A method and system for intelligent question answering of financial management data

Abstract

The present invention relates to a method and system for intelligent question and answer of financial management data, including setting a first matching library and a second matching library mapped to the first matching library, and setting an association relationship between a data content library and the second matching library. By pre-setting different matching libraries with greater fuzziness and greater precision respectively, a full understanding of user personalized questions is achieved, and answers that the user may be interested in are output accordingly. Therefore, flexible combination results of multiple different data items can be automatically fed back according to the content of the user's question without pre-setting precise matching keywords, which greatly improves the work efficiency of users in obtaining complex financial management data. The system is particularly suitable for the management and use of complex financial systems such as banks.

Description

Technical Field

[0001] The present invention relates to the field of knowledge graphs and artificial intelligence data processing technology, can be applied to the field of financial management data processing and analysis, and relates to a financial management data intelligent question-answering method and system based on a classification matching method. Background Art

[0002] With the rapid development of financial technology, in order to timely respond to the requirements of bank technology for project management and better play the role of financial technology in enabling; at the same time, in order to effectively solve the high requirements of bank software project management, the large number of projects, the high complexity of project data, and the inability of a single project implementation data to meet the requirements of precise project management. In the existing technology, project management data analysis is mostly reflected in the form of reports and analyzed manually. Therefore, there is an urgent need for a technical solution to solve the data requirements of management positions in bank project management work for the project operation level, such as various project budget data, project scale data, project implementation cycle data, project resource data, etc.

[0003] In view of the different statistical data requirements of different management roles, the most ideal processing method is to provide convenient, efficient and accurate answers in the form of questions and answers. For real-world applications, natural language is the best way for human-computer interaction. The intelligent question-and-answer project operation system can more accurately understand user questions described in natural language, and return concise and accurate matching answers by searching heterogeneous corpora or question-and-answer knowledge bases. Compared with search engines, question-and-answer systems can better understand the true intentions of users' questions and better meet the needs of users for simplified operations and precise knowledge. In interactive question-and-answer, the corresponding context is established through the content of user questions, and the user's intentions are accurately understood and corresponding searches are performed, so as to conveniently obtain the required data content, especially the personalized combination of multiple different data.

[0004] However, the interactive question-and-answer method will inevitably face the practical problem of semantic understanding. The usual practice is to limit the specific content of the user's questions, that is, the user can only choose to ask questions in a limited number of established questions and get the corresponding preset answers. It is impossible to achieve intelligent answer output based on the user's personalized needs, and the actual experience is not good. Summary of the invention

[0005] In order to address the deficiencies of the prior art, the present invention proposes a method and system for intelligent question-answering of financial management data. By pre-setting different matching libraries with greater fuzziness and greater precision respectively, a full understanding of the user's personalized questions can be achieved, and the answers that the user may be interested in can be output accordingly. This enables the flexible combination results of a variety of different data items to be automatically fed back according to the content of the user's question without pre-setting precise matching keywords, greatly improving the work efficiency of users in obtaining complex financial management data, and is particularly suitable for the management and use of complex financial systems such as banks.

[0006] To achieve the above objectives, the technical solutions adopted by the present invention include:

[0007] A method for intelligent question answering of financial management data, characterized by comprising:

[0008] S1. Setting a first matching library and a second matching library mapped to the first matching library, wherein the first matching library stores a plurality of first-class matching words, and the second matching library stores a plurality of second-class matching words, wherein the first-class matching words correspond to one or more second-class matching words, and the second-class matching words belong to only one first-class matching word;

[0009] S2, setting an association relationship between a data content library and a second matching library, wherein the data content library stores a plurality of data content tables, the second-category matching words correspond to one or more data content tables, and the data content tables belong to at least one second-category matching word;

[0010] S3, obtaining user questions, and using semantic recognition to extract the question keywords contained in the user questions;

[0011] S4, using the first matching library to verify all the question keywords and obtain a category of keywords;

[0012] S5, using the second matching library to verify all the question keywords and obtain the second category of keywords;

[0013] S6, determining the correspondence between the first-category keywords and the second-category keywords, and combining all the second-category keywords corresponding to the same first-category keyword into a query phrase;

[0014] S7, using the query phrase to match the data content library to obtain a number of corresponding data content tables;

[0015] S8, merging the obtained data content tables to form a number of feedback results corresponding to each category of keywords;

[0016] S9. Feedback several feedback results to users respectively.

[0017] Furthermore, the step S5 further includes:

[0018] The question keywords that do not belong to the first or second category keywords are classified into the third category keywords.

[0019] Furthermore, the step S8 further includes:

[0020] Use three types of keywords to match the feedback results, and sort the feedback results from most to least according to the number of matched three types of keywords.

[0021] Furthermore, the step S4 further includes:

[0022] When the question keyword cannot verify that the first matching library obtains a type of keyword, all the type of matching words are fed back as the type of keyword.

[0023] Furthermore, the step S6 further includes:

[0024] When a first-category keyword has no corresponding second-category keyword, all second-category matching words belonging to the first-category keyword are fed back and combined into a query phrase corresponding to the first-category keyword.

[0025] Furthermore, the step S6 further includes:

[0026] When a second-category keyword has no corresponding first-category keyword, all second-category keywords without corresponding first-category keywords are combined into a subordinated query phrase.

[0027] The present invention also relates to an intelligent question-answering system for financial management data, which is characterized by comprising:

[0028] A first matching library is used to store a type of matching words;

[0029] The second matching library is used to store the second type of matching words;

[0030] A data content library, used to store data content tables;

[0031] Semantic recognition module, used to extract the key words contained in the user's question;

[0032] A keyword matching module, used to verify all question keywords using the first matching library and the second matching library to obtain first-category keywords and second-category keywords;

[0033] A query matching module, used to determine the correspondence between the first category keywords and the second category keywords and establish a query phrase;

[0034] The query feedback module is used to use the query phrase matching to obtain the corresponding data content table and form a feedback result.

[0035] The present invention also relates to a computer-readable storage medium, characterized in that a computer program is stored on the storage medium, and the computer program implements the above method when executed by a processor.

[0036] The present invention also relates to an electronic device, characterized in that it comprises a processor and a memory;

[0037] The memory is used to store the first matching library, the second matching library and the data content library;

[0038] The processor is used to execute the above method by calling the first matching library, the second matching library and the data content library.

[0039] The present invention also relates to a computer program product, comprising a computer program and / or instructions, characterized in that the computer program and / or instructions implement the steps of the above method when executed by a processor.

[0040] The beneficial effects of the present invention are:

[0041] By adopting the intelligent question-answering method and system for financial management data described in the present invention, by pre-setting different matching libraries with greater fuzziness and greater precision, a full understanding of the user's personalized questions can be achieved, and answers that the user may be interested in can be output accordingly. This makes it possible to automatically feedback flexible combination results of multiple different data items based on the content of the user's question without pre-setting precise matching keywords, greatly improving the user's work efficiency in obtaining complex financial management data, and is particularly suitable for the management of complex financial systems such as banks. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 It is a flow chart of the intelligent question-answering method for financial management data of the present invention.

[0043] Figure 2 It is a schematic diagram of the structure of the intelligent question-answering system for financial management data of the present invention. DETAILED DESCRIPTION

[0044] In order to more clearly understand the content of the present invention, it will be described in detail with reference to the drawings and embodiments.

[0045] The first aspect of the present invention relates to a process of steps as follows Figure 1 The intelligent question-answering method for financial management data shown includes:

[0046] S1. Set a first matching library and a second matching library mapped to the first matching library, wherein the first matching library stores a plurality of first-class matching words, and the second matching library stores a plurality of second-class matching words, wherein the first-class matching words correspond to one or more second-class matching words, and the second-class matching words belong to only one first-class matching word.

[0047] Among them, one type of matching words is preset major category matching words, which can be specifically defined as needed, such as setting different business fields or operating departments as major category matching words, so that the major categories involved in the problem can be quickly identified.

[0048] The second-category matching words correspond to specific question content classifications. Unlike the first-category matching words, the second-category matching words are used to understand the specific types of data content involved in the user's questions, such as a specific data report or a certain type of data in a specific year.

[0049] For example, the user question is "2021 marketing department year-end performance report", in which "marketing department" is matched as a first-category keyword, and "2021" and "year-end performance report" are matched as second-category keywords.

[0050] S2. Setting an association relationship between a data content library and a second matching library, wherein the data content library stores a plurality of data content tables, the second-category matching words correspond to one or more data content tables, and the data content table belongs to at least one second-category matching word.

[0051] The correspondence between the second-class matching words and the data content table can be fixed based on experience, or can be obtained based on the statistical indicators of the correlation coefficient matrix reflecting the closeness of the correlation between attributes (such as project budget, historical evaluation project workload and project requirements, etc.). Therefore, there is no data content table without subordinates, and there is no second-class matching word without corresponding relationship, but at the same time, this correspondence and subordinate relationship is not absolutely unique.

[0052] S3. Obtain user questions and use semantic recognition to extract the question keywords contained in the user questions.

[0053] Preferably, the question keywords are obtained by performing NLP techniques such as word segmentation and stop word removal on the input natural language question.

[0054] The user's questions can be input in text or converted into text through voice input. There are also preset guidance options to help the user ask corresponding questions.

[0055] S4. Use the first matching library to verify all question keywords and obtain a category of keywords.

[0056] Since the first-category keywords are pre-set major categories of keywords, there is a certain possibility that the user did not specifically emphasize the major category to which the question belongs when asking the question, or the user believes that the question is general and has no suitable major category classification. When the question keyword cannot verify that the first matching library obtains the first-category keywords, all the first-category matching words are fed back as the first-category keywords. Through this setting method, it can be ensured that the final results have good comprehensiveness, while not affecting the limiting effect of the second-category keywords on the search results.

[0057] S5. Use the second matching library to verify all the question keywords and obtain the second category of keywords.

[0058] After determining and obtaining the first and second category keywords, there are usually remaining unclassified question keywords. The question keywords that do not belong to the first or second category keywords can be preferably classified into the third category keywords. The third category keywords do not need to be specifically involved in the query and retrieval of the data table content, but the third category keywords can be used to reasonably sort the final search results, so that the feedback results are closer to the content required by the user.

[0059] S6. Determine the correspondence between the first-category keywords and the second-category keywords, and combine all the second-category keywords that correspond to the same first-category keyword into a query phrase.

[0060] At the same time, for special situations that may arise, targeted settings are still made from the perspective of comprehensiveness and completeness of the results. When a first-category keyword does not have a corresponding second-category keyword, all second-category matching words belonging to the first-category keyword are fed back and combined into a query phrase corresponding to the first-category keyword; when a second-category keyword does not have a corresponding first-category keyword, all second-category keywords without corresponding first-category keywords are combined into a subordinated query phrase.

[0061] For subordinated query phrases, their feedback priority is not limited to being completely subordinated, and the feedback results can still be sorted in a targeted manner according to the sorting means involved in the method. However, when operating the corresponding matching data content library, the matching operation sequence of subordinated query phrases can be reasonably placed at the end. This is because subordinated query phrases do not have a specific corresponding first-class keyword, and the span between their second-class keywords may be very large, and there may be duplications with other prior query phrases. Therefore, matching subordinated query phrases later can achieve a more reasonable matching workload.

[0062] S7. Use the query phrase to match the data content library to obtain a number of corresponding data content tables.

[0063] S8. The obtained data content table is merged to form a plurality of feedback results corresponding to each type of keyword. In particular, preferably, the feedback results are matched using three types of keywords, and the feedback results are sorted from most to least according to the number of matched three types of keywords. That is, the adaptability between the feedback results and the user's questions is fuzzily judged by matching the number of occurrences of the three types of keywords in the feedback results.

[0064] The number of matched three-category keywords may include two dimensions: one is the number of different three-category keywords that can be matched in the feedback results, and the other is the total number of matches corresponding to a certain three-category keyword. In use, the basis for judgment can be arbitrarily selected according to actual needs, for example, by setting different weights to adjust the role of the two dimensions in the sorting.

[0065] S9. Feedback the multiple feedback results to the user respectively, and in particular, feed back the feedback results to the user in sequence according to the mutual order of judgment and identification.

[0066] The feedback can be in the form of pre-stored formats such as text and reports, or in the form of visual presentation of processed raw data, such as bar charts, line graphs and tables, making the results more readable.

[0067] The following is a further explanation of the implementation of the method of the present invention through specific examples.

[0068] Taking the data acquisition in the summary process of a financial project as an example, using existing technology to retrieve relevant data requires manual selection of necessary data items for different statistical and summary needs. This not only consumes a lot of time and energy, but also the obtained data statistics are difficult to ensure completeness and accuracy. The relationship between different data statistics is completely vague and untraceable, and it is basically impossible to achieve linkage and collaborative analysis between different data.

[0069] When the method of the present invention is used to obtain relevant data, it can support obtaining the required data in a "question-and-answer" manner similar to natural language.

[0070] For example, the user can directly enter the question "Comparison of the key customer and field sales performance of the first and third sales departments in the second and third quarters, especially the performance of Company A". First, the corresponding question keywords need to be extracted from the question, including: first sales department, second sales department, second quarter, third quarter, key customer, field sales, performance, Company A. At this time, these question keywords belong to the same level and are completely independent of each other, and there is no need to establish any definite connection.

[0071] In the second step, the extracted question keywords are verified using the first matching library and the second matching library respectively, so as to obtain the first category keywords and the second category keywords. For example, the first category keywords include the first sales department and the second sales department; the second category keywords include the second quarter, the third quarter, major customers, and ground promotion. The first matching library is a predefined large category matching library, and the specific content can be set according to actual work experience. The first matching library (first category keywords) can be used to quickly and accurately locate the approximate classification of the question content. This classification can be a class divided according to the business execution department, or a class divided according to the time limit (for example, keywords similar to the second quarter and the third quarter can also be set as a class according to needs), or other suitable classification keywords. On the other hand, the first category of matching words in the first matching library can actually preferably correspond to the classification method of the data storage library, so that data retrieval can support initial positioning with a class of keywords and then accurate retrieval, thereby improving the overall performance of data query.

[0072] The second matching library is a library that matches specific data content (question content) under the first matching library, that is, it corresponds to the specific content that the user wants to know under a large category (a type of keyword).

[0073] In particular, although the second matching library is set to be subordinate to the first matching library, in fact, there is not necessarily a necessary subordinate relationship between the first-category matching words and the second-category matching words. For example, there is no natural subordination between "the first sales department" and "the second quarter", that is, the subordinate relationship between the first matching library and the second matching library is a completely intentionally set logical relationship. The first-category matching words and the second-category matching words can be set arbitrarily as needed. The expected effect of this setting is to reasonably decompose user problems, so that complex user problems can be guided to the preset classification logical relationship in order to obtain more targeted answers.

[0074] Other question keywords that are not matched as first-category keywords and second-category keywords, such as "performance, Company A", can be classified as third-category keywords for post-processing of retrieved data, such as sorting.

[0075] The third step is to determine the correspondence between the first category keywords and the second category keywords, that is, to group the second category keywords under the first category keywords according to the pre-set logical subordinate relationship between the first category matching words and the second category matching words, to form one or more query phrases. For example, the query phrases "the first sales department and the second quarter, the third quarter, major customers, and local promotion" and "the second sales department and the second quarter, the third quarter, major customers, and local promotion". Through this step, the original user question has been effectively decomposed, and this decomposition is fully based on the pre-set subordinate logical relationship, so that the decomposed query phrases can be conveniently used for data query.

[0076] The fourth step is to use the query phrase to match the data content library. For example, through the above two query phrases, the second quarter key customer report of the first sales department, the third quarter key customer report of the first sales department, the second quarter ground promotion report of the first sales department, the third quarter ground promotion report of the first sales department, the second quarter key customer report of the second sales department, the third quarter key customer report of the second sales department, the second quarter ground promotion report of the second sales department, and the third quarter ground promotion report of the second sales department can be obtained respectively. At this time, the various data obtained have a high probability of covering the various analysis data required for the original user's question. Users can save a lot of time and energy compared with the existing technology by further screening and analyzing these data. At the same time, since the data is retrieved based on the preset classification method (first-class matching words and second-class matching words), it is convenient to preset suitable feedback presentation forms for the relevant data, such as various visual presentation forms such as graphs and tables, which is convenient for users to intuitively analyze.

[0077] Usually, a certain number of three types of keywords are included in user questions. These three types of keywords can be used to match the feedback results obtained from the search, so as to give a ranking of the feedback results based on the relevance of the original user question. For example, the three types of keywords "performance, company A" are used to match the above data tables, and the most relevant ones to company A are the third quarter key customer report of the first sales department and the third quarter key customer report of the second sales department. Therefore, these two items can be ranked as the preferred results and fed back in a higher position.

[0078] Since the three types of keywords are not used as preset keywords for search classification in the early configuration stage, it is preferred not to use the three types of keywords as the basis for screening and excluding feedback results to ensure that the feedback results can maintain a certain degree of integrity and avoid data omissions.

[0079] Another aspect of the present invention also relates to a financial management data intelligent question-answering system, the structure of which is as follows: Figure 2 As shown, including:

[0080] A first matching library is used to store a type of matching words;

[0081] The second matching library is used to store the second type of matching words;

[0082] A data content library, used to store data content tables;

[0083] Semantic recognition module, used to extract the key words contained in the user's question;

[0084] A keyword matching module, used to verify all question keywords using the first matching library and the second matching library to obtain first-category keywords and second-category keywords;

[0085] A query matching module, used to determine the correspondence between the first category keywords and the second category keywords and establish a query phrase;

[0086] The query feedback module is used to use the query phrase matching to obtain the corresponding data content table and form a feedback result.

[0087] By using this system, the above-mentioned operation processing method can be executed and the corresponding technical effects can be achieved.

[0088] An embodiment of the present invention also provides a computer-readable storage medium capable of implementing all the steps in the method in the above embodiment, wherein a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, all the steps in the method in the above embodiment are implemented.

[0089] An embodiment of the present invention also provides an electronic device for executing the above method. As an implementation device of the method, the electronic device has at least a processor and a memory, and in particular, the memory stores data and related computer programs required for executing the method, such as a first matching library, a second matching library, and a data content library, etc., and the processor calls the data and programs in the memory to execute all steps of the implementation method and obtains the corresponding technical effect.

[0090] Preferably, the electronic device may include a bus architecture, the bus may include any number of interconnected buses and bridges, and the bus will include various circuits linked together by one or more processors and memories. The bus may also link together various other circuits such as peripherals, voltage regulators, and power management circuits, which are all well known in the art and are therefore not further described herein. The bus interface provides an interface between the bus and the receiver and transmitter. The receiver and transmitter may be the same component, i.e., a transceiver, providing a unit 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 to store data used by the processor when performing operations.

[0091] In addition, the electronic device may further include components such as a communication module, an input unit, an audio processor, a display, and a power supply. The processor (or controller, operation control) used may include a microprocessor or other processor device and / or a logic device, which receives input and controls the operation of various components of the electronic device; the memory may be one or more of a cache, a flash memory, a hard drive, a removable medium, a volatile memory, a non-volatile memory, or other suitable devices, which may store the above-mentioned related data information, and may also store a program for executing 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 to provide input to the processor, for example, it may be a key or a touch input device; the power supply is used to provide power to the electronic device; the display is used to display display objects such as images and text, for example, it may be an LCD display. The communication module is a transmitter / receiver that sends and receives signals via an antenna. The communication module (transmitter / receiver) is coupled to the processor to provide input signals and receive output signals, which may be the same as the case of a conventional mobile communication terminal. Based on different communication technologies, multiple communication modules may be provided in the same electronic device, such as a cellular network module, a Bluetooth module and / or a wireless local area network module, etc. The communication module (transmitter / receiver) is also coupled to a speaker and a microphone via an audio processor to provide an audio output via the speaker and receive an audio input from the microphone, thereby realizing a common telecommunication function. The audio processor may include any suitable buffer, decoder, amplifier, etc. In addition, the audio processor is also coupled to a central processor, so that recording can be performed on the machine through the microphone, and the sound stored on the machine can be played through the speaker.

[0092] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0093] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A system that specifies the functions of a box or multiple boxes.

[0094] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a product including an instruction system, which is implemented in the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0095] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps of the functions specified in a box or multiple boxes. Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they know the basic creative concept. Therefore, the attached claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0096] The above is only a preferred specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for intelligent question answering of financial management data, characterized in that: include: S1. Setting a first matching library and a second matching library mapped to the first matching library, wherein the first matching library stores a plurality of first-class matching words, and the second matching library stores a plurality of second-class matching words, wherein the first-class matching words correspond to one or more second-class matching words, and the second-class matching words belong to only one first-class matching word; S2, setting an association relationship between a data content library and a second matching library, wherein the data content library stores a plurality of data content tables, the second-category matching words correspond to one or more data content tables, and the data content tables belong to at least one second-category matching word; S3, obtaining user questions, and using semantic recognition to extract the question keywords contained in the user questions; S4, using the first matching library to verify all the question keywords and obtain a category of keywords; S5, using the second matching library to verify all the question keywords and obtain the second category of keywords; S6, determining the correspondence between the first-category keywords and the second-category keywords, and combining all the second-category keywords corresponding to the same first-category keyword into a query phrase; S7, using the query phrase to match the data content library to obtain a number of corresponding data content tables; S8, merging the obtained data content tables to form a number of feedback results corresponding to each category of keywords; S9. Feedback several feedback results to users respectively.

2. The method according to claim 1, characterized in that The step S5 further comprises: The question keywords that do not belong to the first or second category keywords are classified into the third category keywords.

3. The method according to claim 2, characterized in that The step S8 further comprises: Use three types of keywords to match the feedback results, and sort the feedback results from most to least according to the number of matched three types of keywords.

4. The method according to claim 1, characterized in that The step S4 further comprises: When the question keyword cannot verify that the first matching library obtains a type of keyword, all the type of matching words are fed back as the type of keyword.

5. The method according to claim 1, characterized in that The step S6 further comprises: When a first-category keyword has no corresponding second-category keyword, all second-category matching words belonging to the first-category keyword are fed back and combined into a query phrase corresponding to the first-category keyword.

6. The method according to claim 1, characterized in that The step S6 further comprises: When a second-category keyword has no corresponding first-category keyword, all second-category keywords without corresponding first-category keywords are combined into a subordinated query phrase.

7. A financial management data intelligent question-answering system, characterized in that: include: A first matching library is used to store a type of matching words; The second matching library is used to store the second type of matching words; A data content library, used to store data content tables; Semantic recognition module, used to extract the key words contained in the user's question; A keyword matching module, used to verify all question keywords using the first matching library and the second matching library to obtain first-category keywords and second-category keywords, wherein the first-category matching words correspond to one or more second-category matching words, and the second-category matching words are only subordinate to one first-category matching word; A query matching module, used to determine the correspondence between the first-category keywords and the second-category keywords and establish a query phrase, wherein the second-category matching words correspond to one or more data content tables, and the data content table belongs to at least one second-category matching word; The query feedback module is used to use the query phrase matching to obtain the corresponding data content table and form a feedback result.

8. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

9. An electronic device, characterized in that: including a processor and a memory; The memory is used to store the first matching library, the second matching library and the data content library; The processor is used to execute the method according to 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: When the computer program and / or the instructions are executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images