21, node s23, node s24 and node s25, edges between node s12 and node s21, node s22, node s24 and node s25, node s13 and node s21, node s22, node s23, node The edge between s24 and node s25.
  • no edge connection is performed between the first nodes corresponding to different first elements, and no edge connection is performed between the second nodes corresponding to different second elements, so that the obtained node relationship graph is a bipartite graph.
  • traversing the attributes of each first element and the attribute requirements of each second element, and determining the element pair whose attribute requirements match the attributes includes: taking each first element as a reference element, and performing the following processing: The attribute of the reference element is compared with the attribute requirements of each second element; the second element whose attribute requirements are consistent with the attribute of the first reference element is a touch element, and the reference element and the touch element are obtained. Element pair of elements.
  • each first element when traversing the attributes of each first element and the attribute requirements of each second element, each first element may be used as a reference element, respectively, and an element pair corresponding to each reference element may be determined.
  • another element other than the reference element in the element pair is called a touch element.
  • the first element set includes: element 11, element 12, and element 13, and the second element set includes: element 21, element 22, element 23, element 24, and element 25
  • the first node in the first node set includes: node s11, node s12 and node 13
  • the second node in the second node set includes: node s21, node s22, node s23, node s24 and node s25
  • First, using element 11 as the reference element determine whether the attributes of element 11 are consistent with the attribute requirements of each second element: element 21, element 22, element 23, element 24 and element 25. After determining the element pair corresponding to element 11, Next, using element 12 as a reference element, the element pair corresponding to element 12 is determined, and so on, until all the first elements are taken as reference elements respectively, and the element pairs corresponding to all the first elements are obtained.
  • the attribute includes: type.
  • the attribute requirement includes: a type requirement.
  • the search attribute requires a second element that matches the attribute of the first element to be the touch
  • the reaching element includes: searching for at least one target second element whose type is the same as that of the target first element; and determining the reaching element in the at least one target second element.
  • the resource recommendation device when determining the element pair corresponding to the reference element by the reference element, the resource recommendation device first searches for the second element that matches the reference element in type based on the type requirement of the second element.
  • the first element set includes: element 11, element 12, and element 13, and the second element set includes: element 21, element 22, element 23, element 24, and element 25.
  • the element pair corresponding to element 11 based on the type of element 11 is text, the type of element 21 is required to be text, the type of element 22 is required to be text, the type of element 23 is required to be a picture, the type of element 24 is required to be a picture, and the type of element 25 is required to be video, then the determined target
  • the two elements include: element 21 and element 22.
  • the determination method of determining the touch element in the at least one target element includes one of the following:
  • Determining method 1 All target second elements are determined as touch elements.
  • the second target element that can completely carry the target first element is the touch element.
  • the determination method is determination method 1
  • all target second elements are directly determined as touch elements.
  • the determined target second elements include: element 21 and element 22, then element 21 and element 22 are touch elements.
  • the determining the touch element in the at least one target second element includes: according to the element parameter of the target first element, and the at least one target second element Calculate the degree of adaptation between the first element of the target and the second element of each target in the parameter requirements of each target second element in the Describe the touch element.
  • the degree of adaptation between the reference element and each target second element is determined according to the element parameters of the reference element and the parameter requirements of each target second element.
  • the calculation method of the degree of fit can be different according to the type.
  • the calculation formula of the fitness is as shown in formula (1):
  • length is the length of the reference element, that is, the text element in the material
  • avgLength represents the parameter requirement of the second element of the target.
  • the parameter requirements of the target second element may include a minimum length and a maximum length, and in this case, avgLength may be an intermediate value between the minimum length and the maximum length in the element requirements.
  • the degree of adaptation is 100, otherwise it is 0.
  • strict requirements are imposed on the pictures in the materials and the pictures in the resources, so that the resources can be effectively used while displaying the materials.
  • the degree of adaptation is considered to be 100, otherwise it is 0.
  • bitRate is the bit rate of the reference element, that is, the material element
  • maxBitRate is the maximum bit rate required by the target second element
  • size is the size of the reference element, that is, the material element
  • maxSize is the maximum size required by the target second element
  • duration is the reference element. That is, the duration of the material element
  • maxDuration is the maximum duration required by the target second element.
  • the degree of adaptation after calculating the degree of adaptation between the reference element and the second element of the target, it is determined whether the degree of adaptation is within the set degree of adaptation. If the degree of adaptation is within the range of the set degree of adaptation, it is considered that the corresponding target second element is a touch element, and the reference element and the target second element are an element pair.
  • the fitness range can be: greater than or equal to 20. In practical applications, the fit range can be set according to actual needs.
  • the two do not match, and the corresponding first node and the corresponding second node are unreachable.
  • the types of the first element and the second element are the same, and the degree of adaptation between them does not satisfy the adaptation degree range, the two do not match, and the corresponding first node and the corresponding second node are unreachable.
  • the type of the first element and the second element are the same, and the degree of adaptation between them satisfies the range of the degree of adaptation, then the two are consistent, the corresponding first node and the corresponding second node are reachable, and the connection is side.
  • the implementation of S304 includes: according to the The weights of the edges, in the node graph, look for matches.
  • the resource recommendation device determines the degree of adaptation between the reference element and each target second element according to the element parameter of the reference element and the parameter requirements of each target second element.
  • the calculation method of the degree of fit can be different according to the type. For the calculation of the degree of adaptation, reference may be made to the above description, which will not be repeated here.
  • the degree of adaptation between the elements corresponding to the two nodes connected by each edge is obtained, the degree of adaptation is marked as the weight of the edge. weights to find matches in the node graph.
  • the matching algorithm used to search for matching according to the edge and the weight of the edge may include: Kuhn-Munkres (KM) algorithm, maximum flow algorithm, and the like. In this embodiment of the present application, no limitation is imposed on the matching algorithm used for searching for matching.
  • S307 Establish an association relationship between the first element represented by the first node connected by the target edge and the second element represented by the second node, and output the association relationship.
  • the resource recommendation device After finding a match in the node relationship graph, the resource recommendation device determines all the edges included in the match, and establishes a relationship between the first element and the second element corresponding to the first node and the second node connected by each edge, respectively.
  • the connection relationship and outputting the connection relationship enable the user to know which materials in the material can be displayed in a resource, and where the specific material is displayed in the resource.
  • the resource recommendation method provided by the embodiment of the present application will be further described by taking an advertisement scenario in which the resource is an advertisement slot as an example.
  • the KM algorithm can be used to solve the optimal weighted matching problem for bipartite graphs.
  • a bipartite graph is a special kind of graph whose vertices can be divided into two independent sets U and V, such that all edges connect a point in U and a point in V. That is to say, the edge from the vertex in U will only be connected to V, and will not be connected to U itself. V is the same.
  • Matching refers to a subgraph M of the bipartite graph G. If any two edges in the edge set of M do not have a common vertex, the box subgraph M is a match. That is, some set of edges that have no common vertex.
  • the optimal weighted matching of a bipartite graph refers to finding a match on a given weighted bipartite graph so that the sum of the weights of all matching edges is the largest.
  • the weighted bipartite graph 701 includes two sets: U and V, where node A and node B belong to set U, node a and node b belong to set V, and the The weights of the edges are shown in Figure 7.
  • the best matching of the weighted bipartite graph 301 is obtained by using the KM algorithm.
  • the ad slot element and the material element are abstracted into two sets of vertices, the ad slot element is located in the set U, the material element is located in the set V, and the edge between the ad slot element and the material element indicates whether the material element conforms to the , the weight of the edge represents the degree to which the material element meets the requirements of the advertising space element. The more it meets the requirements, the higher the weight. At the same time, there will be no edge between the advertising space element and the advertising space element, and there will be no edge between the material element and the material element.
  • a weighted bipartite graph of an ad slot-material On this weighted bipartite graph, the KM algorithm can be used to find a match with the largest weight, that is, to find the most qualified material elements for each element in the ad slot.
  • the resource recommendation method provided by the embodiment of the present application may be shown in FIG. 8 , including:
  • the user 81 submits the material to the resource recommendation device 82 .
  • the user submits a collection of materials to the resource recommendation device, which can be any number of text information, pictures and videos (each text is regarded as a material element, and the same is true for pictures and videos)
  • the resource recommendation device 82 pulls the advertisement space from the advertisement space pool 83 .
  • the resource recommendation device pulls the set of advertising slots from the target advertising slot pool.
