Question and answer topic management method and device, equipment and storage medium

Abstract

The invention discloses a question and answer topic management method and device, equipment and a storage medium, and belongs to the technical field of artificial intelligence. The method comprises the following steps: when a topic search instruction is received, determining a target topic according to the topic search instruction; determining a corresponding keyword to be identified based on the target topic; searching a historical question and answer record within a preset time range according to the to-be-identified keyword to obtain a target question and answer record matched with the to-be-identified keyword; and generating and displaying topic summary information according to the target question and answer record. In this way, when the topic search instruction is received, the target topic corresponding to the search content specified by the user is determined firstly, then the to-be-recognized keyword corresponding to the target topic is determined, and finally the historical question and answer record is queried according to the to-be-recognized keyword, so that the topic summary information is generated and displayed to the user. The questions and records with similar contents of the user are summarized and fed back based on the historical question and answer records, and the knowledge obtaining efficiency of the user is improved.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a question and answer topic management method, device, equipment and storage medium. Background Art

[0002] Currently, in programs where artificial intelligence interacts with users, it is often only able to identify and answer single questions from users. The feedback on user queries or search commands is limited to answering single questions through network searches. This makes it very inefficient for users to acquire knowledge and information, and the information they obtain is incomplete.

[0003] The above contents are only used to assist in understanding the technical solution of the present invention and do not constitute an admission that the above contents are prior art. Summary of the invention

[0004] The main purpose of the present invention is to provide a question-and-answer topic management method, device, equipment and storage medium, aiming to solve the technical problem that the existing technology can only target user queries and searches for a single question, resulting in incomplete information acquisition of similar content by users.

[0005] To achieve the above object, the present invention provides a question-and-answer topic management method, which comprises the following steps:

[0006] When receiving a topic search instruction, determining a target topic according to the topic search instruction;

[0007] Determining corresponding keywords to be identified based on the target topic;

[0008] Searching historical question and answer records within a preset time range according to the keyword to be identified, and obtaining a target question and answer record matching the keyword to be identified;

[0009] Generate and display topic summary information based on the target question and answer record.

[0010] Optionally, when receiving a topic search instruction, determining a target topic according to the topic search instruction includes:

[0011] When receiving a topic search instruction, determining instruction information according to the topic search instruction;

[0012] Obtaining a search text according to the instruction information;

[0013] A preset topic library is searched according to the search text to obtain a target topic.

[0014] Optionally, searching a preset topic library according to the search text to obtain a target topic includes:

[0015] Determining retrieval semantics according to the search text;

[0016] Each question and answer topic in the preset topic library is traversed according to the search semantics to obtain a target topic.

[0017] Optionally, searching for historical question and answer records within a preset time range according to the keyword to be identified to obtain a target question and answer record matching the keyword to be identified includes:

[0018] Query the question and answer record information within the preset time range to obtain historical question and answer records;

[0019] Query the historical question and answer records according to the to-be-identified keywords to obtain query result records;

[0020] The query result records are screened to obtain target question and answer records that semantically match the keywords to be identified.

[0021] Optionally, the step of screening the query result records to obtain target question and answer records that semantically match the keywords to be identified includes:

[0022] Determine whether each query question and answer result in the query result record has invalid semantics;

[0023] A target question and answer record matching the keyword to be identified is obtained according to the determination result, and the target question and answer record is the query question and answer result without invalid semantics.

[0024] Optionally, the determining whether each query question and answer result in the query result record has invalid semantics includes:

[0025] Determine multiple query question and answer results according to the query result records;

[0026] Query the context information of each query and answer result;

[0027] Inputting the query question and answer results and the context information into a preset language model to obtain semantic analysis information of each query question and answer result output;

[0028] It is determined whether each query and answer result has invalid semantics based on the semantic analysis information.

[0029] Optionally, determining whether each query and answer result has invalid semantics according to the semantic analysis information includes:

[0030] Determine the tone information and credibility information of each query and answer result according to the semantic analysis information, wherein the tone information includes affirmative tone, negative tone and interrogative tone;

[0031] It is determined whether each query and answer result has invalid semantics according to the tone information and the credibility information.

[0032] Optionally, generating and displaying topic summary information according to the target question and answer record includes:

[0033] Determining record semantic information according to the target question and answer record;

[0034] Determining multiple knowledge point classifications according to the recorded semantic information;

[0035] Classifying the recorded semantic information according to the knowledge point classification to obtain a plurality of knowledge point classification records;

[0036] The classified records of each knowledge point are aggregated to obtain topic summary information, and the topic summary information is displayed.

[0037] Optionally, after generating and displaying topic summary information according to the target question and answer record, the method further includes:

[0038] When receiving a topic sharing instruction, query the topic summary information according to the topic sharing instruction to obtain the sharing topic information and the sharing object;

[0039] Generate a sharing link according to the sharing topic information, wherein the sharing link includes the sharing topic information;

[0040] The sharing link is sent to the sharing object.

[0041] Optionally, after generating and displaying topic summary information according to the target question and answer record, the method further includes:

[0042] When receiving a topic forwarding instruction, determining a forwarding target question and answer record and a forwarding object according to the topic forwarding instruction;

[0043] The forwarding target question and answer record is sent to the forwarding object and displayed.

