Service recommendation method and device based on service architecture

Abstract

The invention provides a service recommendation method and device based on a service architecture, relates to the field of service architectures, can be applied to the financial field and other fields, and comprises the following steps: obtaining first associated data information according to an association relationship between an application function and a service architecture activity; analyzing and obtaining an application function operated by the user according to historical data of the user operation, and generating second associated data information through the application function operated by the user and the first associated data information; and constructing an architecture knowledge graph according to the association between the business architecture activities and the activities, and analyzing through an attention mechanism model according to the second association data information and the architecture knowledge graph to obtain a business recommendation result.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of business architecture, which can be applied to the financial field and other fields, and in particular to a business recommendation method and device based on business architecture. BACKGROUND

[0002] In the mobile banking app of a financial institution, in order to improve user stickiness and increase app activity, after a user actively uses a certain business function, the system will display other business recommendation modules to attract the user to click to handle other businesses and increase user stickiness.

[0003] The existing recommendation function has the following problems:

[0004] First, most existing recommendation methods are based on customer portraits or historical data for recommendation, and the system always pushes the same type of business to the user, which easily causes the problem of "information cocoon room", and second, the pushed business type is usually fixed, which cannot be dynamically updated. This leads to low user interest in other recommended businesses after actively handling a business, and thus cannot improve the app conversion rate.

[0005] Therefore, the industry urgently needs a method that combines business functions with user demand analysis, mines user potential demands, and makes differentiated recommendations. SUMMARY

[0006] The present application aims to provide a business recommendation method and device based on business architecture, which uses financial institution business architecture assets to mine the internal correlation between financial businesses and businesses, and combines an artificial intelligence model to solve the problems of information cocoon room and dynamic updating.

[0007] To achieve the above purpose, the business recommendation method based on business architecture provided by the present application specifically includes: obtaining first correlation data information according to the correlation between application functions and business architecture activities; obtaining the application functions operated by the user according to the user operation history data analysis, generating second correlation data information through the application functions operated by the user and the first correlation data information; constructing an architecture knowledge graph according to the correlation between business architecture activities and activities, and obtaining a business recommendation result through an attention mechanism model analysis according to the second correlation data information and the architecture knowledge graph.

[0008] In the above business recommendation method based on business architecture, the generation of second correlation data information through the application functions operated by the user and the first correlation data information includes: generating user journey data according to the time sequence characteristics of the application functions operated by the user and the user operation history data; and generating second correlation data information through application functions according to the user journey data and the first correlation data information.

[0009] In the business recommendation method based on the business architecture, optionally, the constructing the architecture knowledge graph according to the business architecture activities and the correlations between the activities comprises: obtaining graph nodes according to the business architecture activities; obtaining graph correlation edges according to the correlation activities and the correlation objects between the business architecture activities; and constructing the architecture knowledge graph according to the graph nodes and the graph correlation edges.

[0010] In the business recommendation method based on the business architecture, optionally, the obtaining the business recommendation result according to the second correlation data information and the architecture knowledge graph through the attention mechanism model analysis comprises: generating a business training graph by merging knowledge through matching according to the second correlation data information and the architecture knowledge graph; and obtaining the business recommendation result according to the business training graph through the attention mechanism model analysis.

[0011] In the business recommendation method based on the business architecture, optionally, the generating the business training graph by merging knowledge through matching according to the second correlation data information and the architecture knowledge graph comprises: generating the business training graph by merging knowledge through common pointing according to the business architecture activities in the second correlation data information and the business architecture activities in the architecture knowledge graph.

[0012] In the business recommendation method based on the business architecture, optionally, the obtaining the business recommendation result according to the business training graph through the attention mechanism model analysis comprises: obtaining correlation recommendation business data and user information according to the business training graph; generating a vector matrix according to the correlation recommendation business data, and generating a pointing vector according to the user information; analyzing the relevance between the recommendation business in the correlation recommendation business data and the user according to the vector matrix and the pointing vector through the attention mechanism model; and obtaining the business recommendation result according to the relevance analysis.

[0013] In the business recommendation method based on the business architecture, optionally, the obtaining the business recommendation result according to the relevance analysis comprises: calculating the weight coefficient of the corresponding recommendation business according to the relevance through a normalization exponential function; and obtaining the business recommendation result by screening a preset number of recommendation businesses according to the high and low of the weight coefficient.

[0014] In the business recommendation method based on the business architecture, optionally, the method further comprises: obtaining operation information of user feedback according to the business recommendation result; and updating the second correlation data information through the operation information.

[0015] The application further provides a business recommendation device based on a business architecture, which comprises an association module, a mining module and a recommendation module; the association module is used for obtaining first association data information according to the association relationship between application functions and business architecture activities; the mining module is used for obtaining the application functions operated by a user according to user operation history data analysis, generating second association data information through the application functions operated by the user and the first association data information; and the recommendation module is used for constructing an architecture knowledge graph according to the association between business architecture activities and activities, and obtaining a business recommendation result through an attention mechanism model analysis according to the second association data information and the architecture knowledge graph.

[0016] The application further provides an electronic device, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the above method when executing the computer program.

[0017] The application further provides a computer readable storage medium, which stores a computer program for executing the above method.

[0018] The application further provides a computer program product, comprising computer programs / instructions, which implement the steps of the above method when executed by a processor.

[0019] The application has the beneficial technical effect that the business architecture modeling method is used to establish the connection between business architecture activities and the operation behaviors of customers in a mobile bank app, and the artificial intelligence model is used to realize the business recommendation with a more differentiated and iterative optimization mechanism. BRIEF DESCRIPTION OF DRAWINGS

[0020] The accompanying drawings, which are included to provide a further understanding of the application and constitute a part of this application, illustrate embodiments of the application and together with the description serve to explain the application. In the drawings:

[0021] Figure 1 A flowchart of a business recommendation method based on a business architecture provided by an embodiment of the application;

[0022] Figure 2 A flowchart of the acquisition of second association data information provided by an embodiment of the application;

[0023] Figure 3 A flowchart of the acquisition of an architecture knowledge graph provided by an embodiment of the application;

[0024] Figure 4 A flowchart of the acquisition of a business recommendation result provided by an embodiment of the application;

[0025] Figure 5 An attention mechanism analysis logic diagram provided by an embodiment of the application;

[0026] Figure 6 A structural schematic diagram of a business recommendation device based on a business architecture provided by an embodiment of the present application;

[0027] Figure 7 A structural schematic diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0028] The embodiments of the present application will be described in detail below with reference to the accompanying drawings and embodiments, so that how the present application applies technical means to solve technical problems and achieves technical effects can be fully understood and implemented. It should be noted that, as long as there is no conflict, each embodiment in the present application and each feature in each embodiment can be combined with each other, and the technical solutions formed thereby are all within the protection scope of the present application.

[0029] In addition, the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a group of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described herein can be executed in an order different from that shown.

[0030] The information collected in the technical solutions in the present application is information and data authorized by the user or authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of related data comply with relevant laws, regulations and standards of relevant countries and regions, necessary security measures are taken, do not violate public order and good customs, and provide corresponding operation portal for user to choose authorization or refusal.

[0031] The business architecture refers to the overall structure, mutual relationship and principle standard of each element of an enterprise. The business process model of an enterprise is divided into business domains, value streams, business activities, business tasks and business steps from top to bottom; wherein the business domain is composed of a group of activities including planning, execution and supervision of complete value streams, is the first level of the process model, and embodies the overall value creation process of the enterprise; the value stream is a relatively high-level description of how the business domain creates value, is the second level of the process model, and each value stream can only belong to one domain, and each activity can only belong to one value stream. The business activity is triggered by an event, is an interactive process between the event and stakeholders to meet the needs of the stakeholders or specific business purposes, describes an end-to-end complete business process, and is the third level of the process model. The business task is used to identify the specific business process executed by an independent responsible single role, is the fourth level of the process model, and is a collection of business steps with clear business purposes.

[0032] Please refer to Figure 1 The business recommendation method based on the business architecture provided by the present application specifically includes:

[0033] S101 obtaining first association data information according to the association relationship between application functions and business architecture activities;

[0034] S102 obtaining application functions of user operations according to user operation history data analysis, and generating second association data information through the application functions of user operations and the first association data information;

[0035] S103 constructing an architecture knowledge graph according to business architecture activities and the association between activities, and obtaining a business recommendation result through attention mechanism model analysis according to the second association data information and the architecture knowledge graph.

[0036] In the above embodiment, by utilizing the advantages of dynamic updating of enterprise business architecture assets and full information, by associating user journey with business architecture, the business value can be combined with user demand, and the most suitable business function for the user among the latest services provided by the financial institution can be recommended to the user. The whole process can be divided into business function and architecture activity association, user recommendation model training, and recommendation result feedback. The specific implementation of each step will be described in detail in subsequent embodiments, and will not be described here.

[0037] Please refer to Figure 2 In an embodiment of the present application, generating second association data information through the application functions of user operations and the first association data information comprises:

[0038] S201 generating user journey data according to the user operation history data through the time sequence characteristics of the application functions of user operations;

[0039] S202 generating second association data information through application function association according to the user journey data and the first association data information.

[0040] In the above embodiment, first, the first association data information, i.e., the data generated after the association of business functions and architecture activities, needs to be obtained. Specifically, each function in the mobile bank can be corresponded to an architecture asset. A business function can belong to multiple architecture activities, or it can belong to one architecture activity. The business functions of the mobile bank are associated with the "activities" in the architecture assets, and accordingly, a "business function-architecture activity" relationship table A is obtained. Please refer to the following Table 1:

[0041] Table 1

[0042]

[0043] On this basis, the second association data information can be constructed, that is, through mobile banking burying points and log analysis methods, the historical business functions used by the user are obtained from the database and collected to form a user journey, such as homepage-purchase financial products-return homepage. Then the user journey is put into the "business function-architecture activity" relationship table A, and the "user-business function-architecture activity" relationship table B of the initial user, that is, the second association data information, is obtained. Please refer to Table 2 below.

[0044] Table 2

[0045]

[0046] Please refer to Figure 3 In an embodiment of the present application, constructing an architecture knowledge graph according to business architecture activities and the association between activities includes:

[0047] S301 obtaining a graph node according to a business architecture activity;

[0048] S302 obtaining a graph association edge according to an associated activity and an associated object between each business architecture activity;

[0049] S303 constructing an architecture knowledge graph according to the graph node and the graph association edge.

[0050] Specifically, in actual work, the construction method of the knowledge graph at this place is mainly to construct an architecture knowledge graph C with architecture activities as nodes and associated activities, associated objects and other factors as edges by using data extraction, entity extraction and knowledge fusion technology. For example, the associated content of "accepting the application of the customer to purchase the products sold by the agent" includes other activities under the same value stream, products corresponding to the activities, and customer types corresponding to the activities. Based on this knowledge graph, other activities under the same value stream can be constructed, and the associated business functions can be obtained. Please refer to Table 3 below for details:

[0051] Table 3

[0052]

[0053] Please refer to Figure 4 In an embodiment of the present application, obtaining a business recommendation result by attention mechanism model analysis according to the second association data information and the architecture knowledge graph includes:

[0054] S401 generating a business training graph by knowledge merging through matching according to the second association data information and the architecture knowledge graph;

[0055] S402 obtaining a business recommendation result by attention mechanism model analysis according to the business training graph.

[0056] According to the second correlation data information and the architecture knowledge graph, knowledge merging is performed through matching to generate a business training graph.

[0057] Specifically, in actual work, the business training graph mainly matches the data of the architecture task knowledge graph C and the data of the relationship table B by constructing a mapping relationship. If the same architecture activity entity is pointed to, information can be fused through the technology of knowledge merging to obtain a customer-correlation recommended business training graph D. The recommended content can be other business functions, or information such as associated product-related news and partner introduction information obtained from the graph. For example, the following table 4 shows:

[0058] Table 4

[0059]

[0060] Please refer to Figure 5 In an embodiment of the present application, the business recommendation result is obtained by analyzing the business training graph through an attention mechanism model, and the business recommendation result comprises:

[0061] S501 obtains associated recommended business data and user information according to the business training graph;

[0062] S502 generates a vector matrix according to the associated recommended business data, and generates a pointing vector according to the user information;

[0063] S503 analyzes the relevance of the recommended business and the user in the associated recommended business data according to the vector matrix and the pointing vector through an attention mechanism model;

[0064] S504 obtains a business recommendation result according to the relevance analysis.

[0065] According to the relevance analysis, the business recommendation result comprises: calculating a weight coefficient of the corresponding recommended business according to the relevance through a normalization exponential function; and obtaining a preset number of recommended businesses according to the high and low of the weight coefficient to generate a business recommendation result.

[0066] Specifically, in actual work, the business recommendation result is mainly obtained by using the attention mechanism model to obtain several business functions with the highest recommendation weight. The importance of different weights is measured through the attention mechanism, and different attention weight values a are given. For example, the associated recommended business is represented by a vector matrix (s1, s2, s3…), the user is represented by a vector m, and the attention weight value a is used to calculate the relevance between the user and the recommended business, that is, e(s im) function calculates the relevance of the recommended business s and the current customer m state, the relevance function can be obtained by dot product e(s, m) = s T m. According to the relevance function, the weight of each equity vector is calculated by the normalization exponential function softmax According to the size of the alpha weight value, the recommendation degree of different functions is judged, and the functions with the highest weight are output; since the attention mechanism belongs to the prior art, the principle thereof will not be further described herein.