  • each ad slot has a different style, and is composed of one or more ad slot elements, and the ad slot elements include a text field, an image field, and a video field.
  • the resource recommendation device 82 calculates the degree of adaptation.
  • the resource recommendation device 82 calculates the degree of adaptation between each element in the material and each element of the advertising space.
  • the resource recommendation device 82 constructs a weighted bipartite graph.
  • the resource recommendation device 82 outputs a weighted bipartite graph of material-advertising space based on the calculated fit degree.
  • the resource recommendation device 82 searches for a match.
  • the resource recommendation device performs KM matching on the weighted bipartite graph. If the matching is successful, it means that there are material elements suitable for this advertising space, and it is the best match.
  • the resource recommendation device 82 outputs a result set.
  • the resource recommendation device 82 outputs the combination of the material element-ad slot element to the user 81 based on the matching.
  • the resource recommendation device takes the matched material element and the ad slot as a combination, adds it to the result set, and outputs the result set.
  • the calculation rule for the weight corresponding to the edge connecting a material element and the advertising space element may include:
  • the value of the weight is normalized between 0 and 100.
  • a very small weight indicates that the corresponding material element does not meet the requirements of the advertising space element. Reach (UNREACHABLE).
  • length is the length of the text element in the material
  • is the middle value between the minimum length and the maximum length of the text element in the ad slot.
  • the width and height of the material element strictly meet the requirements of the ad slot element, and the adaptation degree is 100.
  • the aspect ratio of the material element strictly meets the requirements of the ad slot element; the closer the bit rate, size, and duration of the material element are to the maximum value required by the ad slot element, the higher the score.
  • the scores of the attributes are averaged to obtain the final fitness.
  • the material element can be considered to be consistent with the advertisement element.
  • bitRate is the bit rate of the material element
  • maxBitRate is the maximum bit rate required by the advertising element
  • size is the size of the material element
  • maxSize is the maximum size required by the advertising element
  • duration is the duration of the material element
  • maxDuration is the advertising element. The maximum duration required.
  • a weighted bipartite graph can be constructed for an advertising space and a material set, and the matching result can be obtained by running the KM algorithm on the bipartite graph.
  • the elements of the advertisement slot A are shown in Table 1, and the elements of the material uploaded by the user are shown in Table 2.
  • the weighted bipartite graph composed of the vertices in the first set and the vertices in the second set As shown in Table 3, the UN characterization is unreachable.
  • Main title - text 2 subtitle - text 1, main image - picture 3, sub image - picture 1, main video - video 2.
  • FIG. 9 is a schematic diagram of an implementation flow of a resource recommendation apparatus according to an embodiment of the present application. As shown in FIG. 9 , the apparatus 900 includes:
  • the obtaining unit 901 is configured to obtain the elements included in the material, obtain the first set of elements, and obtain the elements included in the resource, and obtain the second set of elements;
  • a mapping unit 902 configured to map each first element in the first element set to a first node, and map each second element in the second element set to a second node;
  • a construction unit 903 configured to connect an edge between the first node and the second node, and construct a node relationship graph
  • a matching unit 904 configured to search for a match in the node relationship graph
  • the output unit 905 is configured to, when a match is found, take the resource as the resource to be recommended, and output the resource identifier of the resource to be recommended.
  • the building unit 903 is further configured to:
  • a connection edge is established between the corresponding first node and the corresponding second node, and the node relationship graph is constructed.
  • the building unit 903 is further configured to:
  • An edge is connected between the first node and the corresponding second node respectively corresponding to the first element and the second element in the element pair to obtain a node relationship graph.
  • the building unit 903 is further configured to:
  • the attribute search requires that the second element that matches the attribute of the first reference element is a touch element, and an element pair including the reference element and the touch element is obtained.
  • the building unit 903 is further configured to:
  • the search type requires at least one second target element of the same type as the reference element; the attribute includes: the type, and the attribute requirement includes: the type requirement;
  • the touch element is determined.
  • the building unit 903 is further configured to:
  • the degree of adaptation between the reference element and each second target element is calculated; the attribute also Including: the element parameters, the attribute requirements include: the parameter requirements;
  • the second target element whose adaptation degree satisfies the set adaptation degree range is determined as the touch element.
  • the apparatus 900 further includes: a labeling unit, configured to connect the first node and the second node connected by the edge, the degree of adaptation between the corresponding first element and the corresponding second element, labeling is the weight of the corresponding edge;
  • the matching unit 904 is further configured to:
  • the apparatus 900 further includes: an association unit configured to:
  • An association relationship is established between the first element represented by the first node connected by the target edge and the second element represented by the second node, and the association relationship is output.
  • the resource recommending apparatus includes the included units, which can be implemented by a processor in an electronic device; of course, it can also be implemented by a specific logic circuit; in the process of implementation, the processor It can be a central processing unit (CPU, Central Processing Unit), a microprocessor (MPU, Micro Processor Unit), a digital signal processor (DSP, Digital Signal Processor) or a field programmable gate array (FPGA, Field-Programmable Gate Array) Wait.
  • CPU Central Processing Unit
  • MPU Micro Processor Unit
  • DSP Digital Signal Processor
  • FPGA Field-Programmable Gate Array
  • the above-mentioned resource recommendation method is implemented in the form of a software function module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.
  • the technical solutions of the embodiments of the present application may be embodied in the form of software products in essence or the parts that contribute to related technologies.
  • the computer software products are stored in a storage medium and include several instructions to make A computer device (which may be a personal computer, a server, or a network device, etc.) executes all or part of the methods described in the various embodiments of the present application.
  • the aforementioned storage medium includes: a U disk, a mobile hard disk, a read only memory (Read Only Memory, ROM), a magnetic disk or an optical disk and other media that can store program codes.
  • ROM Read Only Memory
  • the aforementioned storage medium includes: a U disk, a mobile hard disk, a read only memory (Read Only Memory, ROM), a magnetic disk or an optical disk and other media that can store program codes.
  • the embodiments of the present application are not limited to any specific combination of hardware and software.
  • an embodiment of the present application provides an electronic device, including a memory and a processor, where the memory stores a computer program that can be run on the processor, and when the processor executes the program, the computer program provided in the foregoing embodiments is implemented. Steps in the resource recommendation method.
  • the electronic device may be a client or a server.
  • the embodiments of the present application provide a storage medium, that is, a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, implements the steps in the resource recommendation method provided in the foregoing embodiments.
  • FIG. 10 is a schematic diagram of a hardware entity of an electronic device according to an embodiment of the present application.
  • the electronic device 1000 includes: a processor 1001 , at least one communication bus 1002 , and at least one external communication interface 1004 and memory 1005.
  • the communication bus 1002 is configured to realize the connection communication between these components.
  • the electronic device 1000 further includes a user interface 1003, wherein the user interface 1003 may include a display screen, and the external communication interface 1004 may include a standard wired interface and a wireless interface.
  • the memory 1005 is configured to store instructions and applications executable by the processor 1001, and can also cache data to be processed or processed by the processor 1001 and various modules in the electronic device (for example, image data, audio data, voice communication data and video data).
  • Communication data which can be realized by flash memory (FLASH) or random access memory (Random Access Memory, RAM).
  • the disclosed apparatus and method may be implemented in other manners.
  • the device embodiments described above are only illustrative.
  • the division of the units is only a logical function division. In actual implementation, there may be other division methods.
  • multiple units or components may be combined, or Can be integrated into another system, or some properties can be ignored, or not implemented.
  • the coupling, or direct coupling, or communication connection between the various components shown or discussed may be through some interfaces, and the indirect coupling or communication connection of devices or units may be electrical, mechanical or other forms. of.
  • the unit described above as a separate component may or may not be physically separated, and the component displayed as a unit may or may not be a physical unit; it may be located in one place or distributed to multiple network units; Some or all of the units may be selected according to actual needs to achieve the purpose of the solution in this embodiment.
  • each functional unit in each embodiment of the present application may all be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above integration
  • the unit can be implemented either in the form of hardware or in the form of hardware plus software functional units.
  • the aforementioned program can be stored in a computer-readable storage medium, and when the program is executed, the execution includes: The steps of the above method embodiments; and the aforementioned storage medium includes: a removable storage device, a read only memory (Read Only Memory, ROM), a magnetic disk or an optical disk and other media that can store program codes.
  • ROM Read Only Memory
  • the above-mentioned integrated units of the present application are implemented in the form of software function modules and sold or used as independent products, they may also be stored in a computer-readable storage medium.
  • the computer software products are stored in a storage medium and include several instructions to make A computer device (which may be a personal computer, a server, or a network device, etc.) executes all or part of the methods described in the various embodiments of the present application.
  • the aforementioned storage medium includes various media that can store program codes, such as a removable storage device, a ROM, a magnetic disk, or an optical disk.

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Accounting & Taxation (AREA)
  • Development Economics (AREA)
  • Finance (AREA)
  • Theoretical Computer Science (AREA)
  • Strategic Management (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Economics (AREA)
  • Game Theory and Decision Science (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

一种资源推荐方法、资源推荐装置、设备及存储介质，所述方法包括：获取素材所包括的元素，得到第一元素集合，并获取资源所包括的元素，得到第二元素集合；将所述第一元素集合中各第一元素映射为第一节点，并将所述第二元素集合中各第二元素映射为第二节点；在第一节点和第二节点之间连接边，构建节点关系图；在所述节点关系图中，查找匹配；在查找到匹配的情况下，将所述资源作为待推荐资源，输出所述待推荐资源的资源标识。

Description

资源推荐方法及装置、设备、存储介质
相关申请的交叉引用
本申请基于申请号为202110051017.X、申请日为2021年1月14日的中国专利申请提出，并要求该中国专利申请的优先权，该中国专利申请的全部内容在此以引入方式并入本申请。
技术领域
本申请涉及信息处理领域，涉及但不限于一种资源推荐方法及装置、设备、存储介质。
背景技术
当前互联网网站普遍会投放广告，以此增加网站的营业收入，广告的展示形式有多种，如横幅方式、悬浮动画、幻灯片等等，广告素材也有图片、视频和动画等多种表现形式，而且广告素材也会根据排期、客户要求、或者活动安排等进行动态调整。
目前，广告主在投放广告时，需要先选择广告位，再将广告素材上传至广告位，但往往会遇到图片尺寸不符、视频时长过长、码率不符等广告素材与广告位的样式要求不符的问题，此时，广告主需要修改素材或者回退选择广告位，且在回退选择广告位后，仍然会存在上传的广告素材与广告位的样式要求不符的问题，因此，为广告主带来大量且操作繁琐的工作量。
发明内容
有鉴于此，本申请为解决相关技术中存在的至少一个问题而提供一种资源推荐方法及装置、设备、存储介质，能够向用户推荐与素材适配的广告位，提高用户的工作效率。
第一方面，本申请实施例提供一种资源推荐方法，所述方法包括：
获取素材所包括的元素，得到第一元素集合，并获取资源所包括的元素，得到第二元素集合；
将所述第一元素集合中各第一元素映射为第一节点，并将所述第二元素集合中各第二元素映射为第二节点；
在第一节点和第二节点之间连接边，构建节点关系图；
在所述节点关系图中，查找匹配；
在查找到匹配的情况下，将所述资源作为待推荐资源，输出所述待推荐资源的资源标识。
第二方面，本申请实施例提供一种资源推荐装置，所述装置包括：
获取单元，配置为获取素材所包括的元素，得到第一元素集合，并获取资源所包括的元素，得到第二元素集合；
映射单元，配置为将所述第一元素集合中各第一元素映射为第一节点，并将所述第二元素集合中各第二元素映射为第二节点；
构建单元，配置为在第一节点和第二节点之间连接边，构建节点关系图；
匹配单元，配置为在所述节点关系图中，查找匹配；
输出单元，配置为在查找到匹配的情况下，将所述资源作为待推荐资源，输出所述待推荐资源的资源标识。
第三方面，本申请实施例提供一种计算机设备，包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，所述处理器执行所述计算机程序时实现上述资源推荐方法中的步骤。
第四方面，本申请实施例提供一种计算机可读存储介质，其上存储有计算机程序，该计算机程序被处理器执行时实现上述资源推荐方法中的步骤。
本申请实施例中，提供了一种资源推荐方法，获取素材所包括的元素，得到第一元素集合，并获取资源所包括的元素，得到第二元素集合；将所述第一元素集合中各第一元素映射为第一节点，并将所述第二元素集合中各第二元素映射为第二节点；在第一节点和第二节点之间连接边，构建节点关系图；在所述节点关系图中，查找匹配；在查找到匹配的情况下，将所述资源作为待推荐资源，输出所述待推荐资源的资源标识；如此，能够在用户上传素材之前，有效的判断素材与资源之间是否适配，并将适配的资源作为待推荐资源推荐给用户，避免用户盲目的选择资源，从而避免选取的资源所待上传的素材不适配所带来的素材修改或资源重选的问题的发生，提高用户的工作效率。
附图说明
图1为本申请实施例提供的信息处理系统的可选地结构示意图；
图2为本申请实施例提供的信息处理系统的可选地结构示意图；
图3为本申请实施例提供的资源推荐方法的可选地流程示意图；
图4为本申请实施例提供的节点关系图的可选地结构示意图；
图5为本申请实施例提供的资源推荐方法的可选地流程示意图；
图6为本申请实施例提供的资源推荐方法的可选地流程示意图；
图7为本申请实施例提供的节点关系图的可选地结构示意图；
图8为本申请实施例提供的资源推荐方法的可选地流程示意图；
图9为本申请实施例提供的资源推荐装置的一种可选的结构示意图；
图10为本申请实施例提供的电子设备的一种可选的结构示意图。
具体实施方式
为使本申请实施例的目的、技术方案和优点更加清楚，下面将结合本申请实施例中的附图，对申请的技术方案做进一步详细描述。以下实施例用于说明本申请，但不用来限制本申请的范围。
为了更好地理解本申请，对本申请实施例进行进一步详细说明之前，对本申请实施例中涉及的名词和术语进行说明，本申请实施例中涉及的名词和术语适用于如下的解释。
1)素材，文本、图片、视频等内容构成的网络内容，比如：广告素材。
2)资源，能够承载素材的页面显示区域，比如：广告位。
3)元素，素材所包括的内容中的单个的内容，或资源所能承载的内容中的单个内容。基于类型不同，元素可包括文本、图片、视频、音频等。
4)属性，能够表征素材所包括的元素的需求，包括：类型、尺寸、大小等。
5)属性要求，能够表征资源所能承载的元素的能力，包括：类型要求、尺寸要求、大小要求等。
5)节点关系图，以元素为节点，且素材的元素对应的第一节点与资源的元素对应的第二节点之间连接有边的图。其中，当第一节点与第二节点之间连接有边，表征该第一节点对应的元素适配第二节点对应的元素，即第二节点对应的元素能够承载第一节点对应的元素。比如：二分图。
6)二分图，图中的每个边所关联的两个节点分别属于两个不同的节点集合。
7)匹配，在节点关系图中的一个子图中，该子图中的任意两条边都不依附于同一节点，则称该子图为一个匹配。
本申请实施例可提供为资源推荐方法及装置、设备和存储介质。实际应用中，资源推荐方法可由资源推荐装置实现，资源推荐装置中的各功能实体可以由计算机设备(如终端设备、服务器或服务器集群)的硬件资源，如处理器等计算资源、通信资源(如用于支持实现光缆、蜂窝等各种方式通信)协同实现。
本申请实施例的资源推荐方法可应用于图1所示的信息处理系统，信息处理系统中的资源推荐设备能够确定一资源是否为待推荐资源。
在一示例中，如图1所示，该信息处理系统包括客户端10和服务端20；其中，客户端10中安装有能够接收用户输入操作的输入应用程序APP或提供输入页面的浏览器，用户可通过输入应用程序APP或输入页面接收用户输入的素材。服务端20为客户端10的服务，服务端20中包括有资源，且能够接收客户端10发送的素材，并确定一资源对于接收的素材是否为待推荐资源，并将待推荐资源输出至客户端10。客户端10和服务端20之间通过网络30进行交互。
服务端20可实施为实现资源推荐方法的资源推荐设备。服务端20获取素材所包括的元素，得到第一元素集合，并获取资源所包括的元素，得到第二元素集合；将所述第一元素集合中各第一元素映射为第一节点，并将所述第二元素集合中各第二元素映射为第二节点；在第一节点和第二节点之间连接边，构建节点关系图；在所述节点关系图中，查找匹配；在查找到匹配的情况下，将所述资源作为待推荐资源，输出该资源的资源标识，将该资源的资源标识输出至客户端10。客户端10中可通过显示器呈现待推荐资源的资源标识给用户。
在一示例中，如图2所示，信息处理系统中仅包括客户端40，且客户端40实施为实现资源推 荐方法的资源推荐设备。
客户端通过输入应用程序APP或输入页面接收用户输入的素材，并获取素材所包括的元素，得到第一元素集合，并获取资源所包括的元素，得到第二元素集合；将所述第一元素集合中各第一元素映射为第一节点，并将所述第二元素集合中各第二元素映射为第二节点；在第一节点和第二节点之间连接边，构建节点关系图；在所述节点关系图中，查找匹配；在查找到匹配的情况下，将所述资源作为待推荐资源，通过显示器呈现待推荐资源的资源标识给用户。
结合上述信息处理系统，本实施例提出一种资源推荐方法，能够向用户推荐与素材适配的广告位，提高用户的工作效率。
下面，结合图1或图2所示的信息处理系统的示意图，对本申请实施例提供的资源推荐方法、装置、设备和存储介质的各实施例进行说明。
本实施例提供一种资源推荐方法，该方法应用于资源推荐设备，其中，资源推荐设备可为计算机设备或计算机设备组成的分布式网络。该方法所实现的功能可以通过计算机设备中的处理器调用程序代码来实现，当然程序代码可以保存在计算机存储介质中，可见，该计算机设备至少包括处理器和存储介质。
图3为本申请实施例的一种资源推荐方法的实现流程示意图，如图3所示，该方法可以包括如下步骤：
S301、资源推荐设备获取素材所包括的元素，得到第一元素集合，并获取资源所包括的元素，得到第二元素集合。
资源推荐设备接收用户输入的素材，并对素材中的元素进行解析，得到素材所包括的元素，这里，将素材中的元素称为第一元素，且第一元素构成的集合称为第一元素集合。本申请实施例中，一个素材对应一个第一元素集合。其中，素材所包括的第一元素的类型包括以下类型的一种或多种的组合：文本、图片、音频、视频等。在一示例中，素材1对应的第一元素集合为：文本1、文本2和视频2。在一示例中，素材2对应的第一元素集合为：文本1、文本2、图片1、图片2、图片3、视频1和视频2。
