CN114416957A - Financial management data intelligent question-answering method and system - Google Patents
Financial management data intelligent question-answering method and system Download PDFInfo
- Publication number
- CN114416957A CN114416957A CN202210097730.2A CN202210097730A CN114416957A CN 114416957 A CN114416957 A CN 114416957A CN 202210097730 A CN202210097730 A CN 202210097730A CN 114416957 A CN114416957 A CN 114416957A
- Authority
- CN
- China
- Prior art keywords
- class
- keywords
- matching
- library
- question
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000004590 computer program Methods 0.000 claims description 17
- 238000012163 sequencing technique Methods 0.000 claims description 5
- 238000007726 management method Methods 0.000 description 24
- 238000012545 processing Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 7
- 238000004891 communication Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 239000000872 buffer Substances 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000002452 interceptive effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000003631 expected effect Effects 0.000 description 1
- 238000007429 general method Methods 0.000 description 1
- 230000000670 limiting effect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000012805 post-processing Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/02—Banking, e.g. interest calculation or account maintenance
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- General Business, Economics & Management (AREA)
- Artificial Intelligence (AREA)
- Human Computer Interaction (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to an intelligent question-answering method and system for financial management data, which comprises a first matching library, a second matching library mapped on the first matching library, and an incidence relation between a data content library and the second matching library, wherein different matching libraries with high fuzziness and high precision are respectively preset to fully understand personalized problems of a user, and answers which the user may be interested in are correspondingly output, so that flexible combination results of various different data items can be automatically fed back according to the problem content of the user on the premise of not presetting accurate matching keywords, the working efficiency of the user for acquiring complex financial management data is greatly improved, and the intelligent question-answering method and system are particularly suitable for management and use of complex financial systems such as banks and the like.
Description
Technical Field
The invention relates to the technical field of knowledge graph and artificial intelligence data processing, can be applied to the field of financial management data processing and analysis, and relates to an intelligent questioning and answering method and system for financial management data based on a classification matching mode.
Background
Along with the rapid development of financial science and technology, in order to respond to the requirements of the bank science and technology on project management in time, the financial science and technology enabling function is better played; meanwhile, the problems that the bank software project management requirement is high, the total number of projects is large, the project data complexity is high, and single project implementation data cannot meet the requirement of accurate project management are effectively solved. In the prior art, project management data analysis is mostly embodied in a report form and is manually analyzed. Therefore, a technical scheme is urgently needed to meet the data requirements of management posts in the bank project management work on project operation levels, such as various project budget data, project scale data, project implementation cycle data, project resource data and the like.
Aiming at different statistical data requirements of different management roles, the optimal processing mode is to provide convenient, efficient and accurate answers in a question-answering mode. For real-world applications, natural language is the best way to interact with human-computer. The intelligent question-answering project operating system can more accurately understand the user questions described in the natural language form and return concise and accurate matching answers by retrieving a heterogeneous corpus or a question-answering knowledge base. Compared with a search engine, the question-answering system can better understand the real intentions of the user to ask questions, and can meet the requirements of simplicity in operation and precision of knowledge of the user. In interactive question answering, a corresponding context is established through user question content, user intention is accurately understood and corresponding retrieval is carried out, and therefore required data content, particularly personalized combinations of various different data, can be conveniently obtained.
However, the interactive question-answering method is bound to face the practical problem of semantic understanding. The general method is to define the specific content of the user's question, that is, the user can only choose to ask in limited set questions and obtain the preset corresponding answer, and the intelligent answer output cannot be realized according to the personalized requirements of the user, and the actual experience is not good.
Disclosure of Invention
In order to solve the defects of the prior art, the invention provides an intelligent question-answering method and system for financial management data, which can fully understand the personalized problems of a user and correspondingly output answers which the user may be interested in by presetting different matching libraries with high ambiguity and high precision, so that the flexible combination results of various different data items can be automatically fed back according to the problem content of the user on the premise of not presetting precise matching keywords, the working efficiency of the user for acquiring complex financial management data is greatly improved, and the intelligent question-answering method and system are particularly suitable for the management and use of complex financial systems such as banks and the like.
In order to achieve the above purpose, the technical scheme adopted by the invention comprises the following steps:
an intelligent question-answering method for financial management data is characterized by comprising the following steps:
s1, setting a first matching library and a second matching library mapped on the first matching library, wherein the first matching library stores a plurality of first-class matching words, the second matching library stores a plurality of second-class matching words, the first-class matching words correspond to one or more second-class matching words, and the second-class matching words are only subordinate to one first-class matching word;
s2, setting an incidence relation between a data content library and a second matching library, wherein the data content library stores a plurality of data content tables, the second-class matching words correspond to one or more data content tables, and the data content tables at least belong to one second-class matching word;
s3, obtaining the user question, and extracting question keywords contained in the user question by semantic recognition;
s4, verifying all the question keywords by using the first matching library to obtain a class of keywords;
s5, verifying all the question keywords by using a second matching library to obtain second-class keywords;
s6, judging the corresponding relation between the first class key words and the second class key words, and combining all the second class key words simultaneously corresponding to the same first class key words into query phrases;
s7, matching the data content library with the query phrases to obtain a plurality of corresponding data content tables;
s8, combining the obtained data content tables to form a plurality of feedback results respectively corresponding to each type of keywords;
and S9, feeding a plurality of feedback results back to the user respectively.
Further, the step S5 further includes:
the question keywords that do not belong to the first category of keywords or the second category of keywords are classified into three categories of keywords.
Further, the step S8 further includes:
and matching the feedback results by using the three types of keywords, and sequencing the feedback results from at least more according to the number of the matched three types of keywords.
Further, the step S4 further includes:
when the question keywords can not verify the first matching library to obtain the first class of keywords, all the first class of matching words are fed back to serve as the first class of keywords.
Further, the step S6 further includes:
when the first class of keywords does not have the second class of keywords corresponding to the first class of keywords, all the second class of matching words belonging to the first class of keywords are fed back and combined into a query phrase corresponding to the first class of keywords.
Further, the step S6 further includes:
and when the second class of keywords do not have the first class of keywords corresponding to the second class of keywords, combining all the second class of keywords without the first class of keywords into a poor second class of keywords, and then querying phrases.
The invention also relates to an intelligent questioning and answering system for financial management data, which is characterized by comprising the following components:
the first matching library is used for storing a class of matching words;
the second matching library is used for storing the second type of matching words;
the data content library is used for storing a data content table;
the semantic recognition module is used for extracting question keywords contained in the user questions;
the keyword matching module is used for verifying all the question keywords by using the first matching library and the second matching library to obtain a first class of keywords and a second class of keywords;
the query matching module is used for judging the corresponding relation between the first class key words and the second class key words and establishing query phrases;
and the query feedback module is used for obtaining a corresponding data content table by using query phrase matching and forming a feedback result.
The invention also relates to a computer-readable storage medium, characterized in that the storage medium has stored thereon a computer program which, when being executed by a processor, carries out the above-mentioned method.
The invention also relates to an electronic device, characterized in that it comprises a processor and a memory;
the memory is used for storing a first matching library, a second matching library and a data content library;
the processor is used for executing the method by calling the first matching library, the second matching library and the data content library.
The invention also relates to a computer program product comprising a computer program and/or instructions, characterized in that the computer program and/or instructions, when executed by a processor, implement the steps of the above-mentioned method.
The invention has the beneficial effects that:
by adopting the financial management data intelligent question-answering method and system, the full understanding of the personalized problems of the user is realized by respectively presetting different matching libraries with higher fuzziness and higher precision, and answers which the user may be interested in are correspondingly output, so that the flexible combination results of various different data items can be automatically fed back according to the problem content of the user on the premise of not presetting accurate matching keywords, the working efficiency of the user for acquiring complex financial management data is greatly improved, and the financial management data intelligent question-answering method and system are particularly suitable for the management and use of complex financial systems such as banks and the like.
Drawings
FIG. 1 is a flow chart of the financial management data intelligent question answering method of the present invention.
FIG. 2 is a schematic diagram of the financial management data intelligent question-answering system structure.
Detailed Description
For a clearer understanding of the contents of the present invention, reference will be made to the accompanying drawings and examples.
The invention relates to a financial management data intelligent question-answering method with a step flow shown in figure 1, which comprises the following steps:
s1, setting a first matching library and a second matching library mapped on the first matching library, wherein the first matching library stores a plurality of first-class matching words, the second matching library stores a plurality of second-class matching words, the first-class matching words correspond to one or more second-class matching words, and the second-class matching words are only subordinate to one first-class matching word.
The first class matching words are preset large class matching words, and can be specifically defined according to needs, for example, different business fields or operation departments are set as the large class matching words, so that large class distinction related to problems can be quickly identified.
The second class of matching words corresponds to specific problem content categories, and is different from the first class of matching words, and the function of the second class of matching words is to understand the data content categories specifically related to the user problems, such as a specific data report or a specific data of a specific year.
For example, the user question is "2021 year marketing department end-of-year performance report", in which "marketing department" is matched as one type of keyword, while "2021 year", "end-of-year performance report" is matched as two types of keyword.
S2, setting the incidence relation between the data content database and the second matching database, wherein the data content database stores a plurality of data content tables, the second-class matching words correspond to one or more data content tables, and the data content tables at least belong to one second-class matching word.
The corresponding relation between the second-class matching words and the data content table can be fixedly set according to experience, and can also be obtained according to a statistical index of the degree of closeness of the relevant relation between the reflection attributes (such as project budget, project workload estimated in the past year, project demand and the like) of the relevant coefficient matrix. Therefore, there is no data content table without dependencies, and there is no two-class matching word without correspondence, but at the same time, the correspondence and dependencies are not absolutely unique.
And S3, acquiring the user question, and extracting the question key words contained in the user question by using semantic recognition.
Preferably, the question keywords are obtained by performing NLP technical processing such as word segmentation and stop word removal on the input natural language question.
The questions asked by the user can be input by characters, can be converted into characters after voice input, and can help the user to ask corresponding questions through preset guide options.
And S4, verifying all the question keywords by using the first matching library to obtain a class of keywords.
Because the first class keywords are preset large class keywords, the user does not particularly emphasize the large class to which the question belongs when asking the question, or the user considers that the question is general and does not have proper large class classification. And when the question keywords can not verify the first matching library to obtain the first class of keywords, feeding back all the first class of matching words as the first class of keywords. By the setting mode, the final result has better comprehensiveness, and the limiting effect of the second class of keywords on the retrieval result is not influenced.
And S5, verifying all the question keywords by using the second matching library to obtain second-class keywords.
After judging that the first-class keywords and the second-class keywords are obtained, the remaining unclassified questioning keywords usually exist, and questioning keywords which do not belong to the first-class keywords or the second-class keywords can be preferably classified into three classes of keywords. The three types of keywords do not need to participate in query retrieval of the data table content specifically, but the three types of keywords can be used for reasonably sequencing the finally obtained retrieval results, so that the feedback results are closer to the content required by the user.
S6, judging the corresponding relation between the first class key words and the second class key words, and combining all the second class key words simultaneously corresponding to the same first class key words into query phrases.
Meanwhile, for special cases which may occur, the targeted setting is still carried out from the viewpoint of comprehensiveness and completeness of the result. When the first class of keywords does not have the second class of keywords corresponding to the first class of keywords, feeding back all the second class of matching words belonging to the first class of keywords and combining the two class of matching words into a query phrase corresponding to the first class of keywords; and when the second class of keywords do not have the first class of keywords corresponding to the second class of keywords, combining all the second class of keywords without the first class of keywords into a poor second class of keywords, and then querying phrases.
For the query phrases after being inferior, the feedback priority of the query phrases is not limited to be completely inferior, and the feedback results can still be subjected to targeted sequencing according to the sequencing means involved in the method. However, when the corresponding matching data content library is operated, the matching operation sequence of the inferior query phrase can be reasonably placed at the end, because the inferior query phrase does not have a specific corresponding first-class keyword, the span between the second-class keywords may be very large, and meanwhile, the inferior query phrase may be repeated with other previous query phrases, so that the later matching inferior query phrase can realize more reasonable matching workload.
And S7, matching the data content library by using the query phrases to obtain a plurality of corresponding data content tables.
And S8, combining the obtained data content tables to form a plurality of feedback results respectively corresponding to the keywords of each type. Particularly preferably, the feedback results are matched by using three types of keywords, and the feedback results are sorted by at least more according to the number of matched three types of keywords. Namely, the adaptability between the feedback result and the user question is judged by fuzzy matching of the number of the three types of keywords in the feedback result.
The number of the matched three types of keywords can include two dimensions, namely the number of types of different three types of keywords which can be matched in the feedback result, and the total number of the matched three types of keywords. In use, the judgment basis can be selected at will according to actual needs, for example, the two dimensions can be adjusted by setting different weights to play a role in sorting.
And S9, feeding the feedback results back to the user respectively, and particularly feeding the feedback results back to the user in sequence according to the mutual sequence of judgment and identification.
The feedback form can be a pre-stored format such as characters and reports, and can also be a visualization display form of processed raw data, such as bar charts, line graphs and tables, so that the readability of the result is higher.
The following examples further illustrate embodiments of the process of the present invention.
Taking data acquisition in a financial project summarizing process as an example, using the prior art to call related data requires manual selection of necessary data projects respectively according to different statistics and summarizing requirements, which not only consumes a lot of time and energy, but also the obtained data statistics is difficult to ensure the integrity and accuracy, the relationship between different data statistics is completely fuzzy and can not be checked, and linkage cooperative analysis between different data can not be realized basically.
When the method is adopted to obtain the relevant data, the required data can be obtained in a 'question-answer' mode similar to natural language.
For example, the user may directly input the question "big customer to ground performance comparisons, especially company a performance, in quarters two and quarters three for the first and third sales departments". First, it is necessary to extract corresponding question keywords from the question, including: the first sales department, the second quarter, the third quarter, the big client, the ground push, the achievement and the company A, and the questioning keywords belong to the same level and are completely and independently split from each other, and no definite contact is required to be established.
And secondly, verifying the extracted question keywords by using the first matching library and the second matching library respectively so as to obtain a first class of keywords and a second class of keywords. For example, a category of keywords includes a first sales department, a second sales department; the second category of keywords includes second quarter, third quarter, big customer, push to earth. The first matching library is a predefined large-class matching library, specific contents can be set according to actual working experience, general classification of the problem contents can be quickly and accurately positioned by using the first matching library (a class of keywords), the classification can be classified according to business execution departments, or can be classified according to time limits (for example, keywords similar to second quarter and third quarter can be set as a class according to needs), or other suitable classification keywords. On the other hand, one class of matching words in the first matching library can be preferably classified corresponding to the data storage library actually, so that the data retrieval can support accurate retrieval after initial positioning by one class of keywords, and the overall performance of data query is improved.
The second matching library is a library which is subordinate to the first matching library and matches specific data contents (problem contents), namely, contents which a corresponding user specifically wants to know under a large category (under a category of keywords).
Particularly, although the second matching library is set to be subordinate to the first matching library, in fact, there is not necessarily a dependency relationship between the first matching word and the second matching word, for example, there is no dependency of any nature between the "first sales department" and the "second quarter", that is, the dependency relationship between the first matching library and the second matching library is a logic relationship which is set intentionally, the first matching word and the second matching word can be set arbitrarily as required, and the expected effect of this setting is to decompose the user problem reasonably, so that the complicated user problem can be guided to a preset classification logic relationship to obtain a more targeted answer.
For other questioning keywords such as "performance, company a" that do not match to one category of keywords and two categories of keywords, they can be categorized into three categories of keywords for post-processing of the retrieved data, such as ranking, etc.
And thirdly, judging the corresponding relation between the first class of keywords and the second class of keywords, namely collecting the second class of keywords under the first class of keywords according to the preset logic membership between the first class of matching words and the second class of matching words to form one or more query phrases. For example, the query phrases "first department of sales with quarter two, quarter three, big customer, push" and "second department of sales with quarter two, quarter three, big customer, push". Through the step, the original user problem is effectively decomposed substantially, and the decomposition is fully based on the preset subordinate logical relationship, so that the decomposed query phrase can be conveniently used for data query.
And a fourth step of matching the data content library with the query phrases, for example, obtaining a first sales department big second quarter customer report, a first sales department big third quarter customer report, a first sales department push-to-push report, a second sales department big second quarter customer report, a second sales department big third quarter customer report, a second sales department push-to-push report, and a second sales department push-to-push report through the two query phrases. The acquired data can cover the required analysis data under the original user problem with a very high probability, and the user can save a great deal of time and energy compared with the prior art by further screening and analyzing on the basis of the data. Meanwhile, data are obtained by retrieval based on a preset classification mode (a first class matching word and a second class matching word), so that a suitable feedback display mode, such as various visual display modes of a graph, a table and the like, can be conveniently preset for relevant data, and a user can conveniently and visually analyze the relevant data.
Usually, a certain number of three types of keywords are also included in the user question, and the three types of keywords can be used for matching various retrieved feedback results, so that feedback result ranking based on the relevance of the original user question is given. For example, the data tables are matched by using three types of keywords of 'performance, company A', respectively, to obtain a report of the first three quarter big client in the first sales department and a report of the second three quarter big client in the second sales department, so that the two items can be sorted as a preferred result and fed back at a front position.
Because the three types of keywords are the contents which are not used as the preset keywords for searching and classifying in the early configuration stage, the three types of keywords are preferably not used as the basis for screening and eliminating the feedback result, so that the obtained feedback result can be kept with certain integrity, and data omission is avoided.
Another aspect of the present invention also relates to an intelligent questioning and answering system for financial management data, which has a structure as shown in fig. 2, and comprises:
the first matching library is used for storing a class of matching words;
the second matching library is used for storing the second type of matching words;
the data content library is used for storing a data content table;
the semantic recognition module is used for extracting question keywords contained in the user questions;
the keyword matching module is used for verifying all the question keywords by using the first matching library and the second matching library to obtain a first class of keywords and a second class of keywords;
the query matching module is used for judging the corresponding relation between the first class key words and the second class key words and establishing query phrases;
and the query feedback module is used for obtaining a corresponding data content table by using query phrase matching and forming a feedback result.
By using this system, the above-described arithmetic processing method can be executed and a corresponding technical effect can be achieved.
Embodiments of the present invention also provide a computer-readable storage medium capable of implementing all the steps of the method in the above embodiments, the computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements all the steps of the method in the above embodiments.
Embodiments of the present invention further provide an electronic device for executing the method, as an implementation apparatus of the method, the electronic device at least has a processor and a memory, and particularly, the memory stores data required for executing the method and related computer programs, such as a first matching library, a second matching library, a database, and the like, and all steps of implementing the method are executed by invoking the data in the memory and the program by the processor, and corresponding technical effects are obtained.
Preferably, the electronic device may comprise a bus architecture, which may include any number of interconnected buses and bridges linking together various circuits including one or more processors and memory. The bus may also link various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further herein. A bus interface provides an interface between the bus and the receiver and transmitter. The receiver and transmitter may be the same element, i.e., a transceiver, providing a means for communicating with various other systems over a transmission medium. The processor is responsible for managing the bus and general processing, while the memory may be used for storing data used by the processor in performing operations.
Additionally, the electronic device may further include a communication module, an input unit, an audio processor, a display, a power source, and the like. The processor (or controller, operational controls) employed may include a microprocessor or other processor device and/or logic device that receives input and controls the operation of various components of the electronic device; the memory may be one or more of a buffer, a flash memory, a hard drive, a removable medium, a volatile memory, a non-volatile memory or other suitable devices, and may store the above-mentioned related data information, and may also store a program for executing the related information, and the processor may execute the program stored in the memory to realize information storage or processing, etc.; the input unit is used for providing input to the processor, and can be a key or a touch input device; the power supply is used for supplying power to the electronic equipment; the display is used for displaying display objects such as images and characters, and may be an LCD display, for example. The communication module is a transmitter/receiver that transmits and receives signals via an antenna. The communication module (transmitter/receiver) is coupled to the processor to provide an input signal and receive an output signal, which may be the same as in the case of a conventional mobile communication terminal. Based on different communication technologies, a plurality of communication modules, such as a cellular network module, a bluetooth module, and/or a wireless local area network module, may be disposed in the same electronic device. The communication module (transmitter/receiver) is also coupled to a speaker and a microphone via an audio processor to provide audio output via the speaker and receive audio input from the microphone to implement the usual telecommunication functions. The audio processor may include any suitable buffers, decoders, amplifiers and so forth. In addition, the audio processor is also coupled to the central processor, so that recording on the local machine can be realized through the microphone, and sound stored on the local machine can be played through the loudspeaker.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a system for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may 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 an instruction system which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may 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 flow or flows and/or block diagram block or blocks. While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. An intelligent question-answering method for financial management data is characterized by comprising the following steps:
s1, setting a first matching library and a second matching library mapped on the first matching library, wherein the first matching library stores a plurality of first-class matching words, the second matching library stores a plurality of second-class matching words, the first-class matching words correspond to one or more second-class matching words, and the second-class matching words are only subordinate to one first-class matching word;
s2, setting an incidence relation between a data content library and a second matching library, wherein the data content library stores a plurality of data content tables, the second-class matching words correspond to one or more data content tables, and the data content tables at least belong to one second-class matching word;
s3, obtaining the user question, and extracting question keywords contained in the user question by semantic recognition;
s4, verifying all the question keywords by using the first matching library to obtain a class of keywords;
s5, verifying all the question keywords by using a second matching library to obtain second-class keywords;
s6, judging the corresponding relation between the first class key words and the second class key words, and combining all the second class key words simultaneously corresponding to the same first class key words into query phrases;
s7, matching the data content library with the query phrases to obtain a plurality of corresponding data content tables;
s8, combining the obtained data content tables to form a plurality of feedback results respectively corresponding to each type of keywords;
and S9, feeding a plurality of feedback results back to the user respectively.
2. The method of claim 1, wherein the step S5 further comprises:
the question keywords that do not belong to the first category of keywords or the second category of keywords are classified into three categories of keywords.
3. The method of claim 2, wherein the step S8 further comprises:
and matching the feedback results by using the three types of keywords, and sequencing the feedback results from at least more according to the number of the matched three types of keywords.
4. The method of claim 1, wherein the step S4 further comprises:
when the question keywords can not verify the first matching library to obtain the first class of keywords, all the first class of matching words are fed back to serve as the first class of keywords.
5. The method of claim 1, wherein the step S6 further comprises:
when the first class of keywords does not have the second class of keywords corresponding to the first class of keywords, all the second class of matching words belonging to the first class of keywords are fed back and combined into a query phrase corresponding to the first class of keywords.
6. The method of claim 1, wherein the step S6 further comprises:
and when the second class of keywords do not have the first class of keywords corresponding to the second class of keywords, combining all the second class of keywords without the first class of keywords into a poor second class of keywords, and then querying phrases.
7. An intelligent financial management data question-answering system, comprising:
the first matching library is used for storing a class of matching words;
the second matching library is used for storing the second type of matching words;
the data content library is used for storing a data content table;
the semantic recognition module is used for extracting question keywords contained in the user questions;
the keyword matching module is used for verifying all the question keywords by using the first matching library and the second matching library to obtain a first class of keywords and a second class of keywords;
the query matching module is used for judging the corresponding relation between the first class key words and the second class key words and establishing query phrases;
and the query feedback module is used for obtaining a corresponding data content table by using query phrase matching and forming a feedback result.
8. A computer-readable storage medium, characterized in that the storage medium has stored thereon a computer program which, when being executed by a processor, carries out the method of any one of claims 1 to 6.
9. An electronic device comprising a processor and a memory;
the memory is used for storing a first matching library, a second matching library and a data content library;
the processor is configured to execute the method of any one of claims 1 to 6 by calling the first matching library, the second matching library, and the data content library.
10. A computer program product comprising a computer program and/or instructions, characterized in that the computer program and/or instructions, when executed by a processor, implement the steps of the method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210097730.2A CN114416957A (en) | 2022-01-27 | 2022-01-27 | Financial management data intelligent question-answering method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210097730.2A CN114416957A (en) | 2022-01-27 | 2022-01-27 | Financial management data intelligent question-answering method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114416957A true CN114416957A (en) | 2022-04-29 |
Family
ID=81279463
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210097730.2A Pending CN114416957A (en) | 2022-01-27 | 2022-01-27 | Financial management data intelligent question-answering method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114416957A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101178711A (en) * | 2006-11-30 | 2008-05-14 | 腾讯科技（深圳）有限公司 | Chinese auto-answer method and system |
| CN103870507A (en) * | 2012-12-17 | 2014-06-18 | 阿里巴巴集团控股有限公司 | Method and device of searching based on category |
| CN107993724A (en) * | 2017-11-09 | 2018-05-04 | 易保互联医疗信息科技（北京）有限公司 | A kind of method and device of medicine intelligent answer data processing |
| CN110941708A (en) * | 2019-11-04 | 2020-03-31 | 智器云南京信息科技有限公司 | Intelligent question and answer library establishing method, intelligent question and answer method and device and computer equipment |
| US20210064821A1 (en) * | 2019-08-27 | 2021-03-04 | Ushur, Inc. | System and method to extract customized information in natural language text |
-
2022
- 2022-01-27 CN CN202210097730.2A patent/CN114416957A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101178711A (en) * | 2006-11-30 | 2008-05-14 | 腾讯科技（深圳）有限公司 | Chinese auto-answer method and system |
| CN103870507A (en) * | 2012-12-17 | 2014-06-18 | 阿里巴巴集团控股有限公司 | Method and device of searching based on category |
| CN107993724A (en) * | 2017-11-09 | 2018-05-04 | 易保互联医疗信息科技（北京）有限公司 | A kind of method and device of medicine intelligent answer data processing |
| US20210064821A1 (en) * | 2019-08-27 | 2021-03-04 | Ushur, Inc. | System and method to extract customized information in natural language text |
| CN110941708A (en) * | 2019-11-04 | 2020-03-31 | 智器云南京信息科技有限公司 | Intelligent question and answer library establishing method, intelligent question and answer method and device and computer equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110168535B (en) | Information processing method and terminal, computer storage medium | |
| CN110019149A (en) | A kind of method for building up of service knowledge base, device and equipment | |
| CN111368042A (en) | Intelligent question and answer method and device, computer equipment and computer storage medium | |
| US20160350885A1 (en) | System and methods for generating modularized and taxonomy-based classification of regulatory obligations | |
| CN112598547B (en) | Educational question generation method and device based on automatic production line and electronic equipment | |
| CN116541752B (en) | Metadata management method, device, computer equipment and storage medium | |
| CA3153056A1 (en) | Intelligently questioning and answering method, device, computer, equipment and storage medium | |
| CN117520503A (en) | Financial customer service dialogue generation method, device, equipment and medium based on LLM model | |
| CN111125145A (en) | Automatic system for acquiring database information through natural language | |
| CN114398473A (en) | Enterprise portrait generation method, device, server and storage medium | |
| CN117909466A (en) | Domain question-answering system, construction method, electronic device and storage medium | |
| CN111914066A (en) | Multi-source database global search method and system | |
| CN113297251A (en) | Multi-source data retrieval method, device, equipment and storage medium | |
| CN108829651A (en) | A kind of method, apparatus of document treatment, terminal device and storage medium | |
| CN114253990A (en) | Database query method and device, computer equipment and storage medium | |
| CN116775879A (en) | Fine tuning training method of large language model, contract risk review method and system | |
| CN117592470A (en) | Low-cost gazette data extraction method driven by large language model | |
| CN102902705B (en) | Ambiguity in location data | |
| CN115438142B (en) | Conversational interactive data analysis report system | |
| CN114416957A (en) | Financial management data intelligent question-answering method and system | |
| CN115080603B (en) | Database query language conversion method, device, equipment and storage medium | |
| CN117592450A (en) | Panoramic archive generation method and system based on employee information integration | |
| CN117520533A (en) | Chart generation method | |
| CN116719950A (en) | Intelligent question-answering method and system based on knowledge graph sub-graph retrieval | |
| CN116049376A (en) | Method, device and system for retrieving and replying information and creating knowledge |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |