CN119474285A - Result generation method, device, equipment and storage medium - Google Patents
Result generation method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN119474285A CN119474285A CN202310975387.1A CN202310975387A CN119474285A CN 119474285 A CN119474285 A CN 119474285A CN 202310975387 A CN202310975387 A CN 202310975387A CN 119474285 A CN119474285 A CN 119474285A
- Authority
- CN
- China
- Prior art keywords
- information
- question
- result
- keyword
- follow
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
- G06F3/0484—Interaction techniques based on graphical user interfaces [GUI] for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range
- G06F3/04842—Selection of displayed objects or displayed text elements
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
- G06F3/0487—Interaction techniques based on graphical user interfaces [GUI] using specific features provided by the input device, e.g. functions controlled by the rotation of a mouse with dual sensing arrangements, or of the nature of the input device, e.g. tap gestures based on pressure sensed by a digitiser
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/451—Execution arrangements for user interfaces
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
本发明属于计算机技术领域，公开了一种结果生成方法、装置、设备及存储介质。本发明通过获取追问信息；查找所述追问信息对应的相关问答数据；基于所述追问信息及所述相关问答数据生成追问结果数据。由于会在获取到追问信息之后，查找与追问信息相关的相关问答数据，并根据追问信息及相关问答数据进一步生成追问结果数据，使得用户无须自行修改问题或关键词，仅需进行追问，即可获取自身所需的结果，降低了复杂度，提高了用户的使用体验。
The present invention belongs to the field of computer technology, and discloses a result generation method, device, equipment and storage medium. The present invention obtains follow-up information; searches for relevant question and answer data corresponding to the follow-up information; and generates follow-up result data based on the follow-up information and the relevant question and answer data. After the follow-up information is obtained, the relevant question and answer data related to the follow-up information is searched, and the follow-up result data is further generated based on the follow-up information and the relevant question and answer data, so that the user does not need to modify the question or keywords by himself, but only needs to ask questions to obtain the results he needs, which reduces the complexity and improves the user experience.
Description
Technical Field
The present invention relates to the field of computer technologies, and in particular, to a method, an apparatus, a device, and a storage medium for generating a result.
Background
In the field of man-machine interaction, a computer only feeds back corresponding results aiming at the same search word, if a user is not satisfied with the search or generated data result, the user can only modify the problem or the search word which is presented by the user and then try again to acquire the result, and when the search word is adjusted, the user needs to have rich search or inquiry experience to adjust the search word more accurately, so that the result which is really needed by the user is obtained, the user generally does not have rich experience, the overall use complexity is higher, and the use experience is poor.
The foregoing is provided merely for the purpose of facilitating understanding of the technical solutions of the present invention and is not intended to represent an admission that the foregoing is prior art.
Disclosure of Invention
The invention mainly aims to provide a result generation method, device, equipment and storage medium, and aims to solve the technical problem that only a self-adjusting problem or a search word can be achieved when a user is not satisfied with an obtained result in the prior art.
To achieve the above object, the present invention provides a result generation method, comprising the steps of:
responding to the received inquiry information, searching relevant inquiry and answer data corresponding to the inquiry information and question information corresponding to the relevant inquiry and answer data;
acquiring the inquiry information;
searching relevant question-answering data corresponding to the additional information;
and generating the additional query result data based on the additional query information and the related question-answer data.
Optionally, the step of generating the additional query result data based on the additional query information and the related question-answer data includes:
acquiring an information modification intention corresponding to the additional information;
Extracting target question information from the related question-answer data;
constructing inquiry question information according to the information modification intention and the target question information;
And generating the inquiry result data based on the inquiry question information and the related inquiry response data.
Optionally, the step of obtaining the information modification intention corresponding to the inquiry information includes:
Extracting keywords from the overtime information to obtain an overtime keyword set;
carrying out weight analysis on the additional keyword set to obtain a keyword weight sequence;
and matching in a preset knowledge base according to the keyword weight sequence, and determining the information modification intention corresponding to the additional information.
Optionally, the step of performing weight analysis on the query keyword set to obtain a keyword weight sequence includes:
acquiring a problem structure and information property corresponding to the inquiry information;
Determining the weight proportion corresponding to each additional keyword in the additional keyword set according to the problem structure and the information property;
and ordering the overtaking keywords in the overtaking keyword set based on the weight proportion to obtain a keyword weight sequence.
Optionally, the step of constructing the additional question information according to the information modification intention and the target question information includes:
determining a problem modification location and a problem modification indication based on the information modification intent;
And adjusting the target problem information according to the problem modification position and the problem modification instruction to obtain the inquiry problem information.
Optionally, the step of extracting the target question information from the related question-answer data includes:
Determining the attribution field of the problem and the problem modification indication according to the information modification intention;
matching the question belonging field and the question modification instruction with the question information corresponding to each related question-answer data, and determining the matching degree corresponding to each question information;
And selecting target question information from the question information corresponding to each related question-answer data based on the matching degree.
Optionally, the step of adjusting the target problem information according to the problem modification position and the problem modification instruction to obtain the query problem information includes:
Determining keywords to be modified in the target problem information according to the problem modification position;
searching a keyword set corresponding to the problem modification instruction based on the keywords to be modified;
extracting replacement keywords from the keyword set;
and adjusting the keywords to be modified in the target problem information according to the replacement keywords to obtain the inquiry problem information.
Optionally, the step of extracting the replacement keyword from the keyword set includes:
comparing the question information corresponding to the related question-answer data with the target question information to determine a difference keyword;
Screening the keyword set according to the difference keywords to obtain a keyword set to be selected;
and extracting the replacement keywords from the keyword set to be selected.
Optionally, the step of generating the query result data based on the query question information and the related question-answer data includes:
searching in a preset knowledge base based on the inquiry question information to obtain at least one piece of answer corpus information;
Extracting keywords from the answer corpus information to obtain result keywords;
And constructing additional query result data according to the result keywords and the related question-answer data.
