Topic processing method and device, equipment and storage medium

Abstract

The invention belongs to the field of computers, and discloses a topic processing method and device, equipment and a storage medium. The method comprises the steps that in response to a triggered topic processing instruction, a processing type and dialogue information corresponding to the topic processing instruction are determined, and the dialogue information comprises at least one piece of question and answer information; determining whether the dialogue information is associated with webpage information or not; determining topic information to be processed according to the webpage information, the dialogue information and the association relationship between the dialogue information and the webpage information when the association relationship between the dialogue information and the webpage information is determined; and performing topic processing on the to-be-processed topic information according to the processing type. When the topic processing instruction is received, topic processing can be carried out on the to-be-processed topic information according to the webpage information, the dialogue information and the incidence relation between the dialogue information and the webpage information. A user can be helped to better manage topic information, and the topic processing efficiency of the user is improved.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a topic processing method, device, equipment and storage medium. Background Art

[0002] With the continuous advancement of computer technology, the automation and intelligence of computer systems are constantly improving. More and more dialogue systems are being used in production and life.

[0003] When a dialogue system interacts with an interactive object, the interactive object (user) can initiate a topic (ask a question) and the dialogue system can discuss (answer) the topic. Alternatively, multiple users can interact with each other through the dialogue system. However, the dialogue management provided by the dialogue system generally only supports viewing and deleting content one by one, and the utilization rate of the dialogue content generated in the topic discussion is not high. In order to improve the user's application experience and stimulate the user's desire to talk, a topic processing method applied to the dialogue system is needed.

[0004] 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

[0005] The main purpose of the present invention is to provide a topic processing method, device, equipment and storage medium, aiming to solve the technical problem that the existing technology cannot efficiently manage topic information and the utilization rate of topic information generated in topic discussions is low.

[0006] To achieve the above object, the present invention provides a topic processing method, which comprises the following steps:

[0007] In response to the triggered topic processing instruction, determining a processing type and dialogue information corresponding to the topic processing instruction, wherein the dialogue information includes at least one question and answer information;

[0008] Determining whether the conversation information is associated with the webpage information;

[0009] When it is determined that the conversation information and the web page information are associated, determining the topic information to be processed according to the web page information, the conversation information, and the association between the conversation information and the web page information;

[0010] Perform topic processing on the topic information to be processed according to the processing type.

[0011] Optionally, the step of performing topic processing on the topic information to be processed according to the processing type includes:

[0012] Determining topic processing features corresponding to the processing type;

[0013] extracting topic processing information from the topic information to be processed based on the topic processing feature;

[0014] The topic information to be processed is processed according to the topic processing information and the processing type.

[0015] Optionally, the step of performing topic processing on the topic information to be processed according to the processing type includes:

[0016] When the processing type is topic forwarding, determining a forwarding target according to the topic processing instruction;

[0017] The to-be-processed topic information is forwarded to the forwarding target.

[0018] Optionally, the step of forwarding the to-be-processed topic information to the forwarding target includes:

[0019] Determine a topic forwarding method corresponding to the forwarding target;

[0020] When the topic forwarding mode is link forwarding, obtaining a topic link corresponding to the topic information to be processed;

[0021] The topic link is sent to the forwarding target, and the forwarding target is used to extract the to-be-processed topic information based on the topic link or participate in the target topic corresponding to the to-be-processed topic information.

[0022] Optionally, the step of performing topic processing on the topic information to be processed according to the processing type includes:

[0023] When the processing type is topic storage, obtaining web page information corresponding to the question and answer information in the topic information to be processed;

[0024] The to-be-processed topic information and the webpage information are stored.

[0025] Optionally, after the step of determining the processing type and dialog information corresponding to the topic processing instruction in response to the triggered topic processing instruction, the method further includes:

[0026] When the processing type is topic merging, determining at least two topic information to be merged according to the conversation information;

[0027] Performing feature extraction on the topic information to be merged respectively to obtain feature extraction results;

[0028] Determining user intent based on the feature extraction result, and constructing a target question according to the user intent;

[0029] A topic merging result is generated according to the dialogue information and the target question.

[0030] Optionally, after the step of performing topic processing on the topic information to be processed according to the processing type, the method further includes:

[0031] In response to the triggered topic import instruction, determining target topic information corresponding to the topic import instruction;

[0032] Generate search keywords based on the target topic information;

[0033] Generate search results corresponding to the target topic information according to the search keyword.

[0034] Optionally, the topic processing method further includes:

[0035] In a target topic participated by multiple users, determining the demand information of each user in the target topic;

[0036] Analyze the demand information and generate topic discussion goals;

[0037] A discussion result of the target topic is generated based on the topic discussion goal.

[0038] Optionally, the processing type includes at least one of topic forwarding, topic feature extraction, topic storage, topic deletion, topic sorting, topic merging and topic summarization.

[0039] Optionally, the step of performing topic processing on the topic information to be processed according to the processing type includes:

[0040] When the processing type is topic sorting, determining a topic sorting feature according to the topic processing instruction, the topic sorting feature including: at least one of time, number of topic participants, and number of conversations;

[0041] The topics in the topic information to be processed are sorted according to the topic sorting feature.

[0042] In addition, to achieve the above-mentioned purpose, the present invention also provides a topic processing device, the device comprising:

[0043] A response module, configured to respond to a triggered topic processing instruction and determine a processing type and dialogue information corresponding to the topic processing instruction, wherein the dialogue information includes at least one question and answer information;

[0044] A judgment module, used to determine whether the dialogue information is associated with the webpage information;

[0045] A determination module, configured to determine the topic information to be processed according to the web page information, the dialogue information and the association between the dialogue information and the web page information when determining that the dialogue information and the web page information are associated with each other;

[0046] A processing module is used to perform topic processing on the topic information to be processed according to the processing type.

[0047] In addition, to achieve the above objectives, the present invention also proposes a topic processing device, which includes: a memory, a processor, and a topic processing program stored in the memory and executable on the processor, wherein the topic processing program is configured to implement the steps of the topic processing method described above.

[0048] In addition, to achieve the above-mentioned purpose, the present invention further proposes a storage medium, on which a topic processing program is stored, and when the topic processing program is executed by a processor, the steps of the topic processing method described above are implemented.

[0049] The present invention responds to a triggered topic processing instruction, determines the processing type and dialogue information corresponding to the topic processing instruction, the dialogue information includes at least one question and answer information; determines whether the dialogue information is associated with the web page information; when it is determined that the dialogue information is associated with the web page information, determines the topic information to be processed according to the web page information, the dialogue information and the association between the dialogue information and the web page information; and performs topic processing on the topic information to be processed according to the processing type. Since the present invention can perform topic processing on the topic information to be processed according to the web page information, the dialogue information and the association between the dialogue information and the web page information when receiving the topic processing instruction, it can help users better manage topic information and improve the user's topic processing efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 It is a structural diagram of a topic processing device in a hardware operating environment involved in an embodiment of the present invention;

[0051] Figure 2 It is a flowchart of the first embodiment of the topic processing method of the present invention;

[0052] Figure 3 A topic interaction diagram of the first embodiment of the topic processing method of the present invention;

[0053] Figure 4 It is a flowchart of a second embodiment of the topic processing method of the present invention;

[0054] Figure 5 A topic sorting diagram of a second embodiment of the topic processing method of the present invention;

[0055] Figure 6 It is a flowchart of a third embodiment of the topic processing method of the present invention;

[0056] Figure 7 It is a structural block diagram of the first embodiment of the topic processing device of the present invention.

[0057] 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

[0058] 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.

[0059] Reference Figure 1 , Figure 1 The figure is a schematic diagram of the structure of a topic processing device in a hardware operating environment involved in an embodiment of the present invention.

[0060] like Figure 1 As shown, the topic processing 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), or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk storage. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0061] Those skilled in the art will understand that Figure 1 The structure shown in the figure does not constitute a limitation on the topic processing device, and may include more or less components than shown in the figure, or combine some components, or arrange the components differently.

[0062] 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 topic processing program.

[0063] exist Figure 1In the topic processing 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 topic processing device of the present invention can be set in the topic processing device, and the topic processing device calls the topic processing program stored in the memory 1005 through the processor 1001, and executes the topic processing method provided by the embodiment of the present invention.

[0064] Based on the above topic processing device, an embodiment of the present invention provides a topic processing method, referring to Figure 2 , Figure 2 Schematic diagram of the flow chart of the first embodiment of the topic processing method of the present invention.

[0065] In this embodiment, the topic processing method includes the following steps:

[0066] Step S10: In response to the triggered topic processing instruction, determining the processing type and dialogue information corresponding to the topic processing instruction, wherein the dialogue information includes at least one question and answer information.

[0067] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a mobile phone, a tablet computer, a personal computer, etc., or an electronic device or a browser that can realize the above functions. The following takes the browser as an example to illustrate this embodiment and the following embodiments.

[0068] It should be noted that the topic processing instruction may be a command triggered by a user to process at least one generated dialog information, and may include a processing type and the dialog information to be processed. The processing type includes at least one of topic forwarding, topic feature extraction, topic storage, topic deletion, topic sorting, topic merging, and topic summarization. The dialog information may include interaction information between the user and the browser, for example, Figure 3 , Figure 3 A topic interaction diagram of the first embodiment of the topic processing method of the present invention; Figure 3 The left side of the middle contains multiple topics created by the user. You can also create a new topic through the New chat button. When you click the corresponding topic list, the corresponding conversation information is displayed on the right. The user can process at least one of the topics. Figure 3There are common topic processing buttons in the upper right corner, including topic deletion and topic download, etc. The user's commonly used processing types can be displayed here according to the user's usage habits. The question and answer information can be questions initiated by the user. The browser can respond to the questions, generate answer information corresponding to the user's questions and display them in the corresponding dialogue information. The browser can integrate an intelligent big model, which can be a pre-trained human-computer interaction model based on an intelligent language model and / or an intelligent drawing model. The intelligent big model can understand the user's intention based on the information input by the user and generate corresponding response information.

[0069] Furthermore, in some scenarios, there may be connections between topics opened by the user. In this case, the user may merge multiple topics. After step S10, the method may include: when the processing type is topic merging, determining at least two topics to be merged according to the conversation information;

[0070] Performing feature extraction on the topic information to be merged respectively to obtain feature extraction results;

[0071] Determining user intent based on the feature extraction result, and constructing a target question according to the user intent;

[0072] A topic merging result is generated according to the dialogue information and the target question.

[0073] It should be noted that the feature extraction of the topic information to be merged may be to extract topic features in the topic information to be merged, such as the name of the topic, the subject of the conversation information, purpose, user needs and other information. The determination of the user intention based on the feature extraction result and the construction of the target question according to the user intention may be to use the intelligent big model in the browser to predict the user's intention based on the extracted features, and generate the target question according to the user's intention. The generation of the topic merging result based on the conversation information and the target question may be to generate the answer information corresponding to the target question based on the question and answer information in the conversation information, and the topic merging result includes the answer information and the topic information to be merged.

[0074] Step S20: Determine whether the dialog information is associated with the webpage information.

[0075] It should be noted that determining whether the conversation information is associated with the web page information may be determining whether the conversation information contains web page information and / or whether web page information is introduced. For example, when a user asks a question or initiates a conversation, it involves generating corresponding answer information based on a web page, processing the web page information (including summarizing, crawling, etc.) and / or introducing web page information when generating answer information in the browser.

[0076] Step S30: When it is determined that the dialogue information and the web page information are associated, the topic information to be processed is determined according to the web page information, the dialogue information, and the association between the dialogue information and the web page information.

[0077] It should be noted that, the determining of the topic information to be processed based on the web page information, the conversation information, and the association relationship between the conversation information and the web page information may be associating the question and answer information related to the web page information with the web page information based on the association relationship between the conversation information and the web page information, and then determining the topic information to be processed based on the associated information and the conversation information. The topic information to be processed may be the associated information and the conversation information.

[0078] Step S40: performing topic processing on the topic information to be processed according to the processing type.

[0079] It should be noted that the topic processing of the topic information to be processed according to the processing type may be topic processing of the topic information to be processed according to the processing strategy or processing steps corresponding to the processing type. For example, when the processing type is deletion, the topic information to be processed is deleted; when the processing type is saving, the topic information to be processed is saved to the saving path corresponding to the topic processing instruction or the preset default path.

[0080] Further, in order to meet the diverse needs of users for topic processing, for example, users may need to store topic information to avoid loss of topic information, the step S40 may include: when the processing type is topic storage, obtaining web page information corresponding to the question and answer information in the topic information to be processed;

[0081] The to-be-processed topic information and the webpage information are stored.

[0082] It should be noted that when there is an association relationship between the dialogue information and the web page information, the web page information may be associated with a question and answer in the dialogue information. For example, the dialogue information does not initially associate with the web page information. When the user asks a question Q, the browser refers to the content in the web page W to reply. At this time, the question and answer information Q and the web page W have a reference relationship, and the dialogue information is associated with the web page information. When storing topics, the topic information to be processed and the web page information associated with the question and answer information in the topic information to be processed can be stored at the same time. The stored web page information does not have to be all the content in the web page, and can only include content related to the question and answer information or links to the web page. The storage method of the web page information can be preset according to the actual scenario. This embodiment is not limited here.

[0083] Furthermore, in order to reduce user operations, the topic information may also be imported from outside. This embodiment further includes: in response to the triggered topic import instruction, determining the target topic information corresponding to the topic import instruction;

[0084] Generate search keywords based on the target topic information;

[0085] Generate search results corresponding to the target topic information according to the search keyword.

[0086] It should be noted that the topic import instruction can be a command triggered by the user to directly import a topic, and the imported topic can be question-and-answer information, for example, whether superconductivity really exists, or a piece of dialogue information, for example: N pieces of information interacted between user A and the browser. The target topic information can be the import information corresponding to the topic import instruction. The generation of search keywords based on the target topic information can be, when the target topic information is question-and-answer information, using the question-and-answer information as the search keyword, and when the target topic information is not question-and-answer information, performing semantic analysis on the target topic information, understanding the user's intention, and generating search keywords based on the user's intention. The generation of search results corresponding to the target topic information based on the search keywords can be, based on the intelligent big model integrated in the browser, generating answer information corresponding to the search keyword, i.e., search results.

[0087] Furthermore, a topic may include multiple topic-participating users, that is, multiple users participate in the discussion of the same topic. In order to meet the needs of multiple users, this embodiment further includes: determining the demand information of each user in the target topic in which multiple users participate;

[0088] Analyze the demand information and generate topic discussion goals;

[0089] A discussion result of the target topic is generated based on the topic discussion goal.

[0090] It should be noted that the determination of the demand information of each user in the target topic may be to obtain the speech information of each user in the topic information, and determine the user's demand according to the user's speech information. The analysis of the demand information and the generation of the topic discussion target may be to determine the discussion result expected by the user according to the demand information. The generation of the discussion result of the target topic based on the topic discussion target may be to generate a discussion result that satisfies all or most users according to the topic discussion target of each user. For example, the target topic is a travel plan participated in by multiple users, and the demand of user A is to travel on non-working days; the demand of user B is not to travel on the 2nd to the 5th; the demand of user C is to travel after nine o'clock; and user D has no demand. The topic discussion target of each user may be determined according to the needs of each user. Then, based on the topic discussion target of each user, a discussion result that satisfies the needs of all users may be generated, which may be to depart at ten o'clock in the morning on the 7th, and the 7th is a non-working day. In actual implementation, there may be a situation where the needs of each user cannot be met at the same time. At this time, the needs of most users may be met first, and the demand information of each user may be displayed.

[0091] In response to a triggered topic processing instruction, this embodiment determines the processing type and dialogue information corresponding to the topic processing instruction, wherein the dialogue information includes at least one question and answer information; determines whether the dialogue information is associated with the web page information; when it is determined that the dialogue information is associated with the web page information, determines the topic information to be processed according to the web page information, the dialogue information, and the association between the dialogue information and the web page information; and performs topic processing on the topic information to be processed according to the processing type. Since this embodiment can perform topic processing on the topic information to be processed according to the web page information, the dialogue information, and the association between the dialogue information and the web page information when receiving the topic processing instruction, it can help users better manage topic information and improve the user's topic processing efficiency.

[0092] refer to Figure 4 , Figure 4 It is a flowchart diagram of the second embodiment of the topic processing method of the present invention.

[0093] Based on the above first embodiment, in this embodiment, step S40 includes:

[0094] Step S401: Determine the topic processing feature corresponding to the processing type.

[0095] It should be noted that different processing types correspond to different processing methods. For example, when the processing type is deletion, the topic processing feature may be the storage path of the topic information to be processed and the identifier of the topic information to be processed; when the processing type is topic extraction, the topic processing feature may be the topic extraction condition; when the processing type is topic storage, the topic processing feature may be the topic storage path; when the processing type is topic sorting, the topic processing feature may be the topic sorting method, etc.

[0096] Step S402: extracting topic processing information from the topic information to be processed based on the topic processing feature.

[0097] It should be noted that the extracting of topic processing information from the topic information to be processed based on the topic processing feature may be extracting the topic processing information corresponding to the topic processing feature from the topic information to be processed based on the topic processing feature. For example, when the processing type is topic extraction, the topic processing feature may be a topic extraction condition, and the topic processing information may be information that satisfies the topic extraction condition and is extracted from the topic information to be processed based on the topic extraction condition. When the processing type is topic sorting, the topic processing feature may be a basis for topic sorting, and may be sorted according to the number of topic participants, the last processing time of the topic, etc. If the basis for topic sorting is the number of topic participants, then the topic processing feature is the number of topic participants, and the topic processing information may be the number of participants corresponding to each topic.

[0098] Step S403: Process the topic information to be processed according to the topic processing information and the processing type.

[0099] It should be noted that the processing of the topic information to be processed according to the topic processing information and the processing type may be processing the topic information to be processed according to the processing type using the topic processing information as a processing basis. For example, if the processing type is topic sorting and the topic processing information is the last processing time corresponding to the topic participating in the topic sorting, then the processing of the topic information to be processed may be sorting the topics participating in the topic sorting from near to far according to the last processing time corresponding to the topic.

[0100] In a specific implementation, when the processing type is topic sorting, a topic sorting feature is determined according to the topic processing instruction, and the topic sorting feature includes at least one of time, number of topic participants, and number of conversations; and topics in the topic information to be processed are sorted according to the topic sorting feature. Figure 5 , Figure 5 A topic sorting diagram of a second embodiment of the topic processing method of the present invention; Figure 5The multiple topics in the table are all generated on the same day. The topic sorting feature is the last processing time of the topic. The last processing time of the topic is displayed next to each topic. The results of sorting the topics by the last processing time are as follows: Figure 5 shown.

[0101] This embodiment determines the topic processing features corresponding to the processing type; extracts topic processing information from the topic information to be processed based on the topic processing features; and processes the topic information to be processed according to the topic processing information and the processing type. This embodiment extracts features of the topic information to be processed based on the topic processing features corresponding to the processing type, extracts topic processing information for processing the topic information to be processed, and processes the topic information to be processed based on the topic processing information and the processing type. It can help users better manage topic information and improve users' topic processing efficiency.

[0102] refer to Figure 6 , Figure 6 It is a flowchart diagram of the third embodiment of the topic processing method of the present invention.

[0103] Based on the above embodiments, in this embodiment, step S40 further includes:

[0104] Step S404: when the processing type is topic forwarding, determining a forwarding target according to the topic processing instruction.

[0105] It should be noted that the forwarding target may be a terminal or user to which the topic information to be processed corresponds to and to which the information is to be forwarded, and may include at least one of a user identifier, a forwarding address, and a terminal identifier.

[0106] Step S405: forwarding the topic information to be processed to the forwarding target.

[0107] It should be noted that forwarding the topic information to be processed to the forwarding target may be forwarding the topic information to be processed to the forwarding target according to the forwarding method in the topic processing instruction. The forwarding method may include at least one of combined forwarding, separate forwarding, timed forwarding and link forwarding.

[0108] Furthermore, when there are multiple forwarding targets, the topic information to be processed needs to be forwarded to the forwarding targets respectively. At this time, the demand for the network and bandwidth is large, the forwarding speed is slow, and the user can only view the forwarded topic information but cannot operate the topic discussion. Therefore, in order to improve the efficiency of topic forwarding, the step S405 may include: determining the topic forwarding method corresponding to the forwarding target;

[0109] When the topic forwarding mode is link forwarding, obtaining a topic link corresponding to the topic information to be processed;

[0110] The topic link is sent to the forwarding target, and the forwarding target is used to extract the to-be-processed topic information based on the topic link or participate in the target topic corresponding to the to-be-processed topic information.

[0111] It should be noted that when a user triggers a topic processing instruction for topic forwarding, the user can specify a topic forwarding method. The topic link can be a topic extraction link, a topic extraction code, or a topic extraction QR code, or it can be an identifier in other forms. The topic link can be used by the user to obtain the pending topic information corresponding to the topic link based on the topic link. The target topic can be a conversation corresponding to the pending topic information, and the user can participate in the discussion of the target topic through the topic link, which can be similar to a topic invitation. For example, user A forwards the pending topic information to user B via a topic link. When user B receives the topic extraction QR code, the user can obtain the pending topic information corresponding to the topic extraction QR code. At the same time, the user can also directly enter the conversation corresponding to the pending topic information to participate in the discussion of the topic. In order to prevent any user who obtains the topic extraction QR code from entering the topic, user A can set permissions when forwarding the topic, and set the user ID that can enter the topic through the topic extraction QR code.

[0112] In this embodiment, when the processing type is topic forwarding, the forwarding target is determined according to the topic processing instruction; the topic forwarding method corresponding to the forwarding target is determined; when the topic forwarding method is link forwarding, the topic link corresponding to the topic information to be processed is obtained; the topic link is sent to the forwarding target, and the forwarding target is used to extract the topic information to be processed based on the topic link or participate in the target topic corresponding to the topic information to be processed. This embodiment can forward the topic information to be processed to the forwarding target according to the forwarding target in the topic processing instruction. It can help users better manage topic information and improve user experience.

[0113] Reference Figure 7 , Figure 7 It is a structural block diagram of the first embodiment of the topic processing device of the present invention.

[0114] like Figure 7 As shown, the topic processing device proposed in the embodiment of the present invention includes:

[0115] A response module 10, configured to respond to a triggered topic processing instruction and determine a processing type and dialogue information corresponding to the topic processing instruction, wherein the dialogue information includes at least one question and answer information;

[0116] A determination module 20, used to determine whether the conversation information is associated with the webpage information;

[0117] A determination module 30, for determining, when determining that the conversation information and the web page information are associated, the topic information to be processed according to the web page information, the conversation information and the association between the conversation information and the web page information;

[0118] The processing module 40 is used to perform topic processing on the topic information to be processed according to the processing type.

[0119] In response to a triggered topic processing instruction, this embodiment determines the processing type and dialogue information corresponding to the topic processing instruction, wherein the dialogue information includes at least one question and answer information; determines whether the dialogue information is associated with the web page information; when it is determined that the dialogue information is associated with the web page information, determines the topic information to be processed according to the web page information, the dialogue information, and the association between the dialogue information and the web page information; and performs topic processing on the topic information to be processed according to the processing type. Since this embodiment can perform topic processing on the topic information to be processed according to the web page information, the dialogue information, and the association between the dialogue information and the web page information when receiving the topic processing instruction, it can help users better manage topic information and improve the user's topic processing efficiency.

[0120] 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.

[0121] In addition, for technical details not fully described in this embodiment, reference can be made to the topic processing method provided in any embodiment of the present invention, and will not be repeated here.

[0122] Based on the first embodiment of the topic processing device of the present invention, a second embodiment of the topic processing device of the present invention is proposed.

[0123] In this embodiment, the processing module 40 is further used to determine the topic processing feature corresponding to the processing type;

[0124] extracting topic processing information from the topic information to be processed based on the topic processing feature;

[0125] The topic information to be processed is processed according to the topic processing information and the processing type.

[0126] Furthermore, the processing module 40 is further configured to determine a forwarding target according to the topic processing instruction when the processing type is topic forwarding;

[0127] The to-be-processed topic information is forwarded to the forwarding target.

[0128] Furthermore, the processing module 40 is also used to determine the topic forwarding method corresponding to the forwarding target;

[0129] When the topic forwarding mode is link forwarding, obtaining a topic link corresponding to the topic information to be processed;

[0130] The topic link is sent to the forwarding target, and the forwarding target is used to extract the to-be-processed topic information based on the topic link or participate in the target topic corresponding to the to-be-processed topic information.

[0131] Furthermore, the processing module 40 is further configured to obtain web page information corresponding to the question and answer information in the topic information to be processed when the processing type is topic storage;

[0132] The to-be-processed topic information and the webpage information are stored.

[0133] Furthermore, the response module 10 is further configured to determine at least two topic information to be merged according to the conversation information when the processing type is topic merging;

[0134] Performing feature extraction on the topic information to be merged respectively to obtain feature extraction results;

[0135] Determining user intent based on the feature extraction result, and constructing a target question according to the user intent;

[0136] A topic merging result is generated according to the dialogue information and the target question.

[0137] Furthermore, the processing module 40 is further configured to determine target topic information corresponding to the topic import instruction in response to the triggered topic import instruction;

[0138] Generate search keywords based on the target topic information;

[0139] Generate search results corresponding to the target topic information according to the search keyword.

[0140] Furthermore, the processing module 40 is also used to determine the demand information of each user in the target topic among the target topics participated by multiple users;

[0141] Analyze the demand information and generate topic discussion goals;

[0142] A discussion result of the target topic is generated based on the topic discussion goal.

[0143] Furthermore, the processing type includes at least one of topic forwarding, topic feature extraction, topic storage, topic deletion, topic sorting, topic merging and topic summarization.

[0144] Furthermore, the processing module 40 is further configured to determine a topic sorting feature according to the topic processing instruction when the processing type is topic sorting, wherein the topic sorting feature includes at least one of time, number of topic participants, and number of conversations;

[0145] The topics in the topic information to be processed are sorted according to the topic sorting feature.

[0146] Other embodiments or specific implementations of the topic processing device of the present invention can refer to the above-mentioned method embodiments, which will not be described in detail here.

[0147] In addition, an embodiment of the present invention further provides a storage medium, on which a topic processing program is stored. When the topic processing program is executed by a processor, the steps of the topic processing method described above are implemented.

[0148] 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.

[0149] 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.

[0150] 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 can also be implemented 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 / random access memory, 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, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0151] 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.

[0152] The present invention discloses A1, a topic processing method, the topic processing method comprising the following steps:

[0153] In response to the triggered topic processing instruction, determining a processing type and dialogue information corresponding to the topic processing instruction, wherein the dialogue information includes at least one question and answer information;

[0154] Determining whether the conversation information is associated with the webpage information;

[0155] When it is determined that the conversation information and the web page information are associated, determining the topic information to be processed according to the web page information, the conversation information, and the association between the conversation information and the web page information;

[0156] Perform topic processing on the topic information to be processed according to the processing type.

[0157] A2. The topic processing method as described in A1, wherein the step of performing topic processing on the topic information to be processed according to the processing type comprises:

[0158] Determining topic processing features corresponding to the processing type;

[0159] extracting topic processing information from the topic information to be processed based on the topic processing feature;

[0160] The topic information to be processed is processed according to the topic processing information and the processing type.

[0161] A3. In the topic processing method described in A1, the step of performing topic processing on the topic information to be processed according to the processing type comprises:

[0162] When the processing type is topic forwarding, determining a forwarding target according to the topic processing instruction;

[0163] The to-be-processed topic information is forwarded to the forwarding target.

[0164] A4. In the topic processing method described in A3, the step of forwarding the topic information to be processed to the forwarding target comprises:

[0165] Determine a topic forwarding method corresponding to the forwarding target;

[0166] When the topic forwarding mode is link forwarding, obtaining a topic link corresponding to the topic information to be processed;

[0167] The topic link is sent to the forwarding target, and the forwarding target is used to extract the to-be-processed topic information based on the topic link or participate in the target topic corresponding to the to-be-processed topic information.

[0168] A5. In the topic processing method described in A1, the step of performing topic processing on the topic information to be processed according to the processing type comprises:

[0169] When the processing type is topic storage, obtaining web page information corresponding to the question and answer information in the topic information to be processed;

[0170] The to-be-processed topic information and the webpage information are stored.

[0171] A6. The topic processing method according to any one of A1 to A5, further comprising, after the step of determining the processing type and dialog information corresponding to the topic processing instruction in response to the triggered topic processing instruction:

[0172] When the processing type is topic merging, determining at least two topic information to be merged according to the conversation information;

[0173] Performing feature extraction on the topic information to be merged respectively to obtain feature extraction results;

[0174] Determining user intent based on the feature extraction result, and constructing a target question according to the user intent;

[0175] A topic merging result is generated according to the dialogue information and the target question.

[0176] A7. The topic processing method as described in any one of A1 to A5, after the step of performing topic processing on the topic information to be processed according to the processing type, further comprising:

[0177] In response to the triggered topic import instruction, determining target topic information corresponding to the topic import instruction;

[0178] Generate search keywords based on the target topic information;

[0179] Generate search results corresponding to the target topic information according to the search keyword.

[0180] A8. The topic processing method according to any one of A1 to A5, further comprising:

[0181] In a target topic participated by multiple users, determining the demand information of each user in the target topic;

[0182] Analyze the demand information and generate topic discussion goals;

[0183] A discussion result of the target topic is generated based on the topic discussion goal.

[0184] A9. The topic processing method as described in any one of A1-A5, wherein the processing type includes at least one of topic forwarding, topic feature extraction, topic storage, topic deletion, topic sorting, topic merging and topic summarization.

[0185] A10. In the topic processing method according to any one of A1 to A5, the step of performing topic processing on the topic information to be processed according to the processing type comprises:

[0186] When the processing type is topic sorting, determining a topic sorting feature according to the topic processing instruction, the topic sorting feature including: at least one of time, number of topic participants, and number of conversations;

[0187] The topics in the topic information to be processed are sorted according to the topic sorting feature.

[0188] The present invention discloses B11, a topic processing device, the topic processing device comprising:

[0189] A response module, configured to respond to a triggered topic processing instruction and determine a processing type and dialogue information corresponding to the topic processing instruction, wherein the dialogue information includes at least one question and answer information;

[0190] A judgment module, used to determine whether the dialogue information is associated with the webpage information;

[0191] A determination module, configured to determine the topic information to be processed according to the web page information, the dialogue information and the association between the dialogue information and the web page information when determining that the dialogue information and the web page information are associated with each other;

[0192] A processing module is used to perform topic processing on the topic information to be processed according to the processing type.

[0193] B12. The topic processing device as described in B11, wherein the processing module is further used to determine the topic processing feature corresponding to the processing type;

[0194] extracting topic processing information from the topic information to be processed based on the topic processing feature;

[0195] The topic information to be processed is processed according to the topic processing information and the processing type.

[0196] B13. The topic processing device as described in B11, wherein the processing module is further configured to determine a forwarding target according to the topic processing instruction when the processing type is topic forwarding;

[0197] The to-be-processed topic information is forwarded to the forwarding target.

[0198] B14, the topic processing device as described in B13, the processing module is further used to determine the topic forwarding method corresponding to the forwarding target;

[0199] When the topic forwarding mode is link forwarding, obtaining a topic link corresponding to the topic information to be processed;

[0200] The topic link is sent to the forwarding target, and the forwarding target is used to extract the to-be-processed topic information based on the topic link or participate in the target topic corresponding to the to-be-processed topic information.

[0201] B15. The topic processing device as described in B11, wherein the processing module is further used to obtain web page information corresponding to the question and answer information in the topic information to be processed when the processing type is topic storage;

[0202] The to-be-processed topic information and the webpage information are stored.

[0203] B16. The topic processing device as described in any one of B11 to B15, wherein the processing module is further configured to determine at least two topic information to be merged according to the dialogue information when the processing type is topic merging;

[0204] Performing feature extraction on the topic information to be merged respectively to obtain feature extraction results;

[0205] Determining user intent based on the feature extraction result, and constructing a target question according to the user intent;

[0206] A topic merging result is generated according to the dialogue information and the target question.

[0207] B17. The topic processing device as described in any one of B11 to B15, wherein the processing module is further used to determine target topic information corresponding to the topic import instruction in response to the triggered topic import instruction;

[0208] Generate search keywords based on the target topic information;

[0209] Generate search results corresponding to the target topic information according to the search keyword.

[0210] B18. The topic processing device as described in any one of B11 to B15, wherein the topic processing device is further used to determine demand information of each user in a target topic in which multiple users participate;

[0211] Analyze the demand information and generate topic discussion goals;

[0212] A discussion result of the target topic is generated based on the topic discussion goal.

[0213] The present invention discloses C19, a topic processing device, which includes: a memory, a processor, and a topic processing program stored in the memory and executable on the processor, wherein the topic processing program is configured to implement the steps of the topic processing method described in any one of A1 to A10.

[0214] The present invention discloses D20, a storage medium, on which a topic processing program is stored. When the topic processing program is executed by a processor, the steps of the topic processing method as described in any one of A1 to A10 are implemented.

Claims

1. A topic processing method, characterized in that: The topic processing method comprises the following steps: In response to the triggered topic processing instruction, determining a processing type and dialogue information corresponding to the topic processing instruction, wherein the dialogue information includes at least one question and answer information; Determining whether the conversation information is associated with the webpage information; When it is determined that the conversation information and the web page information are associated, determining the topic information to be processed according to the web page information, the conversation information, and the association between the conversation information and the web page information; Perform topic processing on the topic information to be processed according to the processing type.

2. The topic processing method according to claim 1, characterized in that: The step of performing topic processing on the topic information to be processed according to the processing type includes: Determining topic processing features corresponding to the processing type; extracting topic processing information from the topic information to be processed based on the topic processing feature; The topic information to be processed is processed according to the topic processing information and the processing type.

3. The topic processing method according to claim 1, characterized in that: The step of performing topic processing on the topic information to be processed according to the processing type includes: When the processing type is topic forwarding, determining a forwarding target according to the topic processing instruction; The to-be-processed topic information is forwarded to the forwarding target.

4. The topic processing method according to claim 3, characterized in that: The step of forwarding the to-be-processed topic information to the forwarding target includes: Determine a topic forwarding method corresponding to the forwarding target; When the topic forwarding mode is link forwarding, obtaining a topic link corresponding to the topic information to be processed; The topic link is sent to the forwarding target, and the forwarding target is used to extract the to-be-processed topic information based on the topic link or participate in the target topic corresponding to the to-be-processed topic information.

5. The topic processing method according to claim 1, characterized in that: The step of performing topic processing on the topic information to be processed according to the processing type includes: When the processing type is topic storage, obtaining web page information corresponding to the question and answer information in the topic information to be processed; The to-be-processed topic information and the webpage information are stored.

6. The topic processing method according to any one of claims 1 to 5, characterized in that: After the step of determining the processing type and dialogue information corresponding to the topic processing instruction in response to the triggered topic processing instruction, the method further includes: When the processing type is topic merging, determining at least two topic information to be merged according to the conversation information; Performing feature extraction on the topic information to be merged respectively to obtain feature extraction results; Determining user intent based on the feature extraction result, and constructing a target question according to the user intent; A topic merging result is generated according to the dialogue information and the target question.

7. The topic processing method according to any one of claims 1 to 5, characterized in that: After the step of performing topic processing on the topic information to be processed according to the processing type, the method further includes: In response to the triggered topic import instruction, determining target topic information corresponding to the topic import instruction; Generate search keywords based on the target topic information; Generate search results corresponding to the target topic information according to the search keyword.

8. A topic processing device, characterized in that: The topic processing device comprises: A response module, configured to respond to a triggered topic processing instruction and determine a processing type and dialogue information corresponding to the topic processing instruction, wherein the dialogue information includes at least one question and answer information; A judgment module, used to determine whether the dialogue information is associated with the webpage information; A determination module, configured to determine the topic information to be processed according to the web page information, the dialogue information and the association between the dialogue information and the web page information when determining that the dialogue information and the web page information are associated with each other; A processing module is used to perform topic processing on the topic information to be processed according to the processing type.

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

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

Images