Intelligent question and answer method and device

By identifying the problem categories and determining the corresponding filtering conditions, combining semantic analysis and intention management tables, the problem of single function of the intelligent question-answer system is solved, and the accuracy and efficiency of question-and-answer system is improved.

CN119003735APending Publication Date: 2024-11-22JINGDONG TECH HLDG CO LTD
View PDF 6 Cites 0 Cited by

Patent Information

Application Number
CN202411170751.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-23
Publication Date
2024-11-22

AI Technical Summary

Technical Problem

The existing intelligent question and answer system has a single function and cannot effectively distinguish filtering conditions for different types of questions, which affects the accuracy and efficiency of the answer results.

Method used

By identifying problem categories, determine the corresponding filter conditions, including semantic analysis, intent management table and merging of preset indicator values, generate highly targeted filter conditions, and provide problem prompt information when the core intention is not clear, guiding users to update the problem .

Benefits of technology

It improves the accuracy and efficiency of Q&A, avoids problems that can only deal with specific types of questions, and enhances the flexibility and pertinence of the intelligent Q&A system.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119003735A_ABST
    Figure CN119003735A_ABST
Patent Text Reader

Abstract

The invention provides an intelligent question answering method and device, and the method comprises the steps: responding to a received target question, and determining the question type of the target question; based on the question category of the target question, determining a target screening condition corresponding to the target question; and querying an answer result corresponding to the target question based on the target screening condition. According to the embodiment, the question and answer accuracy and efficiency can be improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to an intelligent question-answering method and device. Background Art

[0002] With the continuous development of artificial intelligence technology, intelligent question-answering systems are increasingly used in various fields. As an efficient way of information interaction, intelligent question-answering systems can greatly improve user experience and work efficiency.

[0003] However, the existing intelligent question-answering systems still have some limitations. Some systems have single functions and can only respond to specific types of questions, or use the same method to determine the answer screening conditions for all questions, which affects the accuracy of the answer results and reduces the efficiency of intelligent question-answering. Summary of the invention

[0004] In view of this, the embodiments of the present disclosure provide an intelligent question-and-answer method, device, electronic device, and storage medium, which can improve the accuracy and efficiency of question-and-answer.

[0005] In a first aspect, an embodiment of the present disclosure provides an intelligent question-answering method, the method comprising:

[0006] In response to receiving a target question, determining a question category of the target question;

[0007] Based on the question category of the target question, determining a target screening condition corresponding to the target question;

[0008] Based on the target screening condition, query the answer result corresponding to the target question.

[0009] Optionally, determining the problem category of the target problem includes:

[0010] Identify whether there are preset indicators and preset keywords in the target question;

[0011] If the target question contains the preset indicator and the preset keyword, determining that the target question is a screening question;

[0012] If the target question contains the preset keywords but does not contain the preset indicators, determining that the target question is a recommendation question;

[0013] If the preset indicator and the preset keyword do not exist in the target question, it is determined that the target question is another type of question.

[0014] Optionally, when the question category of the target question is a screening question, determining a target screening condition corresponding to the target question based on the question category of the target question includes:

[0015] Performing semantic analysis on the target question to determine the core intent of the target question;

[0016] Based on a pre-configured intent management table and the core intent of the target question, a first screening condition corresponding to the target question is obtained; the intent management table includes a correspondence between the core intent and the screening condition;

[0017] Determine an indicator value of the preset indicator in the target question, and obtain a second screening condition corresponding to the target question based on the indicator value;

[0018] The first screening condition is combined with the second screening condition to obtain a target screening condition corresponding to the target question.

[0019] Optionally, when the question category of the target question is a screening question, determining a target screening condition corresponding to the target question based on the question category of the target question includes:

[0020] Determine whether the target question contains the preset indicators in the above question; the above question is the question received before the target question;

[0021] If included, the indicator value of the preset indicator is updated according to the target problem, and based on the updated indicator value, the target screening condition corresponding to the target problem is determined.

[0022] Optionally, when the question category of the target question is a recommendation question, determining a target screening condition corresponding to the target question based on the question category of the target question includes:

[0023] Performing semantic analysis on the target question to determine the core intent of the target question;

[0024] Based on the pre-configured intent management table and the core intent of the target question, obtaining a third screening condition corresponding to the target question;

[0025] The third screening condition is used as a target screening condition corresponding to the target question.

[0026] Optionally, when determining the core intent of the target problem fails, the method further includes:

[0027] Generate question prompt information; the question prompt information is used to guide the question initiator to update the target question until the core intention of the target question is determined.

[0028] Optionally, when the question category of the target question is other types of questions, determining a target screening condition corresponding to the target question based on the question category of the target question includes:

[0029] The preset question answering rule is determined as the target screening condition corresponding to the target question.

[0030] In a second aspect, an embodiment of the present disclosure provides an intelligent question-answering device, including:

[0031] A category determination module, configured to determine a question category of the target question in response to receiving the target question;

[0032] A condition determination module, which determines a target screening condition corresponding to the target question based on the question category of the target question;

[0033] The query module queries the answer result corresponding to the target question based on the target screening condition.

[0034] In a third aspect, an embodiment of the present disclosure further provides an electronic device, comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the computer device is running, the processor and the memory communicate through the bus, and when the machine-readable instructions are executed by the processor, the steps in the above-mentioned first aspect, or any optional implementation of the first aspect are performed.

[0035] In a fourth aspect, an embodiment of the present disclosure further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned first aspect, or any optional implementation of the first aspect are executed.

[0036] In any one of the above aspects or any implementation of any one of the aspects, in response to receiving a target question, the question category of the target question is determined; based on the question category of the target question, a target screening condition corresponding to the target question is determined; based on the target screening condition, an answer result corresponding to the target question is queried. In this way, different target screening conditions can be distinguished according to the question category, avoiding the problem of only being able to deal with specific types of questions, improving the pertinence of the target screening conditions, and thus improving the accuracy and efficiency of question and answer.

[0037] In a further embodiment of the present disclosure, when the question category of the target question is a screening question, based on the question category of the target question, a target screening condition corresponding to the target question is determined, including: performing semantic analysis on the target question to determine the core intent of the target question; obtaining a first screening condition corresponding to the target question based on a pre-configured intent management table and the core intent of the target question; the intent management table includes a correspondence between the core intent and the screening condition; determining an index value of the preset index in the target question, and obtaining a second screening condition corresponding to the target question based on the index value; merging the first screening condition with the second screening to obtain a target screening condition corresponding to the target question. In this way, the target screening condition of the target question can be jointly constituted by the core intent of the target question and the index value under the preset index, thereby improving the pertinence and accuracy of answer screening, thereby improving the accuracy and efficiency of question and answer.

[0038] In a further embodiment of the present disclosure, when the target question is a screening question and the previous question of the target question includes a preset indicator in the target question, only the indicator value under the indicator can be updated to determine the target screening condition. At this time, there is no need to combine the core intention of the target question again, thereby improving the efficiency of intelligent question and answering.

[0039] In a further embodiment of the present disclosure, when the core intent of the target question fails to be determined, the method further includes: generating question prompt information; the question prompt information is used to guide the question initiator to update the target question until the core intent of the target question is determined. Thus, when the core intent of the question is unclear, the user can be guided to conduct multiple rounds of dialogue to determine the core intent of the target question through prompt information, thereby improving the accuracy and efficiency of question and answer.

[0040] The effects of the above-mentioned intelligent question and answer device, electronic device and storage medium can be found in the description of the above-mentioned intelligent question and answer method, which will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the following is a brief introduction to the drawings required for use in the embodiments. The drawings herein are incorporated into the specification and constitute a part of the specification. These drawings illustrate embodiments consistent with the present disclosure and are used together with the specification to illustrate the technical solutions of the present disclosure. It should be understood that the following drawings only illustrate certain embodiments of the present disclosure and should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can also be obtained based on these drawings without creative work.

[0042] Figure 1A flow chart of an intelligent question-answering method provided by an embodiment of the present disclosure is shown;

[0043] Figure 2 A schematic diagram of a process flow of an intelligent question-answering method provided by an embodiment of the present disclosure is shown;

[0044] Figure 3 A schematic diagram of an intelligent question-answering device provided by an embodiment of the present disclosure is shown;

[0045] Figure 4 An exemplary system architecture is shown in which embodiments of the present disclosure may be applied;

[0046] Figure 5 A schematic diagram of the structure of a computer system of a terminal device or a server used to implement an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0047] In order to make the purpose, technical solutions and advantages of the embodiments of the present disclosure clearer, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, rather than all of the embodiments. The components of the embodiments of the present disclosure generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present disclosure provided in the drawings is not intended to limit the scope of the present disclosure for protection, but merely represents the selected embodiments of the present disclosure. Based on the embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present disclosure.

[0048] It should be noted that in the technical solution of the present invention, the collection, use, storage, sharing and transfer of user personal information involved are in compliance with the provisions of relevant laws and regulations, and it is necessary to inform the user and obtain the user's consent or authorization. When applicable, the user's personal information is de-identified and / or anonymized and / or encrypted.

[0049] Research has found that with the continuous development of artificial intelligence technology, the application of intelligent question-answering systems in various fields is becoming more and more extensive. The process of intelligent question-answering refers to the ability of the intelligent question-answering system to directly interact with the natural language issued by the user and give answers or suggestions that meet the user's needs. As an efficient information interaction mode, the intelligent question-answering system can greatly improve the user experience and work and learning efficiency.

[0050] However, the existing intelligent question-answering systems still have some limitations. For example, some systems have single functions and can only respond to specific types of questions, or use the same method to determine the answer screening conditions for all questions, which affects the accuracy of the answer results and reduces the efficiency of intelligent question-answering. In addition, the intelligent question-answering systems in the prior art perform relatively ordinary in multi-round dialogues and cannot adapt to the changes in user needs during the interaction process. This has affected the accuracy and efficiency of intelligent question-answering.

[0051] Based on the above research, the embodiments of the present disclosure provide an intelligent question-answering method that can distinguish different target screening conditions according to question categories, avoid the problem of only being able to deal with specific types of questions, improve the specificity of the target screening conditions, and thus improve the accuracy and efficiency of question-answering.

[0052] Secondly, when the question category of the target question is a screening question, based on the question category of the target question, the target screening condition corresponding to the target question is determined, including: performing semantic analysis on the target question to determine the core intent of the target question; obtaining a first screening condition corresponding to the target question based on a pre-configured intent management table and the core intent of the target question; the intent management table includes the correspondence between the core intent and the screening condition; determining the index value of the preset index in the target question, and obtaining a second screening condition corresponding to the target question based on the index value; merging the first screening condition with the second screening to obtain the target screening condition corresponding to the target question. In this way, the target screening condition of the target question can be jointly constituted by the core intent of the target question and the index value under the preset index, thereby improving the pertinence and accuracy of answer screening, thereby improving the accuracy and efficiency of question and answer.

[0053] In addition, when the target question is a screening question and the previous question of the target question includes the preset indicators in the target question, only the indicator value under the indicator can be updated to determine the target screening conditions. At this time, there is no need to combine the core intention of the target question again, which improves the efficiency of intelligent question and answering.

[0054] In addition, when the core intent of the target question fails to be determined, the method further includes: generating question prompt information; the question prompt information is used to guide the question initiator to update the target question until the core intent of the target question is determined. Therefore, when the core intent of the question is unclear, the user can be guided to conduct multiple rounds of dialogue to determine the core intent of the target question through prompt information, thereby further improving the accuracy and efficiency of question and answer.

[0055] The raising of the above problems and the solutions are the results obtained by the inventor after practice and careful research. The discovery process of the above problems and the solutions proposed for the above problems should be the contributions made by the inventor to the present disclosure during the disclosure process.

[0056] The technical solutions in the present disclosure will be clearly and completely described below in conjunction with the drawings in the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, rather than all of the embodiments. The components of the present disclosure generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present disclosure provided in the drawings is not intended to limit the scope of the present disclosure claimed for protection, but merely represents the selected embodiments of the present disclosure. Based on the embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present disclosure.

[0057] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0058] To facilitate understanding of this embodiment, a smart question-answering method disclosed in the embodiment of the present disclosure is first introduced in detail. The execution subject of the smart question-answering method provided in the embodiment of the present disclosure is generally a computer device with certain computing capabilities, and the computer device includes, for example: a terminal device or a server or other processing device, and the terminal device can be a user equipment (User Equipment, UE), a mobile device, a user terminal, a terminal, a cellular phone, a cordless phone, a personal digital assistant (Personal Digital Assistant, PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, etc. In some possible implementations, the smart question-answering method can be implemented by a processor calling a computer-readable instruction stored in a memory.

[0059] See also Figure 1 FIG. 1 is a flowchart of an intelligent question-answering method provided by an embodiment of the present disclosure, wherein the method includes S101 to S103, wherein:

[0060] S101: In response to receiving a target question, determining a question category of the target question.

[0061] In this step, after receiving the question sent by the question initiator, the execution subject of the embodiment of the present disclosure may first determine the question category of the question.

[0062] In an embodiment of the present disclosure, determining the question category of the target question includes: identifying whether there are preset indicators and preset keywords in the target question; if the preset indicators and the preset keywords exist in the target question, determining that the target question is a screening question; if the preset keywords exist in the target question and the preset indicators do not exist, determining that the target question is a recommendation question; if the preset indicators and the preset keywords do not exist in the target question, determining that the target question is other types of questions.

[0063] Optionally, the question category of the target question can also be determined by extracting text features of the target question; specifically, features such as word frequency and part of speech of the target question can be extracted, and then the target question can be classified according to these features. In addition, a large model with semantic analysis capabilities can also be used to determine the question category of the target question.

[0064] For example, taking the fund Q&A in the financial field as an example, the preset indicators may include the yield rate in the past year, the yield rate in the past month, the fund risk level, the fund type, the fund size, etc., and the preset keywords may be "fund", "income", etc. When it is identified that the question contains both the preset indicators and the preset keywords, it can be determined as a screening question, such as "What are the funds with a yield rate greater than 20% this year?", "What are the funds with lower risks?", etc., which hit the preset indicators and preset keywords at the same time, can be determined as a screening question. Further, if the question only contains preset keywords, such as "What are the funds suitable for Xiaobai financial management?", at this time, the question does not hit any of the preset indicators, it can be determined as a recommendation question. When the question does not include either preset keywords or preset indicators, such as "Who are you?", "What can you do?", etc., it can be determined as other types of questions.

[0065] It should be noted that the above-mentioned setting of preset keywords and preset indicators is only used as an example of a feasible implementation of the embodiment of the present disclosure, and does not constitute an improper limitation on the present invention. In actual application, it can be adjusted as needed to achieve its functions.

[0066] In a specific implementation, the step of determining the problem category of the target problem can be completed by a pre-trained classification model. When training the model, a large amount of data containing the problem text and its category label can be collected as a training set to ensure that there are different types of problems in the training set, and the preset indicators and preset keywords of each problem are marked. Then the training set data can be preprocessed, such as removing special characters, punctuation marks, performing word segmentation, etc., to convert the text data into a data format acceptable to the model. Then the preprocessed training set data can be input into the classification model so that it has the ability to identify the problem category according to the problem text. In addition, the trained classification model can also be evaluated and tuned using a validation set. It should be noted that the above-mentioned method of training the model is only a feasible implementation method of the classification model trained in the embodiment of the present disclosure. In a specific implementation, it can be trained by any method such as self-supervision, semi-supervision or unsupervision according to the needs. The trained model is based on the ability to realize its function, and the embodiment of the present disclosure does not limit this. In addition, in addition to determining the problem category by using the classification model, any other method can also be used to determine the problem category, such as establishing a rule engine, setting classification rules that meet the needs in the engine, etc., and the embodiment of the present disclosure does not specifically limit this.

[0067] S102: Based on the question category of the target question, determine a target screening condition corresponding to the target question.

[0068] In this step, after determining the question category of the target question, a method for determining the screening condition corresponding to the category may be determined, thereby determining the target screening condition of the target question.

[0069] In an embodiment of the present disclosure, when the question category of the target question is a screening question, the target screening condition of the target question can be determined based on the core intent of the target question and the indicator value under the preset indicator.

[0070] Specifically, when the question category of the target question is a screening question, the target screening condition corresponding to the target question is determined based on the question category of the target question, including: performing semantic analysis on the target question to determine the core intent of the target question; obtaining a first screening condition corresponding to the target question based on a pre-configured intent management table and the core intent of the target question; the intent management table includes the correspondence between the core intent and the screening condition; determining the indicator value of the preset indicator in the target question, and obtaining a second screening condition corresponding to the target question based on the indicator value; merging the first screening condition with the second screening to obtain the target screening condition corresponding to the target question.

[0071] In the disclosed embodiment, the pre-configured intent management table includes the correspondence between each core intent and the filtering condition, which is used to determine the corresponding filtering condition according to the core intent. The disclosed embodiment does not specifically limit the form of the intent management table, and in practical applications, it is based on the ability to achieve its functions. Furthermore, when the correspondence between the core intent and the filtering condition changes or is updated, dynamic adjustment can be achieved by updating the intent management table to improve the efficiency and flexibility of intelligent question and answer.

[0072] Optionally, when determining the core intent of the target question, corresponding screening conditions may be directly generated based on the core intent, without relying on a pre-set corresponding relationship.

[0073] Figure 2 The figure is a flow chart of the intelligent question-answering method provided in the embodiment of the present disclosure. Figure 2 As shown, when the target question category is a screening question, the target question can be first subjected to semantic analysis to determine the core intent of the target question. If the identification is successful, the first screening condition corresponding to the core intent can be obtained from the pre-configured intent management table. As described above, the screening questions also include preset indicators. In this step, the indicator value under the preset indicator can be obtained, and based on the specific indicator value, the second screening condition for the target question can be obtained. The above-mentioned process of core intent identification and indicator identification can be completed by a pre-trained model, or by any other feasible method, and the embodiments of the present disclosure are not limited to this.

[0074] Exemplarily, when the target question is "I am a first-time financial manager, please recommend some lower-risk funds to me", the corresponding core intent identified is "newbie". After obtaining the core intent, the screening condition corresponding to "newbie" can be found in the intent management table and determined as the first screening condition. For the above target question, it can also be determined that the preset indicator contained in the target question is "fund risk level", and the corresponding indicator value is "low risk". After determining the indicator value, the second screening condition of the target question can be determined according to the pre-defined rules. For example, funds with an annualized volatility of less than 10% can be identified as low-risk funds, or funds with a beta coefficient of less than 0.8 can be identified as low-risk funds, and funds with a maximum drawdown controlled at 5% of the fund size can also be identified as low-risk funds. After obtaining the first screening condition determined by the core intent and the second screening condition determined by the indicator value, the two can be merged to determine the target screening condition corresponding to the target question.

[0075] It should be noted that the core intent in the embodiments of the present disclosure can be determined according to actual needs, such as "novice", "small drawdown", "low volatility", "stable income", etc. In addition, indicators and corresponding indicator values ​​can also be set according to needs. For example, the indicator value under the "fund type" indicator can include "money fund", "stock fund", "bond fund", etc. The embodiments of the present disclosure do not limit this, and the function can be realized.

[0076] For example, if the target question is "What are the stock funds suitable for beginners?", its core intention is "beginner", its preset indicator is "fund type", and the specific indicator value under this indicator is "stock fund". When determining the target screening condition for this question, the first screening condition corresponding to "beginner" and the screening condition corresponding to "stock fund" can be used as the target screening condition for the target question.

[0077] In the embodiment of the present disclosure, when the question category of the target question is a screening question, the target screening condition of the target question can also be directly determined based on the preset indicators of the target question.

[0078] Specifically, when the question category of the target question is a screening question, the target screening condition corresponding to the target question is determined based on the question category of the target question, including: judging whether the target question contains the preset indicator in the previous question; the previous question is a question received before the target question; if contained, updating the indicator value of the preset indicator according to the target question, and determining the target screening condition corresponding to the target question based on the updated indicator value.

[0079] In the disclosed embodiment, the pre-configured intent management table includes the correspondence between each core intent and the filtering condition, which is used to determine the corresponding filtering condition according to the core intent. The disclosed embodiment does not specifically limit the form of the intent management table, and in practical applications, it is based on the ability to achieve its functions. Furthermore, when the correspondence between the core intent and the filtering condition changes or is updated, dynamic adjustment can be achieved by updating the intent management table to improve the efficiency and flexibility of intelligent question and answer.

[0080] Optionally, when determining the core intent of the target question, corresponding screening conditions may be directly generated based on the core intent, without relying on a pre-set corresponding relationship.

[0081] In the specific implementation, Figure 2As shown, it is also possible to determine whether the indicator in the current target question has appeared in the previous question, that is, whether the current target question is a follow-up question of the previous question. If so, only the indicator value under the indicator can be updated, and the target screening condition of the target question can be determined based on the updated indicator value. At this time, since the current target question is a follow-up question, the core intent of the current target question is consistent with the previous question, so there is no need to combine it with the screening condition determined by the core intent. The target screening condition of the current target question can be determined only by the screening condition determined by the updated indicator value. This can save the process of repeatedly identifying the core intent and improve the efficiency of intelligent question answering.

[0082] Optionally, except when the current target question is a follow-up question of the previous question, when multiple independent questions are included in the same conversation, it is possible to first identify whether the core intention of the current target question exists in the previous question. If so, the step of repeatedly determining the core intention can be omitted, and the new indicator and the indicator value under the indicator can be directly determined to determine the target screening condition of the target question. This can further improve the efficiency of intelligent question and answer. Exemplarily, when the target question is "help me recommend some stock funds suitable for novices" and the previous question is "help me recommend some money funds suitable for novices", it is recognized that the target question and the previous question both include the indicator "fund type", but the specific indicator value has changed from "money fund" to "stock fund", and the core intention "novice" has not changed. Therefore, it is only necessary to update the indicator value, and determine the target screening condition of the target question based on the updated indicator value "stock fund".

[0083] In an embodiment of the present disclosure, when the question category of the target question is a recommendation question, the corresponding target screening condition can be directly determined based on the core intent of the target question.

[0084] Specifically, when the question category of the target question is a recommendation question, the target filtering condition corresponding to the target question is determined based on the question category of the target question, including: performing semantic analysis on the target question to determine the core intent of the target question; obtaining a third filtering condition corresponding to the target question based on a pre-configured intent management table and the core intent of the target question; and using the third filtering condition as the target filtering condition corresponding to the target question.

[0085] In the specific implementation, Figure 2 As shown, when the question category is a recommendation question, since the target question does not include preset indicators but only preset keywords, there is no need to identify its indicators. Instead, it is necessary to identify its core intent and determine the target screening conditions for the target question from the intent management table based on the identified core intent results.

[0086] For example, when the target question is "What are the funds suitable for beginners?", it does not include preset indicators. Based on the core intention of the target question, you can find the filtering conditions corresponding to "novice" from the corresponding relationship in the intention management table and use them as the target filtering conditions for the target question.

[0087] Furthermore, when the core intent recognition fails, a question prompt message can be generated to prompt the question initiator to gradually improve the target question to determine the core intent of the target question. In this way, the core intent of the target question can be determined through multiple rounds of dialogue, which improves the efficiency and accuracy of intelligent question answering.

[0088] For example, when the target question is "I am more concerned about the volatility of the fund", the question prompt information generated at this time may be "I understand. May I ask what range of volatility you would like to inquire about the funds within?" The question initiator may then further supplement his or her question based on the question prompt information as "I want to find a fund with lower volatility". At this point, the question initiator has improved the target question based on the question prompt information, so that the executing entity of the disclosed embodiment can recognize that the core intention of the target question is "low volatility".

[0089] In an embodiment of the present disclosure, when the question category of the target question is other types of questions, the target screening condition corresponding to the target question is determined based on the question category of the target question, including: determining a preset question answering rule as the target screening condition corresponding to the target question.

[0090] Optionally, when the target question category is other types of questions, the step of determining the target screening conditions can be omitted, and the set content can be pushed directly to the initiator of the question. For example, several popular funds recently can be pushed directly, and polite prompts or greetings such as "Sorry, I can't recommend funds to you based on the content you entered", "I can recommend funds you want to know about, do you have any needs?", "Hello" and so on can be pushed.

[0091] In the specific implementation, Figure 2 As shown, when the target question is other types of questions, the target screening conditions corresponding to the target question can be determined according to the preset answer rules.

[0092] For example, when the target question includes neither preset indicators nor preset keywords, it can be regarded as a question irrelevant to the current scenario or field. For example, when the target question is "Who are you?", it is obviously a question irrelevant to the field of financial funds. In this case, the target screening conditions can be determined directly according to the pre-set answer rules. For example, the answer rules can be set to recommend the fund with the largest number of purchases, and then the corresponding target screening conditions can be determined.

[0093] S103: Based on the target screening condition, query the answer result corresponding to the target question.

[0094] In the embodiments of the present disclosure, Figure 2 As shown, after the target screening conditions are determined, they can be converted into SQL statements so that the answer results corresponding to the target questions can be found in the database and the answer results can be returned to the question initiator.

[0095] It should be noted that the above only uses the financial fund field as an example to illustrate the specific implementation mode of the present invention, which does not constitute an improper limitation of the present invention. The intelligent question-answering method provided by the present invention can be applied to any field or scenario.

[0096] According to a second aspect of the embodiment of the present disclosure, Figure 3 As shown, an intelligent question-answering device 300 is provided, comprising:

[0097] A category determination module 301 is used to determine the question category of the target question in response to receiving the target question;

[0098] A condition determination module 302 determines a target screening condition corresponding to the target question based on the question category of the target question;

[0099] The query module 303 queries the answer result corresponding to the target question based on the target screening condition.

[0100] Optionally, the category determination module 301 is specifically configured to:

[0101] Identify whether there are preset indicators and preset keywords in the target question;

[0102] If the target question contains the preset indicator and the preset keyword, determining that the target question is a screening question;

[0103] If the target question contains the preset keywords but does not contain the preset indicators, determining that the target question is a recommendation question;

[0104] If the preset indicator and the preset keyword do not exist in the target question, it is determined that the target question is another type of question.

[0105] Optionally, the condition determination module 302 is specifically configured to:

[0106] Performing semantic analysis on the target question to determine the core intent of the target question;

[0107] Based on a pre-configured intent management table and the core intent of the target question, a first screening condition corresponding to the target question is obtained; the intent management table includes a correspondence between the core intent and the screening condition;

[0108] Determine an indicator value of the preset indicator in the target question, and obtain a second screening condition corresponding to the target question based on the indicator value;

[0109] The first screening condition is combined with the second screening condition to obtain a target screening condition corresponding to the target question.

[0110] Optionally, the condition determination module 302 is further configured to:

[0111] Determine whether the target question contains the preset indicators in the above question; the above question is the question received before the target question;

[0112] If included, the indicator value of the preset indicator is updated according to the target problem, and based on the updated indicator value, the target screening condition corresponding to the target problem is determined.

[0113] Optionally, the condition determination module 302 is specifically configured to:

[0114] Performing semantic analysis on the target question to determine the core intent of the target question;

[0115] Based on the pre-configured intent management table and the core intent of the target question, obtaining a third screening condition corresponding to the target question;

[0116] The third screening condition is used as a target screening condition corresponding to the target question.

[0117] Optionally, the condition determination module 302 is further configured to:

[0118] Generate question prompt information; the question prompt information is used to guide the question initiator to update the target question until the core intention of the target question is determined.

[0119] Optionally, the condition determination module 302 is specifically configured to:

[0120] The preset question answering rule is determined as the target screening condition corresponding to the target question.

[0121] According to the third aspect of an embodiment of the present disclosure, an electronic device for intelligent question and answer is provided, comprising: one or more processors; a storage device for storing one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors implement the method provided by the first aspect of the embodiment of the present invention.

[0122] According to a fourth aspect of an embodiment of the present disclosure, a computer-readable medium is provided, on which a computer program is stored, and when the program is executed by a processor, the method provided by the first aspect of the embodiment of the present disclosure is implemented.

[0123] Figure 4 An exemplary system architecture 400 to which the intelligent question-answering method or intelligent question-answering device implemented by the present disclosure can be applied is shown.

[0124] like Figure 4 As shown, system architecture 400 may include terminal devices 401, 402, 403, network 404 and server 405. Network 404 is used to provide a medium for communication links between terminal devices 401, 402, 403 and server 405. Network 404 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0125] Users can use terminal devices 401, 402, 403 to interact with server 405 through network 404 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 401, 402, 403, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only for example).

[0126] The terminal devices 401 , 402 , and 403 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, and desktop computers.

[0127] The server 405 may be a server that provides various services, such as a backend management server (for example only) that provides support for shopping websites browsed by users using the terminal devices 401, 402, and 403. The backend management server may process the received intelligent question-and-answer request and feed back the processing result (for example only) to the terminal device.

[0128] It should be noted that the intelligent question-answering method provided in the embodiment of the present invention is generally executed by the server 405, and accordingly, the intelligent question-answering device is generally arranged in the server 405. The intelligent question-answering method provided in the embodiment of the present invention can also be executed by the terminal devices 401, 402, and 403, and accordingly, the intelligent question-answering device can be arranged in the terminal devices 401, 402, and 403.

[0129] It should be understood that Figure 4 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to the implementation requirements.

[0130] Reference below Figure 5 , which shows a schematic diagram of the structure of a computer system 500 of a terminal device suitable for implementing an embodiment of the present invention. Figure 5 The terminal device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0131] like Figure 5 As shown, the computer system 500 includes a central processing unit (CPU) 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage part 508 into a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the system 500 are also stored. The CPU 501, the ROM 502, and the RAM 503 are connected to each other through a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0132] The following components are connected to the I / O interface 505: an input section 506 including a keyboard, a mouse, etc.; an output section 507 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 508 including a hard disk, etc.; and a communication section 509 including a network interface card such as a LAN card, a modem, etc. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to the I / O interface 505 as needed. A removable medium 511, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 510 as needed, so that a computer program read therefrom is installed into the storage section 508 as needed.

[0133] In particular, according to the embodiments disclosed in the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 509, and / or installed from the removable medium 511. When the computer program is executed by the central processing unit (CPU) 501, the above-mentioned functions defined in the system of the present invention are executed.

[0134] It should be noted that the computer-readable medium shown in the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0135] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0136] The modules involved in the embodiments of the present invention may be implemented by software or hardware. The modules described may also be set in a processor. For example, a processor includes a category determination module, a condition determination module, and a query module, wherein the names of these modules do not constitute a limitation on the modules themselves in certain circumstances. For example, the category determination module may also be described as a "question category module for determining the target question".

[0137] As another aspect, the present invention further provides a computer-readable medium, which may be included in the device described in the above embodiment; or may exist independently without being assembled into the device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by a device, the device implements the following method:

[0138] In response to receiving a target question, determining a question category of the target question;

[0139] Based on the question category of the target question, determining a target screening condition corresponding to the target question;

[0140] Based on the target screening condition, query the answer result corresponding to the target question.

[0141] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present disclosure, which are used to illustrate the technical solutions of the present disclosure, rather than to limit them. The protection scope of the present disclosure is not limited thereto. Although the present disclosure is described in detail with reference to the above-described embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-described embodiments within the technical scope disclosed in the present disclosure, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present disclosure, and should be included in the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure shall be based on the protection scope of the claims.

Claims

1. An intelligent question-answering method, characterized in that: include: In response to receiving a target question, determining a question category of the target question; Based on the question category of the target question, determining a target screening condition corresponding to the target question; Based on the target screening condition, query the answer result corresponding to the target question.

2. The method according to claim 1, characterized in that Determine the problem category of the target problem, including: Identify whether there are preset indicators and preset keywords in the target question; If the target question contains the preset indicator and the preset keyword, determining that the target question is a screening question; If the target question contains the preset keywords but does not contain the preset indicators, determining that the target question is a recommendation question; If the preset indicator and the preset keyword do not exist in the target question, it is determined that the target question is another type of question.

3. The method according to claim 2, characterized in that When the question category of the target question is a screening question, determining a target screening condition corresponding to the target question based on the question category of the target question includes: Performing semantic analysis on the target question to determine the core intent of the target question; Based on a pre-configured intent management table and the core intent of the target question, a first screening condition corresponding to the target question is obtained; the intent management table includes a correspondence between the core intent and the screening condition; Determine an indicator value of the preset indicator in the target question, and obtain a second screening condition corresponding to the target question based on the indicator value; The first screening condition is combined with the second screening condition to obtain a target screening condition corresponding to the target question.

4. The method according to claim 2, characterized in that: When the question category of the target question is a screening question, determining a target screening condition corresponding to the target question based on the question category of the target question includes: Determine whether the target question contains the preset indicators in the above question; the above question is the question received before the target question; If included, the indicator value of the preset indicator is updated according to the target problem, and based on the updated indicator value, the target screening condition corresponding to the target problem is determined.

5. The method according to claim 2, characterized in that: When the question category of the target question is a recommendation question, determining a target screening condition corresponding to the target question based on the question category of the target question includes: Performing semantic analysis on the target question to determine the core intent of the target question; Based on the pre-configured intent management table and the core intent of the target question, obtaining a third screening condition corresponding to the target question; The third screening condition is used as a target screening condition corresponding to the target question.

6. The method according to any one of claims 3 to 5, characterized in that: When determining the core intent of the target problem fails, the method further includes: Generate question prompt information; the question prompt information is used to guide the question initiator to update the target question until the core intention of the target question is determined.

7. The method according to claim 2, characterized in that: When the question category of the target question is other types of questions, determining a target screening condition corresponding to the target question based on the question category of the target question includes: The preset question answering rule is determined as the target screening condition corresponding to the target question.

8. An intelligent question-answering device, characterized in that: include: A category determination module, configured to determine a question category of the target question in response to receiving the target question; A condition determination module, which determines a target screening condition corresponding to the target question based on the question category of the target question; The query module queries the answer result corresponding to the target question based on the target screening condition.

9. An electronic device, characterized in that: include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.

10. A computer readable medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Citation Information

Patent Citations

  • Question and answer processing method and device, electronic equipment and storage medium

    CN111460095A

  • Intelligent question and answer implementation method and device, equipment and storage medium

    CN112860865A

  • Information acquisition method and related equipment

    CN113886525A

  • Question and answer method, device and equipment and readable medium

    CN117743546A

  • Natural language question answering method and apparatus, and server

    WO2018149326A1