CN112948669A

CN112948669A - Business processing method based on big data and artificial intelligence and block chain financial platform

Info

Publication number: CN112948669A
Application number: CN202110156338.6A
Authority: CN
Inventors: 吕维东
Original assignee: Individual
Current assignee: Individual
Priority date: 2020-08-02
Filing date: 2020-08-02
Publication date: 2021-06-11
Also published as: CN112948671A; CN111931049A; CN111931049B

Abstract

The embodiment of the invention provides a business processing method based on big data and artificial intelligence and a block chain financial platform, which extract the entity relation characteristics of each business keyword list in a way of entity relation identification, determine the form operation track of each business keyword label corresponding to the business service scene based on the entity business item grade, convert each business processing flow into an effective push classification basis, thereby label the form operation track corresponding to the business service scene according to each business keyword, determine the form tracking thermalization table item corresponding to each business service scene by adopting an artificial intelligence model, generate the recommendation image characteristics of the information recommendation process corresponding to the business request information, and then push the corresponding request recommendation information to the digital financial service terminal, thereby effectively combining the specific types of the business service scenes to carry out request response recommendation according to the business request information, and further improve the classification precision of information push.

Description

Business processing method based on big data and artificial intelligence and block chain financial platform

Technical Field

The invention relates to the technical field of big data and artificial intelligence, in particular to a business processing method based on big data and artificial intelligence and a block chain financial platform.

Background

The digital financial service terminals distributed all over the service points can provide convenient inquiry service of business push information for users, thereby facilitating the users to know various information and relevant service use conditions of the digital financial service in time.

However, through research by the present inventors, it is found that, in the process of a service request of a digital financial service terminal, for different types of service scenarios (e.g., a blockchain payment service, a digital currency service, etc.), a request response recommendation cannot be effectively performed in combination with a specific type of the service scenario according to service request information, so that the classification accuracy of information push is low.

Disclosure of Invention

In order to overcome at least the above disadvantages in the prior art, the present invention provides a service processing method and a blockchain financial platform based on big data and artificial intelligence, which can effectively combine the specific types of service scenes to perform request response recommendation according to service request information, thereby improving the classification accuracy of information push.

In a first aspect, the present invention provides a business processing method based on big data and artificial intelligence, which is applied to a blockchain financial platform, wherein the blockchain financial platform is in communication connection with a plurality of digital financial service terminals, and the method includes:

acquiring at least one business keyword list from business request information of the digital financial service terminal in a preset time period, wherein each business keyword label in each business keyword list belongs to the same business service scene, and each business keyword label corresponds to a business processing flow under the business service scene to which the business keyword label belongs;

performing entity relationship identification on the business keyword list based on each business processing flow under the business service scene to obtain entity relationship characteristics of each business keyword list and corresponding entity business item grades;

determining a form operation track of a business service scene corresponding to each business keyword label according to the entity relation characteristics and the corresponding entity business item grades;

marking form operation tracks corresponding to the business service scenes according to the business keywords, determining form tracking thermalization entries corresponding to the business service scenes by adopting an artificial intelligence model, generating recommended portrait characteristics of an information recommendation process corresponding to the business request information according to the form tracking thermalization entries corresponding to the business service scenes, and pushing corresponding request recommendation information to the digital financial service terminal according to the recommended portrait characteristics of the information recommendation process.

In a possible implementation manner of the first aspect, the step of obtaining at least one service keyword list from the service request information of the digital financial service terminal in a preset time period includes:

and acquiring the service keyword labels of the same service scene of the service scene from the service request information of the digital financial service terminal in a preset time period, and determining the service keyword labels belonging to each service scene as a corresponding service keyword list.

In a possible implementation manner of the first aspect, the step of performing entity relationship identification on the service keyword list based on each service processing flow in the service scenario to obtain an entity relationship characteristic of each service keyword list and a corresponding entity service item level includes:

traversing the service keyword labels in the service keyword lists for each service keyword list, extracting service keyword description representations of each service processing flow under the service scene to which the service keyword list belongs from the service keyword labels, and determining service logic information corresponding to the service keyword lists according to the extracted service keyword description representations;

removing set description information contained in each service keyword description representation in the service logic information, performing service pushing feature segmentation and splitting on the service keyword description representation from which the set description information is removed to obtain first service logic information, and determining entity relationship strength of each service pushing feature segment according to service logic strength of the service pushing feature segment in the service keyword description representation contained in the first service logic information;

removing service pushing feature segments with entity relation strength smaller than a preset entity relation strength threshold value in the first service logic information to obtain second service logic information, taking the service pushing feature segments with the entity relation strength not smaller than the preset entity relation strength threshold value as first service pushing feature segments to obtain a first service pushing feature segment list, and determining a second service pushing feature segment list which corresponds to each first service pushing feature segment and is formed by service pushing feature segments connected after the first service pushing feature segments according to matching information of each first service pushing feature segment in the first service pushing feature segment list in the second service logic information;

judging whether the second service pushing feature segment list is empty or not, if the second service pushing feature segment list is empty, circularly returning, and if the second service pushing feature segment list is not empty, counting the entity relationship strength of each service pushing feature segment in the second service pushing feature segment list, and judging whether the entity relationship strength of each service pushing feature segment meets the minimum entity relationship strength condition or not;

if the entity relationship strength of the service pushing feature segment does not meet the minimum entity relationship strength condition, circularly returning, if the entity relationship strength of the service pushing feature segment meets the minimum entity relationship strength condition, splicing the service pushing feature segment with a first service pushing feature segment corresponding to the second service pushing feature segment list to obtain a new first service pushing feature segment, determining a second service pushing feature segment list of the new first service pushing feature segment, and performing circular identification on the second service pushing feature segment list corresponding to the new first service pushing feature segment to obtain all target first service pushing feature segments meeting the minimum entity relationship strength condition and corresponding entity relationship strengths;

the data returned circularly is all the currently obtained target first service pushing characteristic segments meeting the minimum entity relation strength condition and the corresponding entity relation strength, all the target first service pushing characteristic segments meeting the minimum entity relation strength condition and the corresponding entity relation strength are obtained, the target first service pushing characteristic segments are used as the entity relation characteristics of the service keyword list, and the entity relation strength of each target first service pushing characteristic segment in the second service pushing characteristic segment list is used as the entity service item grade corresponding to the entity relation characteristics.