[0067] In an embodiment of the present application, the method further comprises: obtaining operation information of user feedback according to the business recommendation result; and updating the second association data information through the operation information. In actual work, one or more business recommendation results can be displayed to the user according to actual needs, and the result data after the user clicks in can be used as new data of the relationship table B and as a sample for model training, so as to iteratively optimize the model.

[0068] Please refer to Figure 6 The present application also provides a business recommendation device based on business architecture, which comprises an association module, a mining module and a recommendation module; the association module is used to obtain first association data information according to the association relationship between application functions and business architecture activities; the mining module is used to obtain application functions operated by a user according to user operation history data analysis, and generate second association data information through the application functions operated by the user and the first association data information; and the recommendation module is used to construct an architecture knowledge graph according to business architecture activities and the association between the activities, and obtain a business recommendation result through attention mechanism model analysis according to the second association data information and the architecture knowledge graph. Since the principle of solving problems of the device is similar to that of the business recommendation method based on business architecture, the implementation of the device can be referred to the implementation of the business recommendation method based on business architecture, and the repeated parts will not be described herein.

[0069] It should be noted that the business recommendation method and system based on business architecture provided in the embodiments of the present application can be used in the financial field, and can also be used in any technical field other than the financial field, and the application field of the business recommendation method and system based on business architecture is not limited in the embodiments of the present application.

[0070] The beneficial technical effects of the present application are that the business architecture modeling method is used to establish a connection between business architecture activities and the operation behavior of a customer in a mobile bank app, and an artificial intelligence model is used to realize a business recommendation with a more differentiated and iterative optimization mechanism.

[0071] The application further provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above method when executing the computer program.

[0072] The application further provides a computer readable storage medium storing a computer program for executing the above method.

[0073] The application further provides a computer program product comprising computer programs / instructions, which, when executed by a processor, implement the steps of the above method.

[0074] As shown in Figure 7 , the electronic device 600 can further comprise a communication module 110, an input unit 120, an audio processor 130, a display 160, and a power supply 170. It is worth noting that the electronic device 600 does not necessarily have to comprise all the components shown in Figure 7 ; in addition, the electronic device 600 can further comprise components not shown in Figure 7 , which can be referred to the prior art.

[0075] As shown in Figure 7 , the central processor 100, which is also sometimes referred to as a controller or an operating control, can comprise a microprocessor or other processor device and / or logic device, which receives input and controls the operation of the various components of the electronic device 600.

[0076] The memory 140, for example, can be one or more of a cache, a flash memory, a hard drive, a removable media, a volatile memory, a non-volatile memory, or other suitable device. The above information related to failure can be stored, and in addition, programs for executing the information related to failure can also be stored. The central processor 100 can execute the programs stored in the memory 140 to achieve information storage or processing, etc.

[0077] The input unit 120 provides input to the central processor 100. The input unit 120 is, for example, a key or a touch input device. The power supply 170 is used to provide power to the electronic device 600. The display 160 is used to display display objects such as images and text. The display can be, for example, an LCD display, but is not limited thereto.

[0078] The memory 140 can be a solid state memory such as a read only memory (ROM), a random access memory (RAM), a SIM card, etc. It can also be a memory that retains information even when power is turned off, can be selectively erased and provided with more data, examples of which are sometimes referred to as EPROM, etc. The memory 140 can also be some other type of device. The memory 140 includes a buffer memory 141 (sometimes referred to as a buffer). The memory 140 can include an application / function storage 142 for storing application programs and function programs or a flow for executing the operation of the electronic device 600 by the central processing unit 100.

[0079] The memory 140 can also include a data storage (data 143) for storing data such as contacts, digital data, pictures, sounds and / or any other data used by the electronic device. A driver storage (driver 144) of the memory 140 can include various drivers of the electronic device for a communication function and / or for performing other functions of the electronic device such as a messaging application, an address book application, etc.

[0080] The communication module 110 is a transmitter / receiver 110 that transmits and receives signals via an antenna 111. The communication module (transmitter / receiver) 110 is coupled to the central processing unit 100 to provide input signals and receive output signals, which can be the same as in the case of a conventional mobile communication terminal.

[0081] Based on different communication technologies, a plurality of communication modules 110 such as a cellular network module, a Bluetooth module and / or a wireless local area network module, etc. can be provided in the same electronic device. The communication module (transmitter / receiver) 110 is also coupled to a speaker 131 and a microphone 132 via an audio processor 130 to provide audio output via the speaker 131 and receive audio input from the microphone 132, thereby implementing a general telecommunication function. The audio processor 130 can include any suitable buffer, decoder, amplifier, etc. In addition, the audio processor 130 is also coupled to the central processing unit 100, thereby enabling recording on a local machine through the microphone 132 and enabling playing of a sound stored on the local machine through the speaker 131.