资源推荐设备获取资源所能承载的元素进行解析，得到资源所包括的元素。这里，将资源中的元素称为第二元素，且第二元素构成的集合称为第二元素集合。本申请实施例中，一个资源对应一个第二元素集合。在一示例中，资源1对应的第二元素集合为：标题1、主图、副图和视频1。其中，标题的类型为文本、主图的类型为图片、副图的类型为图片，视频1的类型为视频。在一示例中，素材2对应的第一元素集合为：文本1、文本2、图片1、图片2、图片3、视频1和视频2。
S302、资源推荐设备将所述第一元素集合中各第一元素映射为第一节点，并将所述第二元素集合中各第二元素映射为第二节点。
比如：第一元素集合包括：元素11、元素12和元素13。将元素11、元素12、和元素13一一对应地映射为第一节点：节点s11、节点s12、和节点s13，这里，节点s11、节点s12和节点构成第 一节点集合。
比如：第二元素集合包括：元素21、元素22、元素23、元素24和元素25，将元素21、元素22、元素23、元素24和元素25一一对应地映射为第二节点：节点s21、节点s22、节点s23、节点s24和节点s25，这里，节点s21、节点s22、节点s23、节点s24和节点s25构成第二节点集合。
S303、资源推荐设备在第一节点和第二节点之间连接边，构建节点关系图。
在第一节点集合的第一节点和第二节点集合的第二节点之间连接边，构成的节点关系图为二分图，此时，第一节点与任一其他第一节点之间不存在边，第二节点与任一其他第二节点之间不存在边。
本申请实施例中，根据第一节点对应的元素的属性和第二节点对应的元素的属性要求之间的关系来，在第一节点和第二节点之间连接边。当第一节点对应的元素的属性与第二节点对应的元素的属性要求相符，则在该第一节点和该第二节点之间连接边；当第一节点对应的元素的属性与第二节点对应的元素的属性要求不相符，则在该第一节点和该第二节点之间不连接边。
在一示例中，构建的节点关系图如图4所示，节点s11、节点s12和节点13构成第一节点集合，节点s21、节点s22、节点s23、节点s24和节点s25构成第二节点集合，且连接的边包括：节点s11与节点s21、节点s23、节点s24和节点s25之间的边，节点s12与节点s21、节点s22、节点s24和节点s25之间的边，节点s13与节点s21、节点s22、节点s23、节点s24和节点s25之间的边。
S304、资源推荐设备在所述节点关系图中，查找匹配。
在得到节点关系图后，基于匹配算法在节点关系图中查找子图，使得查找的子图中任意两条边都不依附于同一节点，则称该子图为一个匹配。
本申请实施例中，查找匹配所使用的匹配算法可包括：最大流(Maximal Flow)或者匈牙利算法(Hungarian Algorithm)。
本申请实施例中，对查找匹配所使用的匹配算法不进行任何的限定。
在一示例中，对于图4所示的节点关系图，第一元素集合包括：元素11、元素12和元素13，第二元素集合包括：元素21、元素22、元素23、元素24和元素25，对应的，第一节点集合中的第一节点包括：节点s11、节点s12和节点13，第二节点集合中的第二节点包括：节点s21、节点s22、节点s23、节点s24和节点s25，所查找的匹配包括：节点s11-节点s23，节点S12-节点S25，节点S13-节点S21。
在一示例中，第一元素集合包括：元素11、元素12和元素13。第二元素集合包括：元素21、元素22、元素23、元素24和元素25，对应的，第一节点集合中的第一节点包括：节点s11、节点s12和节点13，第二节点集合中的第二节点包括：节点s21、节点s22、节点s23、节点s24和节点s25，基于第一节点集合中的第一节点和第二节点集合中的第二节点构成的节点关系图查找的匹配包括：节点s11-节点s23，节点s13-节点s25。
S305、资源推荐设备在查找到匹配的情况下，将所述资源作为待推荐资源，输出所述待推荐资源的资源标识。
当在该资源对应的节点关系图中查找到匹配的情况下，则资源推荐设备确定该资源为待推荐资源，获取该资源的资源标识，输出待推荐资源的资源标识以呈现给用户，使得用户能够获知所呈现的资源能够承载该素材。
在实际应用中，资源推荐设备可针对一素材分别与多个资源分别实施上述S301至S304的步骤，并从多个资源中确定可推荐资源，并将所确定的可推荐资源的资源标识输出给用户。其中，每一个资源对应一个节点关系图，当从以节点关系图中查找到匹配，则认为该节点关系图对应的资源为待推荐资源，该资源能承载当前素材；当从以节点关系图中未查找到匹配，则认为该节点关系图对应的资源不是待推荐资源，该资源无法承载当前素材。
在一示例中，用户上传的素材为素材1，资源提供商提供的资源包括：资源1、资源2和资源3。根据素材1的元素和资源1的元素，得到节点关系图1，且在节点关系图1中查找到匹配：匹配1；根据素材1的元素和资源2的元素，得到节点关系图2，且在节点关系图2中未查找到匹配；根据素材1的元素和资源3的元素，得到节点关系图3，且在节点关系图3中查找到匹配：匹配2，则认为资源1和资源3能够承载素材1，则可将资源1和资源3推荐给用户。
当用户获知能够承载素材即能够适配素材的资源，且包括多个资源的情况下，用户可根据各资源的计费、位置等资源信息从多个资源中选择用户展示素材的目标资源。
在实际应用中，资源推荐设备确定的待推荐资源包括多个资源的情况下，可获取各待推荐资源的计费、位置等资源信息，根据资源信息计算各资源的推荐度，在输出待推荐资源的资源标识的同时，输出各待推荐资源的推荐度。
本申请实施例提供的资源推荐方法，获取素材所包括的元素，得到第一元素集合，并获取资源所包括的元素，得到第二元素集合；将所述第一元素集合中各第一元素映射为第一节点，并将所述第二元素集合中各第二元素映射为第二节点；在第一节点和第二节点之间连接边，构建节点关系图；在所述节点关系图中，查找匹配；在查找到匹配的情况下，将所述资源作为待推荐资源，输出所述待推荐资源的资源标识；如此，能够在用户上传素材之前，有效的判断素材与资源之间是否适配，并将适配的资源作为待推荐资源推荐给用户，避免用户盲目的选择资源，从而避免选取的资源所待上传的素材不适配所带来的素材修改或资源重选的问题的发生，提高用户的工作效率。
在一些实施例中，如图5所示，S303的实施包括：
S3031、获取所述第一元素的属性和所述第二元素的属性要求。
第一元素的属性包括：类型和元素参数，其中，类型包括：文本、图片、视频等表征元素的样式，元素参数表征元素的尺寸等。当类型为文本，则元素参数包括：长度，当类型为图片，则元素参数包括：尺寸、大小、分辨率中的一种或多种的组合。当类型为视频，则元素参数包括：宽高比、大小、码率、时长中的一种或多种的组合。
第二元素的属性要求包括：类型要求和参数要求，其中，类型要求包括：本、图片、视频等资源所能承载的元素的样式，参数要求表征对于所承载元素的样式的具体要求等。当类型要求为文本，则参数要求包括：长度，当类型要求为图片，则参数要求包括：尺寸、大小、分辨率中的一种或多 种的组合。当类型要求为视频，则参数要求包括：宽高比、大小、码率、时长中的一种或多种的组合。
S3032、根据所述第一元素的属性和所述第二元素的属性要求，在对应的第一节点和对应的第二节点之间建立连接边，构建所述节点关系图。
在确定素材中各第一元素的属性和资源中各第二元素的属性要求后，确定各第一元素与各第二元素是否相符，在相符的第一元素和第二元素分别对应的第一节点和第二节点之间连接边，得到节点关系图。在一些实施例中，S3032的实施包括：遍历各第一元素的属性和各第二元素的属性要求，确定属性要求与属性相符的元素对；在所述元素对中的第一元素和第二元素分别对应的第一节点和对应的第二节点之间连接边，得到节点关系图。
在一示例中，对于图4所示的节点关系图，第一元素集合包括：元素11、元素12和元素13，第二元素集合包括：元素21、元素22、元素23、元素24和元素25，对应的，第一节点集合中的第一节点包括：节点s11、节点s12和节点13，第二节点集合中的第二节点包括：节点s21、节点s22、节点s23、节点s24和节点s25；将元素11的属性、元素12的属性和元素13的属性分别与元素21的属性要求、元素22的属性要求、元素23的属性要求、元素24的属性要求和元素25的属性要求，确定属性要求与属性相符的元素对，其中，确定的元素对包括：元素11与元素21、元素11与元素23、元素11与元素24，元素11与元素25、元素12与元素21、元素12与元素22、元素12与元素24、元素12与元素25，元素13与元素21、元素13与元素22、元素13与元素23、元素13与元素24、元素13与元素25；则连接的边包括：节点s11与节点s21、节点s23、节点s24和节点s25之间的边，节点s12与节点s21、节点s22、节点s24和节点s25之间的边，节点s13与节点s21、节点s22、节点s23、节点s24和节点s25之间的边。
这里，不同的第一元素对应的第一节点之间不进行边的连接，不同的第二元素对应的第二节点之间不进行边的连接，使得得到的节点关系图为二分图。
在一些实施例中，遍历各第一元素的属性和各第二元素的属性要求，确定属性要求与属性相符的元素对，包括：以各第一元素分别为参考元素，执行以下处理：分别将所述参考元素的属性，与各第二元素的属性要求进行比较；查找属性要求与所述第参考元素的属性相符的第二元素为触达元素，得到包括所述参考元素和所述触达元素的元素对。
这里，在遍历各第一元素的属性和各第二元素的属性要求时，可分别以各第一元素为参考元素，确定各参考元素对应的元素对。这里，将元素对中参考元素以外的另一元素称为触达元素。
在一示例中，对于图4所示的节点关系图，第一元素集合包括：元素11、元素12和元素13，第二元素集合包括：元素21、元素22、元素23、元素24和元素25，对应的，第一节点集合中的第一节点包括：节点s11、节点s12和节点13，第二节点集合中的第二节点包括：节点s21、节点s22、节点s23、节点s24和节点s25；首先以元素11为参考元素，确定元素11的属性是否与各第二元素：元素21、元素22、元素23、元素24和元素25的属性要求是否相符，在确定元素11对应的元素对后，接着以元素12为参考元素，确定元素12对应的元素对，以此类推，直到完成所有的第一元素 分别作为参考元素，得到所有的第一元素对应的元素对。
在一些实施例中，所述属性包括：类型，对应的，所述属性要求包括：类型要求，此时，所述查找属性要求与所述第一元素的属性相符的第二元素为所述触达元素，包括：查找类型要求与所述目标第一元素的类型相同的至少一个目标第二元素；在所述至少一个目标第二元素中，确定所述触达元素。
本申请实施例中，资源推荐设备针对以参考元素确定该参考元素对应的元素对时，首先基于第二元素的类型要求，查找在类型上与参考元素相符合的第二元素。在一示例中，第一元素集合包括：元素11、元素12和元素13，第二元素集合包括：元素21、元素22、元素23、元素24和元素25，在确定元素11对应的元素对时，基于元素11的类型为文本，元素21的类型要求为文本、元素22类型要求为文本、元素23类型要求为图片、元素24类型要求为图片，素25类型要求为视频，则确定的目标第二元素包括：元素21和元素22。
在确定目标第二元素后，在至少一个目标第二元素中，确定触达元素。其中，在至少一个目标元素中确定触达元素的确定方式包括以下之一：
确定方式一、将所有的目标第二元素确定为触达元素。
确定方式二、能够完整承载目标第一元素的目标第二元素为触达元素。
在确定方式为确定方式一的情况下，直接将所有的目标第二元素确定为触达元素。在一示例中，如上述示例，确定的目标第二元素包括：元素21和元素22，则元素21和元素22为触达元素。
当确定方式为确定方式二，所述在所述至少一个目标第二元素中，确定所述触达元素，包括：根据所述目标第一元素的元素参数，与所述至少一个目标第二元素中各目标第二元素的参数要求，计算所述目标第一元素与各目标第二元素之间的适配度；将适配度满足设定适配度范围的目标第二元素，确定为所述触达元素。
这里，根据参考元素的元素参数和各目标第二元素的参数要求，确定参考元素和各目标第二元素之间的适配度。
适配度的计算方式根据类型的不同可不同。
在一示例中，当类型为文本，则适配度的计算公式如公式(1)所示：
(1-(|length-avgLength|/avgLength))*100          公式(1)
其中，length为参考元素即素材中文本元素的长度，avgLength表征目标第二元素的参数要求。在实际应用中，目标第二元素的参数要求可包括最小长度和最大长度，此时，avgLength可为元素要求中的最小长度和最大长度的中间值。
在一示例中，当类型为图片，当参考元素的元素参数和目标第二元素的参数要求完全相同，则认为适配度为100，否则为0。这里，对素材中的图片和资源中的图片要求进行严格要求，使得资源能够在展示素材的同时，被有效利用。
在一示例中，当类型为图片，当参考元素的元素参数和目标第二元素的参数要求之间的误差小于设定的误差，则认为适配度为100，否则为0。
在一示例中，当类型为视频，则适配度的计算公式如公式(2)所示：
(bitRate/maxBitRate+size/maxSize+duration/maxDuration)/3*100     公式(2)；
其中，bitRate为参考元素即素材元素的比特率，maxBitRate为目标第二元素要求的最大比特率，size为参考元素即素材元素的大小，maxSize为目标第二元素要求的最大大小，duration为参考元素即素材元素的时长，maxDuration为目标第二元素要求的最大时长。
本申请实施例中，当计算出参考元素与以目标第二元素的适配度后，判断适配度是否在设定的适配度范围内。在适配度是否在设定的适配度范围内，则认为对应的目标第二元素为触达元素，参考元素与该目标第二元素为一对元素对。
适配度范围可为：大于或等于20。在实际应用中，适配度范围可根据实际需求进行设定。
本申请实施例中，当第一元素与第二元素的类型不同，则二者不符，对应的第一节点和对应的第二节点之间不可达。当第一元素与第二元素的类型相同，且二者之间的适配度不满足适配度范围，则二者不符，对应的第一节点和对应的第二节点之间不可达。当第一元素与第二元素的类型相同，且二者之间的适配度满足适配度范围，则二者相符，对应的第一节点和对应的第二节点之间可达，连接为边。
在一些实施例中，在S304之前，还包括：
将所述边连接的第一节点与第二节点，对应的第一元素和对应的第二元素之间的适配度，标记为相应边的权重；对应的，S304的实施包括：根据所述边的权重，在所述节点关系图中，查找匹配。
资源推荐设备根据参考元素的元素参数和各目标第二元素的参数要求，确定参考元素和各目标第二元素之间的适配度。适配度的计算方式根据类型的不同可不同。适配度的计算可参考上述描述，这里不再赘述。
当得到各边连接的两个节点对应的元素之间的适配度后，将适配度标记为该边的权重，此时，根据节点关系图中各节点之间的边，以及各边的权重来在节点关系图中查找匹配。根据边以及边的权重查找匹配所使用的匹配算法可包括：Kuhn–Munkres(KM)算法、最大流算法等。本申请实施例中，对查找匹配所使用的匹配算法不进行任何的限定。
在一些实施例中，在S305之后，如图6所示，还包括：
S306、确定所述匹配包括的目标边；
S307、在所述目标边连接的第一节点表征的第一元素和第二节点表征的第二元素之间建立关联关系，并输出所述关联关系。
资源推荐设备在查找到节点关系图中的匹配后，确定匹配所包括的所有的边，并在各边所连接的第一节点和第二节点分别对应的第一元素和第二元素之间建立连接关系，并输出连接关系使得用户能够获知素材中哪些素材能够展示在一个资源中，以及具体展示在资源的哪个位置。
下面，以资源为广告位的广告场景为例，对本申请实施例提供的资源推荐方法进行进一步说明。
这里，首先对KM算法进行介绍。
KM算法可用于求解二分图最佳带权匹配问题。
二分图是一类特殊的图，它的顶点可以分成两个独立的集合U和V，使得所有的边都是连结一个U中的点和一个V中的点。也就是说，U中顶点出发的边，只会连结到V，不会连到U自身。V同理。
匹配是指二分图G的一个子图M，M的边集中的任意两条边都没有共同的顶点，则框子图M为一个匹配。也就是说一些没有共同顶点的边的集合。
二分图最佳带权匹配是指在给定带权二分图上求出一个匹配，使得所有匹配边权值之和最大。
在一示例中，如图7所示，带权二分图701包括两个集合：U和V，其中，节点A和节点B属于集合U，节点a和节点b属于集合V，各节点之间的边的权值如图7所示。利用KM算法求得带权二分图301的最佳匹配，匹配结果如图7所示，包括边702，其中，边702包括A-b之间的边和B-a之间的边，最大权值为10+20＝30。这里，图7所示的带权二分图701中的其他的匹配(A-a,B-b，权值＝100+(-101)＝-1)的权重为-1，小于30。
本申请实施例中所使用的KM算法的执行过程包括：
初始化可行顶标的值，对集合U中的每个顶点执行以下操作：a)、利用匈牙利算法在相等子图中找匹配，b)、若未找到增广路径则修改可行顶标的值，重复a)步骤、b)步骤直到找到相等子图的完备匹配。
在广告位场景下，将广告位元素和素材元素抽象成两个集合中的顶点，广告位元素位于集合U中，素材元素位于集合V中，广告位元素与素材元素的边表示素材元素是否符合，边的权重表征素材元素符合广告位元素要求的程度，越符合要求则权值越高，同时，不会存在广告位元素到广告位元素的边，素材元素到素材元素的边，这样可构建一个广告位-素材的带权二分图。在这个带权二分图上，就可以用KM算法来找出一个权值最大的匹配，也就是为这个广告位中各元素找到最符合条件的素材元素。
本申请实施例提供的资源推荐方法可如图8所示，包括：
S801、用户81向资源推荐设备82提交素材。
这里，用户提交素材集合到资源推荐设备，可以是任意个数的文字信息、图片和视频(每个文字视为一个素材元素，图片、视频同理)
S802、资源推荐设备82从广告位池83中拉取广告位。
资源推荐设备从目标广告位池拉取广告位集合。其中，每个广告位有不同的样式，由一个或多个广告位元素组成，广告位元素包括文本域、图片域和视频域。
S803、资源推荐设备82计算适配度。
资源推荐设备82根据计算素材中各元素和广告位各元素之间的适配度。
S804、资源推荐设备82构建带权二分图。
资源推荐设备82基于计算的适配度输出素材-广告位的带权二分图。
S805、资源推荐设备82查找匹配。
资源推荐设备对带权二分图进行KM匹配，若匹配成功，表示有素材元素适配这个广告位，并且是最优匹配。
S806、资源推荐设备82输出结果集。
资源推荐设备82基于匹配向用户81输出素材元素-广告位元素的组合。
这里，资源推荐设备将匹配的素材元素与广告位作为一个组合，加入结果集，并输出结果集。
本申请实施例中，连接一素材元素与广告位元素的边对应权值即素材元素与广告位元素之间的适配度的计算规则可包括：
1、权重的值归一化在0-100之间，一个极小的权重(比如：-2的20次方)表示对应的素材元素不符合广告位元素的要求，这两个元素之间不可触达(UNREACHABLE)。
2、不同类型的素材元素和广告位元素之间UNREACHABLE。
3、对于同类型的元素，属性与属性要求不符合要求的元素之间UNREACHABLE。符合要求的元素之间的适配度计算方法如下：
对应文本类的元素：长度越接近广告位元素要求的平均值的素材元素的权值越高。在一示例中，适配度的计算公式如公式(1)所示：
(1-(|length-avgLength|/avgLength))*100         公式(1)；
其中，length为素材中文本元素的长度，avgLength|为广告位中文本元素要求的最小长度和最大长度的中间值。
对于图片类的元素：素材元素的宽高严格符合广告位元素的要求，且适配度为100。
对于视频类元素：素材元素的宽高比严格符合广告位元素的要求；素材元素的码率、大小、时长越接近广告位元素要求的最大值，则分数越高，此时，对多种不同属性的分数取平均值得到最终的适配度。
在实际应用中，对于图片类元素，当素材元素与广告元素的宽高比符合，则可认为素材元素与广告元素相符。
在一示例中，如公式(2)所示，对于不同属性的分数，取平均值得到权重：
(bitRate/maxBitRate+size/maxSize+duration/maxDuration)/3*100     公式(2)；
其中，bitRate为素材元素的比特率，maxBitRate为广告位元素要求的最大比特率，size为素材元素的大小，maxSize为广告位元素要求的最大大小，duration为素材元素的时长，maxDuration为广告位元素要求的最大时长。
基于上述规则，可对一个广告位和一个素材集合构建带权二分图，在二分图上运行KM算法，则可得到匹配结果。
在一示例中，广告位A的元素如表1所示，用户上传的素材的元素如表2所示。
表1、广告位A的元素示例
Figure PCTCN2022070845-appb-000001
表2、素材a的元素示例
Figure PCTCN2022070845-appb-000002
将广告位A中各元素作为第一集合中的顶点，并将素材a中各元素作为第二集合中的顶点，则第一集合中的顶点和第二集合中的顶点构成的带权二分图如表3所示，其中，UN表征不可达。
表3、广告位A与素材a构成的带权二分图
Figure PCTCN2022070845-appb-000003
利用KM算法得到表3所示的带权二分图的最大权匹配为：
主标题-文本2、副标题-文本1、主图-图片3、副图-图片1、主视频-视频2。
图9为本申请实施例的一种资源推荐装置的实现流程示意图，如图9所示，装置900包括：
获取单元901，配置为获取素材所包括的元素，得到第一元素集合，并获取资源所包括的元素，得到第二元素集合；
映射单元902，配置为将所述第一元素集合中各第一元素映射为第一节点，并将所述第二元素集合中各第二元素映射为第二节点；
构建单元903，配置为在第一节点和第二节点之间连接边，构建节点关系图；
匹配单元904，配置为在所述节点关系图中，查找匹配；
输出单元905，配置为在查找到匹配的情况下，将所述资源作为待推荐资源，输出所述待推荐资源的资源标识。
在一些实施例中，构建单元903，还配置为：
获取所述第一元素的属性和所述第二元素的属性要求；
根据所述第一元素的属性和所述第二元素的属性要求，在对应的第一节点和对应的第二节点之间建立连接边，构建所述节点关系图。
在一些实施例中，构建单元903，还配置为：
遍历各第一元素的属性和各第二元素的属性要求，确定属性要求与属性相符的元素对；
在所述元素对中的第一元素和第二元素分别对应的第一节点和对应的第二节点之间连接边，得到节点关系图。
在一些实施例中，构建单元903，还配置为：
以各第一元素分别为参考元素，执行以下处理：
分别将所述参考元素的属性，与各第二元素的属性要求进行比较；
查找属性要求与所述第参考元素的属性相符的第二元素为触达元素，得到包括所述参考元素和所述触达元素的元素对。
在一些实施例中，构建单元903，还配置为：
查找类型要求与所述参考元素的类型相同的至少一个第二目标元素；所述属性包括：所述类型，所述属性要求包括：所述类型要求；
在所述至少一个第二目标元素中，确定所述触达元素。
在一些实施例中，构建单元903，还配置为：
根据所述参考元素的元素参数，与所述至少一个第二目标元素中各第二目标元素的参数要求，计算所述参考元素与各第二目标元素之间的适配度；所述属性还包括：所述元素参数，所述属性要求包括：所述参数要求；
将适配度满足设定适配度范围的第二目标元素，确定为所述触达元素。
在一些实施例中，装置900，还包括：标记单元，配置为将所述边连接的第一节点与第二节点，对应的第一元素和对应的第二元素之间的适配度，标记为相应边的权重；
对应的，匹配单元904，还配置为：
根据所述边的权重，在所述节点关系图中，查找匹配。
在一些实施例中，装置900，还包括：关联单元，配置为：
确定所述匹配包括的目标边；
在所述目标边连接的第一节点表征的第一元素和第二节点表征的第二元素之间建立关联关系，并输出所述关联关系。
需要说明的是，本申请实施例提供的资源推荐装置包括所包括的各单元，可以通过电子设备中的处理器来实现；当然也可通过具体的逻辑电路实现；在实施的过程中，处理器可以为中央处理器(CPU，Central Processing Unit)、微处理器(MPU，Micro Processor Unit)、数字信号处理器(DSP，Digital Signal Processor)或现场可编程门阵列(FPGA，Field-Programmable Gate Array)等。
以上装置实施例的描述，与上述方法实施例的描述是类似的，具有同方法实施例相似的有益效果。对于本申请装置实施例中未披露的技术细节，请参照本申请方法实施例的描述而理解。
需要说明的是，本申请实施例中，如果以软件功能模块的形式实现上述的资源推荐方法，并作为独立的产品销售或使用时，也可以存储在一个计算机可读取存储介质中。基于这样的理解，本申请实施例的技术方案本质上或者说对相关技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机、服务器、或者网络设备等)执行本申请各个实施例所述方法的全部或部分。而前述的存储介质包括：U盘、移动硬盘、只读存储器(Read Only Memory，ROM)、磁碟或者光盘等各种可以存储程序代码的介质。这样，本申请实施例不限制于任何特定的硬件和软件结合。
对应地，本申请实施例提供一种电子设备，包括存储器和处理器，所述存储器存储有可在处理器上运行的计算机程序，所述处理器执行所述程序时实现上述实施例中提供的资源推荐方法中的步骤。其中，该电子设备可为客户端，也可为服务端。
对应地，本申请实施例提供一种存储介质，也就是计算机可读存储介质，其上存储有计算机程序，该计算机程序被处理器执行时实现上述实施例中提供的资源推荐方法中的步骤。
这里需要指出的是：以上存储介质和设备实施例的描述，与上述方法实施例的描述是类似的，具有同方法实施例相似的有益效果。对于本申请存储介质和设备实施例中未披露的技术细节，请参照本申请方法实施例的描述而理解。
需要说明的是，图10为本申请实施例电子设备的一种硬件实体示意图，如图10所示，所述电子设备1000包括：一个处理器1001、至少一个通信总线1002、至少一个外部通信接口1004和存储器1005。其中，通信总线1002配置为实现这些组件之间的连接通信。在一示例中，电子设备1000还包括：用户接口1003、其中，用户接口1003可以包括显示屏，外部通信接口1004可以包括标准的有线接口和无线接口。
存储器1005配置为存储由处理器1001可执行的指令和应用，还可以缓存待处理器1001以及电 子设备中各模块待处理或已经处理的数据(例如，图像数据、音频数据、语音通信数据和视频通信数据)，可以通过闪存(FLASH)或随机访问存储器(Random Access Memory，RAM)实现。
应理解，说明书通篇中提到的“一个实施例”或“一实施例”意味着与实施例有关的特定属性、结构或特性包括在本申请的至少一个实施例中。因此，在整个说明书各处出现的“在一个实施例中”或“在一些实施例中”未必一定指相同的实施例。此外，这些特定的属性、结构或特性可以任意适合的方式结合在一个或多个实施例中。应理解，在本申请的各种实施例中，上述各过程的序号的大小并不意味着执行顺序的先后，各过程的执行顺序应以其功能和内在逻辑确定，而不应对本申请实施例的实施过程构成任何限定。上述本申请实施例序号仅仅为了描述，不代表实施例的优劣。
需要说明的是，在本文中，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、物品或者装置不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、物品或者装置所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括该要素的过程、方法、物品或者装置中还存在另外的相同要素。
在本申请所提供的几个实施例中，应该理解到，所揭露的设备和方法，可以通过其它的方式实现。以上所描述的设备实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，如：多个单元或组件可以结合，或可以集成到另一个系统，或一些属性可以忽略，或不执行。另外，所显示或讨论的各组成部分相互之间的耦合、或直接耦合、或通信连接可以是通过一些接口，设备或单元的间接耦合或通信连接，可以是电性的、机械的或其它形式的。
上述作为分离部件说明的单元可以是、或也可以不是物理上分开的，作为单元显示的部件可以是、或也可以不是物理单元；既可以位于一个地方，也可以分布到多个网络单元上；可以根据实际的需要选择其中的部分或全部单元来实现本实施例方案的目的。
另外，在本申请各实施例中的各功能单元可以全部集成在一个处理单元中，也可以是各单元分别单独作为一个单元，也可以两个或两个以上单元集成在一个单元中；上述集成的单元既可以采用硬件的形式实现，也可以采用硬件加软件功能单元的形式实现。
本领域普通技术人员可以理解：实现上述方法实施例的全部或部分步骤可以通过程序指令相关的硬件来完成，前述的程序可以存储于计算机可读取存储介质中，该程序在执行时，执行包括上述方法实施例的步骤；而前述的存储介质包括：移动存储设备、只读存储器(Read Only Memory，ROM)、磁碟或者光盘等各种可以存储程序代码的介质。
或者，本申请上述集成的单元如果以软件功能模块的形式实现并作为独立的产品销售或使用时，也可以存储在一个计算机可读取存储介质中。基于这样的理解，本申请实施例的技术方案本质上或者说对相关技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机、服务器、或者网络设备等)执行本申请各个实施例所述方法的全部或部分。而前述的存储介质包括：移动存储设备、ROM、磁 碟或者光盘等各种可以存储程序代码的介质。
以上所述，仅为本申请的实施方式，但本申请的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本申请揭露的技术范围内，可轻易想到变化或替换，都应涵盖在本申请的保护范围之内。因此，本申请的保护范围应以所述权利要求的保护范围为准。

Claims (18)

  1. 一种资源推荐方法，所述方法包括：
    下载更新数据包至待更新文件包所在的目标磁盘分区；所述更新数据包用于对所述待更新文件包进行更新；获取素材所包括的元素，得到第一元素集合，并获取资源所包括的元素，得到第二元素集合；
    将所述第一元素集合中各第一元素映射为第一节点，并将所述第二元素集合中各第二元素映射为第二节点；
    在第一节点和第二节点之间连接边，构建节点关系图；
    在所述节点关系图中，查找匹配；
    在查找到匹配的情况下，将所述资源作为待推荐资源，输出所述待推荐资源的资源标识。
  2. 根据权利要求1所述的方法，所述在第一节点和第二节点之间连接边，构建节点关系图，包括：
    获取所述第一元素的属性和所述第二元素的属性要求；
    根据所述第一元素的属性和所述第二元素的属性要求，在对应的第一节点和对应的第二节点之间建立连接边，构建所述节点关系图。
  3. 根据权利要求2所述的方法，所述根据所述第一元素的属性和所述第二元素的属性要求，在对应的第一节点和对应的第二节点之间建立连接边，构建所述节点关系图，包括：
    遍历各第一元素的属性和各第二元素的属性要求，确定属性要求与属性相符的元素对；
    在所述元素对中的第一元素和第二元素分别对应的第一节点和对应的第二节点之间连接边，得到节点关系图。
  4. 根据权利要求3所述的方法，遍历各第一元素的属性和各第二元素的属性要求，确定属性要求与属性相符的元素对，包括：
    以各第一元素分别为参考元素，执行以下处理：
    分别将所述参考元素的属性，与各第二元素的属性要求进行比较；
    查找属性要求与所述第参考元素的属性相符的第二元素为触达元素，得到包括所述参考元素和所述触达元素的元素对。
  5. 根据权利要求4所述的方法，所述属性包括：类型，所述属性要求包括类型要求；所述查找属性要求与所述第参考元素的属性相符的第二元素为触达元素，包括：
    查找类型要求与所述参考元素的类型相同的至少一个第二目标元素；
    在所述至少一个第二目标元素中，确定所述触达元素。
  6. 根据权利要求5所述的方法，所述属性还包括：元素参数，所述属性要求包括参数要求；所述在所述至少一个第二目标元素中，确定所述触达元素，包括：
    根据所述参考元素的元素参数，与所述至少一个第二目标元素中各第二目标元素的参数要 求，计算所述参考元素与各第二目标元素之间的适配度；
    将适配度满足设定适配度范围的第二目标元素，确定为所述触达元素。
  7. 根据权利要求1至6中任一项所述的方法，所述方法还包括：
    将所述边连接的第一节点与第二节点，对应的第一元素和对应的第二元素之间的适配度，标记为相应边的权重；
    对应的，在所述节点关系图中，查找匹配，包括：
    根据所述边的权重，在所述节点关系图中，查找匹配。
  8. 根据权利要求1至6中任一项所述的方法，所述方法还包括：
    确定所述匹配包括的目标边；
    在所述目标边连接的第一节点表征的第一元素和第二节点表征的第二元素之间建立关联关系，并输出所述关联关系。
  9. 一种资源处理装置，所述装置包括：
    获取单元，配置为获取素材所包括的元素，得到第一元素集合，并获取资源所包括的元素，得到第二元素集合；
    映射单元，配置为将所述第一元素集合中各第一元素映射为第一节点，并将所述第二元素集合中各第二元素映射为第二节点；
    构建单元，配置为在第一节点和第二节点之间连接边，构建节点关系图；
    匹配单元，配置为在所述节点关系图中，查找匹配；
    输出单元，配置为在查找到匹配的情况下，将所述资源作为待推荐资源，输出所述待推荐资源的资源标识。
  10. 根据权利要求9所述的装置，所述构建单元，还配置为：
    获取所述第一元素的属性和所述第二元素的属性要求；
    根据所述第一元素的属性和所述第二元素的属性要求，在对应的第一节点和对应的第二节点之间建立连接边，构建所述节点关系图。
  11. 根据权利要求10所述的装置，所述构建单元，还配置为：
    遍历各第一元素的属性和各第二元素的属性要求，确定属性要求与属性相符的元素对；
    在所述元素对中的第一元素和第二元素分别对应的第一节点和对应的第二节点之间连接边，得到节点关系图。
  12. 根据权利要求11所述的装置，所述构建单元，还配置为：
    以各第一元素分别为参考元素，执行以下处理：
    分别将所述参考元素的属性，与各第二元素的属性要求进行比较；
    查找属性要求与所述第参考元素的属性相符的第二元素为触达元素，得到包括所述参考元素和所述触达元素的元素对。
  13. 根据权利要求12所述的装置，所述构建单元，还配置为：
    查找类型要求与所述参考元素的类型相同的至少一个第二目标元素；所述属性要求包括所述类型要求，所述属性包括所述类型；
    在所述至少一个第二目标元素中，确定所述触达元素。
  14. 根据权利要求13所述的装置，所述构建单元，还配置为：
    根据所述参考元素的元素参数，与所述至少一个第二目标元素中各第二目标元素的参数要求，计算所述参考元素与各第二目标元素之间的适配度；所述属性还包括：所述元素参数，所述属性要求包括：所述参数要求；
    将适配度满足设定适配度范围的第二目标元素，确定为所述触达元素。
  15. 根据权利要9至14中任一项所述的装置，所述装置还包括：
    标记单元，配置为将所述边连接的第一节点与第二节点，对应的第一元素和对应的第二元素之间的适配度，标记为相应边的权重；
    对应的，所述匹配单元，还配置为根据所述边的权重，在所述节点关系图中，查找匹配。
  16. 根据权利要9至14中任一项所述的装置，所述装置还包括：关联单元，配置为：
    确定所述匹配包括的目标边；
    在所述目标边连接的第一节点表征的第一元素和第二节点表征的第二元素之间建立关联关系，并输出所述关联关系。
  17. 一种计算机设备，包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，所述处理器执行所述计算机程序时实现权利要求1至8任一项所述资源推荐方法中的步骤。
  18. 一种存储介质，其上存储有计算机程序，该计算机程序被处理器执行时，实现权利要求1至8任一项所述的资源推荐方法。
PCT/CN2022/070845 2021-01-14 2022-01-07 资源推荐方法及装置、设备、存储介质 WO2022152061A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110051017.X 2021-01-14
CN202110051017.XA CN113743974A (zh) 2021-01-14 2021-01-14 一种资源推荐方法及装置、设备、存储介质

Publications (2)

Publication Number Publication Date
WO2022152061A1 true WO2022152061A1 (zh) 2022-07-21
WO2022152061A9 WO2022152061A9 (zh) 2022-09-01

Family

ID=78728224

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/070845 WO2022152061A1 (zh) 2021-01-14 2022-01-07 资源推荐方法及装置、设备、存储介质

Country Status (2)

Country Link
CN (1) CN113743974A (zh)
WO (1) WO2022152061A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113743974A (zh) * 2021-01-14 2021-12-03 北京沃东天骏信息技术有限公司 一种资源推荐方法及装置、设备、存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070257938A1 (en) * 2006-05-04 2007-11-08 William Steinbock Element template system
CN105160538A (zh) * 2015-10-27 2015-12-16 武汉改图网技术有限公司 一种印刷品在线设计服务云平台及其在线设计方法
CN108573515A (zh) * 2017-03-10 2018-09-25 阿里巴巴集团控股有限公司 一种合图生成方法及装置、合图模板生成方法及装置
CN111580788A (zh) * 2019-02-15 2020-08-25 阿里巴巴集团控股有限公司 模板搭配信息推荐方法、装置及电子设备
CN113743974A (zh) * 2021-01-14 2021-12-03 北京沃东天骏信息技术有限公司 一种资源推荐方法及装置、设备、存储介质

Family Cites Families (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108805642A (zh) * 2017-05-02 2018-11-13 合信息技术（北京）有限公司 推荐方法及装置
CN114125512B (zh) * 2018-04-10 2023-01-31 腾讯科技（深圳）有限公司 推广内容推送方法、装置及存储介质
CN109471978B (zh) * 2018-11-22 2022-01-28 腾讯科技（深圳）有限公司 一种电子资源推荐方法及装置
CN110264269A (zh) * 2019-06-20 2019-09-20 卓尔智联(武汉)研究院有限公司 广告位推荐方法、装置、电子设备及存储介质
CN110175295B (zh) * 2019-06-21 2021-05-04 卓尔智联(武汉)研究院有限公司 广告位推荐方法、电子设备及计算机可读存储介质
CN110968708A (zh) * 2019-12-20 2020-04-07 华中师范大学 一种教育信息资源属性标注方法及系统
CN111382352B (zh) * 2020-03-02 2021-03-26 腾讯科技（深圳）有限公司 数据推荐方法、装置、计算机设备以及存储介质
CN111522967B (zh) * 2020-04-27 2023-09-15 北京百度网讯科技有限公司 知识图谱构建方法、装置、设备以及存储介质
CN111708964B (zh) * 2020-05-27 2023-06-20 北京百度网讯科技有限公司 多媒体资源的推荐方法、装置、电子设备和存储介质
CN112069423A (zh) * 2020-08-14 2020-12-11 京华信息科技股份有限公司 一种信息推荐方法、装置、存储介质及计算机设备
CN112966067A (zh) * 2020-09-24 2021-06-15 王海宏 基于区块链和在线金融的信息推送方法、系统及服务中心

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070257938A1 (en) * 2006-05-04 2007-11-08 William Steinbock Element template system
CN105160538A (zh) * 2015-10-27 2015-12-16 武汉改图网技术有限公司 一种印刷品在线设计服务云平台及其在线设计方法
CN108573515A (zh) * 2017-03-10 2018-09-25 阿里巴巴集团控股有限公司 一种合图生成方法及装置、合图模板生成方法及装置
CN111580788A (zh) * 2019-02-15 2020-08-25 阿里巴巴集团控股有限公司 模板搭配信息推荐方法、装置及电子设备
CN113743974A (zh) * 2021-01-14 2021-12-03 北京沃东天骏信息技术有限公司 一种资源推荐方法及装置、设备、存储介质

Also Published As

Publication number Publication date
CN113743974A (zh) 2021-12-03
WO2022152061A9 (zh) 2022-09-01

Similar Documents

Publication Publication Date Title
US20190370859A1 (en) Managing associations between device identifiers
US10230672B2 (en) Inserting a search box into a mobile terminal dialog messaging protocol
US9600807B2 (en) Server-side modification of messages during a mobile terminal message exchange
US20120036023A1 (en) System for conducting demand-side, real-time bidding in an advertising exchange
WO2018161940A1 (zh) 媒体文件的推送方法及装置、存储介质以及电子装置
US20110208559A1 (en) Automatic Management of Networked Publisher-Subscriber Relationships
US20110225038A1 (en) System and Method for Efficiently Evaluating Complex Boolean Expressions
KR20130028916A (ko) 다른 사용자의 사용자 선호에 기초하여 사용자에 대하여 디스플레이되는 컨텐츠 커스터마이징
WO2013163575A1 (en) Providing content to a user across multiple devices
US11436628B2 (en) System and method for automated bidding using deep neural language models
JP2009129458A (ja) コンテンツ推薦装置及び方法
CN105393600B (zh) 用于在无线环境中提供多服务发现的方法和系统
WO2014071554A1 (zh) 内容推荐方法、系统及装置
US20130325607A1 (en) Mobile-2-web retargeting
WO2019085664A1 (zh) 轻应用推送方法、装置及服务器、存储介质
US10672025B2 (en) System and method for traffic quality based pricing via deep neural language models
JP6426109B2 (ja) ソーシャルネットワーキングシステムからのサードパーティ委託広告
US11783381B2 (en) Visual inventory rules building system
WO2022152061A1 (zh) 资源推荐方法及装置、设备、存储介质
JP2018524670A (ja) インターネット広告提供装置および方法
US8150910B2 (en) Service providing device, program, method, and system
US11973733B2 (en) Enhancing a social media post with content that is relevant to the audience of the post
US20160189204A1 (en) Systems and methods for building keyword searchable audience based on performance ranking
US8843817B2 (en) System and method for obtaining user information
US10402409B2 (en) Method for ranking social and search web traffic with virality scores

Legal Events

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

Ref document number: 22738942

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 22738942

Country of ref document: EP

Kind code of ref document: A1