In a possible implementation manner of the first aspect, the step of determining, according to the entity relationship feature and the corresponding entity business item level, a form operation trajectory of a business service scenario to which each business keyword label corresponds includes:

screening the entity relation characteristics according to the entity relation characteristics and the corresponding entity business item grades to obtain marked entity relation characteristics of which the entity business item grades are greater than the preset entity business item grades;

obtaining a first form operation element list corresponding to a first entity relationship object and a second form operation element list corresponding to a second entity relationship object on a mark entity relationship characteristic, wherein the first form operation element list comprises a plurality of form operation nodes for performing form operation on related form areas in the mark entity relationship characteristic by the first entity relationship object, the second form operation element list comprises a plurality of form operation nodes for performing form operation on the related form areas in the mark entity relationship characteristic by the second entity relationship object, and each form operation node comprises a plurality of form operation node components;

based on the category of preset form operation nodes, performing Gaussian classification on a plurality of form operation nodes in the first form operation element list to obtain a first form operation element list after Gaussian classification; the preset form operation node category belongs to types corresponding to a plurality of form operation node components;

combining all form operation node components corresponding to each preset form operation node category in the first form operation element list after Gaussian classification into a first initial form operation node list;

removing the duplicate of the first initial form operation node list to obtain a first form operation node list, so as to obtain a first form operation node list corresponding to the preset form operation node category list;

combining each form operation node component in the first form operation node list into a first form operation node component list corresponding to the first entity relationship object, wherein the first form operation node component list corresponds to a preset form operation node category list, and the preset form operation node category type is a list formed by various form operation node categories used for form operation crawling;

extracting, from the second form operation element list, each form operation node component corresponding to each preset form operation node category in the preset form operation node category list, and combining the extracted component into a second form operation node component list corresponding to the second entity relationship object, where the second form operation node component list corresponds to the preset form operation node category list, and the first form operation node component list and the second form operation node component list are lists composed of form operation node components extracted from the corresponding form operation element list, respectively;

determining track nodes of the same form operation node components between the first form operation node component list and the second form operation node component list, and obtaining operation description values from track range values corresponding to the track nodes;

when the operation description value is larger than a preset description value threshold value, determining that the first entity relationship object and the second entity relationship object are form operation units;

using any two entity relationship elements in the marked entity relationship characteristic as a first entity relationship object and a second entity relationship object to perform form operation crawling, and obtaining a form operation unit list with form operation behaviors in the marked entity relationship characteristic until the detection of the entity relationship elements in the marked entity relationship characteristic is completed;

taking the track node of the entity relation element in the form operation unit list as the track node of the target form operation unit;

taking the track node of the entity relationship element corresponding to the marked entity relationship characteristic as a target total entity relationship element track node;

calculating track segmentation of the target form operation unit track node and the target total entity relationship element track node to obtain track segmentation characteristics corresponding to the mark entity relationship characteristics;

and when the track segmentation characteristics meet the preset segmentation length, determining the track formed by the track segmentation characteristics corresponding to the mark entity relation characteristics as the form operation track of the business service scene corresponding to each business keyword mark.

In a possible implementation manner of the first aspect, the step of determining, by using an artificial intelligence model, a form tracking thermalization entry corresponding to each business service scenario according to the form operation trajectory of the business service scenario to which each business keyword tag corresponds includes:

obtaining a corresponding track passing service section and an initial service table entry of the track passing service section from the form operation track of the business service scene corresponding to each business keyword label;

classifying the track via service segments according to a pre-trained artificial intelligence model to obtain classified service table entries;

comparing the initial service table entry with the classified service table entry to obtain table entry matching information;

and determining a form tracking thermalization table entry corresponding to each business service scene according to the table entry matching information.

In a possible implementation manner of the first aspect, the initial service entry includes at least one initial sub-service entry, and the classification service entry includes at least one classification sub-service entry;

the step of comparing the initial service table entry with the classification service table entry to obtain table entry matching information includes:

fusing each initial sub-service table entry with each classified sub-service table entry respectively to obtain sub-fusion information, and obtaining at least one piece of sub-fusion information when the fusion of at least one classified sub-service table entry is completed; the at least one classification sub-service table entry corresponds to the at least one sub-fusion information one to one, and the sub-fusion information represents whether the initial sub-service table entry is matched with the classification sub-service table entry or not;

splicing the at least one piece of sub-fusion information to obtain fusion information corresponding to each initial sub-service table entry; the fusion information represents whether a classification sub-service table item fused with an initial sub-service table item exists or not, and the fusion information corresponds to each initial sub-service table item;

extracting the initial sub-service table entry of the classification sub-service table entry with fusion represented by the fusion information in the at least one initial sub-service table entry to obtain a fusion initial sub-service table entry;

according to the fusion information, extracting a classification sub-service table item fused with the fusion initial sub-service table item from the at least one classification sub-service table item to serve as a fusion classification sub-service table item;

splicing the initial sub-service table entries except for the fused initial sub-service table entry in the at least one initial sub-service table entry to obtain an initial splicing information list;

splicing the classified sub-service table entries except for the fused classified sub-service table entry in the at least one classified sub-service table entry to obtain a classified splicing information list;

splicing the initial splicing information list and the classified splicing information list to obtain the table item matching information;

the initial sub-service table entry comprises initial service label information, initial service main key information and initial associated object information, and the classification sub-service table entry comprises classification service label information, classification service main key information and classification associated object information.

In a possible implementation manner of the first aspect, each initial sub-service entry includes initial service tag information and initial service main key information, and each classification sub-service entry includes classification service tag information and classification service main key information;

the step of fusing each initial sub-service table entry with each classified sub-service table entry to obtain sub-fusion information, and obtaining at least one sub-fusion information when the fusion of at least one classified sub-service table entry is completed includes:

coding the initial service label information with the classified service label information of each classified sub-service table entry respectively to obtain coding discrimination information corresponding to each classified sub-service table entry; the coding discrimination information represents whether the initial service label information is the same as the classified service label information;

determining an initial service main key interface by using the initial service main key information, and determining a classification service main key interface of each classification sub-service table entry by using the classification service main key information of each classification sub-service table entry;

according to the initial service main key interface and each classified service main key interface, obtaining interface association information corresponding to each classified service main key interface and the initial service main key interface and a corresponding splicing result corresponding to each classified service main key interface and the initial service main key interface;

and obtaining at least one piece of sub-fusion information by using the interface correlation information and the splicing result.

In a possible implementation manner of the first aspect, the step of determining, according to the entry matching information, a form tracking thermalization entry corresponding to each of the service scenarios includes:

and acquiring target tracking thermalization items corresponding to each item matching node from the item matching information, and using each target tracking thermalization item as a form tracking thermalization item corresponding to each service scene in a clustering and arranging manner.

In a possible implementation manner of the first aspect, the step of generating a recommended portrait feature of an information recommendation process corresponding to the service request information according to a form tracking thermalization entry corresponding to each service scenario, and pushing corresponding request recommendation information to the digital financial service terminal according to the recommended portrait feature of the information recommendation process includes:

acquiring table item service access information, service access object information associated with the table item service access information and historical access object information from an information list mapped by a form tracking thermalization table item corresponding to each service scene, wherein the historical access object information comprises access object information of at least one historical access request;

inputting the service access object information and the historical access object information into a machine learning model, performing service pushing feature extraction on the service access object information through the machine learning model to obtain a first service pushing feature vector, and performing service pushing feature extraction on each historical access object information to obtain a second service pushing feature vector;

splicing the quantities in the first service push characteristic vector to obtain a first service access authentication vector used for expressing the service access authentication of the service access object information, and splicing the quantities in the second service push characteristic vector to obtain a second service access authentication vector used for expressing the service access authentication of the historical access object information;

calculating the Hamming distance between the first service access authentication vector and each second service access authentication vector, and taking the calculated Hamming distance as the Hamming distance between the service access object information and the historical access object information;

determining the calculated Hamming distance as a corresponding strong association degree when the corresponding business access object information is strongly associated with the historical access object information; the strong correlation degree is used for measuring the degree that the business access object information is correlated with the historical access object information;

based on the first service push characteristic vector and a third service push characteristic vector of the table item service access information, calculating push service information of the service access object information to the table item service access information, and operating the push service information and the strong association degree to obtain push service configuration information of the table item service access information aiming at the service access object information and a push service area of the history access object information in the table item service access information;

according to the push service configuration information and a push service area corresponding to a strong association condition that the strong association degree reaches the strong association condition, determining recommended portrait feature information corresponding to the push service area in the push service configuration information, and generating recommended portrait feature information of an information recommendation process corresponding to the service request information according to the extracted recommended portrait feature information

In a second aspect, an embodiment of the present invention further provides a business processing apparatus based on big data and artificial intelligence, which is applied to a blockchain financial platform, where the blockchain financial platform is communicatively connected to a plurality of digital financial service terminals, and the apparatus includes:

the acquisition module is used for acquiring at least one business keyword list from business request information of the digital financial service terminal in a preset time period, wherein each business keyword label in each business keyword list belongs to the same business service scene, and each business keyword label corresponds to a business processing flow under the business service scene to which the business keyword label belongs;

the identification module is used for carrying out entity relationship identification on the business keyword list based on each business processing flow under the business service scene to obtain entity relationship characteristics and corresponding entity business item grades of each business keyword list;

the determining module is used for determining the form operation track of the business service scene corresponding to each business keyword label according to the entity relation characteristics and the corresponding entity business item grades;

the generating module is used for marking the form operation track of the corresponding business service scene according to each business keyword, determining a form tracking thermalization table entry corresponding to each business service scene by adopting an artificial intelligence model, generating the recommended portrait characteristics of the information recommendation process corresponding to the business request information according to the form tracking thermalization table entry corresponding to each business service scene, and pushing the corresponding request recommendation information to the digital financial service terminal according to the recommended portrait characteristics of the information recommendation process.

In a third aspect, an embodiment of the present invention further provides a business processing system based on big data and artificial intelligence, where the business processing system based on big data and artificial intelligence includes a blockchain financial platform and a plurality of digital financial service terminals communicatively connected to the blockchain financial platform;

the block chain financial platform is used for acquiring at least one business keyword list from business request information of the digital financial service terminal in a preset time period, each business keyword label in each business keyword list belongs to the same business service scene, and each business keyword label corresponds to a business processing flow under the business service scene to which the business keyword label belongs;

the block chain financial platform is used for carrying out entity relation identification on the business keyword list based on each business processing flow under the business service scene to obtain entity relation characteristics and corresponding entity business item grades of each business keyword list;

the block chain financial platform is used for determining form operation tracks of business service scenes to which the business keywords are correspondingly marked according to the entity relation characteristics and the corresponding entity business item grades;

the block chain financial platform is used for marking form operation tracks corresponding to the business service scenes according to the business keywords, determining form tracking thermalization entries corresponding to each business service scene by adopting an artificial intelligence model, generating recommended portrait features of an information recommendation process corresponding to the business request information according to the form tracking thermalization entries corresponding to each business service scene, and pushing corresponding request recommendation information to the digital financial service terminal according to the recommended portrait features of the information recommendation process.

In a fourth aspect, an embodiment of the present invention further provides a blockchain financial platform, where the blockchain financial 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 configured to be communicatively connected to at least one digital financial service terminal, the machine-readable storage medium is configured to store a program, an instruction, or code, and the processor is configured to execute the program, the instruction, or the code in the machine-readable storage medium to perform the big data and artificial intelligence based business processing method in the first aspect or any one of possible designs 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 a business processing method based on big data and artificial intelligence in the first aspect or any one of the possible designs of the first aspect.

Based on any one of the aspects, the entity relationship characteristics of each business keyword list are extracted in an entity relationship identification mode, and the form operation track of the business service scene corresponding to each business keyword label is determined based on the entity business item grade, so that each business processing flow is converted into an effective pushing classification basis. The form operation track corresponding to the business service scene is marked according to each business keyword, an artificial intelligence model is adopted to determine a form tracking thermalization table entry corresponding to each business service scene, a recommended portrait feature of an information recommendation process corresponding to the business request information is generated according to the form tracking thermalization table entry corresponding to each business service scene, and the corresponding request recommendation information is pushed to the digital financial service terminal according to the recommended portrait feature of the information recommendation process, so that request response recommendation can be effectively combined with the specific type of the business service scene according to the business request information, and the classification precision of information push is improved.

Drawings

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

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

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

FIG. 3 is a functional block diagram of a business processing apparatus based on big data and artificial intelligence according to an embodiment of the present invention;

fig. 4 is a block diagram illustrating a block chain financial platform for implementing the business processing method based on big data and artificial intelligence according to an embodiment of the present invention.