[0082] Those skilled in the art will appreciate that embodiments of the present application can be readily used as a method, a system or a computer program product. Accordingly, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application can take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage devices, etc.) embodying computer readable program code thereon.

[0083] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flowcharts and / or blocks Figure 1 means for functionally implementing the steps of the flowchart block or blocks

[0084] These computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture including instructions which implement the flowchart block or blocks. Figure 1 one or more flowcharts and / or blocks Figure 1 means for functionally implementing the steps of the flowchart block or blocks

[0085] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flowcharts and / or blocks Figure 1 means for functionally implementing the steps of the flowchart block or blocks

[0086] The specific embodiments described above are illustrative of certain specific embodiments of the application, and simple serve to describe the principles of the application and the best mode in which it should be practiced. Other embodiments of the application will readily occur to those skilled in the art, and the principles and contribution of the application to the art are intended to be limited only by the scope of the following claims.

Claims

1. A business recommendation method based on a business architecture, characterized by, The method comprises: obtaining first association data information according to the association relationship between application functions and business architecture activities; obtaining the application functions operated by the user according to the user operation history data analysis, and generating second association data information through the application functions operated by the user and the first association data information; constructing an architecture knowledge graph according to the association between business architecture activities and activities, and obtaining a business recommendation result through attention mechanism model analysis according to the second association data information and the architecture knowledge graph.

2. The business recommendation method based on a business architecture according to claim 1, characterized by, Generating second association data information through the application functions operated by the user and the first association data information comprises: generating user journey data according to the user operation history data through the time sequence characteristics of the application functions operated by the user; generating second association data information through application function association according to the user journey data and the first association data information. 3.The business recommendation method based on a business architecture according to claim 1, characterized in that, Constructing an architecture knowledge graph according to the association between business architecture activities and activities comprises: obtaining graph nodes according to business architecture activities; obtaining graph association edges according to associated activities and associated objects between business architecture activities; constructing an architecture knowledge graph according to the graph nodes and the graph association edges.

4. The business recommendation method based on a business architecture according to claim 1, characterized by, Obtaining a business recommendation result through attention mechanism model analysis according to the second association data information and the architecture knowledge graph comprises: merging knowledge through matching according to the second association data information and the architecture knowledge graph to generate a business training graph; obtaining a business recommendation result through attention mechanism model analysis according to the business training graph.

5. The business recommendation method based on a business architecture according to claim 4, characterized by, Merging knowledge through matching according to the second association data information and the architecture knowledge graph to generate a business training graph comprises: merging knowledge through common pointing according to the business architecture activities in the second association data information and the business architecture activities in the architecture knowledge graph to generate a business training graph. 6.The business recommendation method based on the business architecture according to claim 4, characterized in that, Obtaining a business recommendation result through attention mechanism model analysis according to the business training graph comprises: obtaining associated recommended business data and user information according to the business training graph; generating a vector matrix according to the associated recommended business data, and generating a pointing vector according to the user information; analyzing the relevance of recommended businesses to users in the associated recommended business data according to the vector matrix and the pointing vector through attention mechanism model analysis; obtaining a business recommendation result according to the relevance analysis. 7.The business recommendation method based on the business architecture according to claim 6, characterized in that, Obtaining a business recommendation result according to the relevance analysis comprises: calculating the weight coefficient of the corresponding recommended business according to the relevance through a normalized exponential function; obtaining a preset number of recommended businesses to generate a business recommendation result according to the high and low of the weight coefficient. 8.The business recommendation method based on a business architecture according to claim 1, characterized in that, The method further comprises: obtaining user feedback operation information according to the business recommendation result; updating the second association data information through the operation information.

9. A service recommendation apparatus based on a service architecture, characterized by, The device comprises an association module, a mining module, and a recommendation module; the association module is used for obtaining first association data information according to the association relationship between application functions and business architecture activities; The mining module is used for obtaining an application function operated by a user according to user operation history data analysis, and generating second association data information through the application function operated by the user and the first association data information; The recommendation module is used for constructing an architecture knowledge graph according to business architecture activities and associations between the activities, and obtaining a business recommendation result through an attention mechanism model analysis according to the second association data information and the architecture knowledge graph.

10. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor implements the method in any one of claims 1 to 8 when executing the computer program.

11. A computer readable storage medium, characterized in that, The computer readable storage medium stores a computer program, and the computer program implements the method in any one of claims 1 to 8 when executed by the processor.

Images