[0044] Optionally, after generating and displaying topic summary information according to the target question and answer record, the method further includes:

[0045] Upon receiving a topic editing instruction, determining the target question and answer record to be edited and the editing content information according to the topic editing instruction;

[0046] Performing text replacement on the edit target question and answer record according to the edit content information to obtain an updated question and answer record;

[0047] The topic summary information is updated according to the updated question and answer record.

[0048] Optionally, after updating the topic summary information according to the updated question and answer record, the method further includes:

[0049] Obtain updated content information of the updated topic summary information;

[0050] The historical question and answer record is updated according to the updated content information.

[0051] In addition, to achieve the above-mentioned purpose, the present invention also provides a question-and-answer topic management device, the question-and-answer topic management device comprising:

[0052] A topic determination module, configured to determine a target topic according to the topic search instruction when receiving the topic search instruction;

[0053] A keyword determination module, used to determine corresponding keywords to be identified based on the target topic;

[0054] A record query module, used to search for historical question and answer records within a preset time range according to the keyword to be identified, and obtain a target question and answer record matching the keyword to be identified;

[0055] The topic summary module is used to generate and display topic summary information based on the target question and answer record.

[0056] Optionally, the record query module is also used to query the question and answer record information within a preset time range to obtain historical question and answer records; query the historical question and answer records according to the keywords to be identified to obtain query result records; filter the query result records to obtain target question and answer records that semantically match the keywords to be identified.

[0057] Optionally, the record query module is also used to determine whether each query question and answer result in the query result record has invalid semantics; and obtain a target question and answer record matching the keyword to be identified based on the determination result, wherein the target question and answer record is the query question and answer result without invalid semantics.

[0058] Optionally, the record query module is also used to determine multiple query question and answer results based on the query result record; query the context information of each query question and answer result; input the query question and answer result and the context information into a preset language model to obtain semantic analysis information of each query question and answer result output; and determine whether each query question and answer result has invalid semantics based on the semantic analysis information.

[0059] Optionally, the record query module is also used to determine the tone information and credibility information of each query and question result based on the semantic analysis information, the tone information including affirmative tone, negative tone and interrogative tone; and judge whether each query and question result has invalid semantics based on the tone information and the credibility information.

[0060] Optionally, the topic summary module is also used to determine record semantic information based on the target question and answer record; determine multiple knowledge point classifications based on the record semantic information; classify the record semantic information according to the knowledge point classification to obtain multiple knowledge point classification records; summarize each knowledge point classification record to obtain topic summary information, and display the topic summary information.

[0061] In addition, to achieve the above-mentioned purpose, the present invention also proposes a question-and-answer topic management device, which includes: a memory, a processor, and a question-and-answer topic management program stored in the memory and running on the processor, and the question-and-answer topic management program is configured to implement the question-and-answer topic management method described above.

[0062] In addition, to achieve the above-mentioned purpose, the present invention also proposes a storage medium, on which a question-and-answer topic management program is stored, and when the question-and-answer topic management program is executed by a processor, the question-and-answer topic management method as described above is implemented.

[0063] When the present invention receives a topic search instruction, it determines a target topic according to the topic search instruction; determines a corresponding keyword to be identified based on the target topic; searches for historical question and answer records within a preset time range according to the keyword to be identified, and obtains a target question and answer record that matches the keyword to be identified; and generates and displays topic summary information according to the target question and answer record. In this way, when a topic search instruction is received, the target topic corresponding to the search content specified by the user is first determined, then the keyword to be identified corresponding to the target topic is determined, and finally the historical question and answer record is queried according to the keyword to be identified, thereby generating topic summary information for display to the user, and realizing the aggregation of user questions and records with similar content based on historical question and answer records and feeding back to the user, thereby improving the efficiency of user knowledge acquisition. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 It is a structural diagram of a question-and-answer topic management device in a hardware operating environment involved in an embodiment of the present invention;

[0065] Figure 2 This is a flow chart of the first embodiment of the question-and-answer topic management method of the present invention;

[0066] Figure 3This is a schematic diagram of topic summary information in an embodiment of the question-and-answer topic management method of the present invention;

[0067] Figure 4 This is a flow chart of a second embodiment of the question-and-answer topic management method of the present invention;

[0068] Figure 5 It is a flowchart of the third embodiment of the question-and-answer topic management method of the present invention;

[0069] Figure 6 It is a structural block diagram of the first embodiment of the question-and-answer topic management device of the present invention.

[0070] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0071] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0072] Reference Figure 1 , Figure 1 A schematic diagram of the structure of a question-and-answer topic management device in a hardware operating environment according to an embodiment of the present invention.

[0073] like Figure 1 As shown, the question-and-answer topic management device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (Wireless-Fidelity, Wi-Fi) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM) memory, or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk memory. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0074] Those skilled in the art will understand that Figure 1 The structure shown in the figure does not constitute a limitation on the question-and-answer topic management device, and may include more or less components than those shown in the figure, or combine certain components, or arrange the components differently.

[0075] like Figure 1 As shown, the memory 1005 as a storage medium may include an operating system, a network communication module, a user interface module, and a question-and-answer topic management program.

[0076] exist Figure 1 In the question-and-answer topic management device shown, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the question-and-answer topic management device of the present invention can be set in the question-and-answer topic management device, and the question-and-answer topic management device calls the question-and-answer topic management program stored in the memory 1005 through the processor 1001, and executes the question-and-answer topic management method provided by the embodiment of the present invention.

[0077] The embodiment of the present invention provides a question-and-answer topic management method, referring to Figure 2 , Figure 2 This is a flow chart of a first embodiment of a question-and-answer topic management method of the present invention.

[0078] In this embodiment, the question and answer topic management method includes the following steps:

[0079] Step S10: upon receiving a topic search instruction, determining a target topic according to the topic search instruction.

[0080] In this embodiment, the execution subject of this embodiment may be the question-and-answer topic management device, which has functions such as data processing, data communication, and program execution, and the question-and-answer topic management device may be a server, an intelligent terminal, or a computer. Of course, it may also be other devices with similar functions, and this implementation condition does not limit this. For ease of explanation, this implementation is described by taking the question-and-answer topic management device as an example.

[0081] It should be noted that in order to improve information processing capabilities, in some embodiments, an intelligent assistant can be installed on the terminal device. The intelligent assistant can be a program built based on the natural language processing technology of the Generative Pre-trained Transformer (GPT) model. The intelligent assistant can receive the user's input text, parse the input text into a computer-understandable data format, and then use the pre-trained neural network model to generate response text.

[0082] In the specific implementation, the intelligent assistant uses the neural network in deep learning technology and trains through a large amount of corpus data, so that it can learn the structure, grammatical rules and semantic information of the language. After the user enters the text, the intelligent assistant will first segment and parse the text, convert it into a computer-readable vector form, and then send it to the pre-trained neural network model for inference. During the inference process, the intelligent assistant will predict the most likely next response based on the text entered by the user and the previous context. This prediction process is based on the model's learning of a large amount of corpus data, so it can largely restore the way humans express natural language and generate highly coherent and natural response text. Finally, the intelligent assistant returns the generated response text to the user to complete a dialogue interaction. Throughout the process, the intelligent assistant will continue to learn and optimize to provide more accurate and user-friendly answers.

[0083] It should be understood that the topic search instruction refers to an instruction triggered by the user through the dialogue interface or the search interface, which can be an instruction in the form of voice, text or other forms. When a topic search instruction sent by a user is received, the topic search instruction is first parsed and identified to determine the target topic that is closest to and consistent with the user's search content. The target topic refers to an instruction set containing multiple preset questions, such as: knowledge related to a movie, knowledge related to a celebrity, etc.

[0084] Furthermore, in order to accurately determine the target topic, step S10 includes: upon receiving a topic search instruction, determining instruction information according to the topic search instruction; obtaining a search text according to the instruction information; and searching a preset topic library according to the search text to obtain the target topic.

[0085] In a specific implementation, after receiving the topic search instruction, the instruction information is first determined, including but not limited to the sending time, trigger form, content and other related information of the instruction. Then, the instruction information is extracted and converted, and the search content sent by the user through the topic search instruction is converted into text, that is, the search text is obtained.

[0086] It should be noted that after obtaining the search text, the search text is imported into the preset topic library, and the target topic corresponding to the search text can be queried. Among them, the preset topic library is a collection of all question and answer topics that are pre-stored and maintained, and the question and answer topic is a collection of question and answer records and contents that are similar to the subject and content of each question and are summarized and stored.

[0087] In this way, it is achieved that the target topic corresponding to the search text and the topic search instruction is determined by performing text conversion and extraction on the topic search instruction and then querying the preset topic library.

[0088] Furthermore, in order to accurately search for the target topic, the preset topic library is searched according to the search text, and the step of obtaining the target topic includes: determining the retrieval semantics according to the search text; traversing each question and answer topic in the preset topic library according to the retrieval semantics to obtain the target topic.

[0089] It should be understood that retrieval semantics refers to the information determined based on the search text. By importing the search text into the intelligent assistant, semantic analysis can be performed directly through the neural network model to generate retrieval semantics.

[0090] In the specific implementation, after the search semantics are determined and generated, the answer topics in the preset topic library are traversed through the search semantics, and then the question and answer topic that is most appropriate and has the highest similarity to the search semantic content is taken as the target topic.

[0091] In this way, the content similarity matching of the search text is achieved, thereby determining the target topic that is closest to the content searched by the user.

[0092] Step S20: Determine corresponding keywords to be identified based on the target topic.

[0093] It should be noted that after the target topic is determined, the pre-stored keywords to be identified corresponding to the target topic are called, where the keywords to be identified can be branch information corresponding to the target topic, or related attributes. For example, when the target topic is a certain film or television work, the keywords to be identified can include but are not limited to the starring role, release date, director, duration and other related information of the film or television work.

[0094] Step S30: searching historical question and answer records within a preset time range according to the keyword to be identified, and obtaining a target question and answer record matching the keyword to be identified.

[0095] It should be understood that after the keywords to be identified are determined, the historical question and answer records are queried, so that the conversation records that match the keywords to be identified and have relevance can be extracted from the historical question and answer records, namely the target question and answer records.

[0096] Step S40: Generate and display topic summary information based on the target question and answer record.

[0097] In the specific implementation, refer to Figure 3 This is a schematic diagram for displaying topic summary information. The topic summary information refers to the content displayed to the user generated by the target answer record, and specifically can be classified summary information determined according to the knowledge point classification records.

[0098] Furthermore, in order to generate topic summary information with richer content to display to users, step S40 includes: determining record semantic information based on the target question and answer record; determining multiple knowledge point classifications based on the record semantic information; classifying the record semantic information according to the knowledge point classification to obtain multiple knowledge point classification records; summarizing the knowledge point classification records to obtain topic summary information, and displaying the topic summary information.

[0099] It should be noted that the semantics of each dialogue record is first extracted according to the target question and answer record to obtain the record semantic information, and then the record semantic information is classified. The specific classification method is through knowledge point classification.

[0100] It should be understood that knowledge points refer to the classification of record semantic information with the same semantics or consistent content themes. For example, when the themes of multiple record semantic information are the male lead of a certain movie, the male lead of the movie is taken as a knowledge point, and then the target question and answer records with the theme of the male lead of the movie are classified into one category according to the knowledge point classification, and a knowledge point classification record can be obtained. Similarly, multiple knowledge point classification records can be obtained.

[0101] In a specific implementation, after obtaining multiple knowledge point classification records, the classification records of each knowledge point are summarized according to the classification results, so that record information classified according to hierarchical directories and nodes can be obtained, and then displayed as topic summary information.

[0102] In this way, the target question and answer records can be accurately sorted and displayed according to the knowledge point classification, which improves the amount of information obtained and makes it more organized.

[0103] Furthermore, in order to facilitate users to share topic summary information, after step S40, it also includes: when receiving a topic sharing instruction, querying the topic summary information according to the topic sharing instruction to obtain the sharing topic information and the sharing object; generating a sharing link according to the sharing topic information, the sharing link includes the sharing topic information; and sending the sharing link to the sharing object.

[0104] It should be noted that the topic sharing instruction is an instruction issued by the user to share the topic summary information through the keyboard, touch screen or voice, specifically to share the topic summary information to other users, accounts or devices in the form of a link.

[0105] It should be understood that the sharing topic information refers to the information that needs to be shared by the user based on the topic summary information query, and the sharing object refers to the target object that the user wants to share with, which can be other accounts or devices.

[0106] In a specific implementation, after the sharing topic information is determined, a sharing link is generated based on the sharing topic information. The sharing link contains a web address, in which a display page containing the sharing topic information is generated. The sharing link is then sent to the sharing object, thereby realizing the selected sharing of the topic summary information.

[0107] In this way, the sharing function of the topic summary information is realized after it is generated.

[0108] Furthermore, in order to facilitate users to forward topic summary information, after step S40, it also includes: when receiving a topic forwarding instruction, determining the forwarding target question and answer record and the forwarding object according to the topic forwarding instruction; sending and displaying the forwarding target question and answer record to the forwarding object.

[0109] It should be noted that the topic forwarding instruction can also be issued by the user through the keyboard, touch screen or voice. The topic forwarding instruction refers to the user directly forwarding the target question and answer record in the topic summary information through the system or APP through text. The target question and answer record refers to the question and answer record selected by the user in the topic summary information.

[0110] It should be understood that after the forwarding target question and answer record is determined, the forwarding target question and answer record is directly sent to the chat of the forwarding object within the system.

[0111] In this way, users can quickly forward topic summary information within the APP and system.

[0112] This embodiment determines the target topic according to the topic search instruction when receiving the topic search instruction; determines the corresponding keywords to be identified based on the target topic; searches for historical question and answer records within a preset time range according to the keywords to be identified to obtain target question and answer records that match the keywords to be identified; and generates and displays topic summary information according to the target question and answer records. In this way, when receiving the topic search instruction, the target topic corresponding to the search content specified by the user is first determined, then the keywords to be identified corresponding to the target topic are determined, and finally the historical question and answer records are queried according to the keywords to be identified, thereby generating topic summary information for display to the user, and realizing the aggregation of user questions and records with similar content based on historical question and answer records and feeding back to the user, thereby improving the efficiency of user knowledge acquisition.

[0113] refer to Figure 4 , Figure 4 This is a flow chart of a second embodiment of a question-and-answer topic management method of the present invention.

[0114] Based on the first embodiment described above, the question and answer topic management method of this embodiment includes, in step S30:

[0115] Step S301: query the question and answer record information within a preset time range to obtain historical question and answer records.

[0116] It should be noted that the preset time range refers to a pre-set time period, which refers to a time period defined from the current moment forward, for example: 1 hour ago, a week ago, a day ago, etc.

[0117] It should be understood that the question and answer record information refers to all historical questions, answers, and search records between the user and the intelligent assistant.

[0118] In a specific implementation, the historical question and answer records refer to all question and answer record information within a preset time range from the current moment forward.

[0119] Step S302: query the historical question and answer records according to the to-be-identified keyword to obtain a query result record.

[0120] It should be noted that the historical question and answer records contain text information, and then the keywords to be identified are compared and queried with the text in the historical question and answer records, so that relevant records can be found as query result records.

[0121] Step S303: Filter the query result records to obtain target question and answer records that semantically match the keyword to be identified.

[0122] It should be understood that after the query result records are obtained, the query result records are further screened so as to determine the target question and answer records that semantically match the keywords to be identified.

[0123] Furthermore, in order to obtain the target question and answer record, step S301 includes: determining whether each query question and answer result in the query result record has invalid semantics; obtaining the target question and answer record matching the keyword to be identified based on the determination result, and the target question and answer record is the query question and answer result without invalid semantics.

[0124] In a specific implementation, invalid semantics refers to question and answer records that have no practical meaning, uncertain or ambiguous semantics.

[0125] It should be noted that the judgment result refers to the judgment result of each historical record in the query result record. Each historical record includes two judgment results: the presence of invalid semantics and the absence of invalid semantics. Then the query question and answer result without invalid semantics is used as the target question and answer record.

[0126] In this way, it is possible to filter out the target question and answer records by judging whether there are invalid semantics.

[0127] Furthermore, in order to accurately determine whether there is invalid semantics, the step of determining whether each query question and answer result in the query result record has invalid semantics includes: determining multiple query question and answer results based on the query result record; querying the context information of each query question and answer result; inputting the query question and answer result and the context information into a preset language model to obtain semantic analysis information of each query question and answer result output; and determining whether each query question and answer result has invalid semantics based on the semantic analysis information.

[0128] It should be understood that first, all historical records are extracted from the query result records, and separated according to each message sent, to obtain multiple query and answer results, and then each query and answer result is combined with the two message records sent before and after it as context information. After the context information is obtained, the context information and the query and answer result are input into the preset language model, where the preset language model refers to the language model in the intelligent assistant, which can be combined with the context information to determine the output result of the semantic analysis of each query and answer result, that is, the semantic analysis information.

[0129] In a specific implementation, after the semantic analysis information is obtained, it is determined based on the semantic analysis information whether each query and answer result has invalid semantics.

[0130] In this way, each query and answer result is analyzed based on the preset language model and context information to obtain the specific semantics of each query and answer result, so that it is possible to accurately determine whether there is invalid semantics.

[0131] Furthermore, in order to determine whether there are invalid semantics based on semantic analysis information, the step of judging whether there are invalid semantics in each query and question result according to the semantic analysis information includes: determining the tone information and credibility information of each query and question result according to the semantic analysis information, the tone information including affirmative tone, negative tone and interrogative tone; judging whether there are invalid semantics in each query and question result according to the tone information and the credibility information.

[0132] It should be noted that the semantic analysis information is first extracted to obtain the tone information and credibility information, wherein the tone information includes affirmative tone, negative tone and interrogative tone. The specific judgment method can be to determine it as one of affirmative, negative and interrogative tone according to modal particles, punctuation marks, etc.

[0133] It should be understood that the credibility information refers to the degree of certainty in all messages answered by the intelligent assistant and input by the user. For example, words such as "I think" and "maybe" can be determined as low credibility, and "certainly" and "certain" are used as high credibility. In this way, the credibility of each query and answer result is configured as low or high.

[0134] In a specific implementation, after the tone information and credibility information are obtained, the query and answer records with negative and interrogative tone information or low credibility are determined to be invalid semantics, otherwise there is no invalid semantics.

[0135] In this way, it is possible to accurately determine whether invalid semantics exist based on tone information and credibility information.

[0136] In this embodiment, historical question and answer records are obtained by querying question and answer record information within a preset time range; querying the historical question and answer records according to the keywords to be identified to obtain query result records; and filtering the query result records to obtain target question and answer records that semantically match the keywords to be identified. In this way, the two steps of querying and filtering the question and answer record information are implemented, and the target question and answer records that accurately match the content and semantics are queried, which facilitates the subsequent generation of accurate topic summary information.

[0137] refer to Figure 5 , Figure 5 4 is a flow chart of a third embodiment of a question-and-answer topic management method according to the present invention.

[0138] Based on the first embodiment described above, the question and answer topic management method of this embodiment further includes, after step S40:

[0139] Step S401: upon receiving a topic editing instruction, determining the target question and answer record to be edited and the editing content information according to the topic editing instruction.

[0140] It should be noted that when the received instruction is determined to be a topic editing instruction, the user's selected target question and answer record and the specific editing content are first determined according to the topic editing instruction. The target question and answer record is a specific question and answer record in the topic summary information.

[0141] Step S402: replacing the text of the edit target question and answer record according to the edit content information to obtain an updated question and answer record.

[0142] It should be understood that after the edit content information is determined, the edit content information is used to replace the text at the corresponding position in the edit target question and answer record, so that the information in the question and answer record is updated to obtain an updated question and answer record.

[0143] Step S403: updating the topic summary information according to the updated question and answer record.

[0144] In a specific implementation, after obtaining the updated question and answer record, the topic summary information is updated again according to the updated question and answer record, so that the updated topic summary information finally displayed better meets the needs of users and improves the flexibility of content display.

[0145] Furthermore, in order to keep the historical question and answer records updated after the topic summary information is updated, after step S403, it also includes: obtaining updated content information of the updated topic summary information; and updating the historical question and answer records according to the updated content information.

[0146] It should be noted that after updating the topic summary information, the updated content in the topic summary information is obtained, and then the updated content information is updated to the historical question and answer record, so that the next topic search and generation of topic summary information can be adjusted according to user needs.

[0147] In this way, real-time updating of historical question and answer records is achieved, facilitating real-time search and query by users.

[0148] This embodiment determines the target question and answer record and the edited content information according to the topic editing instruction when receiving the topic editing instruction; replaces the text of the target question and answer record according to the edited content information to obtain an updated question and answer record; and updates the topic summary information according to the updated question and answer record. In this way, the topic summary information is updated, so that the updated topic summary information finally displayed better meets the needs of users and improves the flexibility of content display.

[0149] In addition, an embodiment of the present invention further provides a storage medium, on which a question-and-answer topic management program is stored. When the question-and-answer topic management program is executed by a processor, the steps of the question-and-answer topic management method described above are implemented.

[0150] Since the storage medium adopts all the technical solutions of all the above embodiments, it has at least all the beneficial effects brought by the technical solutions of the above embodiments, which will not be described one by one here.

[0151] Reference Figure 6 , Figure 6 It is a structural block diagram of the first embodiment of the question-and-answer topic management device of the present invention.

[0152] like Figure 6 As shown, the question-and-answer topic management device proposed in the embodiment of the present invention includes:

[0153] The topic determination module 10 is used to determine a target topic according to the topic search instruction when receiving the topic search instruction.

[0154] The keyword determination module 20 is used to determine corresponding keywords to be identified based on the target topic.

[0155] The record query module 30 is used to search for historical question and answer records within a preset time range according to the keyword to be identified, and obtain a target question and answer record matching the keyword to be identified.

[0156] The topic summary module 40 is used to generate and display topic summary information according to the target question and answer record.

[0157] This embodiment determines the target topic according to the topic search instruction when receiving the topic search instruction; determines the corresponding keywords to be identified based on the target topic; searches for historical question and answer records within a preset time range according to the keywords to be identified to obtain target question and answer records that match the keywords to be identified; and generates and displays topic summary information according to the target question and answer records. In this way, when receiving the topic search instruction, the target topic corresponding to the search content specified by the user is first determined, then the keywords to be identified corresponding to the target topic are determined, and finally the historical question and answer records are queried according to the keywords to be identified, thereby generating topic summary information for display to the user, and realizing the aggregation of user questions and records with similar content based on historical question and answer records and feeding back to the user, thereby improving the efficiency of user knowledge acquisition.

[0158] In one embodiment, the topic determination module 10 is further used to determine instruction information according to the topic search instruction when receiving the topic search instruction; obtain search text according to the instruction information; and search a preset topic library according to the search text to obtain a target topic.

[0159] In one embodiment, the topic determination module 10 is further used to determine the search semantics according to the search text; and traverse each question and answer topic in the preset topic library according to the search semantics to obtain a target topic.

[0160] In one embodiment, the record query module 30 is also used to query the question and answer record information within a preset time range to obtain historical question and answer records; query the historical question and answer records according to the keywords to be identified to obtain query result records; filter the query result records to obtain target question and answer records that semantically match the keywords to be identified.

[0161] In one embodiment, the record query module 30 is also used to determine whether each query question and answer result in the query result record has invalid semantics; based on the determination result, a target question and answer record matching the keyword to be identified is obtained, and the target question and answer record is the query question and answer result without invalid semantics.

[0162] In one embodiment, the record query module 30 is also used to determine multiple query question and answer results based on the query result record; query the context information of each query question and answer result; input the query question and answer result and the context information into a preset language model to obtain semantic analysis information of each query question and answer result output; and determine whether each query question and answer result has invalid semantics based on the semantic analysis information.

[0163] In one embodiment, the record query module 30 is also used to determine the tone information and credibility information of each query and question result based on the semantic analysis information, and the tone information includes affirmative tone, negative tone and interrogative tone; and judge whether each query and question result has invalid semantics based on the tone information and the credibility information.

[0164] In one embodiment, the topic aggregation module 40 is also used to determine record semantic information based on the target question and answer record; determine multiple knowledge point classifications based on the record semantic information; classify the record semantic information according to the knowledge point classification to obtain multiple knowledge point classification records; aggregate each knowledge point classification record to obtain topic summary information, and display the topic summary information.

[0165] In one embodiment, the topic aggregation module 40 is also used to query the topic aggregation information according to the topic sharing instruction when receiving the topic sharing instruction, to obtain the sharing topic information and the sharing object; generate a sharing link according to the sharing topic information, the sharing link includes the sharing topic information; and send the sharing link to the sharing object.

[0166] In one embodiment, the topic aggregation module 40 is further used to determine the forwarding target question and answer record and the forwarding object according to the topic forwarding instruction when receiving the topic forwarding instruction; and send and display the forwarding target question and answer record to the forwarding object.

[0167] In one embodiment, the topic aggregation module 40 is also used to determine the editing target question and answer record and editing content information according to the topic editing instruction when receiving the topic editing instruction; perform text replacement on the editing target question and answer record according to the editing content information to obtain an updated question and answer record; and update the topic aggregation information according to the updated question and answer record.

[0168] In one embodiment, the topic summary module 40 is further configured to obtain updated content information of the updated topic summary information; and update the historical question and answer record according to the updated content information.

[0169] It should be understood that the above is only an example and does not constitute any limitation on the technical solution of the present invention. In specific applications, technicians in this field can make settings as needed, and the present invention does not limit this.

[0170] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of the present invention. In practical applications, technicians in this field can select part or all of them according to actual needs to achieve the purpose of the present embodiment, and no limitation is made here.

[0171] In addition, for technical details not fully described in this embodiment, reference can be made to the question and answer topic management method provided in any embodiment of the present invention, and will not be repeated here.

[0172] In addition, it should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0173] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0174] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory (ROM) / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0175] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

[0176] The present invention discloses A1, a question and answer topic management method, the question and answer topic management method comprising:

[0177] When receiving a topic search instruction, determining a target topic according to the topic search instruction;

[0178] Determining corresponding keywords to be identified based on the target topic;

[0179] Searching historical question and answer records within a preset time range according to the keyword to be identified, and obtaining a target question and answer record matching the keyword to be identified;

[0180] Generate and display topic summary information based on the target question and answer record.

[0181] A2. The question and answer topic management method as described in A1, wherein upon receiving a topic search instruction, determining a target topic according to the topic search instruction comprises:

[0182] When receiving a topic search instruction, determining instruction information according to the topic search instruction;

[0183] Obtaining a search text according to the instruction information;

[0184] A preset topic library is searched according to the search text to obtain a target topic.

[0185] A3. The question-and-answer topic management method as described in A2, wherein the step of searching a preset topic library according to the search text to obtain a target topic comprises:

[0186] Determining retrieval semantics according to the search text;

[0187] Each question and answer topic in the preset topic library is traversed according to the search semantics to obtain a target topic.

[0188] A4, as described in A1, the question and answer topic management method, wherein searching for historical question and answer records within a preset time range according to the keyword to be identified to obtain a target question and answer record matching the keyword to be identified, comprises:

[0189] Query the question and answer record information within the preset time range to obtain historical question and answer records;

[0190] Query the historical question and answer records according to the to-be-identified keywords to obtain query result records;

[0191] The query result records are screened to obtain target question and answer records that semantically match the keywords to be identified.

[0192] A5. The question-and-answer topic management method as described in A4, wherein the query result records are screened to obtain target question-and-answer records that semantically match the keywords to be identified, including:

[0193] Determine whether each query question and answer result in the query result record has invalid semantics;

[0194] A target question and answer record matching the keyword to be identified is obtained according to the determination result, and the target question and answer record is the query question and answer result without invalid semantics.

[0195] A6. The question and answer topic management method as described in A5, wherein the step of determining whether each query and answer result in the query result record has invalid semantics comprises:

[0196] Determine multiple query question and answer results according to the query result records;

[0197] Query the context information of each query and answer result;

[0198] Inputting the query question and answer results and the context information into a preset language model to obtain semantic analysis information of each query question and answer result output;

[0199] It is determined whether each query and answer result has invalid semantics based on the semantic analysis information.

[0200] A7. The question and answer topic management method as described in A6, wherein determining whether each query and answer result has invalid semantics based on the semantic analysis information comprises:

[0201] Determine the tone information and credibility information of each query and answer result according to the semantic analysis information, wherein the tone information includes affirmative tone, negative tone and interrogative tone;

[0202] It is determined whether each query and answer result has invalid semantics according to the tone information and the credibility information.

[0203] A8. The question and answer topic management method as described in any one of A1 to A7, wherein the generating and displaying of topic summary information according to the target question and answer record comprises:

[0204] Determining record semantic information according to the target question and answer record;

[0205] Determining multiple knowledge point classifications according to the recorded semantic information;

[0206] Classifying the recorded semantic information according to the knowledge point classification to obtain a plurality of knowledge point classification records;

[0207] The classified records of each knowledge point are aggregated to obtain topic summary information, and the topic summary information is displayed.

[0208] A9. The question and answer topic management method as described in any one of A1 to A7, after generating and displaying topic summary information according to the target question and answer record, further comprising:

[0209] When receiving a topic sharing instruction, query the topic summary information according to the topic sharing instruction to obtain the sharing topic information and the sharing object;

[0210] Generate a sharing link according to the sharing topic information, wherein the sharing link includes the sharing topic information;

[0211] The sharing link is sent to the sharing object.

[0212] A10. The question and answer topic management method as described in any one of A1 to A7, after generating and displaying topic summary information according to the target question and answer record, further comprising:

[0213] When receiving a topic forwarding instruction, determining a forwarding target question and answer record and a forwarding object according to the topic forwarding instruction;

[0214] The forwarding target question and answer record is sent to the forwarding object and displayed.

[0215] A11. The question and answer topic management method as described in any one of A1 to A7, after generating and displaying topic summary information according to the target question and answer record, further comprising:

[0216] Upon receiving a topic editing instruction, determining the target question and answer record to be edited and the editing content information according to the topic editing instruction;

[0217] Performing text replacement on the edit target question and answer record according to the edit content information to obtain an updated question and answer record;

[0218] The topic summary information is updated according to the updated question and answer record.

[0219] A12. The question and answer topic management method as described in A11, after updating the topic summary information according to the updated question and answer record, further comprising:

[0220] Obtain updated content information of the updated topic summary information;

[0221] The historical question and answer record is updated according to the updated content information.

[0222] The present invention also discloses B13, a question and answer topic management device, the question and answer topic management device comprising:

[0223] A topic determination module, configured to determine a target topic according to the topic search instruction when receiving the topic search instruction;

[0224] A keyword determination module, used to determine corresponding keywords to be identified based on the target topic;

[0225] A record query module, used to search for historical question and answer records within a preset time range according to the keyword to be identified, and obtain a target question and answer record matching the keyword to be identified;

[0226] The topic summary module is used to generate and display topic summary information based on the target question and answer record.

[0227] B14. In the question and answer topic management device as described in B13, the record query module is further used to query the question and answer record information within a preset time range to obtain historical question and answer records; query the historical question and answer records according to the keywords to be identified to obtain query result records; and filter the query result records to obtain target question and answer records that semantically match the keywords to be identified.

[0228] B15. In the question and answer topic management device as described in B14, the record query module is also used to determine whether each query and question result in the query result record has invalid semantics; and obtain a target question and answer record matching the keyword to be identified based on the determination result, wherein the target question and answer record is the query and question result without invalid semantics.

[0229] B16. In the question and answer topic management device as described in B15, the record query module is also used to determine multiple query and answer results based on the query result record; query the context information of each query and answer result; input the query and answer result and the context information into a preset language model to obtain semantic analysis information of each query and answer result output; and determine whether each query and answer result has invalid semantics based on the semantic analysis information.

[0230] B17. In the question and answer topic management device as described in B16, the record query module is also used to determine the tone information and credibility information of each query and answer result based on the semantic analysis information, the tone information includes affirmative tone, negative tone and interrogative tone; and judge whether each query and answer result has invalid semantics based on the tone information and the credibility information.

[0231] B18. In the question and answer topic management device as described in B13, the topic aggregation module is further used to determine record semantic information based on the target question and answer record; determine multiple knowledge point classifications based on the record semantic information; classify the record semantic information according to the knowledge point classification to obtain multiple knowledge point classification records; aggregate the knowledge point classification records to obtain topic aggregation information, and display the topic aggregation information.

[0232] The present invention also discloses C19, a question and answer topic management device, which includes: a memory, a processor, and a question and answer topic management program stored in the memory and running on the processor, and the question and answer topic management program is configured to implement the question and answer topic management method as described above.

[0233] The present invention also discloses D20, a storage medium, on which a question-and-answer topic management program is stored, and when the question-and-answer topic management program is executed by a processor, the question-and-answer topic management method as described above is implemented.

Claims

1. A question and answer topic management method, characterized in that: The question-and-answer topic management method comprises: When receiving a topic search instruction, determining a target topic according to the topic search instruction; Determining corresponding keywords to be identified based on the target topic; Searching historical question and answer records within a preset time range according to the keyword to be identified, and obtaining a target question and answer record matching the keyword to be identified; Generate and display topic summary information based on the target question and answer record.

2. The question and answer topic management method according to claim 1, characterized in that: When receiving a topic search instruction, determining a target topic according to the topic search instruction includes: When receiving a topic search instruction, determining instruction information according to the topic search instruction; Obtaining a search text according to the instruction information; A preset topic library is searched according to the search text to obtain a target topic.

3. The question and answer topic management method according to claim 2, characterized in that: The step of searching a preset topic library according to the search text to obtain a target topic includes: Determining retrieval semantics according to the search text; Each question and answer topic in the preset topic library is traversed according to the search semantics to obtain a target topic.

4. The question and answer topic management method according to claim 1, characterized in that: The step of searching for historical question and answer records within a preset time range according to the keyword to be identified to obtain a target question and answer record matching the keyword to be identified includes: Query the question and answer record information within the preset time range to obtain historical question and answer records; Query the historical question and answer records according to the to-be-identified keywords to obtain query result records; The query result records are screened to obtain target question and answer records that semantically match the keywords to be identified.

5. The question and answer topic management method according to claim 4, characterized in that: The step of screening the query result records to obtain target question and answer records that semantically match the keywords to be identified includes: Determine whether each query question and answer result in the query result record has invalid semantics; A target question and answer record matching the keyword to be identified is obtained according to the determination result, and the target question and answer record is the query question and answer result without invalid semantics.

6. The question and answer topic management method according to claim 5, characterized in that: The determining whether each query question and answer result in the query result record has invalid semantics includes: Determine multiple query question and answer results according to the query result records; Query the context information of each query and answer result; Inputting the query question and answer results and the context information into a preset language model to obtain semantic analysis information of each query question and answer result output; It is determined whether each query and answer result has invalid semantics based on the semantic analysis information.

7. The question and answer topic management method according to claim 6, characterized in that: The determining whether each query and answer result has invalid semantics according to the semantic analysis information includes: Determine the tone information and credibility information of each query and answer result according to the semantic analysis information, wherein the tone information includes affirmative tone, negative tone and interrogative tone; It is determined whether each query and answer result has invalid semantics according to the tone information and the credibility information.

8. A question and answer topic management device, characterized in that: The question-and-answer topic management device comprises: A topic determination module, configured to determine a target topic according to the topic search instruction when receiving the topic search instruction; A keyword determination module, used to determine corresponding keywords to be identified based on the target topic; A record query module, used to search for historical question and answer records within a preset time range according to the keyword to be identified, and obtain a target question and answer record matching the keyword to be identified; The topic summary module is used to generate and display topic summary information based on the target question and answer record.

9. A question and answer topic management device, characterized in that: The question-and-answer topic management device comprises: a memory, a processor, and a question-and-answer topic management program stored in the memory and running on the processor, wherein the question-and-answer topic management program is configured to implement the question-and-answer topic management method according to any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium stores a question-and-answer topic management program, and when the question-and-answer topic management program is executed by the processor, the question-and-answer topic management method according to any one of claims 1 to 7 is implemented.

Images