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 a big data and artificial intelligence based business processing system 10 provided by an embodiment of the invention. The big data and artificial intelligence based business processing system 10 may include a blockchain financial platform 100 and a digital financial services terminal 200 communicatively connected to the blockchain financial platform 100. The big data and artificial intelligence based business processing system 10 shown in FIG. 1 is only one possible example, and in other possible embodiments, the big data and artificial intelligence based business processing system 10 may also include only some of the components shown in FIG. 1 or may also include other components.

In this embodiment, the internet-of-things cloud blockchain financial platform 100 and the digital financial service terminal 200 in the big data and artificial intelligence based service processing system 10 may cooperatively execute the big data and artificial intelligence based service processing method described in the following method embodiment, and the detailed description of the method embodiment may be referred to in the specific steps of the blockchain financial platform 100 and the digital financial service terminal 200.

To solve the technical problem in the foregoing background art, fig. 2 is a schematic flow chart of a business processing method based on big data and artificial intelligence according to an embodiment of the present invention, and the business processing method based on big data and artificial intelligence according to the present embodiment may be executed by the blockchain financial platform 100 shown in fig. 1, and the business processing method based on big data and artificial intelligence is described in detail below.

Step S110, obtaining at least one service keyword list from the service request information of the digital financial service terminal in a preset time period.

And step S120, performing entity relationship identification on the business keyword list based on each business processing flow under the business service scene to obtain the entity relationship characteristics and the corresponding entity business item grade of each business keyword list.

Step S130, determining the form operation track of the business service scene corresponding to each business keyword label according to the entity relation characteristics and the corresponding entity business item grade.

Step S140, marking the form operation track of the corresponding business service scene according to each business keyword, determining the form tracking thermalization table entry corresponding to each business service scene by adopting an artificial intelligence model, and generating the recommended portrait characteristics of the information recommendation process corresponding to the business request information according to the form tracking thermalization table entry corresponding to each business service scene.

In this embodiment, each service keyword label in each service keyword list belongs to the same service scenario, and each service keyword label corresponds to a service processing flow in the service scenario to which it belongs. For example, the service keyword labels of the service scenes belonging to the same service scene can be obtained from the service request information of the digital financial service terminal in a preset time period, and the service keyword label belonging to each service scene is determined as a corresponding service keyword list.

Illustratively, the service request information may include a plurality of service keyword tags, each service keyword tag may refer to a related part-of-speech and semantic field sequence of the keyword, and these part-of-speech and semantic field sequences may be used to represent different information with classification attributes in the actual service request push. Similarly, for different service keyword labels, the types of the corresponding service scenarios are different, so that the service keyword labels can correspond to a certain service scenario one by one, that is, the service scenario can be used to represent the type of the service scenario field.

In this embodiment, the entity relationship may be used to indicate that a relationship field capable of indicating the associated service scenario service exists, the entity relationship characteristic may be used to indicate a relationship field sequence corresponding to the entity relationship, and the corresponding entity service event level may be used to indicate how frequently the relationship field sequence corresponding to the entity relationship has the frequent pattern item of the interaction tag between the entity relationship and the associated service scenario service.

In this embodiment, the form operation trajectory may be used to represent recorded information in units of a time axis of a generated form operation behavior, so that the form operation trajectory corresponding to a business service scenario may be labeled according to each business keyword, a form tracking thermalization table entry corresponding to each business service scenario may be determined by using an artificial intelligence model, and the form tracking thermalization table entries are used to represent thermalization items (for example, items with an operation cycle number exceeding two times) in a form operation process, so that recommended representation features of an information recommendation process corresponding to the business request information may be generated specifically according to the form tracking thermalization table entry corresponding to each business service scenario.

Based on the design, the embodiment extracts the entity relationship characteristics of each service keyword list in an entity relationship identification mode, and determines the form operation track of the service scene to which each service keyword label corresponds based on the entity service item level, so that each service processing flow is converted into an effective pushing classification basis. The form operation track corresponding to the business service scene is marked according to each business keyword, an artificial intelligence model is adopted to determine a form tracking thermalization table entry corresponding to each business service scene, a recommended portrait feature of an information recommendation process corresponding to the business request information is generated according to the form tracking thermalization table entry corresponding to each business service scene, and the corresponding request recommendation information is pushed to the digital financial service terminal according to the recommended portrait feature of the information recommendation process, so that request response recommendation can be effectively combined with the specific type of the business service scene according to the business request information, and the classification precision of information push is improved.

In one possible implementation, step S120 may be implemented by the following exemplary sub-steps, which are described in detail below.

And a substep S121, traversing the service keyword labels in the service keyword list for each service keyword list, extracting the service keyword description representation fusing each service processing flow under the service scene to which the service keyword list belongs from the service keyword labels, and determining the service logic information corresponding to the service keyword list according to the extracted service keyword description representation.

And a substep S122, removing the set description information contained in each service keyword description representation in the service logic information, performing service pushing characteristic segmentation and splitting on the service keyword description representation from which the set description information is removed to obtain first service logic information, and determining the entity relationship strength of each service pushing characteristic segment according to the service logic strength of the service pushing characteristic segment in the service keyword description representation contained in the first service logic information.

For example, the service logic strength of the service push feature segment in the service keyword description representation included in the first service logic information may refer to a length of an overlapping segment part of the service push feature segment in the service keyword description representation included in the first service logic information.

And substep S123, removing service push feature segments with entity relationship strength smaller than a preset entity relationship strength threshold value from the first service logic information to obtain second service logic information, using the service push feature segments with entity relationship strength not smaller than the preset entity relationship strength threshold value as first service push feature segments to obtain a first service push feature segment list, and determining a second service push feature segment list corresponding to each first service push feature segment and composed of service push feature segments connected after the first service push feature segment according to matching information of each first service push feature segment in the first service push feature segment list in the second service logic information.

And a substep S124, determining whether the second service pushing feature segment list is empty, if the second service pushing feature segment list is empty, returning in a circulating manner, and if the second service pushing feature segment list is not empty, counting the entity relationship strength of each service pushing feature segment in the second service pushing feature segment list, and determining whether the entity relationship strength of each service pushing feature segment meets the minimum entity relationship strength condition.

And a substep S125, if the entity relationship strength of the service pushing feature segment does not meet the minimum entity relationship strength condition, circularly returning, if the entity relationship strength of the service pushing feature segment meets the minimum entity relationship strength condition, splicing the service pushing feature segment with a first service pushing feature segment corresponding to a second service pushing feature segment list to obtain a new first service pushing feature segment, determining a second service pushing feature segment list of the new first service pushing feature segment, and performing circular recognition on the second service pushing feature segment list corresponding to the new first service pushing feature segment to obtain all target first service pushing feature segments meeting the minimum entity relationship strength condition and corresponding entity relationship strengths.

For example, the data returned in the loop is all currently obtained target first service push feature segments meeting the minimum entity relationship strength condition and corresponding entity relationship strengths, all target first service push feature segments meeting the minimum entity relationship strength condition and corresponding entity relationship strengths are obtained, the target first service push feature segments are used as the entity relationship features of the service keyword list, and the entity relationship strengths of the target first service push feature segments in the second service push feature segment list are used as the entity service item levels corresponding to the entity relationship features.

In a possible implementation manner, for step S130, in order to accurately and comprehensively determine the entity relationship element having the form operation behavior, thereby improving coverage and accuracy of form operation crawling, and effectively determining the form operation trajectory of the business service scenario to which each business keyword label corresponds, the following exemplary sub-steps may be implemented. The detailed description is as follows.

And a substep S131, selecting the marked entity relation characteristic greater than the preset entity business item grade from the entity relation characteristics according to the entity relation characteristics and the corresponding entity business item grade.

In the substep S132, a first form operation element list corresponding to the first entity relationship object and a second form operation element list corresponding to the second entity relationship object are obtained on the marked entity relationship feature.

For example, the first form operation element list includes a plurality of form operation nodes for form operations by the first entity relationship object on related form regions in the tagged entity relationship feature, the second form operation element list includes a plurality of form operation nodes for form operations by the second entity relationship object on related form regions in the tagged entity relationship feature, and each form operation node includes a plurality of form operation node components.

And a substep S133, based on the preset form operation node category, performing gaussian classification on the plurality of form operation nodes in the first form operation element list to obtain a first form operation element list after gaussian classification. And presetting the types of the form operation nodes, wherein the types of the form operation nodes belong to the types corresponding to the components of the plurality of form operation nodes.

In the sub-step S134, the form operation node components corresponding to each preset form operation node category in the list of preset form operation node categories in the first form operation element list after gaussian classification are combined into a first initial form operation node list.

And a substep S135, performing deduplication on the first initial form operation node list to obtain a first form operation node list, so as to obtain a first form operation node list corresponding to the preset form operation node category list, and combining each form operation node component in the first form operation node list into a first form operation node component list corresponding to the first entity relationship object.

For example, the first form operation node component list corresponds to a preset form operation node category list, and the preset form operation node category type is a list composed of various form operation node categories used for form operation crawling.

In the substep S136, form operation node components corresponding to the preset form operation node categories in the preset form operation node category list are extracted from the second form operation element list and combined into a second form operation node component list corresponding to the second entity relationship object.

For example, the second form operation node component list corresponds to a preset form operation node category list, and the first form operation node component list and the second form operation node component list are lists formed by form operation node components extracted from the corresponding form operation element list.

And a substep S137, determining a track node of the same form operation node component between the first form operation node component list and the second form operation node component list, obtaining an operation description value from a track range value corresponding to the track node, and determining the first entity relationship object and the second entity relationship object as a form operation unit when the operation description value is greater than a preset description value threshold value.

And a substep S138, using any two entity relationship elements in the marked entity relationship characteristic as a first entity relationship object and a second entity relationship object to perform form operation crawling, and obtaining a form operation unit list with form operation behaviors in the marked entity relationship characteristic until the detection of the entity relationship elements in the marked entity relationship characteristic is completed.

And the substep S139 is to take the track node of the entity relationship element in the form operation unit list as the track node of the target form operation unit, take the track node of the entity relationship element corresponding to the mark entity relationship characteristic as the track node of the target total entity relationship element, calculate the track segmentation of the track node of the target form operation unit and the track node of the target total entity relationship element to obtain the track segmentation characteristic corresponding to the mark entity relationship characteristic, and determine the track formed by the track segmentation characteristic corresponding to the mark entity relationship characteristic as the form operation track of the business keyword mark corresponding to the business service scene when the track segmentation characteristic meets the preset segmentation length.

Based on the steps, when the entity relation element with the form operation behavior performs the form operation, the same form operation node component exists between the corresponding form operation nodes; therefore, when the form operation crawling is carried out, a form operation element list consisting of a plurality of form operation nodes of the entity relationship elements is obtained, whether the form operation behavior exists in the entity relationship elements is determined according to whether the common attribute condition exists between the form operation node component lists corresponding to the operation lists among the entity relationship elements, and whether the entity relationship elements are form operation units is further determined.

In a possible implementation manner, further aiming at step S140, in the process of labeling the form operation trajectory corresponding to the business service scenario to which the business keyword belongs according to each business keyword and determining the form tracking thermalization entry corresponding to each business service scenario by using an artificial intelligence model, the following exemplary substeps are implemented, which are described in detail as follows.

And a substep S141, obtaining the initial business table entry of the corresponding track passing business segment and the track passing business segment from the form operation track of the business service scene corresponding to each business keyword label.

And a substep S142, classifying the track passing through the service section according to a pre-trained artificial intelligence model to obtain a classified service list item.

And a substep S143, comparing the initial service table item with the classification service table item to obtain table item matching information.

For example, the initial service entry may include at least one initial sub-service entry, and the classification service entry includes at least one classification sub-service entry. On this basis, each initial sub-service table entry can be fused with each classified sub-service table entry respectively to obtain sub-fusion information, and when at least one classified sub-service table entry is fused, at least one piece of sub-fusion information is obtained. And the sub-fusion information represents whether the initial sub-service table entry is matched with the classification sub-service table entry or not.

And then, splicing at least one piece of sub-fusion information to obtain fusion information corresponding to each initial sub-service table entry. The fusion information represents whether a classification sub-service table entry fused with the initial sub-service table entry exists or not, and the fusion information corresponds to each initial sub-service table entry.

Therefore, the initial sub-service table entry with the fusion information representing the existence of the fused classified sub-service table entry in the at least one initial sub-service table entry can be extracted to obtain the fused initial sub-service table entry, and the classified sub-service table entry fused with the fused initial sub-service table entry is extracted from the at least one classified sub-service table entry according to the fusion information and serves as the fused classified sub-service table entry.

And then splicing the initial sub-service table entries except the fused initial sub-service table entry in at least one initial sub-service table entry to obtain an initial splicing information list, splicing the classified sub-service table entries except the fused classified sub-service table entry in at least one classified sub-service table entry to obtain a classified splicing information list, and splicing the initial splicing information list and the classified splicing information list to obtain table entry matching information.

The initial sub-service table entry may include initial service tag information, initial service main key information, and initial associated object information, and the classification sub-service table entry includes classification service tag information, classification service main key information, and classification associated object information.

Illustratively, each initial sub-service table entry includes initial service tag information and initial service master key information, and each classification sub-service table entry includes classification service tag information and classification service master key information.

Therefore, in the process of fusing each initial sub-service table entry with each classified sub-service table entry to obtain sub-fusion information, and obtaining at least one piece of sub-fusion information when at least one classified sub-service table entry is fused, the initial service label information can be coded with the classified service label information of each classified sub-service table entry respectively to obtain the coding discrimination information corresponding to each classified sub-service table entry.

The coding discrimination information may represent whether the initial service tag information is the same as the classification service tag information.

Then, the initial service main key information is used for determining an initial service main key interface, and the classification service main key information of each classification sub-service table entry is used for determining the classification service main key interface of each classification sub-service table entry.

Therefore, interface association information corresponding to each classification service main key interface and the initial service main key interface and a splicing result corresponding to each classification service main key interface and the initial service main key interface can be obtained according to the initial service main key interface and each classification service main key interface, and then at least one piece of sub-fusion information is obtained by utilizing the interface association information and the splicing result.

For example, in the process of obtaining at least one sub-fusion information by using the interface association information and the splicing result, the service fusion information corresponding to each classified sub-service table entry may be constructed; and when the coding discrimination information represents that the initial service label information is the same as the classification service label information and the service fusion information exceeds a preset matching degree threshold, generating sub-fusion information of which the initial sub-service table entry is matched with the classification sub-service table entry. For another example, when the coding discrimination information indicates that the initial service tag information is the same as the classification service tag information, and the service fusion information is less than or equal to the preset matching degree threshold, sub-fusion information in which the initial sub-service table entry is not matched with the classification sub-service table entry is generated.

For another example, when the coding discrimination information indicates that the initial service tag information is different from the classification service tag information, and the service fusion information exceeds a preset matching degree threshold, sub-fusion information in which the initial sub-service table entry is not matched with the classification sub-service table entry is generated.

For another example, when the coded discrimination information indicates that the initial service tag information is different from the classification service tag information and the service fusion information is less than or equal to the preset matching degree threshold, sub-fusion information in which the initial sub-service table entry is not matched with the classification sub-service table entry is generated, and when at least one classification sub-service table entry is spliced, at least one piece of sub-fusion information is obtained. Wherein, the at least one piece of sub-fusion information corresponds to at least one classified sub-service table entry one to one.

And a substep S144, determining the form tracking thermalization table entry corresponding to each business service scene by adopting an artificial intelligence model according to the table entry matching information.

For example, the target tracking thermalization items corresponding to each item matching node may be obtained from the item matching information, and each target tracking thermalization item is used as a form tracking thermalization item corresponding to each business service scenario determined by using an artificial intelligence model in a manner of clustering and arranging.

In a possible implementation manner, still referring to step S140, in the process of generating the recommended sketch feature of the information recommendation process corresponding to the service request information according to the form tracking thermalization table entry corresponding to each service scenario, the following exemplary sub-steps may be implemented, which are described in detail below.

And a substep S145, obtaining table item service access information and service access object information and historical access object information related to the table item service access information from an information list mapped by the form tracking thermalization table item corresponding to each service scene, wherein the historical access object information comprises access object information of at least one historical access request.

And a substep S146, inputting the service access object information and the historical access object information into a machine learning model, performing service pushing feature extraction on the service access object information through the machine learning model to obtain a first service pushing feature vector, and performing service pushing feature extraction on each historical access object information to obtain a second service pushing feature vector.

And a substep S147, performing splicing processing on each vector in the first service push characteristic vector to obtain a first service access authentication vector used for expressing the service access authentication of the service access object information, and performing splicing processing on each vector in the second service push characteristic vector to obtain a second service access authentication vector used for expressing the service access authentication of the historical access object information.

And a substep S148, calculating the Hamming distance between the first service access authentication vector and each second service access authentication vector, and using the calculated Hamming distance as the Hamming distance between the service access object information and the historical access object information.

And a substep S149, determining the calculated Hamming distance as a corresponding strong association degree when the corresponding business access object information is strongly associated with the historical access object information. The strong association is used to measure how well the business access object information is being associated with the historical access object information.

And a substep S1491, calculating the pushing service information of the table service access information by the service access object information based on the first service pushing feature vector and the third service pushing feature vector of the table service access information, and operating the pushing service information and the strong correlation degree to obtain pushing service configuration information of the table service access information aiming at the service access object information and a pushing service region of the history access object information in the table service access information.

And a substep S1492, determining recommended portrait characteristic information corresponding to the push service area in the push service configuration information according to the push service configuration information and the push service area corresponding to the condition that the strong correlation degree reaches the strong correlation degree, and generating recommended portrait characteristics of an information recommendation process corresponding to the service request information according to the extracted recommended portrait characteristic information.

In this way, the depth recognition of the recommended portrait feature pushing service is further carried out through the recognition mode with strong correlation, so that the recommended portrait feature information corresponding to the pushing service area is determined in the pushing service configuration information, the recommended portrait feature of the information recommendation process corresponding to the service request information is generated according to the extracted recommended portrait feature information, and the accuracy of pushing classification can be effectively improved.

For another example, after step S140, the business processing method based on big data and artificial intelligence provided in this embodiment may further include the following steps, which are described in detail below.

And step S150, acquiring target identification push information, and performing service index classification and push structure association processing on the target identification push information to obtain a corresponding target service index classification list.

Step S160, performing information identification on the target service index classification list to obtain an information push tag list and corresponding history push feedback parameters, and determining the information push tag list with the history push feedback parameters meeting the preset matching rules as a target push reference policy.

Step S170, traversing the target service index classification list according to the target push reference strategy, circularly updating push key elements of the push structure, adding push nodes to the target service index classification list conforming to the target push reference strategy, and extracting push source characteristics and corresponding source characteristic importance degree information in the target service index classification list with the added push nodes.

And S180, configuring a preset information pushing model according to the pushing source characteristics, the source characteristic importance degree information and the pushing node to obtain a configured preset information pushing model, and performing information pushing processing on the target service index classification list based on the configured preset information pushing model.

In this embodiment, the target identification push information may be request recommendation information corresponding to service request information of the digital financial service terminal 200 in a preset time period. For example, the digital financial services terminal 200 may be distributed throughout different websites to provide services for users, and the users may send service request information at any time during the operation process to obtain request recommendation information.

In this embodiment, the service index may refer to index information generated in a specific digital financial service process and used for measuring each service requested to be recommended, and the push structure may refer to structural configuration information used for performing a reference to a push policy in the specific digital financial service process, for example, the configuration information may be arranged in a preset calibrated fixed format.

In this embodiment, each information push tag in the information push tag list may be used to represent a classification list specifically referred to in a subsequent information push process, and the corresponding history push feedback parameter may refer to content feature information, such as evaluation information and collection information, fed back by the user before the information push tag is used as a reference object for subsequent push.

In this embodiment, the push key element may refer to a content node included in push information in a subsequent push process, each content node may correspond to one push node, the push source characteristic may be used to represent a characteristic of an information source in the subsequent push process, and the corresponding source characteristic importance degree information may be used to represent a weight occupied by the characteristic of the information source.

In this embodiment, in step S180, the preset information push model may be configured according to the push source characteristics and the source characteristic importance information, so as to obtain the configured preset information push model. For example, the push source characteristics, the source characteristic importance degree information, and the push nodes may be input into a preset information push model for training to obtain a corresponding information push node list, and the corresponding information push node list is compared with the push nodes, and then the model parameters of the preset information push model are continuously updated according to the comparison difference until a training termination condition is reached, and information push processing may be performed on the target service index classification list based on the configured preset information push model. For example, the configured preset information push model may be used to obtain a corresponding target push node for the target service index classification list, and then perform information push processing based on the push source content related to the target push node.

Based on the above steps, the embodiment performs iterative calibration of the push structure body on the service index in the target identification push information, so as to continuously update the push key elements of the push structure body, and fuses the push source characteristics and the corresponding source characteristic importance information to configure the preset information push model, so that the accuracy of information push of the configured preset information push model is higher, the data processing efficiency is greatly improved, and the analysis efficiency of information push is further improved.

In one possible implementation, step S160 can be implemented by the following exemplary sub-steps, which are described in detail below.

And a substep S161, performing information identification on the target service index classification list to obtain a corresponding information push label list.

In the substep S162, a first target push feedback parameter of the push structure and a global push feedback parameter of the push structure included in each information push tag list are obtained.

And a substep S163, determining a corresponding first historical push feedback parameter according to a matching relationship between the first target push feedback parameter and the global push feedback parameter.

And a substep S164, determining an information push tag list with the first historical push feedback parameter matching the preset parameter characteristic as a target push reference policy.

In one possible implementation, step S150 may be implemented by the following exemplary substeps, which are described in detail below.

And a substep S151, performing segmentation and service index classification operations on the target identification push information to obtain a corresponding service index classification list.

And a substep S152, acquiring the pushing key elements of the pushing structure body, and determining the pushing key elements in the service index classification list.

And a substep S153, calibrating a corresponding pushing structure body for the pushing key elements in the service index classification list to obtain a corresponding target service index classification list.

In a possible implementation manner, for step S170, in the process of traversing the target service index classification list according to the target push reference policy and circularly updating the push key element of the push structure, the following exemplary sub-steps may be implemented, which are described in detail below.

And a substep S171, determining a service index sequence in the target service index classification list, which matches with the information push tag list of the target push reference policy.

And a substep S172, obtaining a second target push feedback parameter of the push structure body and a global push feedback parameter of the push structure body included in each service index sequence, and determining a corresponding second historical push feedback parameter according to a matching relationship between the second target push feedback parameter and the global push feedback parameter.

And a substep S173, determining a service index sequence with a second historical push feedback parameter greater than a second preset historical push feedback parameter threshold value as a target service index sequence, performing push structure calibration on a service index in the target service index sequence according to a target push reference strategy, and updating a push key element of the push structure.

For example, a calibration rule for calibrating the push structure body for each policy unit in the target push reference policy may be obtained. And then, calibrating the pushing structure body according to the business indexes in the target business index sequence according to the calibration rule and the strategy unit, and updating the pushing key elements of the pushing structure body.

And a substep S174 of re-executing the step of obtaining the second target push feedback parameter of the push structure and the global push feedback parameter of the push structure included in each service index sequence, iteratively calibrating the push structure for the service indexes in the target service index sequence, and updating the push key elements of the push structure until the iteration number meets a preset iteration threshold.

In a possible implementation manner, for step S170, in the process of extracting the push source feature and the corresponding source feature importance degree information in the target service index classification list of the added push node, the following exemplary sub-steps may be implemented, which are described in detail below.

And a substep S175, determining a push source characteristic of the target service index classification list of the added push node.

And a substep S176, calculating the source characteristic importance degree information of the target service index classification list of the added push node.

For example, the number of occurrences of the target service index in the target service index classification list of the added push node may be obtained, and the total number of push nodes occurring in the target identification push information may be obtained. And then, determining corresponding frequent pattern item information according to the matching relation between the occurrence frequency of the target service index and the total number of the push nodes. On the basis, the global pushing quantity in the target identification pushing information is obtained, the target service pushing quantity containing the target service index is obtained, the target matching relation between the global pushing quantity and the target service pushing quantity is calculated, the logarithm of the target matching relation is calculated, and a corresponding logarithm result is obtained. And then multiplying the frequent pattern item information by a logarithm result to obtain the importance degree of the target service index, and combining the importance degrees corresponding to the service indexes in the same target service index classification list to generate source characteristic importance degree information.

Fig. 3 is a schematic functional module diagram of a business processing apparatus 300 based on big data and artificial intelligence according to an embodiment of the present invention, and this embodiment may divide the business processing apparatus 300 based on big data and artificial intelligence according to the method embodiment executed by the blockchain financial platform 100, that is, the following functional modules corresponding to the business processing apparatus 300 based on big data and artificial intelligence may be used to execute each method embodiment executed by the blockchain financial platform 100. The big data and artificial intelligence based business processing apparatus 300 may include an obtaining module 310, a recognition module 320, a determination module 330, and a generation module 340, and the functions of the functional modules of the big data and artificial intelligence based business processing apparatus 300 are described in detail below.

An obtaining module 310, configured to obtain at least one service keyword list from service request information of the digital financial service terminal in a preset time period, where each service keyword label in each service keyword list belongs to the same service scenario, and each service keyword label corresponds to a service processing flow in the service scenario to which the service keyword label belongs. The obtaining module 310 may be configured to perform the step S110, and the detailed implementation of the obtaining module 310 may refer to the detailed description of the step S110.

The identifying module 320 is configured to perform entity relationship identification on the service keyword list based on each service processing flow in the service scene to obtain an entity relationship characteristic and a corresponding entity service item level of each service keyword list. The identification module 320 may be configured to perform the step S120, and the detailed implementation of the identification module 320 may refer to the detailed description of the step S120.

The determining module 330 is configured to determine, according to the entity relationship characteristic and the corresponding entity business item level, a form operation trajectory of the business service scene to which each business keyword label corresponds. The determining module 330 may be configured to perform the step S130, and the detailed implementation of the determining module 330 may refer to the detailed description of the step S130.

The generating module 340 is configured to label, according to each service keyword, a form operation trajectory corresponding to a service scene to which the service keyword belongs, determine, by using an artificial intelligence model, a form tracking thermalization entry corresponding to each service scene, and generate, according to the form tracking thermalization entry corresponding to each service scene, a recommended portrait feature of an information recommendation process corresponding to the service request information. The generating module 340 may be configured to execute the step S140, and the detailed implementation of the generating module 340 may refer to the detailed description of the step S140.

It should be noted that the division of the modules of the above apparatus is only a logical division, and the actual implementation may be wholly or partially integrated into one physical entity, or may be physically separated. And these modules 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 financial platform 100 for implementing the big data and artificial intelligence based business processing method according to an embodiment of the present invention, and as shown in fig. 4, the blockchain financial 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 identifying module 320, the determining module 330, and the generating module 340 included in the big data and artificial intelligence based business processing apparatus 300 shown in fig. 3), so that the processor 110 may execute the big data and artificial intelligence based business 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 transceiving actions of the transceiver 140, so as to transceive data with the aforementioned digital financial service 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 financial platform 100, which implement the similar principle and technical effect, and the detailed description of the embodiments is omitted here.

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 invention are not limited to only one bus or one type of bus.

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

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 run entirely on the user's computer, or as a stand-alone software package on the user's computer, partly on the user's computer and partly on a remote computer or entirely on the remote computer or medical services 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 lists are processed, the use of alphanumeric characters, or other designations in this specification is not intended to limit the order in which the processes and methods of this specification are performed, 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 by hardware devices, they may also be implemented by software-only solutions, such as installing the described system on an existing healthcare 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. A business processing method based on big data and artificial intelligence is applied to a block chain financial platform which is in communication connection with a plurality of digital financial service terminals, and the method comprises the following steps:

marking form operation tracks corresponding to the business service scenes according to the business keywords, determining form tracking thermalization entries corresponding to each business service scene by adopting an artificial intelligence model, generating recommended portrait characteristics of an information recommendation process corresponding to the business request information according to the form tracking thermalization entries corresponding to each business service scene, and pushing corresponding request recommendation information to the digital financial service terminal according to the recommended portrait characteristics of the information recommendation process;

the method comprises the steps that business keyword labels of business service scenes belonging to the same business service scene are obtained from business request information of a digital financial service terminal in a preset time period, and the business keyword labels belonging to each business service scene are determined to be a corresponding business keyword list;

the service request information comprises a plurality of service keyword labels, each service keyword label refers to a field sequence formed by the word property and the semantic meaning related to the keyword, and the field sequence formed by the word property and the semantic meaning is used for expressing different information with classification attributes in the actual service request pushing; for different service keyword labels, the types of the corresponding service scenes are different.

2. The big data and artificial intelligence based transaction processing method according to claim 1, wherein the step of obtaining at least one transaction keyword list from the transaction request information of the digital financial service terminal for a preset time period comprises:

3. The business processing method based on big data and artificial intelligence as claimed in claim 1, wherein said step of performing entity relationship recognition on said business keyword list based on each business processing flow under said business service scenario to obtain entity relationship features and corresponding entity business item classes of each business keyword list comprises:

4. The business processing method based on big data and artificial intelligence as claimed in claim 1, wherein said step of determining the form operation trajectory of the business service scenario to which each of said business keyword labels corresponds according to said entity relationship features and the corresponding entity business item classes comprises:

5. The business processing method based on big data and artificial intelligence according to any one of claims 1-4, wherein the step of labeling the form operation trajectory of the business service scenario corresponding to each of the business keywords and determining the form tracking thermalization entry corresponding to each of the business service scenarios by using an artificial intelligence model comprises:

6. The big data and artificial intelligence based business processing method of claim 5, wherein the initial business table entry comprises at least one initial sub-business table entry, and the classification business table entry comprises at least one classification sub-business table entry;

7. The big data and artificial intelligence based business processing method according to claim 6, wherein each of the initial sub-business table entries comprises initial business label information and initial business main key information, and each of the classification sub-business table entries comprises classification business label information and classification business main key information;

8. The big data and artificial intelligence based business processing method according to claim 5, wherein said step of determining form tracking thermalization entries corresponding to each of said business service scenarios according to said entry matching information comprises:

and acquiring target tracking thermalization items corresponding to each item matching node from the item matching information, and using each target tracking thermalization item as a form tracking thermalization item corresponding to each business service scene in a clustering and arranging manner.

9. The business processing method based on big data and artificial intelligence according to any one of claims 1-8, wherein the step of generating the recommended representation feature of the information recommendation process corresponding to the business request information according to the form tracking thermalization entry corresponding to each business service scenario, and pushing the corresponding request recommendation information to the digital financial service terminal according to the recommended representation feature of the information recommendation process comprises:

according to the push service configuration information and a push service area corresponding to a strong association condition that the strong association degree reaches the strong association condition, determining recommended portrait feature information corresponding to the push service area in the push service configuration information, and generating recommended portrait features of an information recommendation process corresponding to the service request information according to the extracted recommended portrait feature information;

and pushing corresponding request recommendation information to the digital financial service terminal according to the recommended portrait characteristics of the information recommendation process.

10. A blockchain financial platform comprising a processor, a machine-readable storage medium, and a network interface, the machine-readable storage medium, the network interface, and the processor being connected by a bus system, the network interface being configured to communicatively connect with at least one digital financial services terminal, the machine-readable storage medium being configured to store a program, instructions, or code, and the processor being configured to execute the program, instructions, or code in the machine-readable storage medium to perform the big data and artificial intelligence based business process method of any of claims 1-9.