CN115408616A - Big data analysis method for cloud service push and cloud service push system - Google Patents
Big data analysis method for cloud service push and cloud service push system Download PDFInfo
- Publication number
- CN115408616A CN115408616A CN202211118058.7A CN202211118058A CN115408616A CN 115408616 A CN115408616 A CN 115408616A CN 202211118058 A CN202211118058 A CN 202211118058A CN 115408616 A CN115408616 A CN 115408616A
- Authority
- CN
- China
- Prior art keywords
- page
- cloud service
- node object
- candidate
- collaborative
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/958—Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/451—Execution arrangements for user interfaces
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Human Computer Interaction (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the application provides a big data analysis method and a cloud service pushing system for cloud service pushing, in the process of pushing and loading cloud service, due to the fact that not only is the cloud service subscription support degree between a page display node and candidate hotspot cloud service combined, but also the cloud service subscription support degree between a collaborative page node object of the page display node and the candidate hotspot cloud service is further combined, cloud service subscription judgment is comprehensively carried out from collaborative dimensionality, and the reliability of cloud service subscription can be improved.
Description
Technical Field
The invention relates to the technical field of cloud service pushing, in particular to a big data analysis method and a cloud service pushing system for cloud service pushing.
Background
With the popularization of the cloud computing technology, each internet facilitator deploys various cloud services at the cloud end so that page node objects (users or user groups or virtual page account numbers and the like) can subscribe based on own preference, and then pushes cloud service content to associated target users through the deployed cloud services, so that the page node objects and internet products have more interaction, and the product utilization rate of the internet facilitator is improved. However, for the internet service provider, compared with the active subscription of the page node object based on own preference, a more effective popularization way is to actively push the cloud service which may be concerned or preferred to the page node object. However, in the related art, the cloud service subscription decision logic of the internet service provider for each page node object is single, which results in poor reliability of the cloud service subscription.
Disclosure of Invention
In order to overcome at least the above disadvantages in the prior art, the present invention provides a big data analysis method for cloud service push and a cloud service push system.
In a first aspect, the present application provides a big data analysis method for cloud service push, which is applied to a cloud service push system, where the cloud service push system is in communication connection with a plurality of page display nodes, and the method includes:
performing cloud service subscription verification on an authentication page node object and a candidate hot point cloud service corresponding to the candidate page display node, and determining a basic cloud service subscription support degree corresponding to the candidate page display node;
performing cloud service subscription verification on the collaborative page node object of the authentication page node object and the candidate hot point cloud service, and determining the collaborative cloud service subscription support degree corresponding to the candidate page display node;
and when determining that the authentication page node object and the candidate hot point cloud service have a cloud service subscription confirmation relationship by combining the basic cloud service subscription support degree and the cooperative cloud service subscription support degree, loading the candidate hot point cloud service to the candidate page display node, and operating service content corresponding to the candidate hot point cloud service through the candidate page display node.
In a second aspect, an embodiment of the present application further provides a big data analysis system for cloud service push, where the big data analysis system for cloud service push includes a cloud service push system and multiple page display nodes in communication connection with the cloud service push system;
the cloud service push system is used for:
performing cloud service subscription verification on an authentication page node object and a candidate hot point cloud service corresponding to the candidate page display node, and determining a basic cloud service subscription support degree corresponding to the candidate page display node;
performing cloud service subscription verification on the collaborative page node object of the authentication page node object and the candidate hot point cloud service, and determining the collaborative cloud service subscription support degree corresponding to the candidate page display node;
and when the authentication page node object and the candidate hot point cloud service have a cloud service subscription confirmation relationship by combining the basic cloud service subscription support degree and the collaborative cloud service subscription support degree, loading the candidate hot point cloud service to the candidate page display node, and operating the service content corresponding to the candidate hot point cloud service through the candidate page display node.
In any aspect, the cloud service subscription verification is performed on the authentication page node object and the candidate hot-point cloud service corresponding to the candidate page display node, and the basic cloud service subscription support degree corresponding to the candidate page display node is determined. And performing cloud service subscription verification on the collaborative page node object of the authentication page node object and the candidate hot point cloud service, and determining the collaborative cloud service subscription support degree corresponding to the candidate page display node. And when the authentication page node object and the candidate hot point cloud service have the cloud service subscription confirmation relation by combining the basic cloud service subscription support degree and the cooperative cloud service subscription support degree, loading the candidate hot point cloud service to the candidate page display node, and enabling the candidate page display node to display the candidate hot point cloud service. Therefore, in the cloud service pushing and loading process, the cloud service subscription support degree between the page display node and the candidate hotspot cloud service is combined, and the cloud service subscription support degree between the collaborative page node object of the page display node and the candidate hotspot cloud service is further combined, so that the cloud service subscription determination is comprehensively carried out from collaborative dimensions, and the reliability of cloud service subscription can be improved.
Drawings
Fig. 1 is a schematic flowchart of a big data analysis method for cloud service push according to an embodiment of the present invention.
Detailed Description
The architecture of the cloud service push oriented big data analysis system 10 according to an embodiment of the present invention is described below, where the cloud service push oriented big data analysis system 10 may include a cloud service push system 100 and a page display node 200 communicatively connected to the cloud service push system 100. The cloud service pushing system 100 and the page display node 200 in the cloud service pushing big data analysis system 10 may cooperate to execute the cloud service pushing big data analysis method described in the following method embodiments, and the detailed description of the following method embodiments may be referred to in the specific steps of the cloud service pushing system 100 and the page display node 200.
The big data analysis method for cloud service push provided by this embodiment may be executed by the cloud service push system 100, and the details of the big data analysis method for cloud service push are described below with reference to fig. 1.
And the Process110 performs cloud service subscription verification on the authentication page node object and the candidate hot point cloud service corresponding to the candidate page display node, and determines the basic cloud service subscription support degree corresponding to the candidate page display node.
In some exemplary design ideas, the cloud service push system may perform cloud service subscription verification on an authentication page node object (e.g., a certain user or a certain user group) corresponding to a candidate page display node (e.g., a page display user terminal) and a candidate hot point cloud service (e.g., a community sharing cloud service of a class a commodities on an e-commerce platform, a commodity interaction cloud service of a class a live broadcast on the e-commerce platform, and the like), and determine a basic cloud service subscription support degree corresponding to the candidate page display node.
The cloud service subscription support degree can represent a reference confidence degree of a subscription guide of a relevant page node object for a certain cloud service. The candidate hot point cloud service may be a cloud service whose attention heat (e.g., browsing times) is greater than a preset heat.
And the Process120 performs cloud service subscription verification on the collaborative page node object of the authentication page node object and the candidate hot-point cloud service, and determines a collaborative cloud service subscription support degree corresponding to the candidate page display node.
In this embodiment, the collaborative page node object may be understood as another page node object having a collaborative relationship with the authentication page node object.
In some exemplary design ideas, the cloud service push system may perform cloud service subscription verification on the collaborative page node object of the authentication page node object and the candidate hot point cloud service, and determine a collaborative cloud service subscription support degree corresponding to the candidate page display node.
And the Process130, when determining that the authentication page node object and the candidate hot point cloud service have a cloud service subscription confirmation relationship by combining the basic cloud service subscription support degree and the collaborative cloud service subscription support degree, loading the candidate hot point cloud service to the candidate page display node, and running service content corresponding to the candidate hot point cloud service through the candidate page display node.
For example, when the service content corresponding to the candidate hot point cloud service is run through the candidate page display node, for example, when the candidate hot point cloud service is a community sharing cloud service of a class a commodity on an e-commerce platform, the corresponding service content may be community sharing data content of the class a commodity.
In some exemplary design ideas, the cloud service pushing system may load the candidate hotspot cloud service to the candidate page display node and run service content corresponding to the candidate hotspot cloud service through the candidate page display node when determining that the authentication page node object and the candidate hotspot cloud service have a cloud service subscription confirmation relationship by combining the basic cloud service subscription support degree and the cooperative cloud service subscription support degree.
Based on the steps, in the process of pushing and loading the cloud service, not only is the cloud service subscription support degree between the page display node and the candidate hotspot cloud service combined, but also the cloud service subscription support degree between the collaborative page node object of the page display node and the candidate hotspot cloud service is further combined, so that the cloud service subscription judgment is comprehensively carried out from collaborative dimensionality, and the reliability of the cloud service subscription can be improved.
It should be noted that, in an exemplary design concept, the above Process110 can be further implemented by the following embodiments:
analyzing a page interest point event of an authentication page node object corresponding to a candidate page display node, and determining page interest big data corresponding to the authentication page node object, wherein the page interest big data comprises at least two page interest point event logs, and each of the at least two page interest point event logs is generated through an event related to at least one interest point executed by the authentication page node object on an online service page;
and performing cloud service subscription verification on the authentication page node object and the candidate hot point cloud service by combining with a page interest point event log included in the page interest big data, and determining the subscription support degree of the basic cloud service corresponding to the candidate page display node.
It should be noted that, in an exemplary design idea, the above step of performing cloud service subscription verification on the authentication page node object and the candidate hot-point cloud service in combination with the page interest point event log included in the page interest big data, and determining the basic cloud service subscription support degree corresponding to the candidate page display node may be further implemented by the following embodiments:
for each page interest point event log included in the page interest big data, performing cloud service field matching analysis on the page interest point event log and the candidate hot spot cloud service, and determining the cloud service field matching degree corresponding to the page interest point event log;
for each page interest point event log included in the page interest big data, performing interest influence weight analysis on the page interest point event log by combining interest point connection characteristic data corresponding to the page interest point event log, determining a first interest influence weight corresponding to the page interest point event log (the first interest influence weight is larger when the connection frequency of the interest point connection characteristic data is larger), performing interest influence weight analysis on the page interest point event log by combining interest point continuous characteristic data corresponding to the page interest point event log, determining a second interest influence weight corresponding to the page interest point event log (the second interest influence weight is larger when the continuous parameter value of the interest point continuous characteristic data is larger), and performing interest influence weight analysis on the page interest point event log by combining the interest point event log with the corresponding interest point distribution number, determining a third interest influence weight corresponding to the page interest point event log (the interest point distribution number is larger, the third interest influence weight is larger), then performing interest influence weight analysis on the first interest point event log and the third interest point event log, and determining a third interest influence weight corresponding to the first interest point event log as an actual interest influence weight, and the second interest influence weight may be used as an actual influence weight, and an influence weight may be configured, and an actual influence weight corresponding target influence weight, for example, and an interest influence weight may be determined;
and performing weighted calculation on the matching degree of the cloud service field corresponding to each page interest point event log included in the page interest big data by combining the target interest influence weight corresponding to each page interest point event log (in other words, the target interest influence weight or a positive correlation coefficient of the target interest influence weight can be used as the influence weight to perform weighted calculation on the matching degree of the cloud service field), and determining the subscription support degree of the basic cloud service corresponding to the candidate page display node.
It should be noted that, in an exemplary design idea, the step of performing cloud service field matching analysis on the page interest point event log and the candidate hotspot cloud service for each page interest point event log included in the page interest big data, and determining the cloud service field matching degree corresponding to the page interest point event log may be further implemented by the following embodiments:
and generating a knowledge graph of the candidate hot point cloud service, and outputting a cloud service knowledge graph corresponding to the candidate hot point cloud service, wherein the cloud service knowledge graph comprises a plurality of cloud service knowledge entities.
The method comprises the steps of counting the number of hot spot elements of cloud service knowledge entities by combining with a target cloud service hot spot element library aiming at each cloud service knowledge entity included in the cloud service knowledge map, analyzing the attention heat of the cloud service knowledge entity by combining with the number of the hot spot elements corresponding to the cloud service knowledge entity, and determining the corresponding target attention heat (for example, the target attention heat can be positively correlated with the number of the hot spot elements).
And acquiring a cloud service knowledge entity with the maximum entity association degree between the cloud service knowledge map and the page interest knowledge entity by combining the target cloud service hotspot element library from the cloud service knowledge map, determining the cloud service knowledge entity as a matching cloud service knowledge entity corresponding to the page interest knowledge entity, and determining the entity association degree between the page interest knowledge entity and the matching cloud service knowledge entity as the target entity association degree corresponding to the page interest knowledge entity.
For each page interest point event log included in the page interest big data, combining the target attention heat corresponding to the matching cloud service knowledge entity corresponding to each page interest knowledge entity, performing a knowledge graph on the page interest point event log to generate a target entity association degree corresponding to a page interest knowledge graph, and performing weighted calculation (in other words, the target attention heat degree or a positive correlation coefficient of the target attention heat degree can be used as an influence weight to perform weighted calculation on the target entity association degree), and determining the cloud service field matching degree corresponding to the page interest point event log.
It should be noted that, in an exemplary design concept, the above Process120 can be further implemented by the following embodiments:
for each candidate page node object included in the candidate page node object cluster, performing page cooperation degree analysis on the candidate page node object and the authentication page node object, and determining the page cooperation degree corresponding to the candidate page node object, wherein each candidate page node object executes page cooperation events (such as page content sharing, forwarding, interaction and other events) between an online service page and the authentication page node object;
extracting at least one cooperative page node object corresponding to the authentication page node object from the candidate page node object cluster by combining the page cooperation degree corresponding to each candidate page node object;
and performing cloud service subscription verification on the collaborative page node object and the candidate hot point cloud service aiming at each collaborative page node object in the at least one collaborative page node object, determining the cloud service subscription support degree corresponding to the collaborative page node object, performing weighted calculation on the cloud service subscription support degree corresponding to each collaborative page node object in the at least one collaborative page node object, and determining the collaborative cloud service subscription support degree corresponding to the candidate page display node.
It should be noted that, in an exemplary design idea, the step of performing page cooperation degree analysis on the candidate page node object and the authentication page node object for each candidate page node object included in the candidate page node object cluster to determine the page cooperation degree corresponding to the candidate page node object may be further implemented by the following embodiments:
for each two candidate page node objects in a plurality of candidate page node objects included in a candidate page node object cluster, performing collaborative matching degree analysis on the two candidate page node objects by combining page collaborative event data clusters corresponding to the two candidate page node objects, and outputting collaborative matching degree between the two candidate page node objects, where the collaborative matching degree analysis is performed through three analysis dimensions, where the dimensions include a global interest point distribution number of page collaborative event data included in the page collaborative event data clusters, a first interest point distribution number of page collaborative event data having a cyclic flow characteristic included in the page collaborative event data clusters, and a second interest point distribution number of page collaborative event data having a frequent item characteristic included in the page collaborative event data clusters (the global interest point distribution number is positively correlated with the collaborative matching degree, the first interest point distribution number is positively correlated with the collaborative matching degree, and the second interest point distribution number is positively correlated with the collaborative matching degree);
taking each candidate page node object in the candidate page node object cluster as a logic analysis member, then combining the cooperative matching degree between every two candidate page node objects to configure a cooperative logic network, and outputting a target cooperative logic network corresponding to a plurality of candidate page node objects included in the candidate page node object cluster, where in the target cooperative logic network, whether a member association attribute exists between every two logic analysis members is determined by combining the cooperative matching degree between two candidate page node objects corresponding to the two logic analysis members (for example, when the cooperative matching degree is greater than a set cooperative matching degree, a member association attribute may exist).
And respectively analyzing the cooperative matching degree of the authentication page node object and each candidate page node object by combining the page cooperative event data clusters corresponding to the authentication page node object and each candidate page node object, and outputting the cooperative matching degree between the authentication page node object and each candidate page node object.
And loading the authentication page node object into the target collaborative logic network in combination with the collaborative matching degree between the authentication page node object and each candidate page node object, outputting the authentication page node object collaborative logic network corresponding to the target collaborative logic network, and judging whether member association attributes exist between the logic analysis member corresponding to the authentication page node object and the logic analysis member corresponding to the candidate page node object in the authentication page node object collaborative logic network in combination with the collaborative matching degree between the authentication page node object and the candidate page node object (the same as above).
For each second logic analysis member other than the first logic analysis member corresponding to the authentication page node object in the authentication page node object collaborative logic network (in other words, the authentication page node object collaborative logic network is composed of the first logic analysis member and each second logic analysis member), taking the second logic analysis member and the first logic analysis member as a start position and an end position, performing position walk of the logic analysis member on the authentication page node object collaborative logic network, and determining a minimum cost path including the second logic analysis member and the first logic analysis member, wherein in the minimum cost path, a member association attribute exists between two logic analysis members connected by a network.
For each second logic analysis member other than the first logic analysis member corresponding to the authentication page node object in the authentication page node object collaborative logic network, respectively taking a collaborative matching degree between each logic analysis member included in a minimum cost path corresponding to the second logic analysis member and the first logic analysis member with respect to the corresponding page node object as a feature parameter, outputting a collaborative feature parameter corresponding to the second logic analysis member (for example, each collaborative matching degree may be taken as a feature vector, so that a collaborative feature parameter may be formed by combining a plurality of corresponding feature vectors, an order between feature vectors in the collaborative feature parameter may be determined by combining an order of the corresponding logic analysis member in the minimum cost path), and then combining a feature distance between the collaborative feature parameter corresponding to the second logic analysis member and a collaborative feature parameter corresponding to each other second logic analysis member, obtaining a related second logic analysis member corresponding to the second logic analysis member from other second logic analysis members (for example, a feature distance corresponding to the related second logic analysis member may be minimum).
For each candidate page node object included in the candidate page node object cluster, combining the cooperative matching degree between the candidate page node object and the authentication page node object, and combining the cooperative matching degrees between other candidate page node objects corresponding to the second logic analysis members corresponding to the candidate page node object and the authentication page node object (for example, two cooperative matching degrees may be weighted to determine the page cooperation degree), and the weighted calculation outputs the page cooperation degree corresponding to the candidate page node object.
It should be noted that, in an exemplary design idea, the step of performing page cooperation degree analysis on the candidate page node object and the authentication page node object for each candidate page node object included in the candidate page node object cluster to determine the page cooperation degree corresponding to the candidate page node object may be further implemented by the following embodiments:
aiming at every two candidate page node objects in a plurality of candidate page node objects included in a candidate page node object cluster, combining the page collaborative event data clusters corresponding to the two candidate page node objects, performing collaborative matching degree analysis on the two candidate page node objects, and outputting the collaborative matching degree between the two candidate page node objects, wherein the collaborative matching degree analysis is performed through three analysis dimensions, and the three dimensions include the global interest point distribution quantity of page collaborative event data included in the page collaborative event data cluster, the first interest point distribution quantity of the page collaborative event data with the circular flow characteristic included in the page collaborative event data cluster, and the second interest point distribution quantity of the page collaborative event data with the frequent item characteristic included in the page collaborative event data cluster;
taking each candidate page node object in the candidate page node object cluster as a logic analysis member, then combining the cooperative matching degree between every two candidate page node objects to configure a cooperative logic network, and outputting a target cooperative logic network corresponding to a plurality of candidate page node objects included in the candidate page node object cluster, wherein in the target cooperative logic network, whether a member association attribute exists between every two logic analysis members or not is judged in combination with the cooperative matching degree between the two candidate page node objects corresponding to the two logic analysis members;
combining the page collaborative event data clusters corresponding to the authentication page node object and the candidate page node objects, respectively performing collaborative matching degree analysis on the authentication page node object and the candidate page node objects, and outputting collaborative matching degrees between the authentication page node object and the candidate page node objects;
loading the authentication page node object into the target collaborative logic network in combination with the collaborative matching degree between the authentication page node object and each candidate page node object, outputting the authentication page node object collaborative logic network corresponding to the target collaborative logic network, and judging whether member association attributes exist between the logical analysis member corresponding to the authentication page node object and the logical analysis member corresponding to the candidate page node object in the authentication page node object collaborative logic network or not in combination with the collaborative matching degree between the authentication page node object and the candidate page node object;
aiming at each second logic analysis member except for a first logic analysis member corresponding to the authentication page node object in the authentication page node object collaborative logic network, taking the second logic analysis member and the first logic analysis member as a start position and an end position, performing position walk of the logic analysis member on the authentication page node object collaborative logic network, and determining a walk path cluster corresponding to the second logic analysis member, wherein each walk path cluster comprises at least one walk path, and in each walk path, every two logic analysis members are different, and a member association attribute exists when the network communicates the two logic analysis members;
for each second logic analysis member except the first logic analysis member corresponding to the authentication page node object in the authentication page node object collaborative logic network, calculating the number of wandering units of each wandering path in the wandering path cluster corresponding to the second logic analysis member, determining the number of wandering units corresponding to each wandering path, calculating the degree of wandering association of each wandering path in the wandering path cluster corresponding to the second logic analysis member, and determining the degree of wandering association corresponding to each wandering path, where the degree of wandering association is determined by combining the degrees of collaborative matching between page node objects corresponding to every two adjacent logic analysis members in the corresponding wandering paths (for example, the mean value of the degrees of collaborative matching can be used as the degree of wandering association);
for each second logic analysis member other than the first logic analysis member corresponding to the authentication page node object in the authentication page node object collaborative logic network, extracting a walking feature vector of the second logic analysis member by combining the number of walking units and the walking association degree of each walking path in the walking path cluster corresponding to the second logic analysis member, and determining a walking feature vector corresponding to the second logic analysis member (for example, the number of walking units and the walking association degree of each walking path can be respectively used as a mapping coordinate point, outputting a plurality of mapping coordinate points, and performing operations such as curve fitting on the plurality of mapping coordinate points to determine a corresponding fitting curve which can be used as a corresponding walking feature vector), wherein the walking feature vector is used for reflecting a correlation relationship between the number of walking units and the walking association degree of each walking path in the corresponding walking path cluster (for example, the correlation relationship represents a fitting curve);
clustering the second logic analysis members by combining the wandering feature vectors corresponding to the second logic analysis members (in the clustering process, feature similarity can be calculated for the wandering feature vectors to perform clustering according to the corresponding feature similarity, wherein the feature similarity can refer to curve similarity between fitted curves, and the curve similarity can refer to the calculation mode about contour similarity and the like in the prior art), outputting at least one cluster, and mutually determining every two second logic analysis members belonging to the same cluster as corresponding associated second logic analysis members;
for each candidate page node object included in the candidate page node object cluster, combining the collaborative matching degree between the candidate page node object and the authentication page node object, and combining the collaborative matching degree between other candidate page node objects corresponding to each associated second logical analysis member corresponding to the candidate page node object and the authentication page node object, performing weighted calculation (for example, weighted fusion may be performed on each collaborative matching degree) to output the page collaborative degree corresponding to the candidate page node object.
It should be noted that, in an exemplary design idea, the step of extracting at least one collaborative page node object corresponding to the authenticated page node object from the candidate page node object cluster in combination with the page collaboration degree corresponding to each candidate page node object may be further implemented by the following embodiments:
comparing the page coordination degree corresponding to the candidate page node object with a set coordination degree aiming at each candidate page node object, and determining the candidate page node object as a coordination page node object corresponding to the authentication page node object when the page coordination degree is greater than the set coordination degree;
for each candidate page node object, when the page coordination degree corresponding to the candidate page node object is not greater than the set coordination degree and the page coordination degree corresponding to the candidate page node object is greater than the set coordination degree, determining the candidate page node object as a middle candidate page node object corresponding to the authentication page node object, wherein the set coordination degree is less than the set coordination degree;
respectively analyzing the page coordination degree of the intermediate candidate page node object and each determined cooperative page node object aiming at each intermediate candidate page node object, and determining the page coordination degree between the intermediate candidate page node object and each determined cooperative page node object;
for each intermediate candidate page node object, performing weighted calculation (for example, average calculation may be performed on the page cooperation degree) between the intermediate candidate page node object and each determined cooperation page node object in combination with the determined page cooperation degree between each cooperation page node object and each determined authentication page node object, determining a reference page cooperation degree corresponding to the intermediate candidate page node object, and then performing weighted fusion processing (for example, the reference page cooperation degree and the page cooperation degree may be performed with the reference page cooperation degree and the page cooperation degree between the intermediate candidate page node object and the authentication page node object, and determining the intermediate candidate page node object as a cooperation page node object when the output weighted fusion value is greater than a threshold value, which may be the set cooperation degree), discriminating the intermediate candidate page node object, so as to determine whether to determine the intermediate candidate page node object as the cooperation page node object corresponding to the authentication page node object.
It should be noted that, in an exemplary design idea, the foregoing step of performing, for each collaborative page node object in the at least one collaborative page node object, cloud service subscription verification on the collaborative page node object and the candidate hot point cloud service, determining a cloud service subscription support degree corresponding to the collaborative page node object, then performing weighted calculation on the cloud service subscription support degrees corresponding to each collaborative page node object in the at least one collaborative page node object, and determining a collaborative cloud service subscription support degree corresponding to the candidate page display node may be further implemented by the following embodiments:
analyzing a page interest point event of the collaborative page node object aiming at each collaborative page node object in the at least one collaborative page node object, and determining associated page interest big data corresponding to the collaborative page node object, wherein the associated page interest big data comprises at least two collaborative page interest point event logs;
for each collaborative page node object in the at least one collaborative page node object, performing cloud service subscription verification on the collaborative page node object and the candidate hot point cloud service by combining a collaborative page interest point event log included in the associated page interest big data corresponding to the collaborative page node object, and determining corresponding cloud service subscription support;
and performing weighted calculation on the cloud service subscription support corresponding to each collaborative page node object in combination with the influence weight corresponding to each collaborative page node object and having positive correlation with the page synergy corresponding to the collaborative page node object (in other words, the corresponding influence weight can be determined in combination with the page synergy, and then the weighted calculation is performed, wherein the influence weight and the page synergy are positively correlated), and determining the collaborative cloud service subscription support corresponding to the candidate page display node.
It should be noted that, in an exemplary design concept, the above Process130 can be further implemented by the following embodiments:
and performing weighted calculation on the basic cloud service subscription support degree and the collaborative cloud service subscription support degree, determining a target cloud service subscription support degree, comparing the target cloud service subscription support degree with a set support degree, and determining that the authentication page node object and the candidate hot point cloud service have a cloud service subscription confirmation relationship when the target cloud service subscription support degree is greater than the set support degree.
And when the authentication page node object and the candidate hot point cloud service are determined to have a cloud service subscription confirmation relationship, loading the candidate hot point cloud service to the candidate page display node, and operating the service content corresponding to the candidate hot point cloud service to the authentication page node object through the candidate page display node.
For some possible implementations, the cloud service push system 100 may include a processor 110, a machine-readable storage medium 120, a bus 130, and a communication unit 140.
The processor 110 may perform various appropriate actions and processes by a program stored in the machine-readable storage medium 120, such as program instructions related to the big data analysis method for cloud service push described in the foregoing embodiments. The processor 110, the machine-readable storage medium 120, and the communication unit 140 perform signal transmission through the bus 130.
In particular, the processes described in the above exemplary flow diagrams may be implemented as computer software programs, according to embodiments of the present invention. For example, embodiments of the invention include a computer program product comprising a computer program embodied on a computer-readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network via the communication unit 140, and when executed by the processor 110, performs the above-described functions defined in the methods of the embodiments of the present invention.
The invention further provides a computer-readable storage medium, in which computer-executable instructions are stored, and when the computer-executable instructions are executed by a processor, the computer-readable storage medium is used for implementing the big data analysis method for cloud service push as described in any one of the above embodiments.
Yet another embodiment of the present invention further provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the computer program implements the big data analysis method for cloud service push according to any one of the above embodiments.
The foregoing is only an optional implementation manner of a part of implementation scenarios in the present application, and it should be noted that, for those skilled in the art, other similar implementation means based on the technical idea of the present application are also within the protection scope of the embodiments of the present application without departing from the technical idea of the present application.
Claims (10)
1. A big data analysis method for cloud service push is characterized by comprising the following steps:
performing cloud service subscription verification on an authentication page node object and a candidate hot point cloud service corresponding to the candidate page display node, and determining a basic cloud service subscription support degree corresponding to the candidate page display node;
performing cloud service subscription verification on the collaborative page node object of the authentication page node object and the candidate hot point cloud service, and determining the collaborative cloud service subscription support degree corresponding to the candidate page display node;
and when the authentication page node object and the candidate hot point cloud service have a cloud service subscription confirmation relationship by combining the basic cloud service subscription support degree and the collaborative cloud service subscription support degree, loading the candidate hot point cloud service to the candidate page display node, and operating the service content corresponding to the candidate hot point cloud service through the candidate page display node.
2. The big data analysis method for cloud service push according to claim 1, wherein the cloud service subscription verification is performed on an authentication page node object and a candidate hot point cloud service corresponding to a candidate page display node, and a basic cloud service subscription support degree corresponding to the candidate page display node is determined, specifically including:
analyzing a page interest point event of an authentication page node object corresponding to a candidate page display node, and determining page interest big data corresponding to the authentication page node object, wherein the page interest big data comprises at least two page interest point event logs, and each of the at least two page interest point event logs is generated through an event related to at least one interest point executed by the authentication page node object on an online service page;
and performing cloud service subscription verification on the authentication page node object and the candidate hot point cloud service by combining with a page interest point event log included in the page interest big data, and determining the subscription support degree of the basic cloud service corresponding to the candidate page display node.
3. The big data analysis method for cloud service push according to claim 2, wherein the combining the page interest point event log included in the page interest big data, performing cloud service subscription verification on the authentication page node object and the candidate hot point cloud service, and determining a basic cloud service subscription support degree corresponding to the candidate page display node specifically includes:
performing cloud service field matching analysis on the page interest point event log and the candidate hotspot cloud service aiming at each page interest point event log included in the page interest big data, and determining the cloud service field matching degree corresponding to the page interest point event log;
aiming at each page interest point event log included in the page interest big data, performing interest influence weight analysis on the page interest point event log by combining the interest point linkage characteristic data corresponding to the page interest point event log, and determining a first interest influence weight corresponding to the page interest point event log;
performing interest influence weight analysis on the page interest point event log by combining the interest point continuous characteristic data corresponding to the page interest point event log, and determining a second interest influence weight corresponding to the page interest point event log;
analyzing interest influence weights of the page interest point event logs according to the interest point distribution number corresponding to the page interest point event logs, and determining third interest influence weights corresponding to the page interest point event logs;
performing weighted calculation on the first interest influence weight, the second interest influence weight and the third interest influence weight to determine corresponding target interest influence weights;
and performing weighted calculation on the matching degree of the cloud service field corresponding to each page interest point event log included in the page interest big data by combining the target interest influence weight corresponding to each page interest point event log, and determining the subscription support degree of the basic cloud service corresponding to the candidate page display node.
4. The big data analysis method for cloud service push according to claim 3, wherein for each page interest point event log included in the page interest big data, performing cloud service field matching analysis on the page interest point event log and the candidate hotspot cloud service, and determining a cloud service field matching degree corresponding to the page interest point event log specifically includes:
generating a knowledge graph of the candidate hot point cloud service, and outputting a cloud service knowledge graph corresponding to the candidate hot point cloud service, wherein the cloud service knowledge graph comprises a plurality of cloud service knowledge entities;
for each cloud service knowledge entity included in the cloud service knowledge graph, combining with a target cloud service hotspot element library, counting the number of hotspot elements of the cloud service knowledge entity, and then combining with the number of hotspot elements corresponding to the cloud service knowledge entity, performing attention heat analysis on the cloud service knowledge entity, and determining the corresponding target attention heat;
acquiring a cloud service knowledge entity with the maximum entity association degree between the page interest knowledge entities from the cloud service knowledge map by combining the page interest knowledge entities in the page interest knowledge map obtained by generating the knowledge map for each page interest point event log included in the page interest big data, and determining the cloud service knowledge entity as a matching cloud service knowledge entity corresponding to the page interest knowledge entity;
determining the entity association degree between the page interest knowledge entity and the matching cloud service knowledge entity as the target entity association degree corresponding to the page interest knowledge entity;
and aiming at each page interest point event log included in the page interest big data, combining the target attention heat corresponding to the matching cloud service knowledge entity corresponding to each page interest knowledge entity, performing weight calculation on the target entity association degree corresponding to the page interest point event log obtained by generating a knowledge graph of the page interest point event log, and determining the cloud service field matching degree corresponding to the page interest point event log.
5. The big data analysis method for cloud service push according to claim 1, wherein the performing cloud service subscription verification on the collaborative page node object of the authentication page node object and the candidate hot-point cloud service to determine the collaborative cloud service subscription support corresponding to the candidate page display node specifically comprises:
for each candidate page node object included in the candidate page node object cluster, performing page coordination degree analysis on the candidate page node object and the authentication page node object, and determining the page coordination degree corresponding to the candidate page node object, wherein each candidate page node object executes a page coordination event on an online service page and the authentication page node object;
extracting at least one cooperative page node object corresponding to the authentication page node object from the candidate page node object cluster by combining the page cooperation degree corresponding to each candidate page node object;
performing cloud service subscription verification on the collaborative page node object and the candidate hot point cloud service aiming at each collaborative page node object in the at least one collaborative page node object, and determining the cloud service subscription support degree corresponding to the collaborative page node object;
and performing weighted calculation on the cloud service subscription support degree corresponding to each collaborative page node object in the at least one collaborative page node object, and determining the collaborative cloud service subscription support degree corresponding to the candidate page display node.
6. The big data analysis method for cloud service push according to claim 5, wherein the analyzing the page cooperation degree of each candidate page node object included in the candidate page node object cluster for the candidate page node object and the authentication page node object, and determining the page cooperation degree corresponding to the candidate page node object specifically includes:
aiming at every two candidate page node objects in a plurality of candidate page node objects included in a candidate page node object cluster, combining page collaborative event data clusters corresponding to the two candidate page node objects, performing collaborative matching degree analysis on the two candidate page node objects, and outputting the collaborative matching degree between the two candidate page node objects, wherein the collaborative matching degree analysis is performed through three analysis dimensions, and the dimensions include the global interest point distribution quantity of page collaborative event data included in the page collaborative event data cluster, the first interest point distribution quantity of the page collaborative event data with a circular flow direction characteristic included in the page collaborative event data cluster, and the second interest point distribution quantity of the page collaborative event data with a frequent item characteristic included in the page collaborative event data cluster;
taking each candidate page node object in the candidate page node object cluster as a logic analysis member, then combining the cooperative matching degree between every two candidate page node objects to configure a cooperative logic network, and outputting a target cooperative logic network corresponding to a plurality of candidate page node objects included in the candidate page node object cluster, wherein in the target cooperative logic network, whether a member association attribute exists between every two logic analysis members or not is judged in combination with the cooperative matching degree between the two candidate page node objects corresponding to the two logic analysis members;
combining the page collaborative event data clusters corresponding to the authentication page node object and the candidate page node objects, respectively performing collaborative matching degree analysis on the authentication page node object and the candidate page node objects, and outputting collaborative matching degrees between the authentication page node object and the candidate page node objects;
loading the authentication page node object into the target collaborative logic network in combination with the collaborative matching degree between the authentication page node object and each candidate page node object, outputting the authentication page node object collaborative logic network corresponding to the target collaborative logic network, and judging whether member association attributes exist between the logic analysis member corresponding to the authentication page node object and the logic analysis member corresponding to the candidate page node object in the authentication page node object collaborative logic network in combination with the collaborative matching degree between the authentication page node object and the candidate page node object;
for each second logic analysis member except for the first logic analysis member corresponding to the authentication page node object in the authentication page node object collaborative logic network, taking the second logic analysis member and the first logic analysis member as a starting position and an ending position, performing position walk of the logic analysis member on the authentication page node object collaborative logic network, and determining a minimum cost path comprising the second logic analysis member and the first logic analysis member, wherein in the minimum cost path, a member association attribute exists when the network communicates the two logic analysis members;
for each second logic analysis member except for the first logic analysis member corresponding to the authentication page node object in the authentication page node object collaborative logic network, respectively taking the collaborative matching degree between each logic analysis member included in the minimum cost path corresponding to the second logic analysis member and the first logic analysis member about the corresponding page node object as a characteristic parameter, and outputting a collaborative characteristic parameter corresponding to the second logic analysis member;
combining the characteristic distance between the collaborative characteristic parameter corresponding to the second logic analysis member and the collaborative characteristic parameter corresponding to each other second logic analysis member, and acquiring a related second logic analysis member corresponding to the second logic analysis member from other second logic analysis members;
and for each candidate page node object included in the candidate page node object cluster, combining the cooperative matching degree between the candidate page node object and the authentication page node object, and combining the cooperative matching degree between other candidate page node objects corresponding to the second logic analysis member corresponding to the candidate page node object and the authentication page node object, and performing weighted calculation to output the page cooperative matching degree corresponding to the candidate page node object.
7. The big data analysis method for cloud service push according to claim 5, wherein said extracting, in combination with the page cooperation degree corresponding to each of the candidate page node objects, at least one cooperation page node object corresponding to the authentication page node object from the candidate page node object cluster specifically includes:
aiming at each candidate page node object, comparing the page coordination degree corresponding to the candidate page node object with the set coordination degree;
when the page cooperation degree is greater than the set cooperation degree, determining the candidate page node object as a cooperation page node object corresponding to the authentication page node object;
for each candidate page node object, when the page coordination degree corresponding to the candidate page node object is not greater than the set coordination degree and the page coordination degree corresponding to the candidate page node object is greater than the set coordination degree, determining the candidate page node object as a middle candidate page node object corresponding to the authentication page node object, wherein the set coordination degree is less than the set coordination degree;
for each intermediate candidate page node object, respectively performing page cooperation degree analysis on the intermediate candidate page node object and each determined cooperation page node object, and determining the page cooperation degree between the intermediate candidate page node object and each determined cooperation page node object;
and for each intermediate candidate page node object, performing weighted calculation on the page coordination degree between each determined coordination page node object and each determined authentication page node object in combination with the page coordination degree between each determined coordination page node object and each determined coordination page node object, determining a reference page coordination degree corresponding to the intermediate candidate page node object, and then judging the intermediate candidate page node object in combination with the reference page coordination degree and the page coordination degree between the intermediate candidate page node object and the authentication page node object to determine whether to determine the intermediate candidate page node object as the coordination page node object corresponding to the authentication page node object.
8. The big data analysis method for cloud service push according to claim 5, wherein the performing, for each of the at least one collaborative page node object, cloud service subscription verification on the collaborative page node object and the candidate hot point cloud service, determining a cloud service subscription support degree corresponding to the collaborative page node object, performing weighted calculation on the cloud service subscription support degree corresponding to each of the at least one collaborative page node object, and determining the collaborative cloud service subscription support degree corresponding to the candidate page display node specifically includes:
analyzing a page interest point event of the collaborative page node object aiming at each collaborative page node object in the at least one collaborative page node object, and determining associated page interest big data corresponding to the collaborative page node object, wherein the associated page interest big data comprises at least two collaborative page interest point event logs;
for each collaborative page node object in the at least one collaborative page node object, performing cloud service subscription verification on the collaborative page node object and the candidate hot point cloud service by combining a collaborative page interest point event log included in the associated page interest big data corresponding to the collaborative page node object, and determining corresponding cloud service subscription support;
and performing weighted calculation on the cloud service subscription support corresponding to each collaborative page node object by combining the influence weight of positive correlation between the page collaboration corresponding to each collaborative page node object and the page collaboration corresponding to the collaborative page node object, and determining the collaborative cloud service subscription support corresponding to the candidate page display node.
9. The big data analysis method for cloud service push according to any one of claims 1 to 8, wherein when it is determined that the authentication page node object and the candidate hot point cloud service have a cloud service subscription confirmation relationship in combination with the basic cloud service subscription support and the collaborative cloud service subscription support, the loading of the candidate hot point cloud service to the candidate page display node and the running of the service content corresponding to the candidate hot point cloud service by the candidate page display node specifically include:
performing weighted calculation on the basic cloud service subscription support degree and the collaborative cloud service subscription support degree, determining a target cloud service subscription support degree, and comparing the target cloud service subscription support degree with a set support degree;
when the subscription support degree of the target cloud service is greater than the set support degree, determining that the authentication page node object and the candidate hot point cloud service have a cloud service subscription confirmation relationship;
and when the authentication page node object and the candidate hot point cloud service are determined to have a cloud service subscription confirmation relationship, loading the candidate hot point cloud service to the candidate page display node, and operating the service content corresponding to the candidate hot point cloud service to the authentication page node object through the candidate page display node.
10. A cloud service push system, characterized in that the cloud service push system comprises a processor and a memory for storing a computer program capable of running on the processor, and the processor is configured to execute the big data analysis method for cloud service push according to any one of claims 1 to 9 when the computer program is run.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310218345.3A CN117033761A (en) | 2022-09-14 | 2022-09-14 | Big data analysis method and system for cloud service pushing and subscription verification |
| CN202211118058.7A CN115408616B (en) | 2022-09-14 | 2022-09-14 | Big data analysis method for cloud service pushing and cloud service pushing system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211118058.7A CN115408616B (en) | 2022-09-14 | 2022-09-14 | Big data analysis method for cloud service pushing and cloud service pushing system |
Related Child Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310218345.3A Division CN117033761A (en) | 2022-09-14 | 2022-09-14 | Big data analysis method and system for cloud service pushing and subscription verification |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115408616A true CN115408616A (en) | 2022-11-29 |
| CN115408616B CN115408616B (en) | 2023-05-26 |
Family
ID=84164930
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310218345.3A Pending CN117033761A (en) | 2022-09-14 | 2022-09-14 | Big data analysis method and system for cloud service pushing and subscription verification |
| CN202211118058.7A Active CN115408616B (en) | 2022-09-14 | 2022-09-14 | Big data analysis method for cloud service pushing and cloud service pushing system |
Family Applications Before (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310218345.3A Pending CN117033761A (en) | 2022-09-14 | 2022-09-14 | Big data analysis method and system for cloud service pushing and subscription verification |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN117033761A (en) |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20130029576A (en) * | 2011-09-15 | 2013-03-25 | 주식회사 케이티 | Method for serving health related information and poi information based on cloud and system therefor |
| CN105933940A (en) * | 2016-05-24 | 2016-09-07 | 安徽科技学院 | Seamless handover method based on collaborative base station clustering in ultra-dense network |
| US20200128047A1 (en) * | 2018-10-19 | 2020-04-23 | Oracle International Corporation | Autonomous monitoring of applications in a cloud environment |
| CN111931063A (en) * | 2020-08-28 | 2020-11-13 | 张坚伟 | Information push processing method based on block chain and artificial intelligence and cloud service platform |
| CN111931064A (en) * | 2020-08-28 | 2020-11-13 | 张坚伟 | Information analysis method based on big data and artificial intelligence and cloud service information platform |
| CN112732932A (en) * | 2021-01-08 | 2021-04-30 | 西安烽火软件科技有限公司 | User entity group recommendation method based on knowledge graph embedding |
| US20210160162A1 (en) * | 2019-11-27 | 2021-05-27 | Here Global B.V. | Method and apparatus for estimating cloud utilization and recommending instance type |
| CN112905937A (en) * | 2021-02-15 | 2021-06-04 | 戴亚明 | Service content updating and generating method based on big data and cloud computing service system |
| CN113360789A (en) * | 2021-05-31 | 2021-09-07 | 维沃移动通信有限公司 | Interest point data processing method and device, electronic equipment and storage medium |
| CN113360349A (en) * | 2021-07-28 | 2021-09-07 | 东莞市常学常玩教育科技有限公司 | Information optimization method based on big data and cloud service and artificial intelligence monitoring system |
| CN113868544A (en) * | 2021-12-03 | 2021-12-31 | 杭银消费金融股份有限公司 | Intelligent service file processing method and service server |
| CN114463072A (en) * | 2022-03-23 | 2022-05-10 | 李云 | E-business service optimization method based on business demand AI prediction and big data system |
| US20220233958A1 (en) * | 2020-06-17 | 2022-07-28 | Tencent Technology (Shenzhen) Company Limited | Information recommendation method and apparatus, and electronic device |
-
2022
- 2022-09-14 CN CN202310218345.3A patent/CN117033761A/en active Pending
- 2022-09-14 CN CN202211118058.7A patent/CN115408616B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20130029576A (en) * | 2011-09-15 | 2013-03-25 | 주식회사 케이티 | Method for serving health related information and poi information based on cloud and system therefor |
| CN105933940A (en) * | 2016-05-24 | 2016-09-07 | 安徽科技学院 | Seamless handover method based on collaborative base station clustering in ultra-dense network |
| US20200128047A1 (en) * | 2018-10-19 | 2020-04-23 | Oracle International Corporation | Autonomous monitoring of applications in a cloud environment |
| US20210160162A1 (en) * | 2019-11-27 | 2021-05-27 | Here Global B.V. | Method and apparatus for estimating cloud utilization and recommending instance type |
| US20220233958A1 (en) * | 2020-06-17 | 2022-07-28 | Tencent Technology (Shenzhen) Company Limited | Information recommendation method and apparatus, and electronic device |
| CN111931063A (en) * | 2020-08-28 | 2020-11-13 | 张坚伟 | Information push processing method based on block chain and artificial intelligence and cloud service platform |
| CN113392173A (en) * | 2020-08-28 | 2021-09-14 | 郭举 | Information push updating method and system based on block chain and cloud service information platform |
| CN111931064A (en) * | 2020-08-28 | 2020-11-13 | 张坚伟 | Information analysis method based on big data and artificial intelligence and cloud service information platform |
| CN112732932A (en) * | 2021-01-08 | 2021-04-30 | 西安烽火软件科技有限公司 | User entity group recommendation method based on knowledge graph embedding |
| CN112905937A (en) * | 2021-02-15 | 2021-06-04 | 戴亚明 | Service content updating and generating method based on big data and cloud computing service system |
| CN113360789A (en) * | 2021-05-31 | 2021-09-07 | 维沃移动通信有限公司 | Interest point data processing method and device, electronic equipment and storage medium |
| CN113360349A (en) * | 2021-07-28 | 2021-09-07 | 东莞市常学常玩教育科技有限公司 | Information optimization method based on big data and cloud service and artificial intelligence monitoring system |
| CN113868544A (en) * | 2021-12-03 | 2021-12-31 | 杭银消费金融股份有限公司 | Intelligent service file processing method and service server |
| CN114463072A (en) * | 2022-03-23 | 2022-05-10 | 李云 | E-business service optimization method based on business demand AI prediction and big data system |
Non-Patent Citations (2)
| Title |
|---|
| XIAOYUN YU等: "A Geographical Behavior-Based Point-of-Interest Recommendation", 《2019 IEEE 5TH INTL CONFERENCE ON BIG DATA SECURITY ON CLOUD (BIGDATASECURITY), IEEE INTL CONFERENCE ON HIGH PERFORMANCE AND SMART COMPUTING, (HPSC) AND IEEE INTL CONFERENCE ON INTELLIGENT DATA AND SECURITY (IDS)》 * |
| 未翠翠: "基于关联规则与用户兴趣模型的个性化云服务推荐算法", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115408616B (en) | 2023-05-26 |
| CN117033761A (en) | 2023-11-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10116536B2 (en) | Identifying multiple devices belonging to a single user | |
| CN115114531B (en) | Information pushing method based on electronic commerce big data and artificial intelligent prediction system | |
| CN111274495A (en) | Data processing method and device for user relationship strength, computer equipment and storage medium | |
| CN114155039A (en) | Information processing method and big data system based on E-commerce intention big data mining | |
| CN113422782A (en) | Cloud service vulnerability analysis method and artificial intelligence analysis system based on big data | |
| CN108681493A (en) | Data exception detection method, device, server and storage medium | |
| CN113407951A (en) | Cloud service vulnerability repairing method based on artificial intelligence and big data analysis system | |
| CN111488529A (en) | Information processing method, information processing apparatus, server, and storage medium | |
| CN114221991B (en) | Session recommendation feedback processing method based on big data and deep learning service system | |
| CN112084500A (en) | Method and device for clustering virus samples, electronic equipment and storage medium | |
| CN114969552A (en) | Big data mining method and AI prediction system for personalized information push service | |
| CN114581139A (en) | Content updating method based on big data intention mining and deep learning service system | |
| CN113468403A (en) | User information prediction method based on big data mining and cloud computing AI (Artificial Intelligence) service system | |
| CN115408616A (en) | Big data analysis method for cloud service push and cloud service push system | |
| CN115062227B (en) | User behavior activity analysis method adopting artificial intelligence analysis and big data system | |
| CN114049161B (en) | E-commerce big data feedback-based push optimization method and E-commerce big data system | |
| CN112069491A (en) | Terminal verification method and device based on virtual reality | |
| CN115878900A (en) | User online intention analysis method based on artificial intelligence and big data e-commerce platform | |
| CN114978765A (en) | Big data processing method serving information attack defense and AI attack defense system | |
| KR101909268B1 (en) | System for sharing profiling information based on rapi and method thereof | |
| CN114757721A (en) | Service prediction analysis method and AI (Artificial Intelligence) mining system for joint big data mining | |
| CN115455426A (en) | Business error analysis method based on vulnerability analysis model development and cloud AI system | |
| CN114239900A (en) | Optimal path selection method, device, equipment and readable storage medium | |
| CN114219516B (en) | Information flow session recommendation method based on big data and deep learning service system | |
| CN112488247A (en) | Information processing method combining live webcasting and online e-commerce delivery and cloud server |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20230504 Address after: 8th Floor, Taihua wutong Industrial Park, Sanwei Community, Hangcheng Street, Bao'an District, Shenzhen, Guangdong 518000 Applicant after: Shenzhen Zuolian Interactive Technology Co.,Ltd. Address before: No. 186, Fengxiang Road, Linxiang District, Lincang City, Yunnan Province 677000 Applicant before: He Rimei |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |