CN110879868A

CN110879868A - Consultant scheme generation method, device, system, electronic equipment and medium

Info

Publication number: CN110879868A
Application number: CN201911152780.0A
Authority: CN
Inventors: 姚逸彬; 唐子洋; 赵可嘉; 张城; 李嘉; 刘晓怡; 余振庭
Original assignee: Industrial and Commercial Bank of China Ltd ICBC
Current assignee: Industrial and Commercial Bank of China Ltd ICBC
Priority date: 2019-11-21
Filing date: 2019-11-21
Publication date: 2020-03-13

Abstract

The disclosure provides an advisory scheme generation method, which comprises the steps of obtaining keywords, client data and frame information, obtaining key data from the Internet based on the keywords, determining partial data supporting an analysis conclusion from the key data based on at least one analysis conclusion, determining target data matched with the client data from the partial data, splicing the target data based on the frame information, and processing the spliced target data by using a trained text processing model to generate an advisory scheme. The present disclosure also provides an advisory proposal generation apparatus, an electronic device, a computer-readable storage medium, and an advisory proposal generation system.

Description

Consultant scheme generation method, device, system, electronic equipment and medium

Technical Field

The disclosure relates to an advisory scheme generation method, an advisory scheme generation device, an electronic device and a medium.

Background

In the data explosion era, considerable big data are accumulated inside and outside the banking industry, and the treasures of the big data are not mined, which is mainly caused by the fact that the means and the method for intelligently understanding the big data by a machine are limited, so that a large amount of logic analysis work also needs manual intervention, and the intelligence level is low.

In the fields of economy, finance and the like, the current personalized advisor service scheme mainly relies on manual analysis and draft editing, and has problems in multiple aspects, such as (1) too high manpower and time cost for writing reports and failure to provide high-quality service for more clients in a limited time; (2) the writing of the advisor service scheme adopts a manual writing mode, so that many situations depend on the personal experience and the reading of a writer, the same situation is easily caused, and a result with great difference is obtained; (3) in the same industry written by adopting machine intelligence, the intelligence level is very low, and a consultant service scheme meeting the personalized requirements of the client cannot be provided for the client. Therefore, a technical scheme or a system capable of automatically acquiring data inside and outside the industry, combining the self condition of the client and various influence factors, realizing intelligent one-key manuscript composition and providing a personalized solution for the client is needed to be provided.

Disclosure of Invention

One aspect of the present disclosure provides an advisory scheme generation method including obtaining keywords, client data, and frame information, obtaining key data from the internet based on the keywords, determining partial data supporting the analysis conclusion from the key data based on at least one analysis conclusion, determining target data matching the client data from the partial data, stitching the target data based on the frame information, and processing the stitched target data using a trained text processing model to generate an advisory scheme.

Optionally, the determining, based on at least one analysis conclusion, the portion of data that supports the analysis conclusion from the key data includes determining, based on user input, an analysis conclusion, and determining, from the key data, the portion of data that supports the analysis conclusion.

Optionally, the determining, based on at least one analysis conclusion, the portion of data from the critical data that supports the analysis conclusion includes processing the critical data, determining at least one analysis conclusion, and determining, from the critical data, the portion of data that supports each of the at least one analysis conclusion.

Optionally, obtaining the customer data comprises obtaining customer image material and structured data from a business system, and generating a customer portrait and panoramic view information comprising a plurality of key-value pairs as the customer data based on the customer image material and the structured data from the business system.

Optionally, the text processing model is configured to strip the spliced target data into a plurality of sentence segments and a graph, perform full-text graph annotation operation based on the graph, optimize readability of a sentence based on the plurality of sentence segments, and perform automatic typesetting operation.

Another aspect of the disclosure provides an advisory solution generating apparatus comprising a first obtaining module, a second obtaining module, a first determining module, a second determining module, a splicing module, and a processing module. The first obtaining module is used for obtaining the keywords, the client data and the frame information. And the second obtaining module is used for obtaining key data from the Internet based on the key words. The first determination module is used for determining partial data supporting the analysis conclusion from the key data based on at least one analysis conclusion. And the second determining module is used for determining target data matched with the client data from the partial data. And the splicing module is used for splicing the target data based on the frame information. And the processing module is used for processing the spliced target data by using the trained text processing model to generate an advisor scheme.

Another aspect of the disclosure provides an advisor proposal generation system including a data processing subsystem, a customer analysis subsystem, and a proposal generation subsystem. The data processing subsystem is used for obtaining key words, obtaining key data from the Internet based on the key words, and determining partial data supporting the analysis conclusion from the key data based on at least one analysis conclusion. And the customer analysis subsystem is used for obtaining customer data and determining target data matched with the customer data from the partial data. And the scheme generation subsystem is used for acquiring frame information, splicing the target data based on the frame information, and processing the spliced target data by using the trained text processing model to generate an advisor scheme.

Optionally, the data processing subsystem includes a data preprocessing module and a material library. And the data preprocessing module is used for processing the key data based on semantic analysis and a knowledge graph and determining partial data supporting the analysis conclusion. And the material library is used for receiving the partial data output by the data preprocessing module and storing the partial data according to a plurality of categories.

Optionally, the customer analysis subsystem includes a data reading module, a data analysis module, and a customer data module. And the data reading module is used for acquiring the client image data and the structured data from the service system and processing the client image data into the structured data. And the data analysis module is used for analyzing the structured data through an unsupervised learning algorithm to obtain a client portrait and panoramic view information comprising a plurality of key value pairs. A client data module for storing the client representation and panoramic view information in a plurality of categories.

Another aspect of the disclosure provides an electronic device comprising a processor and a memory for storing one or more computer-readable instructions, wherein the one or more computer-readable instructions, when executed by the at least one processor, cause the processor to perform the method as described above.

Another aspect of the disclosure provides a computer readable medium having stored thereon computer readable instructions that, when executed, cause a processor to perform the method as described above.

Another aspect of the disclosure provides a computer program comprising computer executable instructions for implementing the method as described above when executed.

Drawings

The above and other objects, features and advantages of the present disclosure will become more apparent from the following description of embodiments of the present disclosure with reference to the accompanying drawings, in which:

FIG. 1 schematically illustrates an exemplary application scenario of the advisor scenario generation method and apparatus in accordance with an embodiment of the present disclosure;

FIG. 2 schematically shows a flow diagram of an advisor scenario generation method in accordance with an embodiment of the present disclosure;

FIG. 3 schematically illustrates a flow diagram of a text processing model processing spliced target data according to an embodiment of the disclosure;

FIG. 4 schematically shows a block diagram of an advisor scenario generation system in accordance with an embodiment of the present disclosure;

FIG. 5 schematically shows a block diagram of an advisor scenario generation facility, in accordance with an embodiment of the present disclosure; and

FIG. 6 schematically illustrates a block diagram of a computer system suitable for implementing the advisor solution generation method and system in accordance with an embodiment of the present disclosure.

Detailed Description

Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. It should be understood that the description is illustrative only and is not intended to limit the scope of the present disclosure. In the following detailed description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the disclosure. It may be evident, however, that one or more embodiments may be practiced without these specific details. Moreover, in the following description, descriptions of well-known structures and techniques are omitted so as to not unnecessarily obscure the concepts of the present disclosure.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. The terms "comprises," "comprising," and the like, as used herein, specify the presence of stated features, steps, operations, and/or components, but do not preclude the presence or addition of one or more other features, steps, operations, or components.

All terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art unless otherwise defined. It is noted that the terms used herein should be interpreted as having a meaning that is consistent with the context of this specification and should not be interpreted in an idealized or overly formal sense.

Where a convention analogous to "at least one of A, B and C, etc." is used, in general such a construction is intended in the sense one having skill in the art would understand the convention (e.g., "a system having at least one of A, B and C" would include but not be limited to systems that have a alone, B alone, C alone, a and B together, a and C together, B and C together, and/or A, B, C together, etc.). Where a convention analogous to "A, B or at least one of C, etc." is used, in general such a construction is intended in the sense one having skill in the art would understand the convention (e.g., "a system having at least one of A, B or C" would include but not be limited to systems that have a alone, B alone, C alone, a and B together, a and C together, B and C together, and/or A, B, C together, etc.). It will be further understood by those within the art that virtually any disjunctive word and/or phrase presenting two or more alternative terms, whether in the description, claims, or drawings, should be understood to contemplate the possibilities of including one of the terms, either of the terms, or both terms. For example, the phrase "a or B" should be understood to include the possibility of "a" or "B", or "a and B".

An embodiment of the present disclosure provides an advisory scheme generation method, including obtaining keywords, client data, and frame information, obtaining key data from the internet based on the keywords, determining partial data supporting the analysis conclusion from the key data based on at least one analysis conclusion, determining target data matching the client data from the partial data, splicing the target data based on the frame information, and processing the spliced target data using a trained text processing model to generate an advisory scheme.

FIG. 1 schematically illustrates an application scenario of the advisor scenario generation method and system in accordance with an embodiment of the present disclosure. It should be noted that fig. 1 is only an example of a system architecture to which the embodiments of the present disclosure may be applied to help those skilled in the art understand the technical content of the present disclosure, and does not mean that the embodiments of the present disclosure may not be applied to other devices, systems, environments or scenarios.

As shown in fig. 1, the system architecture 100 according to this embodiment may include

terminal devices

101, 102, 103, a network 104 and a server 105. The network 104 serves as a medium for providing communication links between the

terminal devices

101, 102, 103 and the server 105. Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.

The user may use the

terminal devices

101, 102, 103 to interact with the server 105 via the network 104 to receive or send messages or the like. The

terminal devices

101, 102, 103 may have installed thereon various communication client applications, such as shopping-like applications, web browser applications, search-like applications, instant messaging tools, mailbox clients, social platform software, etc. (by way of example only).

The

terminal devices

101, 102, 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like.

The server 105 may be a server providing various services, such as a background management server (for example only) providing support for websites browsed by users using the

terminal devices

101, 102, 103. The background management server may analyze and perform other processing on the received data such as the user request, and feed back a processing result (e.g., a webpage, information, or data obtained or generated according to the user request) to the terminal device.

It should be noted that the advisor scenario generation method provided by the embodiment of the present disclosure may be generally executed by the server 105. Accordingly, the advisor scenario generation system provided by the disclosed embodiments may be generally located in the server 105.

It should be understood that the number of terminal devices, networks, and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.

FIG. 2 schematically shows a flow diagram of an advisor scenario generation method in accordance with an embodiment of the present disclosure.

As shown in fig. 2, the method includes operations S210 to S260.

In operation S210, keywords, customer data, and frame information are obtained.

According to embodiments of the present disclosure, keywords may be determined in conjunction with customer needs. The frame information may be fixed-format template information stored in the system in advance. In other embodiments of the present disclosure, the frame information may also support a non-fixed format of frame information entered by the user.

According to an embodiment of the present disclosure, obtaining customer data includes obtaining customer image material and structured data from a business system, and generating a customer portrait and panoramic view information including a plurality of key-value pairs as customer data based on the customer image material and the structured data from the business system. For example, a customer profile may include the customer's preferences, the behavior of groups similar to the customer, etc., and a panoramic view is a quantitative result integrated based on data such as the customer's financial statements.

In operation S220, key data from the internet is obtained based on the keyword. The critical data may be obtained from the internet through a general or special purpose search engine, or through web crawler technology. The key data may include, for example, data from aspects such as macro-policy, industry development, regional economic situation, investment and financing strategy, enterprise operation, and financial analysis.

In operation S230, partial data supporting the analysis conclusion is determined from the critical data based on at least one analysis conclusion.

According to an embodiment of the present disclosure, the determining, based on at least one analysis conclusion, the partial data supporting the analysis conclusion from the key data includes determining, based on user input, one analysis conclusion, and determining, from the key data, the partial data supporting the analysis conclusion. For example, a person acting as a consultant may draw a preliminary opinion based on the collected critical data, and enter it into the system as an analytical conclusion. The system may determine data supporting the analysis conclusion based on the analysis conclusion, for example, the data supporting the analysis conclusion may be identified by an artificial intelligence model.