Optionally, the step of extracting keywords from the answer corpus information to obtain result keywords includes:
Acquiring a question keyword corresponding to the additional question information;
searching for a solution keyword corresponding to the question keyword;
and extracting keywords from the answer corpus information according to the answer keywords to obtain result keywords.
Optionally, the step of extracting the keywords from the answer corpus information according to the answer keywords to obtain result keywords includes:
Selecting target corpus information from the at least one piece of answer corpus information according to the related question-answer data;
and extracting keywords from the target corpus information according to the answering keywords to obtain result keywords.
Optionally, the step of searching the relevant question-answer data corresponding to the additional information includes:
acquiring session identification data corresponding to the inquiry information;
searching corresponding history display results and history questioning information according to the session identification data to obtain history display data;
Searching problem information corresponding to the historical display data according to the result response identification corresponding to the historical display data;
and constructing relevant question-answer data according to the history display data and the question information.
Optionally, the step of acquiring the inquiry information includes:
the method comprises the steps of acquiring the inquiry information input by a user through an interactive input box or acquiring the inquiry information input by the user through an inquiry prompt button.
Optionally, the interactive input box and/or the inquiry prompt button include at least one of the following cases:
The interactive input box is displayed independently;
the interactive input box is displayed corresponding to the interactive topics;
Displaying in association with question-answer pairs;
displaying in association with the problem;
Presentation associated with the answer;
and after receiving the operation of selecting the page content by the user, associating and displaying with the selected content.
In addition, in order to achieve the above object, the present invention also proposes a result generation device, which includes the following modules:
The acquisition module is used for acquiring the inquiry information;
the searching module is used for searching the related question-answer data corresponding to the additional information;
and the generating module is used for generating the inquiry result data based on the inquiry information and the related inquiry response data.
Optionally, the generating module is further configured to obtain an information modification intention corresponding to the query information, extract target question information from the relevant question-answer data, construct query question information according to the information modification intention and the target question information, and generate query result data based on the query question information and the relevant question-answer data.
Optionally, the generating module is further configured to extract keywords from the query information to obtain a query keyword set, perform weight analysis on the query keyword set to obtain a keyword weight sequence, and determine an information modification intention corresponding to the query information according to matching of the keyword weight sequence in a preset knowledge base.
Optionally, the generating module is further configured to obtain a question structure and an information property corresponding to the query information, determine a weight ratio corresponding to each query keyword in the query keyword set according to the question structure and the information property, and sort the query keywords in the query keyword set based on the weight ratio to obtain a keyword weight sequence.
In addition, in order to achieve the above object, the present invention also proposes a result generating device comprising a processor, a memory and a result generating program stored on the memory and executable on the processor, the result generating program realizing the steps of the result generating method as described above when being executed by the processor.
In addition, in order to achieve the above object, the present invention also proposes a computer-readable storage medium having stored thereon a result generation program which, when executed, implements the steps of the result generation method as described above.
The method comprises the steps of obtaining the inquiry information, searching relevant inquiry and answer data corresponding to the inquiry information, and generating inquiry result data based on the inquiry information and the relevant inquiry and answer data. After the additional information is acquired, the relevant question and answer data related to the additional information are searched, and additional result data are further generated according to the additional information and the relevant question and answer data, so that a user does not need to modify questions or keywords by himself or herself, and the user can acquire the required result by himself or herself only by performing additional, the complexity is reduced, and the use experience of the user is improved.
Drawings
FIG. 1 is a schematic diagram of an electronic device of a hardware operating environment according to an embodiment of the present invention;
FIG. 2 is a flow chart of a first embodiment of the result generation method of the present invention;
FIG. 3 is a flow chart of a second embodiment of the result generation method of the present invention;
FIG. 4 is a flow chart of a third embodiment of the result generation method of the present invention;
FIG. 5 is a flow chart of a fourth embodiment of the result generation method of the present invention;
FIG. 6 is a flowchart of a fifth embodiment of the result generation method of the present invention;
fig. 7 is a block diagram showing the structure of a first embodiment of the result generating apparatus of the present invention.
The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Referring to fig. 1, fig. 1 is a schematic diagram of a result generating device of a hardware running environment according to an embodiment of the present invention.
As shown in fig. 1, the electronic device may include a processor 1001, such as a central processing unit (Central Processing Unit, CPU), a communication bus 1002, a user interface 1003, a network interface 1004, a memory 1005. Wherein the communication bus 1002 is used to enable connected communication between these components. The user interface 1003 may include a Display, an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may further include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a Wireless interface (e.g., a Wireless-Fidelity (WI-FI) interface). The Memory 1005 may be a high-speed random access Memory (Random Access Memory, RAM) or a stable nonvolatile Memory (NVM), such as a disk Memory. The memory 1005 may also optionally be a storage device separate from the processor 1001 described above.
Those skilled in the art will appreciate that the structure shown in fig. 1 is not limiting of the electronic device and may include more or fewer components than shown, or may combine certain components, or may be arranged in different components.
As shown in fig. 1, an operating system, a network communication module, a user interface module, and a result generation program may be included in the memory 1005 as one type of storage medium.
In the electronic device shown in fig. 1, the network interface 1004 is mainly used for data communication with a network server, the user interface 1003 is mainly used for data interaction with a user, and the processor 1001 and the memory 1005 in the electronic device can be arranged in a result generating device, and the electronic device invokes a result generating program stored in the memory 1005 through the processor 1001 and executes the result generating method provided by the embodiment of the invention.
An embodiment of the present invention provides a result generating method, referring to fig. 2, fig. 2 is a schematic flow chart of a first embodiment of a result generating method of the present invention.
In this embodiment, the result generating method includes the following steps:
And S10, acquiring the inquiry information.
