CN116050426A - Method, system, device and storage medium for fast menu query - Google Patents

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, device and storage medium for fast menu query

technical field

The present invention relates to the field of intelligent interaction, more specifically, to a method, system, device and storage medium for fast menu query.

Background technique

In the iGIX low-code development platform, the generated menu will be released after the application development is completed, so that users can quickly locate specific applications through the menu to use software functions. However, the iGIX low-code development platform has hundreds of built-in basic functions, most of which are menu In addition, the application menu developed based on the platform will make the menu query complex. The current platform provides a fuzzy query method. After the user enters the query keyword, he needs to filter from several query results. , the query accuracy and efficiency are not ideal.

The menu search in the low-code development platform is mostly based on the fuzzy matching algorithm. In the common search box, enter the keywords of the content to be searched for, and automatic jump cannot be realized. You need to manually click the menu to jump, while the development based on iGIX When developing a specific application, the developer needs to constantly query the menu to test the function, which brings many unnecessary operations and reduces the development efficiency.

In addition, most of the data required for natural language model training is static, but with the increase in the number of menus, a large number of unregistered words appear, these words are related to business, and may not be included in the general word segmentation dictionary Such words lead to errors in word segmentation, resulting in abnormalities in the grammatical and semantic analysis stages, which eventually lead to deviations in prediction.

Contents of the invention

In view of this, the purpose of the embodiment of the present invention is to propose a method, system, computer equipment and computer-readable storage medium for quick menu query. The present invention introduces natural language processing technology and supporting tools into the iGIX low-code development platform, and provides Lexical analysis, syntactic analysis, and semantic analysis of the input text can provide users with more accurate query services. At the same time, according to the menu presentation principle in the platform, the dynamic changes of the menu are automatically monitored. When a new menu is generated, Automatically extract the newly generated menu name and synchronously update the dictionary in the lexical analysis. For platform developers, it can further improve the development efficiency of developers and shorten the software development cycle. For the final software users, it greatly enhances the software ease of use.

Based on the above purpose, an aspect of the embodiment of the present invention provides a method for quick menu query, including the following steps: in response to receiving the text input by the user, processing the text; Question reasoning, obtaining the confidence of each similar question, and sorting according to the level of confidence; judging whether there is a similar question with a confidence higher than a threshold; Questions are presented to the user in order.

In some implementations, the processing the text includes: performing word segmentation on the text to obtain a first result, and performing stop words or nonsense words detection on the first result to delete stop words or meaningless words.

In some implementations, the processing the text includes: comparing the text with preset content to filter illegal parts in the text.

In some implementations, the method further includes: in response to the text being successfully matched with a preset keyword, directly returning the reply content corresponding to the preset keyword.

In some embodiments, the method further includes: in response to completing the query each time, adding one to the score of the corresponding query topic according to the current query result, and sorting the query topics according to the scores to form the next query for the user. Recommended results.

In some implementations, the method further includes: setting an expiration time, and reducing the score of the query result corresponding to the query subject by one in response to the duration of each query result exceeding the expiration time.

In some embodiments, the method further includes: in response to detecting an incremental change in the menu data, pushing the data of the menu name to the natural language processing server to update the dictionary data.

Another aspect of the embodiments of the present invention provides a system for quick menu query, including: a processing module configured to process the text in response to receiving the text input by the user; a reasoning module configured to process the text according to The processed text is reasoned about similar questions through the dictionary, and the confidence of each similar question is obtained, and sorted according to the level of confidence; the judgment module is configured to judge whether there are similar questions with a confidence higher than the threshold; and the display module , configured to display the similar questions to the user in order in response to the presence of similar questions with a confidence level higher than a threshold.

In another aspect of the embodiments of the present invention, there is also provided a computer device, including: at least one processor; and a memory, the memory stores computer instructions executable on the processor, and the instructions are executed by the The steps of the above method are realized when the processor executes.

In yet another aspect of the embodiments of the present invention, a computer-readable storage medium is also provided, and the computer-readable storage medium stores a computer program for implementing the above method steps when executed by a processor.

The present invention has the following beneficial technical effects: the natural language processing technology and supporting tools are introduced into the iGIX low-code development platform to perform lexical analysis, syntactic analysis and semantic analysis on the input text, which can provide users with more accurate query services, and at the same time According to the principle of menu presentation in the platform, the dynamic changes of the menu are automatically monitored. When a new menu is generated, the newly generated menu name is automatically extracted, and the dictionary in the lexical analysis is updated synchronously. For platform developers, it can further Improve the development efficiency of developers, shorten the software development cycle, and greatly enhance the ease of use of the software for the final software users.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only These are some embodiments of the present invention, and those skilled in the art can obtain other embodiments according to these drawings without any creative effort.

Fig. 1 is the schematic diagram of the embodiment of the method for quick menu query 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 the hardware structure schematic diagram of the embodiment of the computer equipment of the menu quick query provided by the present invention;

Fig. 4 is a schematic diagram of an embodiment of a computer storage medium for quick menu query provided by the present invention.

Detailed ways

In order to make the object, technical solution and advantages of the present invention clearer, the embodiments of the present invention will be further described in detail below in conjunction with specific embodiments and with reference to the accompanying drawings.

It should be noted that all expressions using "first" and "second" in the embodiments of the present invention are to distinguish two entities with the same name but different parameters or parameters that are not the same, see "first" and "second" It is only for the convenience of expression, and should not be construed as a limitation on the embodiments of the present invention, which will not be described one by one in the subsequent embodiments.

According to the first aspect of the embodiments of the present invention, an embodiment of a method for quick menu query is proposed. FIG. 1 is a schematic diagram of an embodiment of the method for quick menu query provided by the present invention.

As shown in Figure 1, the embodiment of the present invention includes the following steps:

S1. In response to receiving the text input by the user, process the text;

S2. According to the processed text, the similar question reasoning is carried out through the dictionary, and the confidence degree of each similar question is obtained, and sorted according to the level of confidence;

S3. Judging whether there is a similar problem with a confidence level higher than a threshold; and

S4. In response to the presence of similar questions with a confidence level higher than the threshold, present the similar questions to the user in sequence.

The embodiment of the present invention introduces the natural language processing technology into the iGIX low-code development platform, and integrates the functions related to the application menu query to improve the development efficiency and the usability of the software.

Embodiments of the present invention provide a conversational UI (User Interface, user interface), which is the entrance of human-computer interaction. When entering the conversational UI window for the first time, a list of recommended content will appear. These recommended content can be set. With the increase of the number of applications , the system will automatically learn the user's preferences and automatically update the recommendation list. The front-end interactive interface of the embodiment of the present invention is developed based on Inspur self-developed Farris UI and HTML, CSS, jQuery and other front-end technologies. The conversational UI integrates multiple functions, including user command input, result display returned by the dialogue control center, and automatic page jump.

The user enters text through the interactive UI interface, and transmits it to the backend for semantic analysis, and returns the final query result to the user through the conversational UI. The content includes a menu name list or a question and answer content, and the user can directly click on the content of the list , or enter the serial number before the list to realize automatic jump.

In some implementations, the processing the text includes: comparing the text with preset content to filter illegal parts in the text. There is a robot icon on the homepage of the iGIX low-code development platform. The icon supports dragging up and down, and a dialog box (conversational UI) pops up when you click the robot icon. After the user enters the text content, the front-end filters the illegal part of the input content through the content set in advance, mainly to detect whether the text contains executable Script scripting language to prevent malicious code injection. The front end transmits the input text content to the dialog control module of the back end through the request API interface.

In some implementations, the processing the text includes: performing word segmentation on the text to obtain a first result, and performing stop words or nonsense words detection on the first result to delete stop words or meaningless words.

The first step after the text enters the dialogue control module is to call the natural language processing module to carry out word segmentation for the input text content. For the text word segmentation, the embodiment of the present invention adopts the jieba (stutter) word segmentation framework, because the menu name formed by applying the iGIX development framework Most of them are strongly related to the business, and the general word segmentation framework cannot be segmented very accurately. Therefore, the embodiment of the present invention expands based on the dictionary customization function provided by the jieba word segmentation framework, and further improves the accuracy of word segmentation. Developers develop based on iGIX After the development of the framework, the application is finally published as a menu. During this process, the key information such as the name of the menu and the specific application path will be automatically saved in the corresponding database table. The embodiment of the invention integrates with the framework based on this mechanism. When the menu is generated, the name of the menu will be saved in the custom dictionary synchronously. The word segmentation service returns all words in the form of a list, and then the system detects stop words or nonsense words for the cut words, cleans the words, and performs similar reasoning.

Similar question reasoning will return a list of similar questions, including links to specific questions and answers, and confidence levels. The system returns 10 pieces of data by default. If the confidence in the returned data is greater than the set threshold, similar questions can be returned directly. Then judge other natural language processing tasks and return directly to the front end.

The order of judgment here needs to be set. There is a separate part in the configuration interface provided by the system. When the system performs natural language processing, it will first obtain the configuration data, and then judge according to the priority of the configuration. The priority here is reflected in the number 1, 2, and 3. If the user does not set the order, the system defaults to the priority processing and judgment of the menu query, followed by similar questions, and finally the retrieval of user-defined content. Users can set the content of questions and answers through the front-end interface provided by the system, and support custom editing of questions and content. The format of the content includes text and images, and finally stored in the database table. The defined questions are calculated based on the TF-IDF method, and the document library is updated synchronously. For similar questions, the system will automatically update them with the questions adopted in the iGIX community, and update the text similarity calculation document library. The matching of menu names is based on the CBOW algorithm in the Word2Vec model to calculate the similarity of words, and sort based on the confidence of similar questions. If it is greater than the threshold, it will return to the front end. This query method requires user screening, and the system will eventually It returns several menus with similar semantics.

In some implementations, the method further includes: in response to the text being successfully matched with a preset keyword, directly returning the reply content corresponding to the preset keyword. If the user clearly knows the menu to be queried, "open" can be added before the entered menu. The system will first check whether the end of the text contains the corresponding keyword for the entered text. If it does, the system will return the automatically developed tag. Write the keyword "autoOpen" in the returned content, and then perform word segmentation on the text content except "open", and then return the result. If there are multiple different menus, first match the content stored in the frequently used menu library. If If it is a frequently visited word, the frequently visited word will be returned. If multiple words are used with the same frequency, the system will sort them according to the order of the words in the input text by default. The previous words will be returned first, and only one menu name will be returned. For common greetings, such as hello, what function do you have, etc., the front-end system module will filter. This kind of text reply speech system has been built in, and the front-end has a text matching function. After matching the preset keywords, the front-end part Return the reply content directly instead of passing the content to the server for processing.

For the returned content, the front-end supports a variety of modal display, mainly including the function menu name, similar question recommendation in the iGIX Q&A community, and user-defined Q&A content. The dialogue control server returns data in JSON format, and an action field is added to the returned content. The values of this field mainly include clickOpenMenu (the content returned to the front end requires a mouse click to realize the application jump), autoOpenMenu (the semantic analysis is accurate, Realize the automatic jump of the menu), qA (the question set adopted in the iGIX Q&A community) and answer (customized Q&A type), by setting these keywords, the UI interface can differentiate the content of different modes, such as For custom Q&A content, the answer sentence can be displayed directly, and similar questions need to provide a jump function to jump to the iGIX Q&A community to view more accurate answers.

In some embodiments, the method further includes: in response to completing the query each time, adding one to the score of the corresponding query topic according to the current query result, and sorting the query topics according to the scores to form the next query for the user. Recommended results. Every time the user re-enters the conversational UI, the system will automatically recommend the user's frequently used functions. The recommended content defaults to the menu name and specific questions. Only the top 6 frequently searched content will be displayed each time. The user can also use the system to The provided interface sets the recommended content. The recommended content requires the user to click to jump by default. Here, user-defined question and answer pairs are supported. If the user does not set it, the system will randomly push 6 pieces of information, and the user can also close it in the configuration page. For the question recommendation function, after the page is refreshed, the recommended content will no longer be displayed on the interface in the conversational UI. For the built-in recommendation function of the system, the system adopts a scoring system, and every time the same content is detected, 1 will be added to the corresponding score.

In some implementations, the method further includes: setting an expiration time, and reducing the score of the query result corresponding to the query subject by one in response to the duration of each query result exceeding the expiration time. Set the expiration time, usually one week, and set the storage structure as a queue. After receiving the content requested by the front end, first detect the first and last words, and then completely match the data in the queue. If the same and not expired, add it after the score 1. For the problem that the expiration time is reached, the system will automatically delete it from the queue after detection.

In some embodiments, the method further includes: in response to detecting an incremental change in the menu data, pushing the data of the menu name to the natural language processing server to update the dictionary data. There is a data processing service interface between the dialogue control system and the NLP service. When the data menu data is updated, the system detects an incremental change and automatically pushes the data of the menu name to the NLP server. The NLP server automatically updates the dictionary data. For User-defined type of question and answer data, after the user uploads the data, model training needs to be performed through the configuration interface provided by the system, and the system will regularly crawl the data to update the document collection for the adopted question and answer content in the iGIX development community.

The natural language processing module and the dialogue control center are loosely coupled. They are two different service units. The dialogue control system needs to call the natural language processing server in the form of an API interface, and then combine the returned results and return them to the front-end interface. The operation here includes the encapsulation of the function ID corresponding to the specific menu, because in the iGIX development framework, the opening of the menu is identified and located according to the function ID, and other question and answer functions also need to be customized, and the natural language processing module remains unchanged.

The natural language processing module is deployed in the form of microservices, and the dialogue control center is business-related and belongs to the intelligent capability consumption layer. The dialogue control center is developed based on JAVA language, and the natural language processing service center is developed based on Python. In the configuration interface provided by the system, Users can set whether to enable the natural language processing (NLP) service. If the service is not used, the system defaults to providing a rule matching method for approximate calculation of similar problems.

The system uses the natural language processing framework Gensim for text processing. The natural language processing module provides training functions. After the system detects the increment in the problem, it automatically pushes a copy of data to the training end. After the NLP training module detects the pushed data, it automatically updates the embedded word list of the text in TF-IDF. For the similarity prediction of the menu, the embodiment of the present invention is based on the CBOW algorithm in the Word2Vec word embedding model, and conducts customized training of word vectors, and integrates many words in the field of iGIX low-code development into the training corpus. The collection includes the functional application names required by ERP systems in different vertical fields, which greatly improves the prediction accuracy of similarity. At the same time, the system provides a control interface for natural language processing. In the data processing part, you can customize the vocabulary and then perform vocabulary training together with the built-in data set in the system. The entire training process is carried out in the cloud, and users can also set the training in the configuration interface. Parameters such as count (data of each word read), epoch (number of training times), the size of the word vector is processed by the system to 100 dimensions by default. After processing the data, the cloud system automatically trains after clicking the training button. After completion, the NLP processing system automatically deploys and goes online.

It should be pointed out that the steps in the various embodiments of the above-mentioned method for quick menu query can be mutually intersected, replaced, added, and deleted. Therefore, these reasonable permutations and combinations should also belong to the method for quick menu query protection scope of the present invention and should not be limited to the embodiments.

Based on the above purpose, the second aspect of the embodiment of the present invention proposes a system for quick menu query. As shown in Figure 2, the system 200 includes the following modules: a processing module configured to process the text in response to receiving the text input by the user; a reasoning module configured to perform similar questions through a dictionary according to the processed text Reasoning, obtaining the confidence of each similar question, and sorting according to the level of confidence; judging module, configured to determine whether there is a similar question with a confidence higher than a threshold; and a display module, configured to respond to the presence of confidence For similar questions higher than the threshold, the similar questions are displayed to the user in order.

In some implementations, the processing module is configured to: perform word segmentation on the text to obtain a first result, and detect stop words or meaningless words on the first result to delete stop words in the first result. Words or nonsense words.

In some implementations, the processing module is configured to: filter illegal parts of the text by comparing the text with preset content.

In some implementations, the system further includes a return module configured to: in response to the text being successfully matched with a preset keyword, directly return the reply content corresponding to the preset keyword.

In some implementations, the system further includes a recommendation module configured to: in response to completing a query each time, add one to the score of the corresponding query topic according to the current query result, and sort the query topics according to the scores Form the next recommendation result for the user.

In some implementations, the system further includes an expiration module configured to: set an expiration time, and decrease the score of the query result corresponding to the query subject by one in response to the duration of each query result exceeding the expiration time.

In some implementations, the system further includes an updating module configured to: in response to detecting an incremental change of the menu data, push the data of the menu name to the natural language processing server to update the dictionary data.

Based on the above purpose, a third aspect of the embodiments of the present invention proposes a computer device, including: at least one processor; and a memory, the memory stores computer instructions that can run on the processor, and the instructions are executed by the processor to The following steps are implemented: S1. In response to receiving the text input by the user, process the text; S2. Perform similar problem reasoning through the dictionary according to the processed text to obtain the confidence degree of each similar problem, and according to the confidence degree Sorting high and low; S3. Judging whether there are similar questions with a confidence higher than the threshold; and S4. Responding to the existence of similar questions with a confidence higher than the threshold, displaying the similar questions to the user in order.

In some implementations, the processing the text includes: performing word segmentation on the text to obtain a first result, and performing stop words or nonsense words detection on the first result to delete stop words or meaningless words.

In some implementations, the processing the text includes: comparing the text with preset content to filter illegal parts in the text.

In some embodiments, the step further includes: in response to the text being successfully matched with a preset keyword, directly returning the reply content corresponding to the preset keyword.

In some embodiments, the steps further include: in response to completing the query each time, adding one to the score of the corresponding query topic according to the current query result, and sorting the query topics according to the scores to form the next query for the user. Recommended results.

In some embodiments, the step further includes: setting an expiration time, and reducing the score of the query result corresponding to the query subject by one in response to the duration of each query result exceeding the expiration time.

In some embodiments, the steps further include: in response to detecting the incremental change of the menu data, pushing the data of the menu name to the natural language processing server to update the dictionary data.

As shown in FIG. 3 , it is a schematic diagram of the hardware structure of an embodiment of the above-mentioned computer device for fast menu query provided by the present invention.

Taking the device shown in FIG. 3 as an example, the device includes a processor 301 and a memory 302 .

The processor 301 and the memory 302 may be connected through a bus or in other ways, and the connection through a bus is taken as an example in FIG. 3 .

The memory 302, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer-executable programs and modules, such as the method corresponding to the menu quick query method in the embodiment of the present application Program instructions/modules. The processor 301 executes various functional applications and data processing of the server by running non-volatile software programs, instructions and modules stored in the memory 302 , that is, a method for realizing quick menu query.

The memory 302 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and at least one application program required by a function; the data storage area may store data created by using the quick query method of the menu, and the like. In addition, the memory 302 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid-state storage devices. In some embodiments, the memory 302 may optionally include memory that is remotely located relative to the processor 301, and these remote memories may be connected to the local module through a network. Examples of the aforementioned networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

One or more computer instructions 303 corresponding to the quick menu query method are stored in the memory 302 , and when executed by the processor 301 , execute the menu quick query method in any of the above method embodiments.

Any one embodiment of the computer device that executes the above method for fast menu query can achieve the same or similar effects as any of the above-mentioned method embodiments corresponding to it.

The present invention also provides a computer-readable storage medium, and the computer-readable storage medium stores a computer program for executing a method for fast menu query when executed by a processor.

As shown in FIG. 4 , it is a schematic diagram of an embodiment of the computer storage medium for the above-mentioned quick menu query provided by the present invention. Taking the computer storage medium shown in FIG. 4 as an example, the computer readable storage medium 401 stores a computer program 402 for executing the above method when executed by a processor.

Finally, it should be noted that those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be realized through computer programs to instruct relevant hardware to complete, and the program of the method for quick menu query can be stored in a computer-readable When the program is executed, the program may include the processes of the embodiments of the above-mentioned methods. Wherein, the storage medium of the program may be a magnetic disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), and the like. The foregoing computer program embodiments can achieve the same or similar effects as any of the foregoing method embodiments corresponding thereto.

The above are the exemplary embodiments disclosed in the present invention, but it should be noted that various changes and modifications can be made without departing from the scope of the disclosed embodiments of the present invention defined in the 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. In addition, although the elements disclosed in the embodiments of the present invention may be described or required in an individual form, they may also be understood as a plurality unless explicitly limited to a singular number.

It should be understood that as used herein, the singular form "a" and "an" are intended to include the plural forms as well, unless the context clearly supports an 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 serial numbers of the embodiments disclosed in the above-mentioned embodiments of the present invention are only for description, and do not represent the advantages and disadvantages of the embodiments.

Those of ordinary skill in the art can understand that all or part of the steps for implementing the above-mentioned embodiments can be completed by hardware, or can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. The above-mentioned The storage medium may be a read-only memory, a magnetic disk or an optical disk, and the like.

Those of ordinary skill in the art should understand that: the discussion of any of the above embodiments is exemplary only, and is not intended to imply that the scope (including claims) disclosed by the embodiments of the present invention is limited to these examples; under the idea of the embodiments of the present invention , the technical features in the above embodiments or different embodiments can also be combined, and there are many other changes in different aspects of the above embodiments of the present invention, which are not provided in details for the sake of brevity. Therefore, within the spirit and principle of the embodiments of the present invention, any omissions, modifications, equivalent replacements, improvements, etc., shall be included in the protection scope of the embodiments of the present invention.

Claims (10)

1. A method for menu quick inquiry, is characterized in that, comprises the steps: in response to receiving text entered by a user, processing the text; According to the processed text, the similar question reasoning is carried out through the dictionary, and the confidence degree of each similar question is obtained, and sorted according to the level of confidence; Determine whether there are similar questions with a confidence level higher than a threshold; and Responsive to the presence of similar questions with a confidence level higher than a threshold, the similar questions are presented to the user in order. 2. The method according to claim 1, wherein said processing said text comprises: Word segmentation is performed on the text to obtain a first result, and stop words or nonsense words are detected on the first result to delete stop words or nonsense words in the first result. 3. The method according to claim 1, wherein said processing said text comprises: The illegal part in the text is filtered by comparing the text with the preset content. 4. The method according to claim 1, wherein the method further comprises: In response to the text being successfully matched with the preset keyword, the reply content corresponding to the preset keyword is returned directly. 5. The method according to claim 1, wherein the method further comprises: In response to completing each query, the score of the corresponding query topic is increased by one according to the current query result, and the query topics are sorted according to the scores to form the next recommendation result for the user. 6. The method according to claim 5, further comprising: An expiration time is set, and in response to the duration of each query result exceeding the expiration time, the score of the query result corresponding to the query subject is reduced by one. 7. The method according to claim 1, further comprising: In response to detecting the incremental change of the menu data, push the data of the menu name to the natural language processing server to update the dictionary data. 8. A quick search system for menus, comprising: a processing module configured to process the text in response to receiving the text input by the user; The reasoning module is configured to perform similar problem reasoning through the dictionary according to the processed text, obtain the confidence degree of each similar problem, and sort according to the level of confidence; A judging module configured to judge whether there is a similar problem with a confidence level higher than a threshold; and The presenting module is configured to display the similar questions to the user in sequence in response to the presence of similar questions with a confidence level higher than a threshold. 9. A computer device, comprising: at least one processor; and A memory, the memory stores computer instructions operable on the processor, and the steps of the method according to any one of claims 1-7 are implemented when the instructions are executed by the processor. 10. A computer-readable storage medium, the computer-readable storage medium storing a computer program, characterized in that, when the computer program is executed by a processor, the steps of the method according to any one of claims 1-7 are implemented.

Images