CN113392173A

CN113392173A - Information push updating method and system based on block chain and cloud service information platform

Info

Publication number: CN113392173A
Application number: CN202110596669.1A
Authority: CN
Inventors: 张坚伟
Original assignee: Individual
Current assignee: Qingdao Shengxin Conference Service Co ltd
Priority date: 2020-08-28
Filing date: 2020-08-28
Publication date: 2021-09-14
Also published as: CN113392174A; CN111931064B; CN111931064A

Abstract

The embodiment of the invention provides an information pushing and updating method and system based on a block chain and a cloud service information platform. Therefore, the information push updating mark of different information push subscription items in the interest text push process can be performed on the information push subscription terminal in a more targeted manner, the targeted control of using the information push subscription items as the information push updating mark objects is realized, and the push effect is improved.

Description

Information push updating method and system based on block chain and cloud service information platform

Technical Field

The invention relates to the technical field of information push processing, in particular to an information push updating method and system based on a block chain and a cloud service information platform.

Background

Currently, for each information push subscription item, in order to improve information security, an information push model is generally trained in a block chain in advance, in a service of a conventional information push index (that is, a content index policy corresponding to a word vector policy based on information push in an information push process), after relevant information push index content data is pushed, push policy optimization is generally performed based on a feedback large data operation condition, however, in a conventional design, under the condition that data content is complex, especially noise data is more, pertinence and accuracy in a subsequent interest push index policy update process are difficult to guarantee, so that accuracy of index push content is not high.

Disclosure of Invention

In order to overcome at least the above disadvantages in the prior art, an object of the present invention is to provide an information push update method, system and cloud service information platform based on a block chain, in the push process of information push index content data, consideration is added to operation metadata of a field name association structure or a keyword association structure, so as to reflect operation node information of field names and keywords associated according to a logical relationship in each knowledge mining element of user operation behavior big data, and further, after screening of the knowledge mining elements, knowledge graph mining is performed, so that the pertinence and accuracy of a subsequent interest push index policy update process can be improved under the condition of complex data content, especially more noise data, and the accuracy of index push content is improved.

In a first aspect, an embodiment of the present invention provides an information analysis method based on big data and artificial intelligence, which is applied to a cloud service information platform, where the cloud service information platform is in communication connection with a plurality of information push subscription terminals and in communication connection with a block chain service terminal for performing information push control at each information push subscription terminal, and the method includes:

extracting operation metadata of a field name association structure or a keyword association structure in user operation behavior big data aiming at information push index content data uploaded by each information push subscription terminal, and calculating a first knowledge mining element sequence corresponding to the operation metadata of the field name association structure or the keyword association structure in the user operation behavior big data, wherein the operation metadata of the field name association structure or the keyword association structure is used for representing operation node information of field names and keywords associated according to a logical relation in each knowledge mining element of the user operation behavior big data;

acquiring preset public opinion push statistical characteristics of public opinion hotspot objects corresponding to the user operation behavior big data, and calculating content matching information between operation metadata of the field name association structure or the keyword association structure and the preset public opinion push statistical characteristics according to the first knowledge mining element sequence;

extracting a corresponding second knowledge mining element sequence from the first knowledge mining element sequence according to content matching information between the operation metadata of the field name association structure or the keyword association structure and the preset public opinion push statistical characteristics;

and determining knowledge graph mining data of each target knowledge mining element of the second knowledge mining element sequence based on the user operation behavior big data, extracting a corresponding operation heat trend graph from the knowledge graph mining data of each target knowledge mining element according to the operation metadata of the field name association structure or the keyword association structure, and updating an information pushing strategy which is trained by the block chain service terminal and stored in the block chain based on the operation heat trend graph.

In a second aspect, an embodiment of the present invention further provides an information analysis device based on big data and artificial intelligence, which is applied to a cloud service information platform, where the cloud service information platform is in communication connection with a plurality of information push subscription terminals, and is in communication connection with a block chain service terminal for performing information push control on each information push subscription terminal, and the device includes:

the first extraction module is used for extracting operation metadata of a field name association structure or a keyword association structure in user operation behavior big data aiming at information push index content data uploaded by each information push subscription terminal, and calculating a first knowledge mining element sequence corresponding to the operation metadata of the field name association structure or the keyword association structure in the user operation behavior big data, wherein the operation metadata of the field name association structure or the keyword association structure is used for representing operation node information of field names and keywords associated according to a logical relation in each knowledge mining element of the user operation behavior big data;

the calculation module is used for acquiring preset public opinion push statistical characteristics of public opinion hotspot objects corresponding to the user operation behavior big data, and calculating content matching information between the operation metadata of the field name association structure or the keyword association structure and the preset public opinion push statistical characteristics according to the first knowledge mining element sequence;

the second extraction module is used for extracting a corresponding second knowledge mining element sequence from the first knowledge mining element sequence according to content matching information between the operation metadata of the field name association structure or the keyword association structure and the preset public opinion push statistical characteristics;

and the third extraction module is used for determining knowledge graph mining data of each target knowledge mining element of the second knowledge mining element sequence based on the user operation behavior big data, extracting a corresponding operation heat trend graph from the knowledge graph mining data of each target knowledge mining element according to the operation metadata of the field name association structure or the keyword association structure, and updating an information pushing strategy which is trained by the block chain service terminal and stored in the block chain based on the operation heat trend graph.

In a third aspect, an embodiment of the present invention further provides an information analysis system based on big data and artificial intelligence, where the information analysis system based on big data and artificial intelligence includes a cloud service information platform and a plurality of information push subscription terminals in communication connection with the cloud service information platform, and the cloud service information platform is further in communication connection with a block chain service terminal for performing information push control on each information push subscription terminal;

the cloud service information platform is used for extracting operation metadata of a field name association structure or a keyword association structure in user operation behavior big data aiming at information push index content data uploaded by each information push subscription terminal, calculating a first knowledge mining element sequence corresponding to the operation metadata of the field name association structure or the keyword association structure in the user operation behavior big data, and the operation metadata of the field name association structure or the keyword association structure is used for representing operation node information of field names and keywords associated according to a logical relation in each knowledge mining element of the user operation behavior big data;

the cloud service information platform is used for acquiring preset public opinion push statistical characteristics of public opinion hotspot objects corresponding to the user operation behavior big data, and calculating content matching information between operation metadata of the field name association structure or the keyword association structure and the preset public opinion push statistical characteristics according to the first knowledge mining element sequence;

the cloud service information platform is used for extracting a corresponding second knowledge mining element sequence from the first knowledge mining element sequence according to content matching information between the operation metadata of the field name association structure or the keyword association structure and the preset public opinion push statistical characteristics;

the cloud service information platform is used for determining knowledge graph mining data of each target knowledge mining element of the second knowledge mining element sequence based on the user operation behavior big data, extracting a corresponding operation heat trend graph from the knowledge graph mining data of each target knowledge mining element according to operation metadata of the field name association structure or the keyword association structure, and updating an information pushing strategy which is trained by the block chain service terminal and stored in the block chain based on the operation heat trend graph.

In a fourth aspect, an embodiment of the present invention further provides a cloud service information platform, where the cloud service information platform includes a processor, a machine-readable storage medium, and a network interface, where the machine-readable storage medium, the network interface, and the processor are connected through a bus system, the network interface is used for being communicatively connected with at least one information push subscription terminal, the machine-readable storage medium is used for storing a program, an instruction, or a code, and the processor is used for executing the program, the instruction, or the code in the machine-readable storage medium to execute the big data and artificial intelligence based information parsing method in any one possible design of the first aspect or the first aspect.

In a fifth aspect, an embodiment of the present invention provides a computer-readable storage medium, where instructions are stored, and when executed, cause a computer to perform the big data and artificial intelligence based information parsing method in the first aspect or any one of the possible designs of the first aspect.

Based on any one of the aspects, in the process of pushing the information push index content data, the consideration of the operation metadata of the field name association structure or the keyword association structure is added, so that the operation node information of the field names and the keywords which are associated according to the logical relation and exist in each knowledge mining element of the user operation behavior big data can be reflected, the knowledge graph mining is further performed after the knowledge mining elements are screened, the pertinence and the accuracy of the subsequent interest push index strategy updating process can be improved under the condition that the data content is complex, particularly the noise data is more, and the accuracy of the index push content is improved.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.

Fig. 1 is a schematic view of an application scenario of an information analysis system based on big data and artificial intelligence according to an embodiment of the present invention;

FIG. 2 is a schematic flow chart of an information parsing method based on big data and artificial intelligence according to an embodiment of the present invention;

FIG. 3 is a schematic diagram of functional modules of an information analysis apparatus based on big data and artificial intelligence according to an embodiment of the present invention;

fig. 4 is a schematic block diagram of a server for implementing the above-described big data and artificial intelligence based information parsing method according to an embodiment of the present invention.

Detailed Description

The present invention is described in detail below with reference to the drawings, and the detailed operation method in the following method embodiments can also be applied to the device embodiments or the system embodiments.

FIG. 1 is an interaction diagram of an information parsing system 10 based on big data and artificial intelligence according to an embodiment of the present invention. The big data and artificial intelligence based information parsing system 10 may include a cloud service information platform 100, a plurality of information push subscribing terminals 200 (only two shown in fig. 1) communicatively connected to the cloud service information platform 100, and the cloud service information platform 100 is further communicatively connected to a block chain service terminal 300 (only two shown in fig. 1) for performing information push control on each information push subscribing terminal 200. The big data and artificial intelligence based information parsing system 10 shown in FIG. 1 is only one possible example, and in other possible embodiments, the big data and artificial intelligence based information parsing system 10 may also include only some of the components shown in FIG. 1 or may also include other components.

In this embodiment, the information push subscription terminal 200 may be configured to provide an interest text push process of the blockchain service terminal 300 and a related information sharing terminal in a certain area range, so as to facilitate implementation of management of the information sharing terminals at an area level.

In this embodiment, the blockchain service terminal 300 may include a mobile device, a tablet computer, a laptop computer, etc., or any combination thereof. In some embodiments, the mobile device may include a smart home device, a wearable device, a smart mobile device, a virtual reality device, an augmented reality device, or the like, or any combination thereof. In some embodiments, the smart home devices may include control devices of smart electrical devices, smart monitoring devices, smart televisions, smart cameras, and the like, or any combination thereof. In some embodiments, the wearable device may include a smart bracelet, a smart lace, smart glass, a smart helmet, a smart watch, a smart garment, a smart backpack, a smart accessory, or the like, or any combination thereof. In some embodiments, the smart mobile device may include a smartphone, a personal digital assistant, a gaming device, and the like, or any combination thereof. In some embodiments, the virtual reality device and/or the augmented reality device may include a virtual reality helmet, virtual reality glass, a virtual reality patch, an augmented reality helmet, augmented reality glass, an augmented reality patch, or the like, or any combination thereof. For example, the virtual reality device and/or augmented reality device may include various virtual reality products and the like.

In this embodiment, the cloud service information platform 100, the information push subscriber terminal 200, and the blockchain service terminal 300 in the big data and artificial intelligence based information analysis system 10 may cooperatively perform the big data and artificial intelligence based information analysis method described in the following method embodiment, and the detailed description of the following method embodiment may be referred to for the specific steps of the cloud service information platform 100, the information push subscriber terminal 200, and the blockchain service terminal 300.

Based on the inventive concept of the technical solution provided by the present application, the cloud service information platform 100 provided by the present application can be applied to scenes such as smart medical care, smart city management, smart industrial internet, general service monitoring management, and the like, in which a big data technology or a cloud computing technology can be applied, and for example, the cloud service information platform can also be applied to scenes such as but not limited to new energy automobile system management, smart cloud office, cloud platform data processing, cloud game data processing, cloud live broadcast processing, cloud automobile management platform, block chain financial data service platform, and the like, but is not limited thereto.

In order to solve the technical problem in the foregoing background art, fig. 2 is a schematic flow chart of an information analysis method based on big data and artificial intelligence according to an embodiment of the present invention, where the information analysis method based on big data and artificial intelligence according to the present embodiment may be executed by the cloud service information platform 100 shown in fig. 1, and the information analysis method based on big data and artificial intelligence is described in detail below.

Step S110, extracting operation metadata of a field name association structure or a keyword association structure in the user operation behavior big data for the information push index content data uploaded by each information push subscriber terminal 200, and calculating a first knowledge mining element sequence corresponding to the operation metadata of the field name association structure or the keyword association structure in the user operation behavior big data.

Step S120, acquiring a preset public sentiment pushing statistical characteristic of a public sentiment hotspot object corresponding to the user operation behavior big data, and calculating content matching information between operation metadata of a field name association structure or a keyword association structure and the preset public sentiment pushing statistical characteristic according to the first knowledge mining element sequence.

Step S130, extracting a corresponding second knowledge mining element sequence from the first knowledge mining element sequence according to content matching information between the operation metadata of the field name association structure or the keyword association structure and the preset public opinion push statistical feature.

Step S140, determining knowledge graph mining data of each target knowledge mining element of the second knowledge mining element sequence based on the user operation behavior big data, and extracting a corresponding operation heat trend graph from the knowledge graph mining data of each target knowledge mining element according to the operation metadata of the field name association structure or the keyword association structure, so as to update the information push policy stored in the block chain trained by the block chain service terminal 300 based on the operation heat trend graph.

In this embodiment, the operation metadata of the field name association structure or the keyword association structure may be specifically used to represent the field names and the operation node information of the keywords associated according to the logical relationship in each knowledge mining element of the user operation behavior big data. The field names may refer to identification field information corresponding to different application program services, the keywords may refer to word information of information push items corresponding to different application program services, and the operation node information may refer to a node set formed by all operation records of users of the field names and the keywords associated according to a logical relationship in each knowledge mining element.

In this embodiment, the knowledge mining element may refer to a business item having a knowledge mining value, for example, the aforementioned operation node information may reflect an interest attraction situation for each user, so that some rules may be set for screening to determine the knowledge mining element.

In this embodiment, in the process of updating the information push policy stored in the blockchain and trained by the blockchain service terminal 300 based on the operation heat trend map, for example, the business elements formed by map units whose operation heat trends in the operation heat trend map satisfy the preset trend rule may be increased by the preset weight in the information push policy stored in the blockchain and trained by the blockchain service terminal 300, or the preset weight may be decreased by the preset weight.

Based on the design, in the pushing process of the information pushing index content data, the consideration of the operation metadata of the field name association structure or the keyword association structure is added, so that the operation node information of the field names and the keywords which are associated according to the logical relation and exist in each knowledge mining element of the user operation behavior big data can be reflected, and then the knowledge graph mining is carried out after the knowledge mining elements are screened, so that the pertinence and the accuracy of the subsequent interest pushing index strategy updating process can be improved under the condition that the data content is complex, particularly the noise data is more, and the accuracy of the index pushing content is improved.

In a possible implementation manner, for step S110, in the process of extracting operation metadata of a field name association structure or a keyword association structure in the user operation behavior big data for the information push index content data uploaded by each information push subscriber terminal 200, and calculating a first knowledge mining element sequence corresponding to the operation metadata of the field name association structure or the keyword association structure in the user operation behavior big data, the following exemplary sub-steps may be implemented, which are described in detail as follows.

And a substep S111, performing rule tree matching on the big data of the user operation behaviors to obtain rule tree matching characteristics.

For example, the rule tree matching features are used for representing a rule tree node vector corresponding to each knowledge mining element in the user operation behavior big data.

And a substep S112, performing information elimination processing of preset invalid features on the rule tree matching features to obtain first target rule tree matching features, obtaining similar rule tree nodes of all rule tree node vectors in the first target rule tree matching features, and screening out the rule tree node vectors of which the number of the similar rule tree nodes is greater than the set node number from the first target rule tree matching features according to the similar rule tree nodes of all rule tree node vectors to obtain second target rule tree matching features.

And a substep S113, performing normalized template feature extraction on the second target rule tree matching features to obtain a first normalized template feature set, and filtering the rule tree node vectors with feature length larger than a set value in the first normalized template feature set to obtain a first screening rule tree node vector sequence.

And a substep S114, performing mapping comparison on the first normalized template characteristic set according to the first screening rule tree node vector sequence, and determining all time dimensions and all carrier index components of all space dimensions of normalized template characteristic dimensions of the second target rule tree matching characteristics.

For example, the time dimension and the space dimension are dimensions of the rule tree node vector on inverse quantization indexes in the pre-constructed content matching rule, and the quantization indexes are used for representing quantization parameters of the content statistical characteristics.

And a substep S115, determining operation metadata of the field name association structure or the keyword association structure according to all time dimensions and carrier index components of all space dimensions of the characteristic dimensions of the normalized template of the second target rule tree matching characteristics, and determining a first knowledge mining element sequence corresponding to the operation metadata of the field name association structure or the keyword association structure in the user operation behavior big data.

Exemplarily, in the sub-step S115, it may be further implemented by the following exemplary embodiments, which are described in detail as follows.

(1) And respectively obtaining a first time dimension carrier index component group and a first space dimension carrier index component group according to all time dimensions and all space dimensions of the characteristic dimensions of the normalized template of the second target rule tree matching characteristics.

(2) And extracting all normalized template associated objects of the normalized template characteristic dimension according to the first time dimension carrier index component group and the first space dimension carrier index component group.

(3) And performing non-normalized template feature extraction on the second target rule tree matching features to obtain a second normalized template feature set, and filtering the rule tree node vectors with the feature length of the second normalized template feature set larger than a set value to obtain a second screening rule tree node vector sequence.

(4) And mapping and comparing the second normalized template characteristic set according to the second screening rule tree node vector sequence, and determining all time dimensions and all carrier index components of all space dimensions of the non-normalized template characteristic dimensions of the second target rule tree matching characteristics.

For example, the time dimension and the space dimension are directions of the regular tree node vectors on opposite quantization indexes in the pre-constructed content matching rule, and the quantization indexes are used for representing quantization parameters of the content statistical characteristics.

(5) And respectively obtaining a second time dimension carrier index component group and a second space dimension carrier index component group according to all time dimensions and all space dimensions of the non-normalized template feature dimensions of the second target rule tree matching features.

(6) And extracting all non-normalized template associated objects of the non-normalized template characteristic dimension according to the second time dimension carrier index component group and the second space dimension carrier index component group.

(7) And determining all associated nodes according to the normalized template associated object and the unnormalized template associated object, and determining a unit knowledge mining element set, an element mining number set and an element frequent statistics degree set of all similar rule tree nodes on each associated node.

(8) And when the maximum value of the ratio of the median to the average and the ratio of the average to the median of the unit knowledge mining element set, the element mining quantity set and the element frequent statistics degree set is determined to be smaller than a set value, determining the similar rule tree node as the undetermined node of the candidate similar rule tree node.

(9) And for each similar rule tree node in one associated node, determining the characteristic fragment position of the non-normalized template characteristics among the similar rule tree nodes associated with the non-normalized template characteristics in the similar rule tree node, and determining the characteristic fragment position of the non-normalized template characteristics of each candidate similar rule tree node according to the characteristic fragment position.

(10) And determining the operation metadata of the field name association structure or the keyword association structure according to the characteristic fragment position of the non-normalized template characteristic of each candidate similar rule tree node.

(11) And determining a first knowledge mining element sequence corresponding to the operation metadata of the field name association structure or the keyword association structure in the user operation behavior big data.

In a possible implementation manner, for step S120, in the process of obtaining a preset public opinion push statistical feature of a public opinion hotspot object corresponding to the big data of the user operation behavior, and calculating content matching information between the operation metadata of the field name association structure or the keyword association structure and the preset public opinion push statistical feature according to the first knowledge mining element sequence, the following exemplary sub-steps may be implemented, which are described in detail as follows.

And a substep S121, obtaining a public opinion hotspot tag of a public opinion hotspot object corresponding to the user operation behavior big data.

And a substep S122 of obtaining a preset public opinion push statistical characteristic containing the public opinion hotspot object from a preset public opinion hotspot object characteristic database according to the public opinion hotspot tag.

For example, the preset public opinion hotspot object feature database includes a corresponding relationship between a public opinion hotspot tag and a preset public opinion push statistical feature, and the preset public opinion push statistical feature is used for representing a public opinion popularity update condition in a statistical process of the public opinion hotspot object and adaptively changes along with the change of the public opinion hotspot object.

Substep S123, obtaining the traversal knowledge mining element containing the current public opinion hotspot object according to the first knowledge mining element sequence, determining a reference search intention characteristic which takes a preset public opinion pushing statistical characteristic as a reference characteristic according to a traversal knowledge mining element, sequentially dividing the traversal knowledge mining element into a plurality of candidate search intention characteristics corresponding to the reference search intention characteristic by taking operation metadata of a field name association structure or a keyword association structure as a reference, comparing each candidate search intention characteristic with the reference search intention characteristic respectively to obtain a corresponding intention matching value range, when the intention matching value range does not meet the set reference value range, recording the candidate search intention characteristic corresponding to the intention matching value range as a first search intention characteristic, recording the reference search intention characteristic as a second search intention characteristic, to obtain at least one search intention feature combination formed by the first search intention feature and the second search intention feature.

And a substep S124 of calculating content matching information between the operation metadata of the field name association structure or the keyword association structure and the preset public opinion push statistic feature based on a search intention feature combination formed of at least one first search intention feature and a second search intention feature.

Exemplarily, in the sub-step S124, the method may be further implemented by the following exemplary embodiments, which are described in detail as follows.

(1) And determining a corresponding first object unit based on at least one search intention feature combination, and dividing the traversal knowledge mining elements according to the set unit quantity and size by taking the first object unit as a reference to respectively obtain a plurality of second object units containing the first object unit, wherein the second object units correspond to each unit quantity and size.

(2) And analyzing the second object unit to obtain the feature information of each search intention feature combination in the second object unit, determining the candidate magnitude and the corresponding feature value of the search intention feature combination according to the feature information of the search intention feature combination, and determining the first search intention feature sequence according to the candidate magnitude and the corresponding feature value of the search intention feature combination.

(3) And determining a linear intention classification cluster formed by the search intention feature combination meeting the set conditions based on the first search intention feature sequence, the candidate magnitude of the search intention feature combination and the corresponding feature value, determining one of a first linear intention classification cluster and a second linear intention classification cluster of each object unit, and screening each object unit according to one of the first linear intention classification cluster and the second linear intention classification cluster to obtain a screened object unit corresponding to each object unit.

(4) And obtaining the other one of the first linear intention classification cluster and the second linear intention classification cluster based on the screened object unit corresponding to each object unit.

(5) And obtaining a first linear intention classification cluster set according to the first linear intention classification clusters respectively corresponding to the object units, and obtaining a second linear intention classification cluster set according to the second linear intention classification clusters respectively corresponding to the object units.

(6) And determining a first reference linear intention classification cluster corresponding to the first linear intention classification cluster set and a second reference linear intention classification cluster corresponding to the second linear intention classification cluster set, and respectively determining a first cluster node to be matched corresponding to the first linear intention classification cluster set and a second cluster node to be matched corresponding to the second linear intention classification cluster set based on the first linear intention classification cluster set and the first reference linear intention classification cluster and the second linear intention classification cluster set and the second reference linear intention classification cluster.

(7) And comparing a first cluster node to be matched of the first linear intention classification cluster set with a second cluster node to be matched corresponding to the second linear intention classification cluster set to obtain content matching information between operation metadata of a field name association structure or a keyword association structure and the preset public opinion push statistical characteristics.

In one possible implementation manner, for step S130, in the process of extracting the corresponding second knowledge mining element sequence from the first knowledge mining element sequence according to the content matching information between the operation metadata of the field name association structure or the keyword association structure and the preset public opinion push statistical feature, the following exemplary sub-steps may be implemented, which are described in detail below.

And a substep S131 of determining that the knowledge mining element matched with the content matching information exists in the first knowledge mining element sequence according to the content matching information between the operation metadata of the field name association structure or the keyword association structure and the preset public opinion push statistical characteristic.

And a substep S132 of extracting a corresponding second knowledge mining element sequence from the first knowledge mining element sequence according to the knowledge mining elements matched with the content matching information.

In one possible implementation manner, for step S130, in the process of extracting the corresponding operation heat trend graph from the knowledge graph mining data of each target knowledge mining element according to the operation metadata of the field name association structure or the keyword association structure, the following exemplary sub-steps may be implemented, which are described in detail below.

And a substep S131 of screening out a plurality of candidate operation heat degree trend graphs and a plurality of matching degrees corresponding to the candidate operation heat degree trend graphs from the knowledge graph mining data of each target knowledge mining element, wherein the matching degree between the candidate operation heat degree trend graphs and the operation metadata of the field name associated structure or the keyword associated structure is greater than the set matching degree.

And a substep S132 of selecting at least one candidate map unit from the plurality of candidate operation heat degree trend maps according to the matching degree to form a candidate map unit group, and determining the operation heat degree index of each candidate map unit according to the association degree of each candidate map unit in the candidate map unit group and each data area in the knowledge map mining data.

The substep S133 determines a matching degree difference value of a difference between a matching degree corresponding to each of the plurality of candidate operation heat degree trend maps and a preset matching degree, and generates a candidate operation heat degree trend parameter based on a product of a level of the matching degree difference value and the operation heat degree index.

For example, the level of the matching degree difference is obtained by a mapping relationship between the pre-configured matching degree difference and the level.

And a substep S134 of generating an operation heat trend map corresponding to the knowledge map mining data of each target knowledge mining element based on the candidate operation heat trend parameters.

Further, in a possible implementation manner, before the step S110, the following steps may also be included.

Step S101, pushing information push index content data to each information push subscription terminal 200 according to the information push model trained in the block chain of each information push subscription item.

Exemplarily, the present step S101 may be realized by the following sub-steps.

In sub-step S1011, an information push update mark is performed on a push word vector sequence in an interest text push process established between the information push subscription terminal 200 and the corresponding block chain service terminal 300 through the information push model trained in the block chain of each information push subscription item.

In the sub-step S1012, a first templated control service node and a second templated control service node in the browsing templated control currently displayed by the information push subscriber terminal 200 for information browsing in the information push update tagging process are determined.

And a substep S1013, in the interest text pushing process, determining a third templated control service node corresponding to the first templated control service node and matching with the information pushing subscription item, and a fourth templated control service node corresponding to the second templated control service node and matching with the information pushing subscription item.

And a substep S1014 of determining the associated interest coverage service information in the interest text pushing process according to the first templated control service node, the second templated control service node, the third templated control service node, the fourth templated control service node and the browsing structured display strategy, and updating the interest pushing index strategy of the information pushing model according to the associated interest coverage service information in the interest text pushing process.

In this embodiment, the browsing templatized control may be a templatized browsing control corresponding to a browsing structured display policy preset in the interest text pushing process, and the browsing structured display policy may be understood as a display policy of a pushing special-effect browsing service subscribed in the information pushing process.

In this embodiment, each templated control service node may be configured to represent a service set formed by a plurality of template selection items in an information pushing indexing process, which is not limited in detail herein.

Based on the steps, in the interest text pushing process, by determining a third templated control service node corresponding to the first templated control service node and matched with the information pushing subscription item, and a fourth templated control service node corresponding to the second templated control service node and matched with the information pushing subscription item, the associated interest coverage service information in the interest text pushing process is determined according to the first templated control service node, the second templated control service node, the third templated control service node, the fourth templated control service node and the browsing structural display strategy, and the interest pushing index strategy of the information pushing model is updated accordingly. Therefore, the interest push index strategy of the current information push model can be updated based on the templated control service node with the incidence relation, so that the process of adaptively adjusting the interest push index in the next information push control process can be facilitated, and the information push accuracy is further improved.

In one possible implementation, for example, for the sub-step S1014, in the process of determining the associated interest coverage service information in the interest text pushing process according to the first templated control service node, the second templated control service node, the third templated control service node, the fourth templated control service node and the browsing structured presentation policy, the following exemplary sub-steps can be implemented, which are described in detail below.

(1) And determining the associated interest coverage service detection information in the interest text pushing process according to the first templated control service node, the second templated control service node, the third templated control service node, the fourth templated control service node and the browsing templated control.

As one possible example, the browsing templated control may include browsing a structured presentation policy, and the associated interest coverage service detection information may include associated interest coverage service information.

For example, the templated widget service node update may be performed on the browsing templated widget according to a first service push association between the first templated widget service node and the second templated widget service node, and a second service push association between the third templated widget service node and the fourth templated widget service node, such that the first service push association matches the second service push association.

Then, the associated interest coverage service detection information in the interest text pushing process can be determined according to the updated browsing templated control of the templated control service node, the third templated control service node and the fourth templated control service node.

In a possible design, the related interest coverage service detection information in the interest text pushing process can be calculated according to information pushing index update information corresponding to the first templated control service node and the second templated control service node in the browsing templated control after the templated control service node is updated, a browsing structured display strategy in the browsing templated control after the templated control service node is updated, behavior context service logic of the browsing templated control after the templated control service node is updated, and a third templated control service node and a fourth templated control service node.

For another example, in another possible design, the updated browsing templated control of the templated control service node may be updated in the interest text pushing process, so that the point-of-interest object of the first templated control service node in the updated browsing templated control of the templated control service node coincides with the point-of-interest object corresponding to the third templated control service node, and the point-of-interest object of the second templated control service node in the updated browsing templated control of the templated control service node coincides with the point-of-interest object corresponding to the fourth templated control service node, and the associated interest coverage service detection information in the interest text pushing process is determined according to the update information of the point-of-interest object.

In a possible implementation manner, for example, for step S1012, in the process of determining the first templated control service node and the second templated control service node in the browsing templated control currently performing information browsing display by the information push subscriber terminal 200 in the information push updating marking process, it may be determined that the first templated control service node and the second templated control service node having a collaborative information push index relationship or the first templated control service node and the second templated control service node having an information push index timing context relationship exist in the browsing templated control currently performing information browsing display by the information push subscriber terminal 200 in the information push updating marking process.

It should be noted that the coordination information pushing index relationship is used to indicate that a coordination common information pushing index relationship exists, and the information pushing index timing context is used to indicate that an information pushing index timing context exists.

In one possible implementation manner, for example, for step S1012, in the interest text pushing process, a third templated widget service node corresponding to the first templated widget service node and matching with the information pushing subscription item is determined, and a fourth templated widget service node corresponding to the second templated widget service node and matching the information push subscription item, for example, a third templated widget service node of an information push index tag type matching the information push subscription item corresponding to the information push index tag type of the first templated widget service node may be determined in the interest text push process, and a fourth templated widget service node of an information push index tag type corresponding to the information push index tag type of the second templated widget service node and matching with the information push subscription item.

In a possible implementation manner, such as still referring to step S1014, in the process of updating the interest push index policy of the information push model according to the associated interest override service information in the interest text push process, the following exemplary sub-steps may be implemented, which are described in detail below.

(2) Obtaining interest service searching elements represented by associated interest coverage service information in an interest text pushing process, and obtaining first pushing updating keyword vector information of the label constituting elements of an interest label characteristic map aiming at the label constituting elements of each corresponding interest label characteristic map in an interest pushing index strategy of an information pushing model.

For example, the first push update keyword vector information is used to characterize information push configuration content and information push configuration rules of the information push index node of the interest tag feature map.

(3) And performing linkage updating on the first push updating keyword vector information according to each interest package subscription characteristic associated with the interest service searching element to obtain first interest push index strategy linkage information and information push configuration rule information corresponding to the first interest push index strategy linkage information.

(4) Acquiring a first service scene characteristic and a service scene track characteristic of a label component of the interest label characteristic map, and extracting a scene characteristic vector of the first service scene characteristic, wherein the scene characteristic vector of the first service scene characteristic comprises a specific scene characteristic vector.

(5) The specific scene feature vector of the historical label constituent element associated with the interest push index strategy of the information push model is obtained, and the specific scene feature vector of the first service scene feature is updated according to the specific scene feature vector, so that the association sequence between the specific scene feature vectors in the first service scene feature is matched with the association sequence between the specific scene feature vectors in the preset historical label constituent element.

(6) And after the updating is finished, obtaining a scene feature vector of the second service scene feature, and generating the second service scene feature according to the scene feature vector of the second service scene feature.

(7) According to the service scene track characteristics and the scene characteristic vector of the second service scene characteristics, information pushing configuration rule information matched with the service scene track characteristics and first interest pushing index strategy linkage information corresponding to the information pushing configuration rule information are searched and obtained, and the first interest pushing index strategy linkage information corresponding to the information pushing configuration rule information is updated according to the scene characteristic vector of the second service scene characteristics to obtain second interest pushing index strategy linkage information.

(8) And fusing the linkage information of the second interest pushing index strategy and the second service scene characteristics to obtain fused information pushing index reference characteristics of which the tag constituent elements of the interest tag characteristic map are matched with the subscription characteristics of each interest packet associated with the interest service searching elements.

(9) And pushing index reference features to the fusion information of the interest tag feature map for linkage updating to obtain a linkage updating result of the interest tag feature map, wherein the linkage updating result comprises linkage updating content information of each interest packet subscription feature which is associated with each interest service searching element and the tag constituent element of each interest tag feature map.

(10) And updating the linkage updating result of each interest tag feature map into an interest pushing index strategy of the information pushing model.

In one possible implementation manner, for example, for step S1011, in the process of performing information push update tagging on the push word vector sequence in the interest text push process established between the information push subscription terminal 200 and the corresponding blockchain service terminal 300 through the information push model trained in the blockchain of each information push subscription item, the following exemplary sub-steps can be implemented, which are described in detail as follows.

(1) The method includes the steps of acquiring an established information push request thread aiming at a target information push subscription terminal 200 sent by a blockchain service terminal 300, and acquiring corresponding information push subscription item information and push object information from the information push request thread.

(2) Extracting a preset data index script of each information push subscription item in the information push subscription item information relative to the target information push subscription terminal 200, determining an information push model corresponding to push object information according to the preset data index script, respectively associating each information push model to a block chain of the corresponding information push subscription item, then issuing push display configuration information of the block chain service terminal 300 to the target information push subscription terminal 200, and enabling the target information push subscription terminal 200 to record the push display configuration information of the block chain service terminal 300 into a target service terminal sequence corresponding to the information push control sequence.

(3) When a video interaction service request for a target information push subscription item corresponding to a target information push subscription terminal 200, which is sent by a block chain service terminal 300, is received, the target information push subscription terminal 200 is requested to establish an interest text push process between the block chain service terminal 300 and a target information sharing terminal corresponding to the video interaction service request, and an information push update mark is performed on a push word vector sequence in the interest text push process through an information push model trained in a block chain of the target information push subscription item.

In this embodiment, the blockchain service terminal 300 may select a certain target information push subscription terminal 200 to request the cloud service information platform 100 to perform scheduling of the information push service, and in a scheduling process of requesting to perform the information push service, it needs to select related information push subscription item information and push object information. The information push subscription item information may be used to indicate a specific situation of the information push subscription item selected by the blockchain service terminal 300, and the information push subscription item may refer to an item related to the information sharing terminal, which is not specifically limited herein. The push object information may refer to a push object generated online for push sharing, and is not specifically limited herein.

In this embodiment, the information push control sequence may include a plurality of information sharing terminals, such as a virtual reality device, an augmented reality device, and a smart medical terminal, which are controlled by the blockchain service terminal 300.

In this embodiment, the interest text push process may serve as a scheduling entry of the interest subscription push service, and provide a transmission channel for interest text push.

Based on the above steps, in this embodiment, by extracting a preset data index script of each information push subscription item in the information of the information push subscription item relative to the target information push subscription terminal 200, an information push model corresponding to the push object information is determined and is respectively associated to a block chain of the corresponding information push subscription item, when interaction is needed, an interest text push process between the block chain service terminal 300 and the target information sharing terminal is requested to be established from the target information push subscription terminal 200, and information push update marking is performed on a push word vector sequence in the interest text push process through the corresponding information push model. Therefore, information push updating marks of different information push subscription items in the interest text push process can be performed on the information push subscription terminal 200 in a more targeted manner, the targeted control of using the information push subscription items as information push updating mark objects is realized, and the push effect is improved.

Based on the same inventive concept, please refer to fig. 3, which shows a schematic diagram of functional modules of an information analysis apparatus 400 based on big data and artificial intelligence provided in the embodiment of the present application, and the embodiment can divide the functional modules of the information analysis apparatus 400 based on big data and artificial intelligence according to the above method embodiment. For example, the functional blocks may be divided for the respective functions, or two or more functions may be integrated into one processing block. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. It should be noted that, in the embodiment of the present application, the division of the module is schematic, and is only one logic function division, and there may be another division manner in actual implementation. For example, in the case of dividing each function module according to each function, the information analysis apparatus 400 based on big data and artificial intelligence shown in fig. 3 is only a schematic diagram of an apparatus. The big data and artificial intelligence based information analysis apparatus 400 may include a first extraction module 410, a calculation module 420, a second extraction module 430, and a third extraction module 440, and the functions of the functional modules of the big data and artificial intelligence based information analysis apparatus 400 are described in detail below.

The first extraction module 410 is configured to extract operation metadata of a field name association structure or a keyword association structure in user operation behavior big data for information push index content data uploaded by each information push subscriber terminal 200, and calculate a first knowledge mining element sequence corresponding to the operation metadata of the field name association structure or the keyword association structure in the user operation behavior big data, where the operation metadata of the field name association structure or the keyword association structure is used to represent operation node information of a field name and a keyword associated according to a logical relationship in each knowledge mining element of the user operation behavior big data. The first extraction module 410 may be configured to perform the step S110, and the detailed implementation of the first extraction module 410 may refer to the detailed description of the step S110.

A calculating module 420, configured to obtain a preset public opinion push statistical characteristic of a public opinion hotspot object corresponding to the user operation behavior big data, and calculate content matching information between the operation metadata of the field name association structure or the keyword association structure and the preset public opinion push statistical characteristic according to the first knowledge mining element sequence. The calculating module 420 may be configured to perform the step S120, and the detailed implementation of the calculating module 420 may refer to the detailed description of the step S120.

A second extracting module 430, configured to extract a corresponding second knowledge mining element sequence from the first knowledge mining element sequence according to content matching information between the operation metadata of the field name association structure or the keyword association structure and the preset public opinion push statistical feature. The second extraction module 430 may be configured to perform the step S130, and the detailed implementation of the second extraction module 430 may refer to the detailed description of the step S130.

A third extracting module 440, configured to determine, based on the user operation behavior big data, knowledge graph mining data of each target knowledge mining element of the second knowledge mining element sequence, and extract, according to the operation metadata of the field name association structure or the keyword association structure, a corresponding operation heat trend graph from the knowledge graph mining data of each target knowledge mining element, so as to update, based on the operation heat trend graph, an information pushing policy stored in the block chain trained by the block chain service terminal 300. The third extraction module 440 may be configured to perform the step S140, and for a detailed implementation of the third extraction module 440, reference may be made to the detailed description of the step S140.

It should be noted that the division of the modules of the above apparatus is only a logical division, and the actual implementation may be wholly or partially integrated into one physical entity, or may be physically separated. And these modules may all be implemented in software invoked by a processing element. Or may be implemented entirely in hardware. And part of the modules can be realized in the form of calling software by the processing element, and part of the modules can be realized in the form of hardware. For example, the determining module 310 may be a processing element separately set up, or may be implemented by being integrated into a chip of the apparatus, or may be stored in a memory of the apparatus in the form of program code, and the function of the determining module 310 may be called and executed by a processing element of the apparatus. Other modules are implemented similarly. In addition, all or part of the modules can be integrated together or can be independently realized. The processing element described herein may be an integrated circuit having signal processing capabilities. In implementation, each step of the above method or each module above may be implemented by an integrated logic circuit of hardware in a processor element or an instruction in the form of software.

For example, the above modules may be one or more integrated circuits configured to implement the above methods, such as: one or more Application Specific Integrated Circuits (ASICs), or one or more microprocessors (DSPs), or one or more Field Programmable Gate Arrays (FPGAs), among others. For another example, when some of the above modules are implemented in the form of a processing element scheduler code, the processing element may be a general-purpose processor, such as a Central Processing Unit (CPU) or other processor that can call program code. As another example, these modules may be integrated together, implemented in the form of a system-on-a-chip (SOC).

Fig. 4 is a schematic diagram illustrating a hardware structure of a cloud service information platform 100 for implementing the big data and artificial intelligence based information parsing method, according to an embodiment of the present invention, and as shown in fig. 4, the cloud service information platform 100 may include a processor 110, a machine-readable storage medium 120, a bus 130, and a transceiver 140.

In a specific implementation process, at least one processor 110 executes computer-executable instructions stored in the machine-readable storage medium 120 (for example, the big data and artificial intelligence based information parsing apparatus 400 shown in fig. 3 includes a first extraction module 410, a calculation module 420, a second extraction module 430, and a third extraction module 440), so that the processor 110 may execute the big data and artificial intelligence based information parsing method according to the above method embodiment, where the processor 110, the machine-readable storage medium 120, and the transceiver 140 are connected through the bus 130, and the processor 110 may be configured to control transceiving actions of the transceiver 140, so as to perform data transceiving with the aforementioned information push subscribing terminal 200.

For a specific implementation process of the processor 110, reference may be made to the above-mentioned method embodiments executed by the cloud service information platform 100, and implementation principles and technical effects thereof are similar, and details of this embodiment are not described herein again.

In the embodiment shown in fig. 4, it should be understood that the Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the present invention may be embodied directly in a hardware processor, or in a combination of the hardware and software modules within the processor.

The machine-readable storage medium 120 may comprise high-speed RAM memory and may also include non-volatile storage NVM, such as at least one disk memory.

The bus 130 may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended ISA (EISA) bus, or the like. The bus 130 may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, the buses in the figures of the present application are not limited to only one bus or one type of bus.

In addition, the embodiment of the present invention further provides a readable storage medium, where the readable storage medium stores computer execution instructions, and when a processor executes the computer execution instructions, the information parsing method based on big data and artificial intelligence is implemented as above.

Having thus described the basic concept, it will be apparent to those skilled in the art that the foregoing detailed disclosure is to be regarded as illustrative only and not as limiting the present specification. Various modifications, improvements, and offset processing may occur to those skilled in the art, though not expressly stated herein. Such modifications, improvements, and offset processing are suggested in this specification and still fall within the spirit and scope of the exemplary embodiments of this specification.

Also, the description uses specific words to describe embodiments of the description. Such as "one possible implementation," "one possible example," and/or "exemplary" means that a particular feature, structure, or characteristic described in connection with at least one embodiment of the specification is included. Therefore, it is emphasized and should be appreciated that two or more references to "one possible implementation," "one possible example," and/or "exemplary" in various places throughout this specification are not necessarily referring to the same embodiment. Furthermore, some features, structures, or characteristics of one or more embodiments of the specification may be combined as appropriate.

Moreover, those skilled in the art will appreciate that aspects of the present description may be illustrated and described in terms of several patentable species or contexts, including any new and useful combination of processes, machines, manufacture, or materials, or any new and useful improvement thereof. Accordingly, aspects of this description may be performed entirely by hardware, entirely by software (including firmware, resident software, micro-code, etc.), or by a combination of hardware and software. The above hardware or software may be referred to as "data block," module, "" engine, "" unit, "" component, "or" system. Furthermore, aspects of the present description may be presented as a computer product, located in one or more computer-readable media, comprising a computer-readable program information push index.

The computer storage medium may comprise a propagated data signal with a computer program information push index embodied therein, for example, on a baseband or as part of a carrier wave. The propagated signal may take any of a variety of forms, including electromagnetic, optical, etc., or any suitable combination. A computer storage medium may be any computer-readable medium that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. The program information push index located on the computer storage medium may be propagated over any suitable medium, including radio, cable, fiber optic cable, RF, or the like, or any combination of the preceding.

The computer program information push index required for the operations of the various parts of the present specification can be written in any one or more programming languages, including an object oriented programming language such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C + +, C #, vb.net, Python, etc., a conventional programming language such as C, Visual Basic, Fortran 2003, Perl, COBOL 2002, PHP, ABAP, a dynamic programming language such as Python, Ruby, and Groovy, or other programming languages, etc. The program information push index may run entirely on the user computer, or as a stand-alone software package on the user computer, or partly on the user computer and partly on a remote computer, or entirely on the remote computer or a cloud service information platform. In the latter scenario, the remote computer may be connected to the user's computer through any network format, such as a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet), or in a cloud computing environment, or as a service, such as a software as a service (SaaS).

Additionally, the order in which the elements and sequences of processes are described in this specification, the use of numerical letters, or the use of other names are not intended to limit the order of the processes and methods described in this specification, unless explicitly stated in the claims. While various presently contemplated embodiments of the invention have been discussed in the foregoing disclosure by way of example, it is to be understood that such detail is solely for that purpose and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover all modifications and equivalent arrangements that are within the spirit and scope of the embodiments herein. For example, although the system components described above may be implemented through interactive services, they may also be implemented through software-only solutions, such as installing the described system on an existing cloud service information platform or mobile device.

Similarly, it should be noted that in the preceding description of embodiments of the present specification, various features are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure aiding in the understanding of one or more of the embodiments. This method of disclosure, however, is not intended to imply that more features than are expressly recited in a claim. Indeed, the embodiments may be characterized as having less than all of the features of a single embodiment disclosed above.

It is to be understood that the descriptions, definitions and/or uses of terms in the accompanying materials of this specification shall control if they are inconsistent or contrary to the descriptions and/or uses of terms in this specification.

Finally, it should be understood that the embodiments described herein are merely illustrative of the principles of the embodiments of the present disclosure. Other variations are also possible within the scope of the present description. Thus, by way of example, and not limitation, alternative configurations of the embodiments of the specification can be considered consistent with the teachings of the specification. Accordingly, the embodiments of the present description are not limited to only those embodiments explicitly described and depicted herein.

Claims

1. An information push updating method based on a block chain is applied to a cloud service information platform, the cloud service information platform is in communication connection with a plurality of information push subscription terminals and is in communication connection with a block chain service terminal for performing information push control on each information push subscription terminal, and the method comprises the following steps:

acquiring an established information push request thread aiming at a target information push subscription terminal, which is sent by the block chain service terminal, and acquiring corresponding information push subscription item information and push object information from the information push request thread;

extracting a preset data index script of each information push subscription item in information push subscription item information relative to a target information push subscription terminal, determining an information push model corresponding to push object information according to the preset data index script, respectively associating each information push model to a block chain of the corresponding information push subscription item, then issuing push display configuration information of the block chain service terminal to the target information push subscription terminal, and enabling the target information push subscription terminal to record the push display configuration information of the block chain service terminal into a target service terminal sequence corresponding to an information push control sequence;

when a video interaction service request which is sent by a block chain service terminal and aims at a target information push subscription item corresponding to a target information push subscription terminal is received, the target information push subscription terminal is requested to establish an interest text push process between the block chain service terminal and a target information sharing terminal corresponding to the video interaction service request, and an information push updating mark is carried out on a push word vector sequence in the interest text push process through an information push model trained in a block chain of the target information push subscription item.

2. The method for pushing and updating information based on block chains according to claim 1, further comprising:

determining a first templated control service node and a second templated control service node in a browsing templated control currently performing information browsing display by the information push subscription terminal in an information push updating marking process, wherein the browsing templated control is a templated browsing control corresponding to a preset browsing structured display strategy in an interest text push process;

in the interest text pushing process, determining a third templated control service node corresponding to the first templated control service node and matched with the information pushing subscription item, and a fourth templated control service node corresponding to the second templated control service node and matched with the information pushing subscription item;

and determining associated interest coverage service information in the interest text pushing process according to the first templated control service node, the second templated control service node, the third templated control service node, the fourth templated control service node and the browsing structural display strategy, updating an interest pushing index strategy of the information pushing model according to the associated interest coverage service information in the interest text pushing process, and pushing information pushing index content data to each information pushing subscription terminal based on the updated interest pushing index strategy.

3. The method for pushing and updating information based on block chains according to claim 2, further comprising:

extracting operation metadata of a field name association structure or a keyword association structure in user operation behavior big data aiming at the information push index content data uploaded by each information push subscription terminal, and calculating a first knowledge mining element sequence corresponding to the operation metadata of the field name association structure or the keyword association structure in the user operation behavior big data, wherein the operation metadata of the field name association structure or the keyword association structure is used for representing operation node information of field names and keywords associated according to a logical relation in each knowledge mining element of the user operation behavior big data;

4. The blockchain-based information push updating method according to claim 3, wherein the step of extracting operation metadata of a field name association structure or a keyword association structure in the user operation behavior big data for the information push index content data uploaded by each information push subscription terminal, and calculating a first knowledge mining element sequence corresponding to the operation metadata of the field name association structure or the keyword association structure in the user operation behavior big data includes:

performing rule tree matching on the user operation behavior big data to obtain rule tree matching characteristics, wherein the rule tree matching characteristics are used for expressing rule tree node vectors corresponding to each knowledge mining element in the user operation behavior big data;

performing information elimination processing of preset invalid features aiming at the rule tree matching features to obtain first target rule tree matching features, obtaining similar rule tree nodes of all rule tree node vectors in the first target rule tree matching features, and screening out the rule tree node vectors of which the number of the similar rule tree nodes is greater than the set node number from the first target rule tree matching features according to the similar rule tree nodes of all rule tree node vectors to obtain second target rule tree matching features;

performing normalized template feature extraction on the second target regular tree matching features to obtain a first normalized template feature set, and filtering regular tree node vectors with feature lengths larger than a set value in the first normalized template feature set to obtain a first screening regular tree node vector sequence;

mapping and comparing the first normalized template feature set according to the first screening rule tree node vector sequence, and determining all time dimensions and carrier index components of all space dimensions of normalized template feature dimensions of the second target rule tree matching features, wherein the time dimensions and the space dimensions are dimensions of inverse quantization indexes of rule tree node vectors in a pre-constructed content matching rule, and the quantization indexes are used for representing quantization parameters of content statistical features;

and determining operation metadata of a field name association structure or a keyword association structure according to all time dimensions and carrier index components of all space dimensions of the characteristic dimension of the normalized template of the second target rule tree matching characteristic, and determining a first knowledge mining element sequence corresponding to the operation metadata of the field name association structure or the keyword association structure in the user operation behavior big data.

5. The method according to claim 4, wherein the step of determining operation metadata of a field name association structure or a keyword association structure according to all time dimensions and carrier index components of all space dimensions of a normalized template feature dimension of the second target rule tree matching feature, and determining a first knowledge mining element sequence corresponding to the operation metadata of the field name association structure or the keyword association structure in the user operation behavior big data includes:

respectively obtaining a first time dimension carrier index component group and a first space dimension carrier index component group according to all time dimensions and all space dimensions of the characteristic dimensions of the normalized template of the second target rule tree matching characteristics;

extracting all normalized template associated objects of normalized template feature dimensions according to the first time dimension carrier index component group and the first space dimension carrier index component group;

extracting the non-normalized template features of the second target regular tree matching features to obtain a second normalized template feature set, and filtering regular tree node vectors with feature lengths larger than a set value in the second normalized template feature set to obtain a second screening regular tree node vector sequence;

mapping and comparing the second normalized template feature set according to the second screening rule tree node vector sequence, and determining all time dimensions and carrier index components of all space dimensions of the non-normalized template feature dimensions of the second target rule tree matching features, wherein the time dimensions and the space dimensions are directions of inverse quantization indexes of rule tree node vectors in a pre-constructed content matching rule, and the quantization indexes are used for expressing quantization parameters of content statistical features;

respectively obtaining a second time dimension carrier index component group and a second space dimension carrier index component group according to all time dimensions and all space dimensions of the non-normalized template feature dimensions of the second target rule tree matching features;

extracting all non-normalized template associated objects of the feature dimensions of the non-normalized template according to the second time dimension carrier index component group and the second space dimension carrier index component group;

determining all associated nodes according to the normalized template associated object and the non-normalized template associated object, and determining a unit knowledge mining element set, an element mining number set and an element frequent statistics degree set of all similar rule tree nodes on each associated node;

when the maximum value of the ratio of the median to the average and the ratio of the average to the median of the unit knowledge mining element set, the element mining quantity set and the element frequent statistics degree set is smaller than a set value, determining the similar rule tree node as an undetermined node of the candidate similar rule tree node;

for each similar rule tree node in one associated node, determining the feature fragment position of the non-normalized template feature between similar rule tree nodes associated with each non-normalized template feature in the similar rule tree node, and determining the feature fragment position of the non-normalized template feature of each candidate similar rule tree node according to the feature fragment position;

determining operation metadata of a field name association structure or a keyword association structure according to the position of the characteristic segment of the non-canonical template characteristic of each candidate similar rule tree node;

and determining a first knowledge mining element sequence corresponding to the operation metadata of the field name association structure or the keyword association structure in the user operation behavior big data.

6. The method of claim 3, wherein the step of obtaining a preset public opinion push statistical characteristic of a public opinion hotspot object corresponding to the user operation behavior big data, and calculating content matching information between the operation metadata of the field name association structure or the keyword association structure and the preset public opinion push statistical characteristic according to the first knowledge mining element sequence comprises:

acquiring a public opinion hotspot tag of a public opinion hotspot object corresponding to the user operation behavior big data;

acquiring a preset public opinion pushing statistical characteristic containing a public opinion hotspot object from a preset public opinion hotspot object characteristic database according to the public opinion hotspot tag, wherein the preset public opinion hotspot object characteristic database comprises a corresponding relation between the public opinion hotspot tag and the preset public opinion pushing statistical characteristic, and the preset public opinion pushing statistical characteristic is used for representing the public opinion popularity updating situation in the statistical process of the public opinion hotspot object and adaptively changes along with the change of the public opinion hotspot object;

acquiring a traversal knowledge mining element containing the current public opinion hotspot object according to the first knowledge mining element sequence, determining a reference search intention feature taking the preset public opinion push statistical feature as a reference feature according to the traversal knowledge mining element, sequentially dividing the traversal knowledge mining element into a plurality of candidate search intention features corresponding to the reference search intention feature by taking the operation metadata of the field name association structure or the keyword association structure as a reference, respectively comparing each candidate search intention feature with the reference search intention feature to obtain a corresponding intention matching value range, and recording the candidate search intention feature corresponding to the intention matching value range as a first search intention feature and the reference search intention feature as a second search intention feature when the intention matching value range does not meet the set reference value range, to derive at least one search intention feature combination formed by the first search intention feature and the second search intention feature;

calculating content matching information between the operation metadata of the field name association structure or the keyword association structure and the preset public opinion push statistical feature based on the search intention feature combination formed by at least one of the first search intention feature and the second search intention feature.

7. The method of claim 3, wherein the step of extracting a corresponding second knowledge mining element sequence from the first knowledge mining element sequence according to the content matching information between the operation metadata of the field name association structure or the keyword association structure and the predetermined public opinion push statistic characteristics comprises extracting the corresponding second knowledge mining element sequence from the first knowledge mining element sequence

Determining that a knowledge mining element matched with the content matching information exists in the first knowledge mining element sequence according to content matching information between the operation metadata of the field name association structure or the keyword association structure and the preset public opinion push statistical characteristics;

and extracting a corresponding second knowledge mining element sequence from the first knowledge mining element sequence according to the knowledge mining elements matched with the content matching information.

8. The method for pushing and updating information based on block chains according to claim 3, wherein the step of extracting the corresponding operation heat trend graph from the knowledge graph mining data of each target knowledge mining element according to the operation metadata of the field name association structure or the keyword association structure comprises:

screening a plurality of candidate operation heat degree trend graphs with the matching degree between the candidate operation heat degree trend graphs and the operation metadata of the field name associated structure or the keyword associated structure, wherein the matching degree between the candidate operation heat degree trend graphs and the operation metadata of the field name associated structure or the keyword associated structure is greater than a set matching degree, and the matching degrees corresponding to the candidate operation heat degree trend graphs respectively;

selecting at least one candidate map unit from the candidate operation heat degree trend maps according to the matching degree to form a candidate map unit group, and determining the operation heat degree index of each candidate map unit according to the association degree of each candidate map unit in the candidate map unit group and each data area in the knowledge map mining data;

determining a matching degree difference value of a difference between matching degrees corresponding to the candidate operation heat degree trend maps and a preset matching degree, and generating a candidate operation heat degree trend parameter based on a product of a grade of the matching degree difference value and the operation heat degree index, wherein the grade of the matching degree difference value is obtained through a preset mapping relation between the matching degree difference value and the grade;

and generating an operation heat trend map corresponding to the knowledge map mining data of each target knowledge mining element based on the candidate operation heat trend parameters.

9. An information analysis system based on big data and artificial intelligence is characterized by comprising a cloud service information platform and a plurality of information push subscription terminals in communication connection with the cloud service information platform, wherein the cloud service information platform is also in communication connection with a block chain service terminal for performing information push control on each information push subscription terminal;

the cloud service information platform is used for:

10. A cloud service information platform, characterized in that the cloud service information platform includes a processor, a machine-readable storage medium, and a network interface, the machine-readable storage medium, the network interface, and the processor are connected through a bus system, the network interface is configured to be in communication connection with at least one information push subscription terminal, the machine-readable storage medium is configured to store a program, an instruction, or a code, and the processor is configured to execute the program, the instruction, or the code in the machine-readable storage medium to perform the block chain based information push update method according to any one of claims 1 to 9.