According to an embodiment of the present disclosure, the determining, based on at least one analysis conclusion, the part of the data supporting the analysis conclusion from the critical data includes processing the critical data, determining at least one analysis conclusion, and determining, from the critical data, the part of the data supporting each of the at least one analysis conclusion. For example, the obtained key data may be clustered to obtain a plurality of groups of data respectively supporting different analysis conclusions, where each group of data corresponds to one analysis conclusion, thereby obtaining at least one analysis conclusion and the key data supporting each analysis conclusion.

In operation S240, target data matching the customer data is determined from the partial data. According to the embodiment of the disclosure, the client data and the partial data are matched, so that the partial data can be screened to obtain the target data suitable for a specific client.

In operation S250, the target data is spliced based on the frame information.

In operation S260, the spliced target data is processed using the trained text processing model, and a counselor scheme is generated.

FIG. 3 schematically shows a flow diagram of a text processing model processing spliced target data according to an embodiment of the disclosure.

As shown in fig. 3, the method includes operations S310 to S340.

In operation S310, the spliced target data is stripped into a plurality of periods and graphs.

In operation S320, a full-text chart captioning operation is performed based on the chart.

In operation S330, readability of the sentence is optimized based on the plurality of sentence segments.

In operation S340, an automatic layout operation is performed.

According to the embodiment of the present disclosure, the text processing model may be implemented as, for example, a concatenation of four artificial intelligence models, a first artificial intelligence model for stripping the target data into a plurality of sentence segments and diagrams, a second artificial intelligence model for performing full-text diagram inscription operations on the icons, a third artificial intelligence model for optimizing readability of the sentences of the text portions, and a fourth artificial intelligence model for performing automatic typesetting operations. Each artificial intelligence model can be trained independently in the initial stage, then spliced into a complete text processing module, and trained again to obtain a better processing effect.

The method described above is further described below in conjunction with the advisor scenario generation system provided by the disclosed embodiments.

FIG. 4 schematically shows a block diagram of an advisor scenario generation system 400, in accordance with an embodiment of the present disclosure.

As shown in FIG. 4, the system 400 includes three parts, a data processing subsystem 410, a client analysis subsystem 420 and a solution generation subsystem 430, which together form the intelligent advisor solution generation system of the present invention. This figure describes the overall flow of how the advisor services schema is generated.

The data processing subsystem 410 provides raw materials (including but not limited to texts, pictures, reports, etc.) of a service scheme for the whole business process, and after mass data is obtained through the internet or external partners, the data processing subsystem 410 extracts structured data and analytic conclusions through various big data algorithms. In addition, the customer analysis subsystem 420 provides a personalized combination basis for the whole business process, and forms an accurately described customer portrait through the learning of unsupervised algorithms by accessing other business systems and the customer-related image data imported into the system. Then, the rich material segments of the data processing subsystem 410 are matched by using the generation logic of the client analysis subsystem 420, and the service scheme draft is generated intelligently by combining the frame information in the scheme generation subsystem 430.

The data processing subsystem 410 is composed of a data preprocessing module 411 and a material library 412. The data preprocessing module 411 analyzes the input internal and external mass data streams in real time, and sends the processed data to the material library 412, and the material library 412 reserves and stores the data transmitted by the data preprocessing module 411 for the scheme generating subsystem 430 to use.

The data preprocessing module 411 is configured to extract information and analysis conclusions that are valuable to a client from mass data after the mass data on the internet is processed by large data technologies such as semantic analysis and a knowledge graph, and transmit the results to the material library 412.

The material library 412 is used for dividing the transmission data into segments including but not limited to macro policy, industry development, regional economic situation, investment and financing strategy, enterprise operation and financial analysis after receiving the information collected and analyzed by the data preprocessing module 411, and storing the segments, and providing index guidance for the calling of the later-stage scheme generation subsystem 430.

Specifically, the data processing subsystem 410 imports massive internal and external data into the data preprocessing module 411 according to a certain file format; processing the imported mass data through semantic analysis; further processing the processed data by big data technologies such as a knowledge graph and the like; processing the mass data into structured data and an analysis conclusion according to the technical analysis conclusion; the obtained processing result is stored in the material library 412 according to a certain rule.

The customer analysis subsystem 420 is composed of three parts, a data reading module 421, a data analysis module 422 and a customer data module 423. The data reading module 421 receives the externally obtained client image data and the client data of other docked service systems, and then sends the stored client data to the data analysis module 422. After reading customer data (including but not limited to financial reports and the like), the data analysis module 422 performs operations such as calculation of various financial ratios and drawing of relevant display charts, generates financial benchmarking standards and other customer analysis conclusions including customer images and panoramic views in the system by various non-supervised learning, event maps and the like in combination with established expert rules, extracts corresponding customer tags, screening logic, customer indexes and other data according to customer dimensions, and then stores the data in the customer data module 423.

The data reading module 421 is used to receive externally obtained customer image data and customer data of other connected service systems. After the optical character recognition technology is used for reading the image data, the result of the verification of the uploaded person is allowed to ensure the accuracy of the data.

The data analysis module 422 analyzes the customer information through various unsupervised learning (e.g. clustering analysis, social network analysis, etc.), supervised learning, and algorithms of a fact map after receiving the customer information of the data reading module 421, so as to form a multi-dimensional accurate portrait for a single customer.

After receiving the customer images and panoramic view information from the data analysis module 422, the customer data module 423 divides the transmission data into segments including, but not limited to, customer basic information, financial asset status, full-aperture financing, product service, and association relationship for storage, and provides index guidance for the call of the post-scenario generation subsystem 430.

Specifically, the client analysis subsystem 420 imports the acquired client image data into the data reading module 421 according to a certain file format, and meanwhile, interfaces other business systems through internal interfaces and the like to acquire rich client data; the imported customer data is subjected to fine analysis through various unsupervised learning algorithms, and customer characteristics such as customer labels, screening conditions and customer indexes of customers can be accurately and finely described are generated; the processing result is stored in the client data module 423 according to a certain rule.

The scenario generation subsystem 430 receives data transmitted from the data processing subsystem 410 (Uzi material library 412) and the client analysis subsystem 420 (Uzi client data module 423), matches suitable materials from the material library 412 according to client tags, screening logic and client indexes, and performs intelligent text processing operations (including but not limited to full-text chart captioning, automatic typesetting, watermarking and the like) after selecting a corresponding frame to load the materials according to the type of the final advisor service, thereby finally generating an intelligent advisor service scenario.

Specifically, the structured data and the related analysis conclusion stored in the material library 412 are imported into the scheme generation subsystem 430; importing all client-related information in the client data module 423 into the plan generation subsystem 430; matching relevant materials suitable for the client from the imported material information according to the imported client relevant information (including but not limited to client tags, screening logic, client indexes and the like); selecting a corresponding advisory service scheme frame from a frame library according to the type of the client advisory service, and splicing the materials according to a frame format; after splicing is finished, operations including but not limited to full-text chart inscription, automatic typesetting, watermark adding and the like are carried out on the spliced text through an intelligent text processing tool, the expression form of the article is optimized, and the readability is improved; and outputting the final intelligently generated and adjusted advisor scheme. The advisor solutions may be presented to the client in a variety of ways, either through an offline channel, or through an internal, self-online channel, or in cooperation with external associated partners through which the advisor solutions are presented to the client.

The method and the system can automatically acquire data inside and outside the industry, and realize intelligent one-key manuscript composition and provide personalized solutions for clients by combining the conditions of the clients and various influence factors. Compared with the manual writing technology, the intelligent scheme processing system can improve the writing efficiency of the advisor service scheme of the user, and can realize the intelligent generation of the scheme content without manual intervention or a small amount of manual intervention in most scenes. For the formatted and more standardized advisory service scheme, the model, the material and the framework are all built-in systems, so that the quality of service output can be guaranteed fundamentally, and the advisory service maintained at a high level is provided for clients. The specific characteristics of the clients are accurately depicted by combining the related information of the internal and external clients, and further, a personalized and more targeted advisory service scheme is provided for the clients.

Based on the same inventive concept, the present disclosure also provides an advisor scenario generation apparatus, and an advisor scenario generation apparatus according to an embodiment of the present disclosure will be described below with reference to fig. 5.

FIG. 5 schematically shows a block diagram of an advisor scenario generation facility 500, in accordance with an embodiment of the present disclosure.

As shown in fig. 5, the apparatus 500 may include a first obtaining module 510, a second obtaining module 520, a first determining module 530, a second determining module 540, a splicing module 550, and a processing module 560. The apparatus may perform the various methods described above with reference to fig. 2, 3.

The first obtaining module 510, for example, performs operation S210 described above with reference to fig. 2, for obtaining keywords, customer data, and framework information.

The second obtaining module 520, for example, performs operation S220 described above with reference to fig. 2, for obtaining the key data from the internet based on the key words.

A first determining module 530, for example performing operation S230 described above with reference to fig. 2, is configured to determine, based on at least one analysis conclusion, partial data that supports the analysis conclusion from the critical data.

The second determining module 540, for example, performs operation S240 described above with reference to fig. 2, for determining target data matching the customer data from the partial data.

The splicing module 550, for example, performs the operation S250 described above with reference to fig. 2, for splicing the target data based on the frame information.

The processing module 560, for example, performs operation S260 described above with reference to fig. 2 for processing the stitched target data using the trained text processing model to generate the advisor solution.

According to the embodiment of the disclosure, the first determination module is used for determining an analysis conclusion based on user input, and determining partial data supporting the analysis conclusion from the key data.

According to the embodiment of the disclosure, the first determination module is configured to process the key data, determine at least one analysis conclusion, and determine partial data supporting each analysis conclusion of the at least one analysis conclusion from the key data.

According to the embodiment of the disclosure, the first obtaining module obtains the customer data, and generates the customer portrait and the panoramic view information including a plurality of key value pairs as the customer data based on the customer image data and the structured data from the business system.

According to the embodiment of the disclosure, the text processing model is used for stripping the spliced target data into a plurality of sentence segments and graphs, executing full-text graph inscription operation based on the graphs, optimizing readability of sentences based on the sentence segments, and executing automatic typesetting operation.

Any number of modules, sub-modules, units, sub-units, or at least part of the functionality of any number thereof according to embodiments of the present disclosure may be implemented in one module. Any one or more of the modules, sub-modules, units, and sub-units according to the embodiments of the present disclosure may be implemented by being split into a plurality of modules. Any one or more of the modules, sub-modules, units, sub-units according to embodiments of the present disclosure may be implemented at least in part as a hardware circuit, such as a Field Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a system on a chip, a system on a substrate, a system on a package, an Application Specific Integrated Circuit (ASIC), or may be implemented in any other reasonable manner of hardware or firmware by integrating or packaging a circuit, or in any one of or a suitable combination of software, hardware, and firmware implementations. Alternatively, one or more of the modules, sub-modules, units, sub-units according to embodiments of the disclosure may be at least partially implemented as a computer program module, which when executed may perform the corresponding functions.

For example, any of the first obtaining module 510, the second obtaining module 520, the first determining module 530, the second determining module 540, the splicing module 550, and the processing module 560 may be combined in one module to be implemented, or any one of them may be split into a plurality of modules. Alternatively, at least part of the functionality of one or more of these modules may be combined with at least part of the functionality of the other modules and implemented in one module. According to an embodiment of the present disclosure, at least one of the first obtaining module 510, the second obtaining module 520, the first determining module 530, the second determining module 540, the splicing module 550, and the processing module 560 may be implemented at least in part as a hardware circuit, such as a Field Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a system on a chip, a system on a substrate, a system on a package, an Application Specific Integrated Circuit (ASIC), or may be implemented in hardware or firmware in any other reasonable manner of integrating or packaging a circuit, or in any one of three implementations of software, hardware, and firmware, or in a suitable combination of any of them. Alternatively, at least one of the first obtaining module 510, the second obtaining module 520, the first determining module 530, the second determining module 540, the splicing module 550 and the processing module 560 may be at least partially implemented as a computer program module, which when executed, may perform a corresponding function.

FIG. 6 schematically illustrates a block diagram of a computer system suitable for implementing the advisor solution generation method and apparatus in accordance with an embodiment of the present disclosure. The computer system illustrated in FIG. 6 is only one example and should not impose any limitations on the scope of use or functionality of embodiments of the disclosure. The computer system shown in fig. 6 may be implemented as a server cluster including at least one processor (e.g., processor 601) and at least one memory (e.g., storage 608).

As shown in fig. 6, a computer system 600 according to an embodiment of the present disclosure includes a processor 601, which can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM)602 or a program loaded from a storage section 608 into a Random Access Memory (RAM) 603. Processor 601 may include, for example, a general purpose microprocessor (e.g., a CPU), an instruction set processor and/or associated chipset, and/or a special purpose microprocessor (e.g., an Application Specific Integrated Circuit (ASIC)), among others. The processor 601 may also include onboard memory for caching purposes. Processor 601 may include a single processing unit or multiple processing units for performing different actions of a method flow according to embodiments of the disclosure.

In the RAM 603, various programs and data necessary for the operation of the system 600 are stored. The processor 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. The processor 601 performs various operations of the method flows according to the embodiments of the present disclosure by executing programs in the ROM 602 and/or RAM 603. It is to be noted that the programs may also be stored in one or more memories other than the ROM 602 and RAM 603. The processor 601 may also perform various operations of the method flows according to embodiments of the present disclosure by executing programs stored in the one or more memories.

According to an embodiment of the present disclosure, system 600 may also include an input/output (I/O) interface 605, input/output (I/O) interface 605 also connected to bus 604. The system 600 may also include one or more of the following components connected to the I/O interface 605: an input portion 606 including a keyboard, a mouse, and the like; an output portion 607 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage section 608 including a hard disk and the like; and a communication section 609 including a network interface card such as a LAN card, a modem, or the like. The communication section 609 performs communication processing via a network such as the internet. The driver 610 is also connected to the I/O interface 605 as needed. A removable medium 611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 610 as necessary, so that a computer program read out therefrom is mounted in the storage section 608 as necessary.

According to embodiments of the present disclosure, method flows according to embodiments of the present disclosure may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 609, and/or installed from the removable medium 611. The computer program, when executed by the processor 601, performs the above-described functions defined in the system of the embodiments of the present disclosure. The systems, devices, apparatuses, modules, units, etc. described above may be implemented by computer program modules according to embodiments of the present disclosure.

The present disclosure also provides a computer-readable medium, which may be embodied in the apparatus/device/system described in the above embodiments; or may exist separately and not be assembled into the device/apparatus/system. The computer readable medium carries one or more programs which, when executed, implement the method according to an embodiment of the disclosure.

According to embodiments of the present disclosure, a computer readable medium may be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In contrast, in the present disclosure, a computer-readable signal medium may include a propagated data signal with computer-readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, optical fiber cable, radio frequency signals, etc., or any suitable combination of the foregoing.

For example, according to embodiments of the present disclosure, a computer-readable medium may include ROM 402 and/or RAM 403 and/or one or more memories other than ROM 402 and RAM 403 described above.

The invention provides a consultant proposal generating method, a device, electronic equipment and a medium, which provides certificate information, contact information, user information, biological identification information and the like of a client to a client identification system through a client information system, the client identification system obtains various authentication medium information provided by the client and carries out authentication, client footprint information including voice information, face information, scene information for initiating client identification and the like is recorded in the second process, the information is transmitted to a client analysis system, the analysis of the footprint information is completed through artificial intelligence technologies such as tone identification, semantic identification, face identification, micro-expression identification and the like, and finally various types of client appeal information is formed, and the appeal information is finally transmitted back to the client information system and is supplied to each system, in particular to a marketing system and a client service related system, the marketing accuracy is improved, and the satisfaction degree of customers on products and services is improved.

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

Those skilled in the art will appreciate that various combinations and/or combinations of features recited in the various embodiments and/or claims of the present disclosure can be made, even if such combinations or combinations are not expressly recited in the present disclosure. In particular, various combinations and/or combinations of the features recited in the various embodiments and/or claims of the present disclosure may be made without departing from the spirit or teaching of the present disclosure. All such combinations and/or associations are within the scope of the present disclosure.

The embodiments of the present disclosure have been described above. However, these examples are for illustrative purposes only and are not intended to limit the scope of the present disclosure. Although the embodiments are described separately above, this does not mean that the measures in the embodiments cannot be used in advantageous combination. The scope of the disclosure is defined by the appended claims and equivalents thereof. Various alternatives and modifications can be devised by those skilled in the art without departing from the scope of the present disclosure, and such alternatives and modifications are intended to be within the scope of the present disclosure.

Claims

1. A consultant program generation method, comprising:

obtaining keywords, customer data and frame information;

obtaining key data from the internet based on the keyword;

determining partial data supporting the analysis conclusion from the key data based on at least one analysis conclusion;

determining target data matched with the customer data from the partial data;

splicing the target data based on the frame information; and

and processing the spliced target data by using the trained text processing model to generate the advisor scheme.

2. The method of claim 1, wherein the determining, based on at least one analysis conclusion, a portion of data from the critical data that supports the analysis conclusion comprises:

an analysis conclusion is determined based on user input, and partial data supporting the analysis conclusion is determined from the key data.

3. The method of claim 1, wherein the determining, based on at least one analysis conclusion, a portion of data from the critical data that supports the analysis conclusion comprises:

processing the critical data, determining at least one analysis conclusion, and determining from the critical data partial data supporting each of the at least one analysis conclusion.

4. The method of claim 1, wherein obtaining customer data comprises:

obtaining client image data and structured data from a business system; and

based on the customer image material and structured data from a business system, a customer representation and panoramic view information including a plurality of key-value pairs is generated as customer data.

5. The method of claim 1, wherein the text processing model is to:

stripping the spliced target data into a plurality of sentence segments and graphs;

executing full-text chart captions operation based on the chart;

optimizing readability of the sentence based on the plurality of sentence segments; and

and executing automatic typesetting operation.

6. An advisor proposal generation apparatus comprising:

the first obtaining module is used for obtaining keywords, client data and frame information;

the second obtaining module is used for obtaining key data from the Internet based on the key words;

a first determining module, configured to determine, based on at least one analysis conclusion, partial data that supports the analysis conclusion from the key data;

a second determining module, configured to determine target data matching the customer data from the partial data;

the splicing module is used for splicing the target data based on the frame information; and

and the processing module is used for processing the spliced target data by using the trained text processing model to generate an advisor scheme.

7. An electronic device, comprising:

a processor; and

a memory having computer-readable instructions stored thereon that, when executed by the processor, cause the processor to perform the method of any of claims 1-5.

8. A computer readable storage medium having computer readable instructions stored thereon which, when executed by a processor, cause the processor to perform the method of any of claims 1 to 5.

9. An advisor proposal generation system comprising:

the data processing subsystem is used for obtaining a keyword, obtaining key data from the Internet based on the keyword, and determining partial data supporting an analysis conclusion from the key data based on at least one analysis conclusion;

the customer analysis subsystem is used for obtaining customer data and determining target data matched with the customer data from the partial data;

and the scheme generation subsystem is used for acquiring frame information, splicing the target data based on the frame information, and processing the spliced target data by using the trained text processing model to generate an advisor scheme.

10. The system of claim 9, wherein the data processing subsystem comprises:

the data preprocessing module is used for processing the key data based on semantic analysis and a knowledge graph and determining partial data supporting the analysis conclusion; and

and the material library is used for receiving the partial data output by the data preprocessing module and storing the partial data according to a plurality of categories.

11. The method of claim 9, wherein the customer analysis subsystem comprises:

the data reading module is used for acquiring client image data and structured data from a service system and processing the client image data into the structured data;

the data analysis module is used for analyzing the structured data through an unsupervised learning algorithm to obtain a client portrait and panoramic view information comprising a plurality of key value pairs;

a client data module for storing the client representation and panoramic view information in a plurality of categories.