CN116050426A - Method, system, equipment and storage medium for quickly inquiring menu - Google Patents

Method, system, equipment and storage medium for quickly inquiring menu Download PDF

Info

Publication number
CN116050426A
CN116050426A CN202211726017.6A CN202211726017A CN116050426A CN 116050426 A CN116050426 A CN 116050426A CN 202211726017 A CN202211726017 A CN 202211726017A CN 116050426 A CN116050426 A CN 116050426A
Authority
CN
China
Prior art keywords
text
menu
user
query
confidence coefficient
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
Application number
CN202211726017.6A
Other languages
Chinese (zh)
Inventor
李纪波
周祥国
苟素洁
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Inspur General Software Co Ltd
Original Assignee
Inspur General Software Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Inspur General Software Co Ltd filed Critical Inspur General Software Co Ltd
Priority to CN202211726017.6A priority Critical patent/CN116050426A/en
Publication of CN116050426A publication Critical patent/CN116050426A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/30—Semantic analysis
    • 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
    • G06F16/3331—Query processing
    • G06F16/334—Query execution
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/20—Natural language analysis
    • G06F40/205—Parsing
    • G06F40/211—Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/20—Natural language analysis
    • G06F40/253—Grammatical analysis; Style critique
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/20—Natural language analysis
    • G06F40/279—Recognition of textual entities
    • G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Mathematical Physics (AREA)
  • Human Computer Interaction (AREA)
  • Machine Translation (AREA)

Abstract

The invention provides a method, a system, equipment and a storage medium for quickly inquiring a menu, wherein the method comprises the following steps: processing text input by a user in response to receiving the text; carrying out similar problem reasoning through a dictionary according to the processed text to obtain the confidence coefficient of each similar problem, and sequencing according to the confidence coefficient; judging whether a similar problem with the confidence coefficient higher than a threshold exists or not; and responsive to the presence of a similar question with a confidence level above a threshold, presenting the similar question to a user in sequence. The invention carries out lexical analysis, syntactic analysis and semantic analysis on the input text, can provide more accurate query service for users, automatically extracts the names of the newly generated menus when the new menus are generated, synchronously updates the dictionary in the lexical analysis, and greatly enhances the usability of software.

Description

Method, system, equipment and storage medium for quickly inquiring menu
Technical Field
The invention relates to the field of intelligent interaction, in particular to a method, a system, equipment and a storage medium for quickly inquiring a menu.
Background
In the iGIX low-code development platform, after application development is completed, a generated menu is issued so that a user can quickly position specific application through the menu to use software functions, but hundreds of basic functions are built in the iGIX low-code development platform, the form of the menu is used as an entrance, and in addition, the application menu developed based on the platform can lead to certain complexity of menu inquiry.
The menu searching in the low-code development platform is mostly based on a fuzzy matching algorithm, the keyword of the content to be searched is input in a common search box for searching, automatic jump cannot be realized, the menu is required to be clicked manually for jumping, and a developer based on the iGIX is required to continuously search the menu to test functions when developing specific application, so that a lot of unnecessary operations are brought, and the development efficiency is reduced.
In addition, the data required for training the natural language model are static, but a large number of non-login words appear along with the increase of the number of menus, the words are related to business, and the words may not be contained in a general word segmentation dictionary, so that the words are wrong, and thus, the words are abnormal in grammar and semantic analysis stages, and finally, prediction deviation occurs.
Disclosure of Invention
In view of this, an object of the embodiments of the present invention is to provide a method, a system, a computer device and a computer readable storage medium for quickly querying a menu, in which a natural language processing technology and a matching tool are introduced into an iGIX low-code development platform, so that lexical analysis, syntax analysis and semantic analysis can be performed on an input text, more accurate query services can be provided for a user, and meanwhile, for a menu presentation principle in the platform, dynamic change conditions of the menu are automatically monitored, when a new menu is generated, a newly generated menu name is automatically extracted, and a dictionary in lexical analysis is synchronously updated, so that development efficiency of developers can be further improved, a software development period is shortened, and for a final software user, usability of software is greatly enhanced.
Based on the above objects, an aspect of the embodiments of the present invention provides a method for quickly querying a menu, including the following steps: processing text input by a user in response to receiving the text; carrying out similar problem reasoning through a dictionary according to the processed text to obtain the confidence coefficient of each similar problem, and sequencing according to the confidence coefficient; judging whether a similar problem with the confidence coefficient higher than a threshold exists or not; and responsive to the presence of a similar question with a confidence level above a threshold, presenting the similar question to a user in sequence.
In some embodiments, the processing the text includes: and segmenting the text to obtain a first result, and detecting the stop word or the nonsensical word in the first result to delete the stop word or the nonsensical word in the first result.
In some embodiments, the processing the text includes: and comparing the text with preset contents to filter illegal parts in the text.
In some embodiments, the method further comprises: and responding to successful matching of the text and the preset keywords, and directly returning the reply content corresponding to the preset keywords.
In some embodiments, the method further comprises: and in response to each completion of the query, adding one to the score of the corresponding query topic according to the current query result, and sorting the query topics according to the score so as to form the recommendation result of the user next time.
In some embodiments, the method further comprises: setting an expiration time, and subtracting one from the score of the query result corresponding to the query topic in response to the duration of each query result exceeding the expiration time.
In some embodiments, the method further comprises: in response to detecting the incremental change in the menu data, pushing data of the menu name to the natural language processing server to update the dictionary data.
In another aspect of the embodiment of the present invention, a system for quickly querying a menu is provided, including: the processing module is configured to respond to receiving text input by a user and process the text; the reasoning module is configured to conduct similar problem reasoning through a dictionary according to the processed text, obtain the confidence coefficient of each similar problem, and sort according to the confidence coefficient; the judging module is configured to judge whether a similar problem with the confidence coefficient higher than a threshold exists or not; and a presentation module configured to present similar questions to a user in order in response to there being similar questions with a confidence level above a threshold.
In yet another aspect of the embodiment of the present invention, there is also provided a computer apparatus, including: at least one processor; and a memory storing computer instructions executable on the processor, which when executed by the processor, perform the steps of the method as above.
In yet another aspect of the embodiments of the present invention, there is also provided a computer-readable storage medium storing a computer program which, when executed by a processor, implements the method steps as described above.
The invention has the following beneficial technical effects: the method has the advantages that a natural language processing technology and a matched tool are introduced into the iGIX low-code development platform, lexical analysis, syntactic analysis and semantic analysis are carried out on an input text, more accurate query service can be provided for a user, meanwhile, aiming at a menu presentation principle in the platform, the dynamic change condition of a menu is automatically monitored, when a new menu is generated, the name of the newly generated menu is automatically extracted, a dictionary in lexical analysis is synchronously updated, the development efficiency of a developer can be further improved for the developer of the platform, the software development period is shortened, and the usability of software is greatly enhanced for a final software user.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are necessary for the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention and that other embodiments may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic diagram of an embodiment of a method for quick querying of menus provided by the present invention;
FIG. 2 is a schematic diagram of an embodiment of a system for quick menu query provided by the present invention;
FIG. 3 is a schematic diagram of a hardware architecture of an embodiment of a computer device for quick menu query according to the present invention;
FIG. 4 is a schematic diagram of an embodiment of a computer storage medium for quick menu query according to the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the following embodiments of the present invention will be described in further detail with reference to the accompanying drawings.
It should be noted that, in the embodiments of the present invention, all the expressions "first" and "second" are used to distinguish two entities with the same name but different entities or different parameters, and it is noted that the "first" and "second" are only used for convenience of expression, and should not be construed as limiting the embodiments of the present invention, and the following embodiments are not described one by one.
In a first aspect of the embodiment of the present invention, an embodiment of a method for quickly querying a menu is provided. Fig. 1 is a schematic diagram of an embodiment of a method for quickly querying a menu provided by the present invention.
As shown in fig. 1, the embodiment of the present invention includes the following steps:
s1, responding to a received text input by a user, and processing the text;
s2, carrying out similar problem reasoning through a dictionary according to the processed text to obtain the confidence coefficient of each similar problem, and sequencing according to the confidence coefficient;
s3, judging whether a similar problem that the confidence coefficient is higher than a threshold exists or not; and
and S4, responding to the similar problems with the confidence coefficient higher than the threshold value, and displaying the similar problems to the user in sequence.
According to the embodiment of the invention, the natural language processing technology is introduced into the iGIX low-code development platform and is fused with the functions related to the application menu inquiry thereof, so that the development efficiency and the software usability are improved.
The embodiment of the invention provides a conversational UI (User Interface), which is an entrance of man-machine interaction, and can enter a conversational UI window for the first time to generate a recommended content list, wherein the recommended content list can be set, and the system can automatically learn the preference of a User and automatically update the recommended list along with the increase of application times. The front-end interactive interface of the embodiment of the invention is developed based on front-end technologies such as Farris UI, HTML, CSS, jQuery and the like which are self-developed by wave tide. The dialog UI integrates a number of functions including user instruction input, dialog control center return results presentation, and automatic jumping of pages.
The user inputs text through the interactive UI interface, transmits the text to the rear end for semantic analysis, and returns the final query result to the user through the dialogue UI, wherein the content is a menu name list or a question-answer content, and the user can directly click the list content or can automatically jump by inputting a serial number before the list.
In some embodiments, the processing the text includes: and comparing the text with preset contents to filter illegal parts in the text. In the iGIX low-code development platform homepage, there is a robot icon that supports drag up and down, clicking on the robot icon pops up a dialog (conversational UI). After the user inputs text content, the front end filters illegal parts in the input content through the content set in advance, and mainly detects whether the text contains executable Script language or not so as to prevent malicious codes from being injected. The front end transmits the input text content to the dialogue control module of the back end through the request API interface.
In some embodiments, the processing the text includes: and segmenting the text to obtain a first result, and detecting the stop word or the nonsensical word in the first result to delete the stop word or the nonsensical word in the first result.
The first step after the text enters the dialogue control module is to call the natural language processing module to segment the input text content, and for the text segmentation, the embodiment of the invention adopts a jieba (junction) segmentation frame, and because the menu names formed by application in an iGIX development frame are related to business strongly, the universal segmentation frame cannot be segmented very accurately, the embodiment of the invention expands the dictionary custom function provided by the jieba segmentation frame, further improves the segmentation precision, and a developer automatically saves the names of the menus and specific application paths and other key information into corresponding database tables based on the process that the development of the iGIX development frame is completed and finally releases the application into the menus. The word segmentation service returns all words in a list form, then the system detects stop words or nonsensical words of the segmented words, and similar problem reasoning is carried out after the words are washed.
The similar question inference returns an approximate question list, wherein the approximate question list comprises links and confidence degrees of positions of specific questions and answers, the system defaults to return 10 pieces of data, and if the confidence degrees are larger than a set threshold value in the returned data, the similar questions can be directly returned, and the judgment of other natural language processing tasks is not performed any more and the similar questions are directly returned to the front end.
The judging sequence is needed to be set, a configuration interface provided by the system is provided with an independent part, the system firstly acquires the configured data when performing natural language processing, then judges according to the configured priority, the priority is shown in numbers, namely 1, 2 and 3, if the sequence is not set by a user, the system defaults to perform priority processing judgment on the inquiry of the menu, then the system is similar to the inquiry, and finally the user-defined content is searched. The user can set question and answer content through a front-end interface provided by the system, the user-defined editing of questions and content is supported, the format of the content comprises texts and images, the texts and images are finally stored in database tables, the database tables and the iGIX are stored in the same database, meanwhile, the user-defined questions are subjected to text similarity calculation based on a TF-IDF method, a document library is synchronously updated, and the similar question system can be automatically synchronously updated with the adopted questions in the iGIX community and update the text similarity calculation document library. The matching of menu names is that the similarity of words is calculated based on a CBOW algorithm in a Word2Vec model, and the words are sorted based on the confidence level of the similarity problem, if the confidence level is larger than a threshold value, the words are returned to the front end, the query method is that users need to be screened, and finally, the system returns a plurality of menus with similar semantics.
In some embodiments, the method further comprises: and responding to successful matching of the text and the preset keywords, and directly returning the reply content corresponding to the preset keywords. If the user explicitly knows the menu to be queried, an 'open' can be added before the input menu, the system firstly detects whether the tail of the text contains corresponding keywords aiming at the input text, if so, the system returns an automatically developed mark, writes the keywords 'autopen' in the returned content, then performs word segmentation on the text content except the 'open', then returns a result, firstly matches with the stored content of a frequently used menu library if a plurality of different menus exist, returns frequently accessed words if the frequently accessed words are frequently accessed, and if the frequencies of the plurality of words are the same, the system defaults to order according to the sequence of the words in the input text, the former words are preferentially returned, and only one menu name is returned. For common greetings, such as hello, what function you have, etc., the front-end system module filters, the text-to-speech system is already built in, the front-end has a text matching function, after matching a preset keyword, the front-end part directly returns the reply content, and the content is not transmitted to the server for processing.
For the returned content, the front end supports multiple modes of display, mainly comprising function menu names, iGIX question and answer community similar question recommendation and user-defined question and answer content, after the front end senses the back end returned content, the front end carries out differentiated display according to a front-back setting rule, the dialogue control server returns data in a JSON format, an action field is added in the returned content, the value of the field mainly comprises clickOpenMenu (the returned content needs mouse click to realize application skip), autopopenMenu (semantic analysis is accurate to realize automatic skip of menus), qA (question set adopted in the iGIX question and answer community) and answer (user-defined question and answer type), through the set keywords, the UI interface can display different modes of content, such as answer sentences can be directly displayed for the user-defined question and answer content, and similar questions need to provide a skip function to skip to the iX question and answer community to check more accurate answers.
In some embodiments, the method further comprises: and in response to each completion of the query, adding one to the score of the corresponding query topic according to the current query result, and sorting the query topics according to the score so as to form the recommendation result of the user next time. When a user reenters the dialogue UI, the system can automatically recommend the functions commonly used by the user, recommended contents default to menu names and specific problems, and only the content frequently searched before the user is frequently displayed each time, the user can set the recommended contents through an interface provided by the system, the recommended contents default to the need of user click jump, the user-defined question-answer pair is supported to be set, if the user does not set, the system can randomly push 6 pieces of information, the user can close the problem recommendation function in a configuration page, and after page refreshing, the recommended contents are not displayed in the interface in the dialogue UI. For the recommendation function built in the system, the system adopts scoring, and 1 is added to the corresponding score every time the same content is detected.
In some embodiments, the method further comprises: setting an expiration time, and subtracting one from the score of the query result corresponding to the query topic in response to the duration of each query result exceeding the expiration time. Setting an expiration time, generally a week, setting a storage structure as a queue, detecting the head and tail words after receiving the content of the front-end request, then completely matching with the data in the queue, adding 1 after the expiration time, and automatically deleting the system from the queue after detecting the problem of the expiration time.
In some embodiments, the method further comprises: in response to detecting the incremental change in the menu data, pushing data of the menu name to the natural language processing server to update the dictionary data. The dialogue control system and the NLP service are provided with a data processing service interface, when the data menu data are updated, the system detects the increment change and automatically pushes the menu name data to the NLP service end, the NLP service end automatically updates the dictionary data, after the user uploads the user-defined type question-answer data, model training is carried out through a configuration interface provided by the system, the system can regularly crawl the data to update the document set, and the system is used for providing the user-defined type question-answer data.
The natural language processing module and the dialogue control center are loosely coupled, and are two different service units, the dialogue control system needs to call the natural language processing service end in the form of an API interface, then the returned results are combined and processed to return to the front-end interface, the operation includes function ID encapsulation corresponding to a specific menu, because the opening of the menu is identified and positioned according to the function ID in the iGIX development framework, and other question-answering functions also need to be developed in a customized mode, and the natural language processing module is unchanged.
The natural language processing module is deployed in the form of micro service, the dialogue control center is business related and belongs to an intelligent capability consumption layer, the dialogue control center is developed based on JAVA language, the natural language processing service center is developed based on Python, a configuration interface provided by a system can be used for setting whether Natural Language Processing (NLP) service is started or not by a user, and if the service is not adopted, the system defaults to provide a rule matching method to perform approximate calculation of similar problems.
The system uses the natural language processing framework Gensim for text processing. The natural language processing module provides a training function, automatically pushes a piece of data to a training end after the system detects the increment in the problem, and automatically updates an embedded word list of the text in the TF-IDF after the NLP training module detects the pushed data. For similarity prediction of menus, the embodiment of the invention carries out customized training of Word vectors based on a CBOW algorithm in a Word2Vec Word embedding model, integrates a plurality of vocabularies in the iGIX low-code development field into training corpus, and includes function application names required by ERP systems in different vertical fields when text data are collected in the early stage, so that the prediction precision of similarity is greatly improved. Meanwhile, the system provides a control interface for natural language processing, a vocabulary is customized in a data processing part and then trained together with a data set built in the system, the whole training process is carried out at the cloud end, a user can set training parameters such as count (data of each time of word reading) and epoch (frequency of training) in a configuration interface, a size system of a word vector is subjected to default processing to be 100 dimensions, after the data is processed, the cloud end system is automatically trained after a training button is clicked, and after the training is completed, an NLP processing system is automatically deployed and brought on line.
It should be noted that, in the embodiments of the method for quick querying of a menu, the steps may be intersected, replaced, added and deleted, so that the method for quick querying of a menu by using these reasonable permutation and combination changes should also belong to the protection scope of the present invention, and should not limit the protection scope of the present invention to the embodiments.
Based on the above object, in a second aspect of the embodiments of the present invention, a system for quickly querying a menu is provided. As shown in fig. 2, the system 200 includes the following modules: the processing module is configured to respond to receiving text input by a user and process the text; the reasoning module is configured to conduct similar problem reasoning through a dictionary according to the processed text, obtain the confidence coefficient of each similar problem, and sort according to the confidence coefficient; the judging module is configured to judge whether a similar problem with the confidence coefficient higher than a threshold exists or not; and a presentation module configured to present similar questions to a user in order in response to there being similar questions with a confidence level above a threshold.
In some embodiments, the processing module is configured to: and segmenting the text to obtain a first result, and detecting the stop word or the nonsensical word in the first result to delete the stop word or the nonsensical word in the first result.
In some embodiments, the processing module is configured to: and comparing the text with preset contents to filter illegal parts in the text.
In some embodiments, the system further comprises a return module configured to: and responding to successful matching of the text and the preset keywords, and directly returning the reply content corresponding to the preset keywords.
In some embodiments, the system further comprises a recommendation module configured to: and in response to each completion of the query, adding one to the score of the corresponding query topic according to the current query result, and sorting the query topics according to the score so as to form the recommendation result of the user next time.
In some embodiments, the system further comprises an expiration module configured to: setting an expiration time, and subtracting one from the score of the query result corresponding to the query topic in response to the duration of each query result exceeding the expiration time.
In some embodiments, the system further comprises an update module configured to: in response to detecting the incremental change in the menu data, pushing data of the menu name to the natural language processing server to update the dictionary data.
In view of the above object, a third aspect of the embodiments of the present invention provides a computer device, including: at least one processor; and a memory storing computer instructions executable on the processor, the instructions being executable by the processor to perform the steps of: s1, responding to a received text input by a user, and processing the text; s2, carrying out similar problem reasoning through a dictionary according to the processed text to obtain the confidence coefficient of each similar problem, and sequencing according to the confidence coefficient; s3, judging whether a similar problem that the confidence coefficient is higher than a threshold exists or not; and S4, responding to the similar problems with the confidence coefficient higher than the threshold value, and displaying the similar problems to the user in sequence.
In some embodiments, the processing the text includes: and segmenting the text to obtain a first result, and detecting the stop word or the nonsensical word in the first result to delete the stop word or the nonsensical word in the first result.
In some embodiments, the processing the text includes: and comparing the text with preset contents to filter illegal parts in the text.
In some embodiments, the steps further comprise: and responding to successful matching of the text and the preset keywords, and directly returning the reply content corresponding to the preset keywords.
In some embodiments, the steps further comprise: and in response to each completion of the query, adding one to the score of the corresponding query topic according to the current query result, and sorting the query topics according to the score so as to form the recommendation result of the user next time.
In some embodiments, the steps further comprise: setting an expiration time, and subtracting one from the score of the query result corresponding to the query topic in response to the duration of each query result exceeding the expiration time.
In some embodiments, the steps further comprise: in response to detecting the incremental change in the menu data, pushing data of the menu name to the natural language processing server to update the dictionary data.
As shown in fig. 3, a hardware structure diagram of an embodiment of the computer device for quick querying of the menu provided by the present invention is shown.
Taking the example of the device shown in fig. 3, a processor 301 and a memory 302 are included in the device.
The processor 301 and the memory 302 may be connected by a bus or otherwise, for example in fig. 3.
The memory 302 is used as a non-volatile computer readable storage medium for storing non-volatile software programs, non-volatile computer executable programs, and modules, such as program instructions/modules corresponding to the method for quick menu query in the embodiments of the present application. The processor 301 executes various functional applications of the server and data processing, i.e., a method of implementing a quick query of a menu, by running nonvolatile software programs, instructions, and modules stored in the memory 302.
Memory 302 may include a storage program area that may store an operating system, at least one application program required for functionality, and a storage data area; the storage data area may store data created according to the use of a method of a quick query of a menu, etc. In addition, memory 302 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid-state storage device. In some embodiments, memory 302 may optionally include memory located remotely from processor 301, which may be connected to the local module via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
Computer instructions 303 corresponding to one or more methods of menu quick query are stored in memory 302 that, when executed by processor 301, perform the methods of menu quick query in any of the method embodiments described above.
Any one embodiment of the computer device executing the method for quickly inquiring the menu can achieve the same or similar effect as any one embodiment of the method corresponding to the embodiment.
The present invention also provides a computer readable storage medium storing a computer program which when executed by a processor performs a method of fast querying a menu.
FIG. 4 is a schematic diagram of an embodiment of the computer storage medium for quick querying of the menu according to the present invention. Taking a computer storage medium as shown in fig. 4 as an example, the computer readable storage medium 401 stores a computer program 402 that when executed by a processor performs the above method.
Finally, it should be noted that, as will be appreciated by those skilled in the art, all or part of the processes in the methods of the embodiments described above may be implemented by a computer program for instructing relevant hardware, and the program for quickly querying the menu may be stored in a computer readable storage medium, where the program when executed may include the processes of the embodiments of the methods described above. The storage medium of the program may be a magnetic disk, an optical disk, a read-only memory (ROM), a random-access memory (RAM), or the like. The computer program embodiments described above may achieve the same or similar effects as any of the method embodiments described above.
The foregoing is an exemplary embodiment of the present disclosure, but it should be noted that various changes and modifications could be made herein without departing from the scope of the disclosure as defined by the appended claims. The functions, steps and/or actions of the method claims in accordance with the disclosed embodiments described herein need not be performed in any particular order. Furthermore, although elements of the disclosed embodiments may be described or claimed in the singular, the plural is contemplated unless limitation to the singular is explicitly stated.
It should be understood that as used herein, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly supports the exception. It should also be understood that "and/or" as used herein is meant to include any and all possible combinations of one or more of the associated listed items.
The foregoing embodiment of the present invention has been disclosed with reference to the number of embodiments for the purpose of description only, and does not represent the advantages or disadvantages of the embodiments.
It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program for instructing relevant hardware, and the program may be stored in a computer readable storage medium, where the storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.
Those of ordinary skill in the art will appreciate that: the above discussion of any embodiment is merely exemplary and is not intended to imply that the scope of the disclosure of embodiments of the invention, including the claims, is limited to such examples; combinations of features of the above embodiments or in different embodiments are also possible within the idea of an embodiment of the invention, and many other variations of the different aspects of the embodiments of the invention as described above exist, which are not provided in detail for the sake of brevity. Therefore, any omission, modification, equivalent replacement, improvement, etc. of the embodiments should be included in the protection scope of the embodiments of the present invention.

Claims (10)

1. A method for quickly inquiring a menu, which is characterized by comprising the following steps:
processing text input by a user in response to receiving the text;
carrying out similar problem reasoning through a dictionary according to the processed text to obtain the confidence coefficient of each similar problem, and sequencing according to the confidence coefficient;
judging whether a similar problem with the confidence coefficient higher than a threshold exists or not; and
in response to there being a similar problem with a confidence level above a threshold, the similar problems are presented to a user in a sequence.
2. The method of claim 1, wherein the processing the text comprises:
and segmenting the text to obtain a first result, and detecting the stop word or the nonsensical word in the first result to delete the stop word or the nonsensical word in the first result.
3. The method of claim 1, wherein the processing the text comprises:
and comparing the text with preset contents to filter illegal parts in the text.
4. The method according to claim 1, wherein the method further comprises:
and responding to successful matching of the text and the preset keywords, and directly returning the reply content corresponding to the preset keywords.
5. The method according to claim 1, wherein the method further comprises:
and in response to each completion of the query, adding one to the score of the corresponding query topic according to the current query result, and sorting the query topics according to the score so as to form the recommendation result of the user next time.
6. The method of claim 5, wherein the method further comprises:
setting an expiration time, and subtracting one from the score of the query result corresponding to the query topic in response to the duration of each query result exceeding the expiration time.
7. The method according to claim 1, wherein the method further comprises:
in response to detecting the incremental change in the menu data, pushing data of the menu name to the natural language processing server to update the dictionary data.
8. A system for quick querying of a menu, comprising:
the processing module is configured to respond to receiving text input by a user and process the text;
the reasoning module is configured to conduct similar problem reasoning through a dictionary according to the processed text, obtain the confidence coefficient of each similar problem, and sort according to the confidence coefficient;
the judging module is configured to judge whether a similar problem with the confidence coefficient higher than a threshold exists or not; and
and the display module is configured to display similar problems with confidence higher than a threshold value to a user in sequence in response to the similar problems.
9. A computer device, comprising:
at least one processor; and
a memory storing computer instructions executable on the processor, which when executed by the processor, perform the steps of the method of any one of claims 1-7.
10. A computer readable storage medium storing a computer program, characterized in that the computer program when executed by a processor implements the steps of the method of any one of claims 1-7.
CN202211726017.6A 2022-12-30 2022-12-30 Method, system, equipment and storage medium for quickly inquiring menu Pending CN116050426A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211726017.6A CN116050426A (en) 2022-12-30 2022-12-30 Method, system, equipment and storage medium for quickly inquiring menu

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211726017.6A CN116050426A (en) 2022-12-30 2022-12-30 Method, system, equipment and storage medium for quickly inquiring menu

Publications (1)

Publication Number Publication Date
CN116050426A true CN116050426A (en) 2023-05-02

Family

ID=86124892

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211726017.6A Pending CN116050426A (en) 2022-12-30 2022-12-30 Method, system, equipment and storage medium for quickly inquiring menu

Country Status (1)

Country Link
CN (1) CN116050426A (en)

Similar Documents

Publication Publication Date Title
CN107832433B (en) Information recommendation method, device, server and storage medium based on conversation interaction
KR102288249B1 (en) Information processing method, terminal, and computer storage medium
CN109284399B (en) Similarity prediction model training method and device and computer readable storage medium
US9524291B2 (en) Visual display of semantic information
KR100650427B1 (en) Integrated development tool for building a natural language understanding application
US20070106497A1 (en) Natural language interface for driving adaptive scenarios
CN110334347A (en) Information processing method, relevant device and storage medium based on natural language recognition
CN115328756A (en) Test case generation method, device and equipment
CN116521841B (en) Method, device, equipment and medium for generating reply information
US20080162528A1 (en) Content Management System and Method
US20220414463A1 (en) Automated troubleshooter
CN116501960B (en) Content retrieval method, device, equipment and medium
CN112100322A (en) API element comparison result automatic generation method based on knowledge graph
CN112507139B (en) Knowledge graph-based question and answer method, system, equipment and storage medium
CN113392195A (en) Public opinion monitoring method and device, electronic equipment and storage medium
CN116974554A (en) Code data processing method, apparatus, computer device and storage medium
CN111062216B (en) Named entity identification method, device, terminal and readable medium
CN118132699A (en) Reply information generation method, device, client and storage medium
CN117371950A (en) Robot flow automation method, device, all-in-one machine and storage medium
CN112732969A (en) Image semantic analysis method and device, storage medium and electronic equipment
CN112270197A (en) Animation draft generation method and device based on character paragraphs
CN114328936B (en) Method and device for establishing classification model
CN114003714B (en) Intelligent knowledge pushing method for document context sensing
CN116050426A (en) Method, system, equipment and storage medium for quickly inquiring menu
CN118535715B (en) Automatic reply method, equipment and storage medium based on tree structure knowledge base

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