CN111931514A

CN111931514A - Information processing method based on deep learning and big data and block chain service platform

Info

Publication number: CN111931514A
Application number: CN202010734965.9A
Authority: CN
Inventors: 薛杨杨
Original assignee: 薛杨杨
Current assignee: LianBo (Chengdu) Technology Co.,Ltd.
Priority date: 2020-07-28
Filing date: 2020-07-28
Publication date: 2020-11-13
Anticipated expiration: 2040-07-28
Also published as: CN112818695A; CN111931514B; CN112818696A

Abstract

The embodiment of the application provides an information processing method based on deep learning and big data and a block chain service platform, wherein big data interactive information and non-interactive information are comprehensively considered according to a first incidence relation between an interactive semantic vector of the non-interactive information and an interactive semantic vector of big data interactive information, then the non-interactive information is subjected to feature marking processing according to a second incidence relation between the interactive semantic vector of the target semantic comprehensive feature information and the interactive semantic vector of the non-interactive information and semantic components of semantic nodes in the non-interactive information, and the feature marking of the interactive information on similar interactive information is realized through the deep learning of user interactive information, so that the semantic incidence of the semantic node information in the interactive information is improved; in addition, the relevance between semantic node features in the interactive information is combined, the accuracy of the interactive information feature marking information is improved, and the matching degree of subsequent interactive contents is further improved.

Description

Information processing method based on deep learning and big data and block chain service platform

Technical Field

The application relates to the technical field of mobile communication, in particular to an information processing method based on deep learning and big data and a block chain service platform.

Background

Along with the mobile internet technology, through information interaction between the service platform and the user, a solution of related internet service can be better performed on the user, so that frequent consultation activities under the user line are reduced.

However, in the conventional scheme, the semantic relevance of semantic node information in the interactive information between the service platform and the user is not high, so that the matching degree of the subsequent interactive content is not completely matched with the information to be interacted, which is actually initiated by the user, and the information push accuracy of the service platform is further influenced.

Disclosure of Invention

In view of this, an object of the present application is to provide an information processing method and a block chain service platform based on deep learning and big data, which implement feature labeling of interaction information on similar interaction information through deep learning of user interaction information, thereby improving semantic relevance of semantic node information in the interaction information; in addition, the relevance between semantic node features in the interactive information is combined, the relevance is utilized to promote the concern on useful information, reduce the concern on useless information, promote the accuracy of the interactive information feature marking information, and further improve the matching degree of subsequent interactive contents.

According to a first aspect of the application, an information processing method based on deep learning and big data is provided, and is applied to a block chain service platform in communication connection with an intelligent interactive terminal, and the method includes:

acquiring to-be-interacted information sent by the intelligent interactive terminal, determining non-interacted information in a current interaction connection position according to the to-be-interacted information, and determining a first incidence relation between an interaction semantic vector of the non-interacted information and an interaction semantic vector of big data interaction information, wherein the big data interaction information is determined based on an interaction information list in a historical time period;

extracting decision interaction semantic nodes meeting the conditional decision of the non-interaction information from the big data interaction information based on a deep learning model to obtain a first decision interaction semantic node sequence, determining first target semantic nodes from the first decision interaction semantic node sequence based on the first incidence relation, and performing supplementary updating on the semantic node information of the non-interaction information according to the first target semantic nodes to obtain target semantic comprehensive characteristic information;

determining a second incidence relation between the interactive semantic vector of the target semantic comprehensive characteristic information and the interactive semantic vector of the non-interactive information;

and according to the second incidence relation and the semantic component of the semantic node in the non-interactive information, performing feature marking processing on the non-interactive information to obtain feature marked interactive information, and after interactive content is sent to the intelligent interactive terminal according to the feature marked interactive information, storing the interactive content into a corresponding block chain.

In a possible implementation manner of the first aspect, the interactive semantic vector of the non-interactive information includes a semantic label of each known semantic node in the non-interactive information and a semantic order in the non-interactive information; the interactive semantic vector of the big data interactive information comprises a semantic label of each semantic node in the big data interactive information and a semantic sequence in the big data interactive information;

the step of determining the first association relationship between the interactive semantic vector of the non-interactive information and the interactive semantic vector of the big data interactive information includes:

respectively constructing semantic feature vectors of each semantic node in the non-interactive information and the big data interactive information to obtain a plurality of first embedded representations and a plurality of second embedded representations;

determining a first association degree between each first embedded representation and each second embedded representation to obtain the first association relation;

the determining a first target semantic node from the first decision interaction semantic node sequence based on the first incidence relation, and performing supplementary updating on the semantic node information of the non-interaction information according to the first target semantic node includes:

determining a first semantic convergence degree of each semantic node in the non-interactive information about each semantic node in the big data interactive information based on the first association degree, wherein the first semantic convergence degree is used for reflecting the semantic tendency degree of each semantic node in the non-interactive information to each semantic node in the big data interactive information;

determining corresponding decision interaction semantic nodes from the first decision interaction semantic node sequence according to the sequence of the first semantic convergence from high to low, wherein the decision interaction semantic nodes serve as first target semantic nodes;

and generating corresponding semantic nodes at corresponding positions in the non-interactive information according to the semantic sequence of the first target semantic nodes in the big data interactive information and the semantic labels corresponding to the first target nodes.

In a possible implementation manner of the first aspect, the step of performing semantic node feature labeling processing on the non-interactive information according to the second association relationship and a semantic component of a semantic node in the non-interactive information to obtain feature labeled interactive information includes:

determining decision interactive semantic nodes from the target semantic comprehensive characteristic information according to the second incidence relation and the semantic sequence of the semantic nodes in the target semantic comprehensive characteristic information to obtain a second decision interactive semantic node sequence;

determining a second target semantic node from the second decision interaction semantic node sequence based on the known semantic nodes and the semantic components in the non-interaction information;

generating corresponding semantic nodes at corresponding positions in the non-interactive information based on the semantic components and semantic labels corresponding to the second target semantic nodes, so as to perform semantic node feature labeling processing on the non-interactive information and obtain feature labeled interactive information;

the interactive semantic vector of the non-interactive information comprises a semantic label of each known semantic node in the non-interactive information and a semantic sequence in the non-interactive information, and the interactive semantic vector of the target semantic comprehensive characteristic information comprises a semantic label of each semantic node in the target semantic comprehensive characteristic information and a semantic sequence in the target semantic comprehensive characteristic information;

the step of determining a second association relationship between the interactive semantic vector of the target semantic synthesis feature information and the interactive semantic vector of the non-interactive information includes:

respectively constructing semantic feature vectors of each semantic node in the non-interactive information and the target semantic comprehensive feature information to obtain a plurality of third embedded representations and a plurality of fourth embedded representations, and determining a second association degree between each third embedded representation and each fourth embedded representation to obtain a second association relation;

determining decision interactive semantic nodes from the target semantic comprehensive characteristic information according to the second incidence relation and the semantic sequence of the semantic nodes in the target semantic comprehensive characteristic information to obtain a second decision interactive semantic node sequence, wherein the step comprises the following steps:

determining a second semantic convergence degree of each semantic node in the non-interactive information about each semantic node in the target semantic comprehensive characteristic information based on the second association degree, wherein the second semantic convergence degree is used for reflecting the semantic tendency degree of each semantic node in the non-interactive information to each semantic node in the target semantic comprehensive characteristic information;

and determining decision interactive semantic nodes from the target semantic comprehensive characteristic information according to the second semantic convergence and the semantic sequence of the semantic nodes in the target semantic comprehensive characteristic information to obtain a second decision interactive semantic node sequence.

In a possible implementation manner of the first aspect, the step of determining non-interactive information in the current interactive engagement location according to the information to be interacted includes:

acquiring known semantic nodes in a current interactive joining position, determining initial interactive information at least based on the known semantic nodes in the current interactive joining position, and constructing semantic feature vectors of the known semantic nodes in the initial interactive information;

determining the association degree between the semantic node to be interacted and the corresponding known semantic node according to the semantic feature vector of the semantic node to be interacted and the semantic feature vector of the known semantic node in the information to be interacted;

determining a third semantic convergence degree of each known semantic node in the initial interaction information about the semantic node to be interacted based on the association degree between the semantic node to be interacted and the corresponding known semantic node, wherein the third semantic convergence degree is used for reflecting the semantic tendency degree of each semantic node in the initial interaction information to the semantic node to be interacted in the interaction information;

complementary updating is carried out on the semantic feature vectors of the known semantic nodes in the initial interaction information according to the third semantic convergence degree, and non-interaction information is obtained;

the method for determining big data interaction information based on the interaction information list in the historical time period comprises the following steps:

acquiring an interaction information list in a historical time period;

constructing a plurality of pieces of historical interaction information according to the specified interaction connection position and the interaction information list;

aligning the plurality of pieces of historical interaction information according to time, determining a semantic node with the highest display frequency under the same time slice from the aligned plurality of pieces of historical interaction information, and constructing according to the semantic node with the highest display frequency under the same time slice to obtain target historical interaction information;

constructing a semantic feature vector of each semantic node in the target historical interaction information;

determining the association degree between every two semantic nodes in the target historical interaction information according to the semantic feature vector of each semantic node;

determining a fourth semantic convergence degree of each semantic node in the target historical interaction information with respect to other semantic nodes based on the association degree between every two semantic nodes, wherein the fourth semantic convergence degree is used for reflecting the semantic tendency degree of each semantic node in the target historical interaction information to other semantic nodes in the interaction information;

and performing supplementary updating on the semantic feature vectors of the semantic nodes in the target historical interaction information according to the fourth semantic convergence degree to obtain big data interaction information.

In a possible implementation manner of the first aspect, the step of extracting, based on a deep learning model, a decision-making interactive semantic node that satisfies the conditional decision of the non-interactive information from the big data interactive information to obtain a first decision-making interactive semantic node sequence includes:

identifying a plurality of conditional decision interaction segments matched with the current business scene from the non-interaction information based on the deep learning model;

taking each conditional decision interaction segment in the plurality of conditional decision interaction segments as a current conditional decision interaction segment, and executing the following steps until the plurality of conditional decision interaction segments are traversed:

under the condition that the current condition decision interaction section detects a service decision section of the interactive service contained in the big data interaction information, acquiring a section feature vector of the service decision section;

converting the service decision segment into a first service parameter according to a conversion relation between a characteristic vector value and a service parameter in a preset conversion table, and determining the first service parameter as a target service parameter of the big data interaction information and the current conditional decision interaction segment, wherein each target service parameter is a service parameter from the big data interaction information to the conditional decision interaction segment;

dividing an interactive data unit corresponding to the non-interactive information into a plurality of interactive data subunits, determining each interactive data subunit as a current interactive data subunit, and executing the following steps until each interactive data subunit is traversed:

determining each conditional decision interaction segment as a current conditional decision interaction segment, and executing the following steps until the conditional decision interaction segments are traversed:

determining the matching degree of the current interactive data subunit and the current conditional decision interactive section as a first numerical value under the condition that the service parameters of the current interactive data subunit and the current conditional decision interactive section are target service parameters corresponding to the current conditional decision interactive section;

determining the matching degree to be zero under the condition that the service parameters of the current interactive data subunit and the current conditional decision interactive section are greater than or less than the target service parameters corresponding to the current conditional decision interactive section, wherein the matching degree is determined according to the position of the current interactive data subunit, the position of the conditional decision interactive section and a group of target service parameters;

determining the target matching degree of the big data interaction information matched with the current interaction data subunit according to the product of all the matching degrees of the current interaction data subunit;

acquiring the service location of the interactive data subunit corresponding to the maximum matching degree in the target matching degrees, and determining the service location as the target service location of the big data interactive information at a first decision interactive node;

under the condition that the target service location where the big data interaction information of a plurality of decision interaction nodes is respectively located is determined, generating interaction offset updating information of the big data interaction information in the interaction data unit by using the position information of the plurality of target service locations, wherein the plurality of decision interaction nodes comprise the first decision interaction node and the decision interaction nodes behind the first decision interaction node, and under the condition that the plurality of interaction offset updating information generated in the interaction data unit within a target time period is obtained, determining each piece of interaction offset updating information as an interaction offset updating information group;

executing the following steps until the relevance degree of each two interactive offset update information cliques is greater than or equal to a preset threshold value:

determining one of the two interactive offset update information cliques as a current interactive offset update information clique, determining the other interactive offset update information clique as a target interactive offset update information clique, determining each interactive offset update information in the current interactive offset update information clique as current interactive offset update information, and executing the following steps until the current interactive offset update information cliques are traversed:

determining a first degree of association between the current interaction offset update information and each interaction offset update information in the target interaction offset update information group;

after the traversal is completed, determining the average value of the first relevance degrees as the relevance degrees;

merging the two interactive offset updating information cliques with the minimum relevance into a new interactive information clique;

after the steps are executed, obtaining a plurality of first interaction offset updating information cliques, and determining each first interaction offset updating information clique as one type of interaction offset updating information;

after acquiring a type of the interactive offset updating information, determining one piece of the interactive offset updating information in the type of the interactive offset updating information as current interactive offset updating information, and determining the other piece of the interactive offset updating information as first interactive offset updating information, and executing the following steps until all interactive offset updating information in the type of the interactive offset updating information is traversed:

acquiring common tags of every two corresponding service types in the current interaction offset updating information and the first interaction offset updating information, determining a tag migration relation of the common tags as new current interaction offset updating information, and determining one of the rest interaction offset updating information in one type of interaction offset updating information as the first interaction offset updating information;

after the traversal is completed, determining a piece of current interaction offset updating information which is determined finally as hotspot interaction information of one type of interaction offset updating information, determining two pieces of second interaction offset updating information from one type of interaction offset updating information, and acquiring common labels of two corresponding service types under the condition that the service association degree of the corresponding service types on the two pieces of second interaction offset updating information is smaller than a second threshold value;

after a plurality of common labels are obtained, the label migration relation of the common labels is determined to be the optimal public sub-interaction information of the interaction information, so that decision interaction semantic nodes are obtained, and a first decision interaction semantic node sequence is obtained through summarization.

According to a second aspect of the present application, an information processing apparatus based on deep learning and big data is provided, and is applied to a block chain service platform in communication connection with an intelligent interactive terminal, the apparatus includes:

the acquisition module is used for acquiring information to be interacted sent by the intelligent interaction terminal, determining non-interactive information in a current interaction connection position according to the information to be interacted, and determining a first incidence relation between an interactive semantic vector of the non-interactive information and an interactive semantic vector of big data interaction information, wherein the big data interaction information is determined based on an interaction information list in a historical time period;

the extraction module is used for extracting decision interaction semantic nodes meeting the conditional decision of the non-interaction information from the big data interaction information based on a deep learning model to obtain a first decision interaction semantic node sequence, determining first target semantic nodes from the first decision interaction semantic node sequence based on the first incidence relation, and performing supplementary updating on the semantic node information of the non-interaction information according to the first target semantic nodes to obtain target semantic comprehensive characteristic information;

the determining module is used for determining a second incidence relation between the interactive semantic vector of the target semantic comprehensive characteristic information and the interactive semantic vector of the non-interactive information;

and the sending module is used for carrying out feature marking processing on the non-interactive information according to the second incidence relation and the semantic component of the semantic node in the non-interactive information to obtain feature marked interactive information, sending interactive content to the intelligent interactive terminal according to the feature marked interactive information, and storing the interactive content into a corresponding block chain.

In a third aspect, an embodiment of the present invention further provides an information processing system based on deep learning and big data, where the information processing system based on deep learning and big data includes a blockchain service platform and an intelligent interactive terminal in communication connection with the blockchain service platform;

the block chain service platform is used for acquiring information to be interacted sent by the intelligent interaction terminal, determining non-interactive information in a current interaction connection position according to the information to be interacted, and determining a first incidence relation between an interactive semantic vector of the non-interactive information and an interactive semantic vector of big data interaction information, wherein the big data interaction information is determined based on an interaction information list in a historical time period;

the block chain service platform is used for extracting decision interaction semantic nodes meeting the conditional decision of the non-interaction information from the big data interaction information based on a deep learning model to obtain a first decision interaction semantic node sequence, determining first target semantic nodes from the first decision interaction semantic node sequence based on the first incidence relation, and performing supplementary updating on the semantic node information of the non-interaction information according to the first target semantic nodes to obtain target semantic comprehensive characteristic information;

the block chain service platform is used for determining a second incidence relation between the interactive semantic vector of the target semantic comprehensive characteristic information and the interactive semantic vector of the non-interactive information;

and the block chain service platform is used for performing feature marking processing on the non-interactive information according to the second incidence relation and the semantic component of the semantic node in the non-interactive information to obtain feature marked interactive information, and storing the interactive content into a corresponding block chain after sending the interactive content to the intelligent interactive terminal according to the feature marked interactive information.

In a fourth aspect, an embodiment of the present invention further provides a blockchain service platform, where the blockchain service 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 intelligent interactive 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 perform the deep learning and big data based information processing method in the first aspect or any one of possible implementation manners in 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 an information processing method based on deep learning and big data in the first aspect or any one of the possible designs of the first aspect.

Based on any aspect, the big data interactive information and the non-interactive information are comprehensively considered according to a first association relation between an interactive semantic vector of the non-interactive information and an interactive semantic vector of the big data interactive information, then the non-interactive information is subjected to feature marking processing according to a second association relation between the interactive semantic vector of the target semantic comprehensive feature information and the interactive semantic vector of the non-interactive information and semantic components of semantic nodes in the non-interactive information, and feature marking of the interactive information on similar interactive information is realized through deep learning of user interactive information, so that the semantic association of the semantic node information in the interactive information is improved; in addition, the relevance between semantic node features in the interactive information is combined, the relevance is utilized to promote the concern on useful information, reduce the concern on useless information, promote the accuracy of the interactive information feature marking information, and further improve the matching degree of subsequent interactive contents.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, 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 application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.

FIG. 1 is a schematic diagram illustrating an application scenario of an information processing system based on deep learning and big data provided by an embodiment of the present application;

FIG. 2 is a flow chart illustrating an information processing method based on deep learning and big data according to an embodiment of the present disclosure;

FIG. 3 is a schematic diagram showing functional modules of an information processing device based on deep learning and big data provided by an embodiment of the application;

fig. 4 shows a component structural diagram of a blockchain service platform for performing the above deep learning and big data based information processing method according to an embodiment of the present application.

Detailed Description

In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings used in the description of the embodiments will be briefly described below. It is obvious that the drawings in the following description are only examples or embodiments of the present description, and that for a person skilled in the art, the present description can also be applied to other similar scenarios on the basis of these drawings without inventive effort. Unless otherwise apparent from the context, or otherwise indicated, like reference numbers in the figures refer to the same structure or operation.

It should be understood that "system", "device", "unit" and/or "module" as used in this specification is a method for distinguishing different components, elements, parts or assemblies at different levels. However, other words may be substituted by other expressions if they accomplish the same purpose.

As used in this specification and the appended claims, the terms "a," "an," "the," and/or "the" are not intended to be inclusive in the singular, but rather are intended to be inclusive in the plural, unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that steps and elements are included which are explicitly identified, that the steps and elements do not form an exclusive list, and that a method or apparatus may include other steps or elements.

Flow charts are used in this description to illustrate operations performed by a system according to embodiments of the present description. It should be understood that the preceding or following operations are not necessarily performed in the exact order in which they are performed. Rather, the various steps may be processed in reverse order or simultaneously. Meanwhile, other operations may be added to the processes, or a certain step or several steps of operations may be removed from the processes.

FIG. 1 is an interactive schematic diagram of an information processing system 10 based on deep learning and big data according to an embodiment of the present invention. The deep learning and big data based information processing system 10 can comprise a blockchain service platform 100 and an intelligent interactive terminal 200 which is in communication connection with the blockchain service platform 100. The deep learning and big data based information processing system 10 shown in fig. 1 is only one possible example, and in other possible embodiments, the deep learning and big data based information processing system 10 may also include only a portion of the components shown in fig. 1 or may also include other components.

In this embodiment, the blockchain service platform 100 and the intelligent interactive terminal 200 in the deep learning and big data based information processing system 10 may cooperatively perform the deep learning and big data based information processing method described in the following method embodiment, and the detailed description of the method embodiment may be referred to for the specific steps performed by the blockchain service platform 100 and the intelligent interactive terminal 200.

In order to solve the technical problem in the foregoing background art, fig. 2 is a flowchart illustrating an information processing method based on deep learning and big data according to an embodiment of the present invention, which may be executed by the blockchain service platform 100 shown in fig. 1, and the information processing method based on deep learning and big data is described in detail below.

Step S110, obtaining information to be interacted sent by the intelligent interactive terminal 200, determining non-interactive information in the current interactive connection position according to the information to be interacted, and determining a first association relation between an interactive semantic vector of the non-interactive information and an interactive semantic vector of big data interactive information.

Step S120, extracting decision interaction semantic nodes meeting the conditional decision of the non-interaction information from the big data interaction information based on a deep learning model to obtain a first decision interaction semantic node sequence, determining first target semantic nodes from the first decision interaction semantic node sequence based on a first incidence relation, and performing supplementary updating on the semantic node information of the non-interaction information according to the first target semantic nodes to obtain target semantic comprehensive characteristic information.

Step S130, determining a second incidence relation between the interactive semantic vector of the target semantic synthesis characteristic information and the interactive semantic vector of the non-interactive information.

Step S140, according to the second association relationship and the semantic component of the semantic node in the non-interactive information, performing feature tagging processing on the non-interactive information to obtain feature tagged interactive information, and after sending the interactive content to the intelligent interactive terminal 200 according to the feature tagged interactive information, storing the interactive content in the corresponding block chain.

In this embodiment, the big data interaction information may be determined based on an interaction information list in a historical time period, which will be specifically described in detail in the following description.

In this embodiment, the information to be interacted may refer to interactive content selected or input by a user of the intelligent interactive terminal 200 when initiating the interactive session, for example, the interactive content may be input based on a certain interested service item, and details are not limited.

In this embodiment, the interactive semantic vector may be some encoding vectors having character encoding features, and the specific character encoding mode may be obtained by using any credible encoding scheme in the prior art, which is not limited specifically herein.

In this embodiment, the semantic node may refer to a unit in which semantic association specifically exists, for example, a sentence segment in a certain service session, or a time, etc.

Based on the design, the big data interactive information and the non-interactive information are comprehensively considered according to the first association relationship between the interactive semantic vector of the non-interactive information and the interactive semantic vector of the big data interactive information, then the non-interactive information is subjected to feature labeling processing according to the second association relationship between the interactive semantic vector of the target semantic comprehensive feature information and the interactive semantic vector of the non-interactive information and the semantic components of semantic nodes in the non-interactive information, and the feature labeling of the interactive information on similar interactive information is realized through deep learning of user interactive information, so that the semantic association of the semantic node information in the interactive information is improved; in addition, the relevance between semantic node features in the interactive information is combined, the accuracy of the interactive information feature marking information is improved, and the matching degree of subsequent interactive contents is further improved.

In a possible implementation manner, the interactive semantic vector of the non-interactive information may include a semantic label of each known semantic node in the non-interactive information and a semantic order in the non-interactive information, and the interactive semantic vector of the big data interactive information may include a semantic label of each semantic node in the big data interactive information and a semantic order in the big data interactive information.

Based on this, for step S110, in the process of determining the first association relationship between the interaction semantic vector of the non-interaction information and the interaction semantic vector of the big data interaction information, the following exemplary sub-steps may be implemented, which are described in detail as follows:

and a substep S111, respectively constructing semantic feature vectors of each semantic node in the non-interactive information and the big data interactive information to obtain a plurality of first embedded representations and a plurality of second embedded representations.

And a substep S112, determining a first association degree between each first embedded representation and each second embedded representation, to obtain a first association relationship.

On this basis, for example, for step S120, in the process of determining a first target semantic node from the first decision interaction semantic node sequence based on the first association relationship, and performing supplementary update on semantic node information of non-interaction information according to the first target semantic node, the following exemplary sub-steps may be implemented, and are described in detail as follows:

and a substep S121, determining a first semantic convergence degree of each semantic node in the non-interactive information with respect to each semantic node in the big data interactive information based on the first relevance degree, wherein the first semantic convergence degree is used for reflecting the semantic tendency degree of each semantic node in the non-interactive information with respect to each semantic node in the big data interactive information.

And a substep S122, determining corresponding decision interaction semantic nodes from the first decision interaction semantic node sequence according to the sequence of the first semantic convergence from high to low, and using the decision interaction semantic nodes as first target semantic nodes.

And a substep S123 of generating corresponding semantic nodes at corresponding positions in the non-interactive information according to the semantic sequence of the first target semantic node in the big data interactive information and the semantic labels corresponding to the first target semantic node.

In a possible implementation manner, for step S140, in the process of performing semantic node feature labeling processing on the non-interactive information according to the second association relationship and the semantic component of the semantic node in the non-interactive information to obtain feature labeled interactive information, the following exemplary sub-steps may be implemented, which are described in detail below.

And a substep S141, determining decision interactive semantic nodes from the target semantic comprehensive characteristic information according to the second incidence relation and the semantic sequence of the semantic nodes in the target semantic comprehensive characteristic information, and obtaining a second decision interactive semantic node sequence.

And a substep S142, determining a second target semantic node from the second decision interaction semantic node sequence based on the known semantic node and the semantic component in the non-interaction information.

And a substep S143, generating corresponding semantic nodes at corresponding positions in the non-interactive information based on the semantic components and the semantic labels corresponding to the second target semantic nodes, so as to perform semantic node feature labeling processing on the non-interactive information to obtain feature labeled interactive information.

On the basis, the interactive semantic vector of the non-interactive information can comprise the semantic label of each known semantic node in the non-interactive information and the semantic sequence in the non-interactive information, and the interactive semantic vector of the target semantic comprehensive characteristic information comprises the semantic label of each semantic node in the target semantic comprehensive characteristic information and the semantic sequence in the target semantic comprehensive characteristic information.

Thus, for step S130, in the process of determining the second association relationship between the interactive semantic vector of the target semantic synthesis feature information and the interactive semantic vector of the non-interactive information, the following exemplary sub-steps can be further implemented, which are described in detail below.

And a substep S131, respectively constructing semantic feature vectors of each semantic node in the non-interactive information and the target semantic synthesis feature information to obtain a plurality of third embedded representations and a plurality of fourth embedded representations, and determining a second association degree between each third embedded representation and each fourth embedded representation to obtain a second association relation.

Therefore, in the sub-step S141, a second semantic convergence degree of each semantic node in the non-interactive information with respect to each semantic node in the target semantic synthesis feature information may be determined specifically based on the second relevance degree, where the second semantic convergence degree is used to reflect a semantic tendency degree of each semantic node in the non-interactive information with respect to each semantic node in the target semantic synthesis feature information. And then, determining decision interactive semantic nodes from the target semantic comprehensive characteristic information according to the second semantic convergence and the semantic sequence of the semantic nodes in the target semantic comprehensive characteristic information to obtain a second decision interactive semantic node sequence.

In a possible implementation manner, further referring to step S110, in the process of determining the non-interactive information in the current interactive engagement location according to the information to be interacted, the following exemplary sub-steps may be further implemented, which are described in detail below.

And a substep S101, obtaining a known semantic node in the current interactive joining position, determining initial interactive information at least based on the known semantic node in the current interactive joining position, and constructing a semantic feature vector of the known semantic node in the initial interactive information.

And a substep S102, determining the association degree between the semantic node to be interacted and the corresponding known semantic node according to the semantic feature vector of the semantic node to be interacted and the semantic feature vector of the known semantic node in the information to be interacted.

And a substep S103, determining a third semantic convergence degree of each known semantic node in the initial interaction information about the semantic node to be interacted based on the association degree between the semantic node to be interacted and the corresponding known semantic node, wherein the third semantic convergence degree is used for reflecting the semantic tendency degree of each semantic node in the initial interaction information to the semantic node to be interacted in the interaction information.

And step S104, performing supplementary updating on the semantic feature vectors of the known semantic nodes in the initial interaction information according to the third semantic convergence degree to obtain non-interaction information.

On this basis, the manner for determining the big data interaction information based on the interaction information list in the historical time period may specifically be: firstly, an interactive information list in a historical time period is collected, and then a plurality of pieces of historical interactive information are constructed according to the appointed interactive connection position and the interactive information list. On the basis, a plurality of pieces of historical interaction information can be aligned according to time, a semantic node with the highest display frequency under the same time slice is determined from the aligned plurality of pieces of historical interaction information, the target historical interaction information is obtained by constructing according to the semantic node with the highest display frequency under the same time slice, and then the semantic feature vector of each semantic node in the target historical interaction information is constructed, so that the association degree between every two semantic nodes in the target historical interaction information can be determined according to the semantic feature vector of each semantic node. Then, a fourth semantic convergence degree of each semantic node in the target historical interaction information with respect to other semantic nodes can be determined based on the association degree between every two semantic nodes, wherein the fourth semantic convergence degree is used for reflecting the semantic tendency degree of each semantic node in the target historical interaction information to other semantic nodes in the interaction information. Therefore, the semantic feature vectors of the semantic nodes in the target historical interaction information can be supplemented and updated according to the fourth semantic convergence degree, and the big data interaction information is obtained.

In a possible implementation manner, for step S120, in the process of extracting a decision interaction semantic node satisfying a conditional decision of non-interaction information from big data interaction information based on a deep learning model to obtain a first decision interaction semantic node sequence, the following exemplary sub-steps may be further implemented, which are described in detail below.

And a substep S124, identifying a plurality of conditional decision interaction segments matched with the current service scene from the non-interactive information based on the deep learning model, taking each conditional decision interaction segment in the plurality of conditional decision interaction segments as the current conditional decision interaction segment, and executing the following steps until the plurality of conditional decision interaction segments are traversed:

(1) and acquiring a segmented feature vector of a service decision segment under the condition that the service decision segment of the interactive service contained in the big data interactive information is detected by the current condition decision interactive segment based on the deep learning model.

In this embodiment, the deep learning model may be trained in advance, for example, a large amount of interaction information may be collected, and a service decision segmented label of each interaction information may be obtained by performing network training.

(2) And converting the service decision into a first service parameter in a segmented manner according to the conversion relation between the characteristic vector value and the service parameter in a preset conversion table, and determining the first service parameter as a target service parameter of the big data interaction information and the current condition decision interaction segment.

Wherein, each target service parameter is a service parameter from big data interaction information to a conditional decision interaction section.

(3) Dividing an interactive data unit corresponding to non-interactive information into a plurality of interactive data subunits, determining each interactive data subunit as a current interactive data subunit, and executing the following steps until each interactive data subunit is traversed:

(4) determining each conditional decision interaction segment as a current conditional decision interaction segment, and executing the following steps until the conditional decision interaction segments are traversed:

(5) and under the condition that the service parameters of the current interactive data subunit and the current conditional decision interactive section are the target service parameters corresponding to the current conditional decision interactive section, determining the matching degree of the current interactive data subunit and the current conditional decision interactive section as a first numerical value.

(6) And under the condition that the service parameters of the current interactive data subunit and the current conditional decision interactive section are greater than or less than the target service parameters corresponding to the current conditional decision interactive section, determining the matching degree to be zero, wherein the matching degree is determined according to the position of the current interactive data subunit, the position of the conditional decision interactive section and a group of target service parameters.

Substep S125, determining a target matching degree of the big data interaction information matching the current interaction data subunit according to a product of all matching degrees of the current interaction data subunit, obtaining a service location of the interaction data subunit corresponding to a maximum matching degree in the target matching degrees, and determining the service location as a target service location of the big data interaction information in a first decision interaction node, and generating interaction offset update information of the big data interaction information in the interaction data unit by using position information of a plurality of target service locations under the condition that the target service locations of the big data interaction information of the decision interaction nodes are determined respectively, wherein the plurality of decision interaction nodes comprise a first decision interaction node and a decision interaction node behind the first decision interaction node, under the condition that the plurality of interaction offset update information generated in the interaction data unit in the target time period are obtained, and determining each interaction offset updating information as an interaction offset updating information clique.

And a substep S126, executing the following steps until the relevance of each two interactive offset update information groups is greater than or equal to a predetermined threshold value:

(1) determining one interactive offset updating information group of the two interactive offset updating information groups as a current interactive offset updating information group, determining the other interactive offset updating information group as a target interactive offset updating information group, determining each interactive offset updating information group in the current interactive offset updating information group as current interactive offset updating information, and executing the following steps until the current interactive offset updating information group is traversed:

(2) a first degree of association between the current interaction offset update information and each interaction offset update information in the target interaction offset update information blob is determined.

(3) After the traversal is completed, determining the average value of the first relevance degrees as the relevance degree.

(4) And merging the two interactive offset updating information cliques with the minimum relevance into a new interactive information clique.

Substep S127, after the above steps are performed, obtaining a plurality of first interaction offset update information cliques, determining each first interaction offset update information clique as a type of interaction offset update information, after a type of interaction offset update information is obtained, determining one piece of interaction offset update information in the type of interaction offset update information as current interaction offset update information, and determining the other piece of interaction offset update information as first interaction offset update information, and performing the following steps until all pieces of interaction offset update information in the type of interaction offset update information are traversed:

and a substep S128, obtaining common tags corresponding to each two service types in the current interaction offset update information and the first interaction offset update information, determining a tag migration relationship of the common tags as new current interaction offset update information, and determining one interaction offset update information in the remaining interaction offset update information in the class of interaction offset update information as the first interaction offset update information.

And a substep S129, after the traversal is completed, determining a piece of finally determined current interaction offset update information as hotspot interaction information of a type of interaction offset update information, determining two pieces of second interaction offset update information from the type of interaction offset update information, and acquiring a common tag of two corresponding service types under the condition that the service association degree of the corresponding service types on the two pieces of second interaction offset update information is smaller than a second threshold value. After a plurality of common labels are obtained, the label migration relation of the common labels is determined as the optimal public sub-interaction information of a type of interaction information, so that decision interaction semantic nodes are obtained, and a first decision interaction semantic node sequence is obtained through summarization.

Based on the design, in the process of determining the interactive information of the big data interactive information, the service parameters of the service parameter condition decision interactive section of the big data interactive information can be detected through a plurality of condition decision interactive sections, so that the position of the big data interactive information can be determined, and the position accuracy of the determined big data interactive information is high. And further determining the interactive information of the big data interactive information according to the position, and determining the hotspot interactive information according to the interactive information of the big data interactive information, thereby realizing the effect of improving the accuracy of determining the hotspot interactive information.

In a possible implementation manner, in the process of sending the interactive content to the intelligent interactive terminal 200 according to the feature tag interactive information, specifically, a target knowledge point corresponding to each feature tag interactive node may be obtained from the feature tag interactive information, and then the interactive knowledge content corresponding to each target knowledge point is obtained, so that the interactive knowledge content corresponding to each target knowledge point is sent to the intelligent interactive terminal 200.

Further, for example, the information processing method based on deep learning and big data provided by this embodiment may further include the following steps:

step S150, obtaining that the intelligent interactive terminal 200 returns corresponding redundant correction data based on the interactive content, so as to obtain redundant correction big data composed of a plurality of redundant correction data.

Step S160, obtaining at least one redundant service source object according to the redundant correction big data.

Step S170, based on the coded vector representation under the redundant label and a preset artificial intelligence model, performing data analysis on the matching content data of the interactive knowledge points corresponding to the interactive content to obtain redundant content feature vectors and corresponding redundant parameters of the interactive knowledge points.

And step S180, updating the matching content data of the interactive knowledge points according to the redundant content characteristic vectors and the corresponding redundant parameters of the interactive knowledge points, and uploading the updated matching content data of the interactive knowledge points to corresponding block chains.

In this embodiment, the redundant correction data may be used to indicate a redundant data area of an original problem corresponding to information to be interacted in the interactive content, and specifically, a user of the intelligent interactive terminal 200 may mark the interactive content and upload the marked interactive content, which is not specifically limited herein.

In this embodiment, each object feature vector in each redundant service source object belongs to the same redundant tag, and each object feature vector includes a coded vector representation under the redundant tag to which it belongs.

Based on the design, the embodiment returns the corresponding redundancy correction data based on the interactive content by the intelligent interactive terminal to obtain the redundancy correction big data composed of a plurality of redundancy correction data, then at least one redundant service source object is obtained according to the redundant correction big data, and then based on the coded vector representation under the redundant label in the redundant service source object and the preset artificial intelligence model, performing data analysis on the matching content data of the interactive knowledge points corresponding to the interactive content to obtain redundant content feature vectors and corresponding redundant parameters of the interactive knowledge points, therefore, the redundant data of the sent interactive content can be updated in a characteristic identification mode, not simple content shielding, and further, the experience of the user on the acquired information is improved, and the influence of the introduction of redundant data on the accuracy and the matching degree of the interactive content is reduced.

For example, for step S170, in the process of performing data analysis on the matching content data of the interactive knowledge points corresponding to the interactive content based on the coded vector representations under the redundant tags and the preset artificial intelligence model to obtain the redundant content feature vectors and the corresponding redundant parameters of the interactive knowledge points, the following exemplary sub-steps may be specifically implemented for performing accurate feature recognition, which are described in detail below.

And a substep S171, traversing the object characteristic vector in the redundant service source object for each redundant service source object, extracting the coding vector segment comprising each coding vector represented by the redundant label to which the redundant service source object belongs from the object characteristic vector, and determining the redundant feedback information corresponding to the redundant service source object from the matching content data of the interactive knowledge point corresponding to the interactive content according to the extracted coding vector segment.

And a substep S172, extracting the redundant content characteristic vectors of the redundant feedback nodes meeting the requirement of the preset redundant parameters from the redundant feedback information according to a preset artificial intelligence model, and obtaining the redundant content characteristic vectors of the interactive knowledge points and the corresponding redundant parameters.

Exemplarily, for the sub-step S172, it can be further realized by the following exemplary sub-steps, which are described as follows.

And a substep S1721, identifying the meta-object analysis data of the redundant analysis item from the redundant feedback information according to a preset artificial intelligence model.

In this embodiment, the meta-object parsing data includes parsing data corresponding to at least two source elements.

And a substep S1722, respectively constructing an arrangement relation model between each interpretation type source element and the text source element based on the element association relation between the redundant analysis item corresponding to each interpretation type source element and the redundant analysis item corresponding to the text source element.

In this embodiment, the layout relationship model corresponding to each interpretative source element is used to represent an association relationship between each interpretative source element and the text source element, and the element in the layout relationship model is used to represent an element association relationship between the redundant analytic item corresponding to each interpretative source element and the redundant analytic item corresponding to the text source element, where the text source element is one of the specified at least two source elements, and the interpretative source element is a source element other than the text source element in the at least two source elements.

And a substep S1723, obtaining a first redundancy decision result through the first decision tree model based on the data of the text source element, wherein the first redundancy decision result comprises a redundancy representation before redundancy calculation corresponding to the text source element.

And a substep S1724 of obtaining a second redundant decision result through a second decision tree model based on the data of each interpretation type source element and the incidence relation between each interpretation type source element and the text source element.

For example, a sub-redundancy decision result corresponding to each interpretation source element can be obtained through the second decision tree model based on the data of each interpretation source element and the incidence relation between each interpretation source element and the text source element, and then a second redundancy decision result can be obtained based on the sub-redundancy decision result corresponding to each interpretation source element and the weight corresponding to each interpretation source element.

And a substep S1725 of obtaining a final redundancy decision result based on the first redundancy decision result and the second redundancy decision result.

And a substep S1726, extracting redundant content feature vectors and corresponding redundant parameters of the interactive knowledge points from the data under each redundant decision classification label of the final redundant decision result, wherein the redundant parameters are the redundant parameters corresponding to the redundant decision classification labels.

Optionally, in sub-step S1723, a redundant engagement corresponding to the text source element may be calculated based on the data of the text source element, wherein the redundant engagement corresponding to the text source element is related to the amount of content pre-marked by the artificial intelligence model in the data of the text source element. And then, based on the redundancy participation degree corresponding to the text source element, obtaining a first redundancy decision result through a first decision tree model.

Therefore, in the process of obtaining the sub-redundancy decision result corresponding to each interpretation source element through the second decision tree model based on the data of each interpretation source element and the incidence relation between each interpretation source element and the text source element, the redundancy participation degree corresponding to each interpretation source element can be calculated based on the data of each interpretation source element, wherein the redundancy participation degree corresponding to each interpretation source element is related to the content quantity marked in advance by the artificial intelligence model in the data of the interpretation source element. And then, obtaining a sub-redundancy decision result corresponding to each interpretation type source element through a second decision tree model based on the redundancy participation degree corresponding to each interpretation type source element and the arrangement relation model corresponding to each interpretation type source element.

It should be noted that the layout relationship model corresponding to each interpretation source element is used to represent an association relationship between each interpretation source element and a text source element, the layout relationship model corresponding to each interpretation source element is a model constructed based on an element association relationship between a redundant analysis item corresponding to each interpretation source element and a redundant analysis item corresponding to the text source element, and an element in the layout relationship model is used to represent an element association relationship between a redundant analysis item corresponding to each interpretation source element and a redundant analysis item corresponding to the text source element.

In one possible implementation, step S180 may be specifically implemented by the following exemplary sub-steps, which are described in detail below.

And a substep S181 of matching a target content data area to be updated and a service tag corresponding to the target content data area from the matching content data of the interactive knowledge point according to the redundant content feature vector of the interactive knowledge point.

And a substep S182, parsing a corresponding target redundancy parameter from the corresponding redundancy parameter according to the service tag corresponding to the target content data region, and updating related data information in the target content data region to be updated according to the redundancy semantic feature corresponding to the target redundancy parameter, wherein the updating mode includes a deletion mode and a replacement mode.

Therefore, relevant data information in the target content data area to be updated is updated according to the redundant semantic features corresponding to the target redundant parameters, the service label corresponding to the target content data area is considered, unnecessary redundant data can be prevented from being removed when the relevant data information in the target content data area to be updated is updated, and excessive error updating caused by subjective mapping of a user is avoided.

Based on the same inventive concept, please refer to fig. 3, which illustrates a functional module diagram of an information processing apparatus 300 based on deep learning and big data according to an embodiment of the present application, and the embodiment can perform functional module division on the information processing apparatus 300 based on deep learning and big data 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 functional module by corresponding each function, the information processing apparatus 300 based on deep learning and big data shown in fig. 3 is only an apparatus diagram. The deep learning and big data based information processing apparatus 300 may include an obtaining module 310, an extracting module 320, a determining module 330, and a sending module 340, and the functions of the functional modules of the deep learning and big data based information processing apparatus 300 are described in detail below.

The obtaining module 310 is configured to obtain information to be interacted sent by the intelligent interactive terminal 200, determine non-interactive information in a current interaction connection position according to the information to be interacted, and determine a first association relationship between an interactive semantic vector of the non-interactive information and an interactive semantic vector of big data interactive information, where the big data interactive information is determined based on an interactive information list in a historical time period. It is understood that the obtaining module 310 may be configured to perform the step S110, and for a detailed implementation of the obtaining module 310, reference may be made to the content related to the step S110.

The extraction module 320 is configured to extract decision-making interactive semantic nodes meeting the conditional decision of the non-interactive information from the big data interactive information based on the deep learning model to obtain a first decision-making interactive semantic node sequence, determine a first target semantic node from the first decision-making interactive semantic node sequence based on the first association relationship, and perform supplementary update on semantic node information of the non-interactive information according to the first target semantic node to obtain target semantic comprehensive feature information. It is understood that the extracting module 320 may be configured to perform the step S120, and for the detailed implementation of the extracting module 320, reference may be made to the content related to the step S120.

The determining module 330 is configured to determine a second association relationship between the interactive semantic vector of the target semantic synthesis feature information and the interactive semantic vector of the non-interactive information. It is understood that the determining module 330 can be used to perform the step S130, and for the detailed implementation of the determining module 330, reference can be made to the contents related to the step S130.

And the sending module 340 is configured to perform feature labeling processing on the non-interactive information according to the second association relationship and the semantic component of the semantic node in the non-interactive information to obtain feature labeled interactive information, and store the interactive content in the corresponding block chain after sending the interactive content to the intelligent interactive terminal 200 according to the feature labeled interactive information. It is understood that the sending module 340 can be used to execute the step S140, and for the detailed implementation of the sending module 340, reference can be made to the above-mentioned contents related to 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 can be realized in the form of software called by 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 obtaining 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 processing element of the apparatus calls and executes the functions of the obtaining module 310. 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 the blockchain service platform 100 for implementing the control device according to an embodiment of the present invention, and as shown in fig. 4, the blockchain service 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 obtaining module 310, the extracting module 320, the determining module 330, and the sending module 340 included in the deep learning and big data based information processing apparatus 300 shown in fig. 3), so that the processor 110 may execute the deep learning and big data based information processing 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 the transceiving action of the transceiver 140, so as to perform data transceiving with the intelligent interactive terminal 200.

For a specific implementation process of the processor 110, reference may be made to the above-mentioned various method embodiments executed by the blockchain service platform 100, which implement principles and technical effects are similar, and this embodiment is 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 invention also provides a readable storage medium, wherein the readable storage medium stores computer execution instructions, and when a processor executes the computer execution instructions, the information processing method based on deep learning and big data is realized.

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 adaptations to the present description may occur to those skilled in the art, although not explicitly described herein. Such modifications, improvements and adaptations are proposed in the present specification and thus fall within the spirit and scope of the exemplary embodiments of the present 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 situations, 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 represented as a computer product, including computer readable program code, embodied in one or more computer readable media.

The computer storage medium may comprise a propagated data signal with the computer program code embodied therewith, for example, on 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. Program code located on a 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.

Computer program code required for the operation of various portions of this specification may 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, and the like, 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. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or block chain service 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 the process are recited in the specification, the use of alphanumeric characters, or other designations, is not intended to limit the order in which the processes and methods of the specification occur, unless otherwise specified 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 blockchain service 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 processing method based on deep learning and big data is characterized by being applied to a block chain service platform in communication connection with an intelligent interactive terminal, and the method comprises the following steps:

2. The deep learning and big data based information processing method according to claim 1, wherein the interactive semantic vector of the non-interactive information includes a semantic label of each known semantic node in the non-interactive information and a semantic order in the non-interactive information; the interactive semantic vector of the big data interactive information comprises a semantic label of each semantic node in the big data interactive information and a semantic sequence in the big data interactive information;

3. The deep learning and big data based information processing method according to claim 1, wherein the step of performing semantic node feature labeling processing on the non-interactive information according to the second association relationship and semantic components of semantic nodes in the non-interactive information to obtain feature labeled interactive information comprises:

4. The deep learning and big data based information processing method according to claim 1, wherein the step of determining the non-interactive information in the current interactive engagement location according to the information to be interacted comprises:

acquiring an interaction information list in a historical time period;

5. The deep learning and big data based information processing method according to any of claims 1-4, wherein the step of extracting decision interaction semantic nodes satisfying the conditional decision of the non-interaction information from the big data interaction information based on the deep learning model to obtain a first decision interaction semantic node sequence comprises:

6. A blockchain service platform, wherein the blockchain service platform is communicatively connected to an intelligent interactive terminal, the blockchain service platform comprises a processor, a machine-readable storage medium, and a network interface, wherein the machine-readable storage medium, the network interface, and the processor are connected through a bus system, the network interface is configured to be communicatively connected to at least one network communication device, the machine-readable storage medium is configured to store a program, instructions, or code, and the processor is configured to execute the program, instructions, or code in the machine-readable storage medium to perform the following steps:

7. The blockchain service platform of claim 6, wherein the interactive semantic vector of the non-interactive information includes a semantic label of each known semantic node in the non-interactive information and a semantic order in the non-interactive information; the interactive semantic vector of the big data interactive information comprises a semantic label of each semantic node in the big data interactive information and a semantic sequence in the big data interactive information;

the method for determining the first association relationship between the interactive semantic vector of the non-interactive information and the interactive semantic vector of the big data interactive information comprises the following steps:

8. The blockchain service platform of claim 6, wherein the manner of performing semantic node feature tag processing on the non-interactive information according to the second association relationship and semantic components of semantic nodes in the non-interactive information to obtain feature tag interactive information includes:

the method for determining the second association relationship between the interactive semantic vector of the target semantic synthesis feature information and the interactive semantic vector of the non-interactive information includes:

determining decision interactive semantic nodes from the target semantic comprehensive characteristic information according to the second incidence relation and the semantic sequence of the semantic nodes in the target semantic comprehensive characteristic information to obtain a second decision interactive semantic node sequence, wherein the method comprises the following steps:

9. The blockchain service platform of claim 6, wherein the manner of determining the non-interactive information in the current interactive engagement location according to the information to be interacted with comprises:

acquiring an interaction information list in a historical time period;

10. The blockchain service platform according to any one of claims 6 to 9, wherein the manner of extracting decision interaction semantic nodes satisfying the conditional decision of the non-interaction information from the big data interaction information based on the deep learning model to obtain a first decision interaction semantic node sequence includes:

taking each conditional decision interaction segment in the plurality of conditional decision interaction segments as a current conditional decision interaction segment, and executing the following modes until the plurality of conditional decision interaction segments are traversed:

dividing an interactive data unit corresponding to the non-interactive information into a plurality of interactive data subunits, determining each interactive data subunit as a current interactive data subunit, and executing the following modes until each interactive data subunit is traversed:

determining each conditional decision interaction segment as a current conditional decision interaction segment, and executing the following modes until the conditional decision interaction segments are traversed:

performing the following until the association degree of each two interactive offset update information globes is greater than or equal to a predetermined threshold value:

determining one of the two interactive offset update information cliques as a current interactive offset update information clique, determining the other interactive offset update information clique as a target interactive offset update information clique, determining each interactive offset update information in the current interactive offset update information clique as current interactive offset update information, and executing the following modes until the current interactive offset update information cliques are traversed:

after the above manner is executed, obtaining a plurality of first interaction offset update information groups, and determining each first interaction offset update information group as a type of the interaction offset update information;