The execution body of the present embodiment may be the result generating device, in which a result generating program (may also be referred to as an intelligent assistant, and the intelligent assistant may be a pre-trained intelligent language model), and the result generating device may be an electronic device such as a personal computer, a server, or other devices capable of implementing the same or similar functions, which is not limited in this embodiment, and in the present embodiment and each embodiment described below, the result generating method of the present embodiment and each embodiment described below will be described using the result generating device as an example.
It should be noted that, the intelligent assistant will distinguish the flow of interaction with the user by the session, the period of one session opens the interaction window for the user until the whole flow of the interaction window is closed, after the user obtains one time of result data, if the user inputs the problem again, the intelligent assistant will determine that the inquiry information is received.
In order to avoid the inquiry misjudgment, after receiving the questions or search words input by the user, the questions or search words can be matched with other questions in the current session process, the relevance is determined, and if the relevance reaches a preset threshold, the inquiry information is judged to be received.
In a specific implementation, the user can input the inquiry information through an interaction input box arranged in the interaction window, and can also input the inquiry information by clicking an inquiry prompt button displayed in the interaction window. The presentation of the interactive input box and/or the overt prompt button may include at least one of:
the interactive input boxes are independently displayed (namely, an independent area is divided in the interactive window for displaying the interactive input boxes);
The interactive input box is displayed corresponding to the interactive topics (namely, an interactive input box is arranged for each interactive topic in the interactive window);
presentation in association with question-answer pairs (i.e., displaying an interactive input box and/or at least one challenge prompt button in the presentation area of each question-answer pair);
Presentation associated with the question (i.e., displaying an interactive input box and/or at least one inquiry prompt button in the display area of each question entered by the user);
Presentation associated with the answers (i.e., displaying an interactive input box and/or at least one inquiry prompt button in the presentation area of each answer);
After receiving the operation of selecting the page content by the user, the user is associated with the selected content for display (namely, after selecting the page content in the interactive crazy page by the user, an interactive input box and/or at least one inquiry prompt button are displayed near the selected content).
The questions may be questions entered by the user, and the answers may be presented result data.
And step S20, searching relevant question and answer data corresponding to the additional information.
When generating the result data, the intelligent assistant determines the problem information according to the problem or the keyword input by the user and combines the current context and the interactive feedback data of the user history to generate the result data according to the problem information, and the relevant question-answering data corresponding to the additional information at this time may include the problem input by the user and the problem information used when the intelligent assistant generates the result data and the generated result data.
In a specific implementation, in order to ensure that relevant question and answer data can be accurately acquired, the intelligent assistant can set a corresponding unique identifier for each session, and when relevant question and answer data corresponding to the additional information needs to be acquired, the session unique identifier of the session to which the additional information belongs can be acquired, and the relevant question and answer data is searched according to the session unique identifier.
In a specific implementation, in order to ensure that relevant question-answer data can be accurately obtained, the intelligent assistant may set a corresponding unique identifier for each session, and step S20 in this embodiment may include:
acquiring session identification data corresponding to the inquiry information;
searching corresponding history display results and history questioning information according to the session identification data to obtain history display data;
Searching problem information corresponding to the historical display data according to the result response identification corresponding to the historical display data;
and constructing relevant question-answer data according to the history display data and the question information.
The session identifier data corresponding to the acquisition of the inquiry information may be a unique identifier corresponding to the session to which the acquisition of the inquiry information belongs, so as to obtain the session identifier data. According to the session identification data, searching the corresponding history display result and history questioning information, wherein the history display data can be obtained by searching the session with the corresponding unique identification consistent with the session identification data, and then obtaining all the history display results and history questioning data belonging to the session, thereby obtaining the history display data. The history display result may be result data generated by the intelligent assistant based on the questions posed by the user, and the history question data may be question information input by the user in a history manner.
Similarly, when generating result data, the intelligent assistant sets a corresponding unique identifier for the result data and stores the unique identifier in association with problem information used when generating the result data, so that the problem information corresponding to the history display data can be the unique identifier of the result data contained in the acquired history display data, namely the result response identifier, and the problem information associated with the history display data is searched according to the result response identifier, thereby acquiring the problem information corresponding to the history display data.
In actual use, the relevant question-answer data may be constructed according to the history display data and the question information by aggregating the history display data and the question information according to the corresponding relationship, so as to obtain the relevant question-answer data.
And step S30, generating the additional query result data based on the additional query information and the related question-answer data.
It should be noted that, generating the query result data based on the query information and the related question-answer data may be selecting the target question-answer data with the highest correlation with the query information from the related question-answer information, modifying the question information in the target question-answer data according to the query information to obtain the query question information, searching the related corpus data based on the query question information, and generating the query result data according to the corpus data.
The embodiment obtains the inquiry information, searches the relevant question-answer data corresponding to the inquiry information, and generates inquiry result data based on the inquiry information and the relevant question-answer data. After the additional information is acquired, the relevant question and answer data related to the additional information are searched, and additional result data are further generated according to the additional information and the relevant question and answer data, so that a user does not need to modify questions or keywords by himself or herself, and the user can acquire the required result by himself or herself only by performing additional, the complexity is reduced, and the use experience of the user is improved.
Referring to fig. 3, fig. 3 is a flowchart of a second embodiment of a result generation method according to the present invention.
Based on the first embodiment, the step S30 of the result generating method of the present embodiment includes:
Step S301, obtaining the information modification intention corresponding to the additional information.
It should be noted that, the obtaining of the information modification intention corresponding to the query information may be performing semantic analysis on the query information, and determining a cause of dissatisfaction of the user on the generated result data, thereby obtaining the information modification intention. For example, if the query information input by the user is "whether the query information can be more detailed" or not, the user can determine that the information modification intention corresponding to the query information is "obtaining more detailed data results" when considering that the result data currently displayed is too rough, and if the query information input by the user is "result field error", the user can determine that the information modification intention corresponding to the query information is "obtaining data of other fields" when considering that the field of the result data currently displayed is wrong.
And step S302, extracting target problem information from the related question and answer data.
When the user performs the inquiry, the user generally aims at the last displayed result data, and then the target question information is extracted from the relevant question-answer data, which may be the last displayed result data in the relevant question-answer data, and then the question information corresponding to the result data is taken as the target question information.
Further, since the user may attempt to inquire about other questions after asking a question, in order to meet such a scenario, step S302 of this embodiment may include:
Determining the attribution field of the problem and the problem modification indication according to the information modification intention;
matching the question belonging field and the question modification instruction with the question information corresponding to each related question-answer data, and determining the matching degree corresponding to each question information;
And selecting target question information from the question information corresponding to the related question-answer data based on the matching degree.
When the user makes an inquiry about another question, the information modification intention determined according to the inquiry information includes information related to the previously proposed question, such as a question attribution field (e.g., a mechanical field, a software development field, etc.) and a more specific question modification instruction, the question attribution field and the question modification instruction may be extracted from the information modification intention, and then the question attribution field and the question modification instruction are matched with the question information corresponding to each relevant question-answer data, so as to determine a matching degree corresponding to each question information.
In actual use, selecting the target question information from the question information corresponding to the relevant question-answer data based on the matching degree may be selecting the question information with the largest matching degree from the question information corresponding to the relevant question-answer data as the target question information.
And step S303, constructing the follow-up question information according to the information modification intention and the target question information.
It should be noted that, the construction of the challenge question information according to the information modification intention and the target question information may be to adjust the target question information according to the information modification intention, so as to obtain the challenge question information. The adjustment of the target problem information may be, for example, keyword replacement or keyword addition to the target problem information, which is not limited in this embodiment.
And step S304, generating the additional question result data based on the additional question information and the related question-answer data.
It should be noted that, generating the query result data based on the query question information and the related question-answer data may be generating at least one piece of result data according to the query question information, calculating the answer matching degree of each piece of result data in combination with the related question-answer data, and taking one piece of the answer matching degree with the highest answer matching degree as the query result data.
The answer matching degree of each result data calculated in combination with the relevant question-answer data may be a degree of correlation of the calculated result data with the result data contained in the relevant question-answer data, and the degree of correlation may be regarded as the answer matching degree.
In some cases, if the user considers that the previously generated result data is not satisfied, the user may inquire to adjust the subsequently generated result data, and then the answer matching degree of each result data may be calculated by combining the result data and the information modification intention included in the related question-answer data, and at this time, the correlation degree and the difference data between the result data included in the related question-answer data and the generated result data may be calculated first, and then the answer matching degree corresponding to each result data may be determined according to the information modification intention, the correlation degree and the difference data, for example, assuming that the information modification intention is "acquire more detailed data result", the higher the correlation degree is, the more the difference data is, the higher the answer matching degree is, and if the information modification intention is "acquire data in other fields", the lower the correlation program is, the more the difference data is, the answer matching degree is higher.
The embodiment obtains the information modification intention corresponding to the inquiry information, extracts target question information from the related question-answer data, constructs the inquiry question information according to the information modification intention and the target question information, and generates inquiry result data based on the inquiry question information and the related question-answer data. Because the corresponding information modification intention is determined according to the additional information, additional question information is constructed according to the information modification intention and the problem information corresponding to the relevant question-answer data corresponding to the additional information, additional question result data is generated according to the additional question information and the relevant question-answer data, a user does not need to modify questions or keywords by himself or herself, and the user can acquire the required result by himself or herself only by additional questions, so that the complexity is reduced and the use experience of the user is improved.
Referring to fig. 4, fig. 4 is a flowchart of a third embodiment of a result generation method according to the present invention.
Based on the above second embodiment, the step S301 of the result generating method of this embodiment includes:
and step S3011, extracting keywords from the inquiry information to obtain an inquiry keyword set.
It should be noted that, extracting keywords from the query information to obtain the query keyword set may be to perform word segmentation processing on the query information, obtain the word segmentation set after word segmentation, delete the word words, the connective words, etc. in the word segmentation set, thereby obtaining the query keyword set.
And step S3012, carrying out weight analysis on the inquiring keyword set to obtain a keyword weight sequence.
It should be noted that, the weight analysis may be performed on the query keyword set by combining the context to determine the weight of each keyword in the query keyword set, and rank the keywords in the query keyword set according to the weight from high to low, and construct a keyword weight sequence according to the ranking result.
In a specific implementation, in order to ensure the normal construction of the keyword weight sequence, step S3012 in this embodiment may include:
acquiring a problem structure and information property corresponding to the inquiry information;
Determining the weight proportion corresponding to each additional keyword in the additional keyword set according to the problem structure and the information property;
and ordering the overtaking keywords in the overtaking keyword set based on the weight proportion to obtain a keyword weight sequence.
It should be noted that, because the user inputs the query information, the adopted question structure (the grammar structure used for question presentation includes the connection relation, connection sequence, connection word, etc. among the keywords) may affect the weight of the keywords, and in order to ensure the normal construction of the keyword weight sequence, the question structure and the information property corresponding to the query information may be obtained first, then the semantic analysis is performed on the query information according to the question structure and the information property, the weight proportion corresponding to each query keyword in the query keyword set is determined, and then the query keywords in the query keyword set are ordered based on the weight proportion, so as to obtain the keyword weight sequence.
When the pursuit keywords in the pursuit keyword set are ranked based on the weight proportion, the pursuit keywords in the pursuit keyword set can be ranked from large to small according to the corresponding weight proportion, so that the keywords with higher weight proportion are located at the forefront of the sequence.
Step S3013, matching is carried out in a preset knowledge base according to the keyword weight sequence, and information modification intention corresponding to the additional information is determined.
It should be noted that the preset knowledge base may be a database used when training the intelligent assistant in advance, where the database includes a large number of data samples constructed according to the keyword weight sequence and the modification intention. After the intelligent assistant determines the keyword weight sequence corresponding to the query information, the intelligent assistant may perform matching in a preset knowledge base according to the keyword weight sequence, determine at least one data sample, and predict according to the data Yang Ben, so as to determine the information modification intention corresponding to the query information.
The embodiment obtains an additional keyword set by extracting keywords of the additional information, carries out weight analysis on the additional keyword set to obtain a keyword weight sequence, and determines an information modification intention corresponding to the additional information by matching the keyword weight sequence in a preset knowledge base. The keyword extraction is carried out on the additional information, then the weight analysis is carried out on each keyword in the extracted additional keyword set, the importance degree of each keyword is determined, the keyword weight evidence sequence is constructed, and the information modification intention is determined according to the keyword weight sequence, so that the intention recognition error caused by the keyword identification error is avoided when the information modification intention is determined, and the accuracy of the result generation method is improved.
Referring to fig. 5, fig. 5 is a flowchart of a fourth embodiment of a result generation method according to the present invention.
Based on the above second embodiment, the step S303 of the result generating method of the present embodiment includes:
Step S3031, determining a problem modification position and a problem modification instruction based on the information modification intention.
It should be noted that, determining the problem modification position and the problem modification instruction based on the information modification intention may be determining a keyword position related to the information modification intention in the target problem information, determining the problem modification position, and searching for the problem modification instruction matching the information modification intention. The question modification instruction may include an adjustment direction of the keyword, such as replacing with a more detailed synonym or replacing with a term similar to the synonym.
Step S3032, the target problem information is adjusted according to the problem modification position and the problem modification instruction, and the inquiry problem information is obtained.
It should be noted that, the target problem information may be adjusted according to the problem modification position and the problem modification instruction, and the obtaining the additional problem information may be extracting the keyword to be modified in the target problem information according to the problem modification position, and replacing the keyword to be modified according to the problem modification instruction, thereby obtaining the additional problem information.
In a specific implementation, in order to ensure that the exact challenge information can be obtained as much as possible, step S3032 in this embodiment may include:
Determining keywords to be modified in the target problem information according to the problem modification position;
searching a keyword set corresponding to the problem modification instruction based on the keywords to be modified;
extracting replacement keywords from the keyword set;
and adjusting the keywords to be modified in the target problem information according to the replacement keywords to obtain the inquiry problem information.
It should be noted that, the keyword to be modified in the target problem information may be a keyword located at the problem modification position in the target problem information, so as to determine the keyword to be modified. Searching for the keyword set corresponding to the problem modification instruction based on the keyword to be modified may be searching for the corresponding keyword according to the adjustment direction of the keyword in the problem modification instruction and the keyword to be modified, and constructing the keyword set according to the searched keyword.
In practical use, the extraction of the replacement keyword from the keyword set may be to randomly extract a keyword from the keyword set as the replacement keyword. The method comprises the steps of adjusting keywords to be modified in target problem information according to the replacement keywords, and obtaining the additional problem information can be to modify the keywords to be modified in the target problem information into the replacement keywords so as to obtain the additional problem information.
Further, in order to reasonably select the replacement keywords and avoid the repetition of the problem information to be queried and the problem information used before, the step of extracting the replacement keywords from the keyword set in this embodiment may include:
comparing the question information corresponding to the related question-answer data with the target question information to determine a difference keyword;
Screening the keyword set according to the difference keywords to obtain a keyword set to be selected;
and extracting the replacement keywords from the keyword set to be selected.
It should be noted that, the step of screening the keyword set according to the difference keywords may be that the keywords identical to the difference keywords in the keyword set are screened out to obtain the keyword set to be selected. The extracting of the replacement keyword from the set of keywords to be selected may be randomly extracting a keyword from the set of keywords to be selected as the replacement keyword.
It can be understood that, in order to obtain the required result, the user may ask questions for multiple times in the same session, and if the user obtains the required result, the questions are not repeated later, so, in order to avoid that the generated result data is the same as the generated result data, the problem information corresponding to the related question-answer data can be compared with the target problem information, the difference keywords are determined, then the keyword set is screened according to the difference keywords, and the generated question information is not repeated with the problem information used for generating the result data after the target problem information is adjusted by selecting the keywords later.
The method comprises the steps of selecting target question information from question information corresponding to relevant question-answering data, determining a question modification position and a question modification indication based on the information modification intention, and adjusting the target question information according to the question modification position and the question modification indication to obtain additional question information. The target question information which is really queried by the user is extracted from the question information corresponding to the relevant question-answer data, and then the target question information is adjusted according to the question modification position and the question modification instruction determined by the information modification intention, so that the additional question information is obtained, the additional question information can be accurately generated according to the actual modification intention of the user, and the accuracy of the result fed back by the result generation method in the embodiment is improved.
Referring to fig. 6, fig. 6 is a flowchart of a fifth embodiment of a result generation method according to the present invention.
Based on the above second embodiment, the step S304 of the result generating method of this embodiment includes:
And step S3041, searching in a preset knowledge base based on the inquiry question information to obtain at least one piece of answer corpus information.
It should be noted that, searching in the preset knowledge base based on the query question information, to obtain at least one answer corpus information may be to search in the preset knowledge base for the answer corpus information matched with the query question information, so as to obtain at least one answer corpus information. The administrator of the result generating device may set a corresponding data tag for the answer corpus information in the preset knowledge base in advance, and if the tag of the answer corpus information is matched with the keyword in the query question information, it may be determined that the answer corpus information is matched with the query question information.
And step S3042, extracting keywords from the answer corpus information to obtain result keywords.
It should be noted that, the answer corpus information is generally an answer or suggestion obtained on the network, but the content of a part of the answer corpus information is relatively bulky, and there is a lot of useless information, so in order to eliminate the part of useless information, keyword extraction can be performed on the answer corpus information at this time, and keywords related to the answer inquiry question information, that is, result keywords, are obtained.
Further, in order to accurately extract the keywords from the answer corpus information, step S3042 in this embodiment may include:
Acquiring a question keyword corresponding to the additional question information;
searching for a solution keyword corresponding to the question keyword;
and extracting keywords from the answer corpus information according to the answer keywords to obtain result keywords.
It should be noted that, the obtaining of the question keyword corresponding to the challenge question information may be analyzing the challenge question information to obtain at least one keyword included in the challenge question information, thereby obtaining the question keyword. The searching of the answer keyword corresponding to the problem keyword may be searching a preset keyword mapping table for the answer keyword corresponding to the problem keyword, where the answer keyword may be a keyword that may occur when the problem corresponding to the problem keyword is located, and the preset keyword mapping table may include a mapping relationship between the answer keyword and the problem keyword, where the mapping relationship may be preset by a manager of the result generating device, or may be constructed by the intelligent assistant when training the intelligent assistant.
In a specific implementation, keyword extraction is performed on the answer corpus information according to the answer keywords, and the obtained result keywords may be keywords which are the same as or similar to the answer keywords in part of speech and are extracted from the answer corpus information, so as to obtain the result keywords.
Further, since different question information is adopted to answer, the obtained answer corpus information may also be repeated, and in order to avoid that the repeated answer causes the degradation of the actual use experience of the user, in this embodiment, the step of extracting the keyword from the answer corpus information according to the answer keyword to obtain the result keyword may include:
Selecting target corpus information from the at least one piece of answer corpus information according to the related question-answer data;
and extracting keywords from the target corpus information according to the answering keywords to obtain result keywords.
It should be noted that, selecting the target corpus information from the at least one piece of answer corpus information according to the relevant question-answer data may be to obtain answer corpus information corresponding to the relevant question-answer data, removing answer corpus information consistent with the answer corpus information corresponding to the relevant question-answer data from the at least one piece of answer corpus information, and taking the remaining answer corpus information as the target corpus information.
It can be understood that, by combining the answer corpus information used by the related question-answer data and adjusting at least one piece of answer corpus information searched currently, the same result can be prevented from being fed back as much as possible when the user performs the additional query, thereby improving the possibility that the user obtains the result meeting the requirement of the user.
In practical use, in order to avoid insufficient corpus after screening and incapability of feeding back results, after selecting target corpus information from at least one piece of answer corpus information according to related question and answer data, the number of the target corpus information can be detected, if the number of the target corpus information is greater than or equal to a preset number threshold, keyword extraction can be performed on the target corpus information according to the answer keywords, and if the number of the target corpus information is less than the preset number threshold, keyword extraction can be performed on at least one piece of answer corpus information directly according to the answer keywords.
And step S3043, constructing additional query result data according to the result keywords and the related question and answer data.
In a specific implementation, the construction of the additional query result data according to the result keywords and the related query data may be that the related query data is used as context information, prediction is performed according to the context information, connection sequence and connection words of the result keywords are determined, and then the result keywords are connected according to the connection sequence and the connection words, so that the additional query result data is generated.
The embodiment obtains at least one piece of answer corpus information by searching in a preset knowledge base based on the inquiry question information, extracts keywords from the answer corpus information to obtain result keywords, and constructs inquiry result data according to the result keywords and the related inquiry response data. After the answer corpus information is obtained, keyword extraction is carried out on the answer corpus information, and additional query result data are constructed according to the extracted result keywords and related question and answer data, so that the finally obtained result data are not excessively redundant, the user can read the answer corpus information conveniently, and the use experience of the user is improved.
In addition, the embodiment of the invention also provides a storage medium, wherein the storage medium stores a result generation program, and the result generation program realizes the steps of the result generation method when being executed by a processor.
Referring to fig. 7, fig. 7 is a block diagram showing the structure of a first embodiment of the result generating apparatus of the present invention.
As shown in fig. 7, the result generating apparatus provided in the embodiment of the present invention includes:
An acquisition module 10 for acquiring the inquiry information;
The searching module 20 is configured to search relevant question-answer data corresponding to the query information;
and a generating module 30, configured to generate the query result data based on the query information and the related question-answer data.
The embodiment obtains the inquiry information, searches the relevant question-answer data corresponding to the inquiry information, and generates inquiry result data based on the inquiry information and the relevant question-answer data. After the additional information is acquired, the relevant question and answer data related to the additional information are searched, and additional result data are further generated according to the additional information and the relevant question and answer data, so that a user does not need to modify questions or keywords by himself or herself, and the user can acquire the required result by himself or herself only by performing additional, the complexity is reduced, and the use experience of the user is improved.
Further, the generating module 30 is further configured to obtain an information modification intention corresponding to the query information, extract target question information from the relevant question-answer data, construct query question information according to the information modification intention and the target question information, and generate query result data based on the query question information and the relevant question-answer data.
Further, the generating module 30 is further configured to extract keywords from the query information to obtain a query keyword set, perform weight analysis on the query keyword set to obtain a keyword weight sequence, match the keyword weight sequence in a preset knowledge base, and determine an information modification intention corresponding to the query information.
Further, the generating module 30 is further configured to obtain a question structure and an information property corresponding to the query information, determine a weight ratio corresponding to each query keyword in the query keyword set according to the question structure and the information property, and sort the query keywords in the query keyword set based on the weight ratio to obtain a keyword weight sequence.
Further, the generating module 30 is further configured to determine a problem modification position and a problem modification instruction based on the information modification intention, and adjust the target problem information according to the problem modification position and the problem modification instruction to obtain additional problem information.
Further, the generating module 30 is further configured to determine a question attribution field and a question modification instruction according to the information modification intention, match the question attribution field and the question modification instruction with question information corresponding to each of the related question-answer data, determine a matching degree corresponding to each of the question information, and select target question information from the question information corresponding to each of the related question-answer data based on the matching degree.
Further, the generating module 30 is further configured to determine a keyword to be modified in the target problem information according to the problem modification position, search a keyword set corresponding to the problem modification instruction based on the keyword to be modified, extract a replacement keyword from the keyword set, and adjust the keyword to be modified in the target problem information according to the replacement keyword to obtain the additional problem information.
Further, the generating module 30 is further configured to compare the question information corresponding to the related question-answer data with the target question information to determine a difference keyword, screen the keyword set according to the difference keyword to obtain a candidate keyword set, and extract a replacement keyword from the candidate keyword set.
Furthermore, the generating module 30 is further configured to search in a preset knowledge base based on the query question information to obtain at least one piece of answer corpus information, extract keywords from the answer corpus information to obtain result keywords, and construct query result data according to the result keywords and the related question-answer data.
Further, the generating module 30 is further configured to obtain a question keyword corresponding to the query question information, search for a solution keyword corresponding to the question keyword, and extract the keyword of the answer corpus information according to the solution keyword to obtain a result keyword.
Further, the generating module 30 is further configured to select target corpus information from the at least one piece of answer corpus information according to the related question-answer data, and extract keywords from the target corpus information according to the answer keywords to obtain result keywords.
Further, the searching module 20 is further configured to obtain session identification data corresponding to the query information, search a corresponding history display result and history question information according to the session identification data to obtain history display data, search question information corresponding to the history display data according to a result response identification corresponding to the history display data, and construct relevant question-answer data according to the history display data and the question information.
Further, the obtaining module 10 is further configured to obtain the query information input by the user through the interactive input box, or obtain the query information input by the user through the query prompt button.
Further, the interactive input box and/or the inquiry prompt button comprise at least one of the following cases:
The interactive input box is displayed independently;
the interactive input box is displayed corresponding to the interactive topics;
Displaying in association with question-answer pairs;
displaying in association with the problem;
Presentation associated with the answer;
and after receiving the operation of selecting the page content by the user, associating and displaying with the selected content.
It should be understood that the foregoing is illustrative only and is not limiting, and that in specific applications, those skilled in the art may set the invention as desired, and the invention is not limited thereto.
It should be noted that the above-described working procedure is merely illustrative, and does not limit the scope of the present invention, and in practical application, a person skilled in the art may select part or all of them according to actual needs to achieve the purpose of the embodiment, which is not limited herein.
In addition, technical details that are not described in detail in this embodiment may refer to the result generation method provided in any embodiment of the present invention, and are not described herein again.
Furthermore, it should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising one does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The foregoing embodiment numbers of the present invention are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. Read Only Memory)/RAM, magnetic disk, optical disk) and including several instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the method according to the embodiments of the present invention.
The foregoing description is only of the preferred embodiments of the present invention, and is not intended to limit the scope of the invention, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein or in the alternative, which may be employed directly or indirectly in other related arts.
The application discloses A1, a result generation method, which comprises the following steps:
acquiring the inquiry information;
searching relevant question-answering data corresponding to the additional information;
and generating the additional query result data based on the additional query information and the related question-answer data.
A2, the method for generating results according to A1, wherein the step of generating the query result data based on the query information and the related question-answer data includes:
acquiring an information modification intention corresponding to the additional information;
Extracting target question information from the related question-answer data;
constructing inquiry question information according to the information modification intention and the target question information;
And generating the inquiry result data based on the inquiry question information and the related inquiry response data.
A3, the method for generating results according to A2, wherein the step of obtaining the information modification intention corresponding to the additional information includes:
Extracting keywords from the overtime information to obtain an overtime keyword set;
carrying out weight analysis on the additional keyword set to obtain a keyword weight sequence;
and matching in a preset knowledge base according to the keyword weight sequence, and determining the information modification intention corresponding to the additional information.
A4, the method for generating results according to A3, wherein the step of performing weight analysis on the additional keyword set to obtain a keyword weight sequence comprises the following steps:
acquiring a problem structure and information property corresponding to the inquiry information;
Determining the weight proportion corresponding to each additional keyword in the additional keyword set according to the problem structure and the information property;
and ordering the overtaking keywords in the overtaking keyword set based on the weight proportion to obtain a keyword weight sequence.
A5, the method for generating results according to A2, wherein the step of constructing the additional question information according to the information modification intention and the target question information comprises the following steps:
determining a problem modification location and a problem modification indication based on the information modification intent;
And adjusting the target problem information according to the problem modification position and the problem modification instruction to obtain the inquiry problem information.
A6, the result generating method of A2, the step of extracting target question information from the related question-answer data includes:
Determining the attribution field of the problem and the problem modification indication according to the information modification intention;
matching the question belonging field and the question modification instruction with the question information corresponding to each related question-answer data, and determining the matching degree corresponding to each question information;
And selecting target question information from the question information corresponding to each related question-answer data based on the matching degree.
A7, the method for generating a result according to A5, wherein the step of adjusting the target problem information according to the problem modification position and the problem modification instruction to obtain the additional problem information comprises the following steps:
Determining keywords to be modified in the target problem information according to the problem modification position;
searching a keyword set corresponding to the problem modification instruction based on the keywords to be modified;
extracting replacement keywords from the keyword set;
and adjusting the keywords to be modified in the target problem information according to the replacement keywords to obtain the inquiry problem information.
A8, the method for generating results according to A7, wherein the step of extracting the replacement keywords from the keyword set comprises the following steps:
comparing the question information corresponding to the related question-answer data with the target question information to determine a difference keyword;
Screening the keyword set according to the difference keywords to obtain a keyword set to be selected;
and extracting the replacement keywords from the keyword set to be selected.
A9, the method for generating results according to A2, wherein the step of generating the query result data based on the query question information and the related question-answer data includes:
searching in a preset knowledge base based on the inquiry question information to obtain at least one piece of answer corpus information;
Extracting keywords from the answer corpus information to obtain result keywords;
And constructing additional query result data according to the result keywords and the related question-answer data.
A10, the result generation method of A9, the step of extracting keywords from the answer corpus information to obtain result keywords, includes:
Acquiring a question keyword corresponding to the additional question information;
searching for a solution keyword corresponding to the question keyword;
and extracting keywords from the answer corpus information according to the answer keywords to obtain result keywords.
A11, the result generating method according to A10, the step of extracting the keywords of the answer corpus information according to the answer keywords to obtain result keywords, includes:
Selecting target corpus information from the at least one piece of answer corpus information according to the related question-answer data;
and extracting keywords from the target corpus information according to the answering keywords to obtain result keywords.
A12, the method for generating results according to A1, wherein the step of searching the relevant question-answer data corresponding to the additional information includes:
acquiring session identification data corresponding to the inquiry information;
searching corresponding history display results and history questioning information according to the session identification data to obtain history display data;
Searching problem information corresponding to the historical display data according to the result response identification corresponding to the historical display data;
and constructing relevant question-answer data according to the history display data and the question information.
A13, the result generation method according to any one of A1-A12, wherein the step of acquiring the challenge information includes:
the method comprises the steps of acquiring the inquiry information input by a user through an interactive input box or acquiring the inquiry information input by the user through an inquiry prompt button.
A14, the result generation method of any one of A1-A12, wherein the interactive input box and/or the inquiry prompt button comprises at least one of the following cases:
The interactive input box is displayed independently;
the interactive input box is displayed corresponding to the interactive topics;
Displaying in association with question-answer pairs;
displaying in association with the problem;
Presentation associated with the answer;
and after receiving the operation of selecting the page content by the user, associating and displaying with the selected content.
The application also discloses a B15 and a result generating device, wherein the result generating device comprises the following modules:
The acquisition module is used for acquiring the inquiry information;
the searching module is used for searching the related question-answer data corresponding to the additional information;
and the generating module is used for generating the inquiry result data based on the inquiry information and the related inquiry response data.
The result generating device according to B16, wherein the generating module is further configured to obtain an information modification intention corresponding to the query information, extract target question information from the relevant question-answer data, construct query question information according to the information modification intention and the target question information, and generate query result data based on the query question information and the relevant question-answer data.
The result generating device as described in the B17, the generating module is further configured to extract keywords from the query information to obtain a query keyword set, perform weight analysis on the query keyword set to obtain a keyword weight sequence, and determine an information modification intention corresponding to the query information according to matching of the keyword weight sequence in a preset knowledge base.
The result generating device as described in B18, wherein the generating module is further configured to obtain a question structure and an information property corresponding to the query information, determine a weight ratio corresponding to each query keyword in the query keyword set according to the question structure and the information property, and sort the query keywords in the query keyword set based on the weight ratio to obtain a keyword weight sequence.
The application also discloses a C19 and a result generating device, wherein the result generating device comprises a processor, a memory and a result generating program which is stored on the memory and can run on the processor, and the result generating program realizes the steps of the result generating method when being executed by the processor.
The application also discloses D20, a computer readable storage medium, wherein the computer readable storage medium stores a result generation program, and the result generation program realizes the steps of the result generation method when being executed.
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310975387.1A CN119474285A (en) | 2023-08-03 | 2023-08-03 | Result generation method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310975387.1A CN119474285A (en) | 2023-08-03 | 2023-08-03 | Result generation method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN119474285A true CN119474285A (en) | 2025-02-18 |
Family
ID=94591023
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310975387.1A Pending CN119474285A (en) | 2023-08-03 | 2023-08-03 | Result generation method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119474285A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20250077231A1 (en) * | 2023-08-29 | 2025-03-06 | Beijing Zitiao Network Technology Co., Ltd. | Method for displaying information, computer device and storage medium |
-
2023
- 2023-08-03 CN CN202310975387.1A patent/CN119474285A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20250077231A1 (en) * | 2023-08-29 | 2025-03-06 | Beijing Zitiao Network Technology Co., Ltd. | Method for displaying information, computer device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108153876B (en) | Intelligent question and answer method and system | |
| CN110990533B (en) | Method and device for determining standard text corresponding to query text | |
| US20200081977A1 (en) | Keyword extraction method and apparatus, storage medium, and electronic apparatus | |
| WO2021159632A1 (en) | Intelligent questioning and answering method and apparatus, computer device, and computer storage medium | |
| CA2823835C (en) | Voice search and response based on relevancy | |
| CN114707000B (en) | A method, device, electronic device and storage medium for generating a question-answer library based on a knowledge graph | |
| CN112509682A (en) | Text recognition-based inquiry method, device, equipment and storage medium | |
| CN112784141A (en) | Search result quality determination method and device, storage medium and computer equipment | |
| CN104471568A (en) | Learning-Based Processing of Natural Language Problems | |
| CN112231452B (en) | Question answering method, device, equipment and storage medium based on natural language processing | |
| CN110147494B (en) | Information searching method and device, storage medium and electronic equipment | |
| CN110472136B (en) | Query result pushing method and device, storage medium and computer equipment | |
| CN110795542A (en) | Dialogue method and related device and equipment | |
| US11379527B2 (en) | Sibling search queries | |
| CN110597962A (en) | Search result display method, device, medium and electronic equipment | |
| CN109710732A (en) | Information query method, device, storage medium and electronic equipment | |
| CN109522397B (en) | Information processing method and device | |
| CN120045750A (en) | Retrieval enhancement generation method and system based on large language model | |
| CN112632246A (en) | Robot dialogue method and device based on deep learning and computer equipment | |
| CN106407316A (en) | Topic model-based software question and answer recommendation method and device | |
| CN118444895A (en) | Code prompting method | |
| CN114153946A (en) | Intelligent retrieval method, device, equipment and storage medium | |
| US12223002B2 (en) | Semantics-aware hybrid encoder for improved related conversations | |
| US20170109411A1 (en) | Assisted creation of a search query | |
| CN111192170B (en) | Question pushing method, device, equipment and computer readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination |