AI Robot Dialogue Control Method and System Based on Big Data Search

Abstract

The present invention is applicable to the field of chatbot technology, and provides an AI robot dialogue control method and system based on big data search, including the following steps: receiving group chat robot control information, where the group chat robot control information includes the autonomous dialogue frequency and the pause time; processing and identifying group chat messages, and when there is a call signal, the autonomous dialogue frequency is reached, or the pause time is reached in the group chat messages, causing the group chat robot to conduct a dialogue; when there is a call signal, collecting the group chat messages corresponding to the call signal and conducting a dialogue according to the command type of the group chat messages; when the autonomous dialogue frequency is reached, collecting the most recent N group chat messages and conducting an interactive dialogue according to the most recent N group chat messages; when the pause time is reached, collecting the latest group chat message and inputting the group chat message into the AI big data model to obtain the dialogue reply content. In this way, there are various triggering conditions, and it is possible to communicate and reply for various scenarios, enhancing the interactivity of group chats.

Description

Technical Field

[0001] The present invention relates to the technical field of chatbots, and specifically to an AI robot dialogue control method and system based on big data search. Background Art

[0002] With the rapid development of artificial intelligence technology, various chat interaction robots emerge in an endless stream. For example, group chat robots are supported in chat software. The group chat robot can be set to automatically send specific messages at specific times, such as weather forecasts, news summaries, group announcements, etc.; when the user sends a specific question and @ the robot, the robot will immediately give a corresponding answer or guidance; when a new member joins the group chat, the robot can automatically send a welcome message to enhance the friendly atmosphere of the group. However, the interactivity of existing group chat robots is still weak, and the triggering conditions are very single, and they cannot interact with group members more efficiently and deeply. Therefore, an AI robot dialogue control method and system based on big data search are needed to solve the above problems. Summary of the Invention

[0003] Aiming at the deficiencies of the existing technology, the purpose of the present invention is to provide an AI robot dialogue control method and system based on big data search to solve the problems in the above background art.

[0004] The present invention is implemented as follows. An AI robot dialogue control method based on big data search, the method includes the following steps:

[0005] Receiving group chat robot control information, the group chat robot control information including the autonomous dialogue frequency and the pause time;

[0006] Processing and identifying group chat messages, when there is a summoning signal, the autonomous dialogue frequency is reached, or the pause time is reached in the group chat messages, causing the group chat robot to conduct a dialogue;

[0007] When there is a summoning signal, collecting the group chat messages corresponding to the summoning signal and conducting a dialogue according to the command type of the group chat messages, the command type being inquiry query, statistical classification, or text summary;

[0008] When the autonomous dialogue frequency is reached, collecting the most recent N group chat messages and conducting an interactive dialogue according to the most recent N group chat messages;

[0009] When the pause time is reached, collecting the latest group chat message and inputting the group chat message into the AI big data model to obtain the dialogue reply content.

[0010] As a further solution of the present invention: the step of processing and identifying the group chat messages specifically includes:

[0011] Determine whether the group chat robot summoning character appears in the group chat message. When it appears, it is determined that there is a summoning signal;

[0012] Count the number of messages after the last group chat robot conversation in the group chat message. When counting, duplicate messages are deleted. When the number of messages reaches the preset number, it is determined that the autonomous conversation frequency is reached;

[0013] Determine whether the latest group chat message is an interrogative sentence. When it is, time the sending time of the latest group chat message to obtain the timing duration. When the timing duration reaches the preset duration, it is determined that the empty pause time is reached.

[0014] As a further solution of the present invention: the step of collecting the group chat message corresponding to the summoning signal and having a conversation according to the command type of the group chat message specifically includes:

[0015] Collect the group chat message corresponding to the summoning signal and determine the command type corresponding to the group chat message;

[0016] When it is an inquiry query, input the group chat message into the AI big data model to obtain the conversation reply content;

[0017] When it is a statistical classification, perform message backtracking, determine the chat topic and the topic reply to the chat topic, and perform statistics based on the topic reply to obtain statistical classification information;

[0018] When it is a text summary, perform message backtracking, determine the chat topic and the topic reply to the chat topic, and integrate the topic reply based on the AI big data model to obtain text summary information.

[0019] As a further solution of the present invention: the step of determining the command type corresponding to the group chat message specifically includes:

[0020] Preprocess the group chat message. The preprocessing includes word segmentation and stop word removal;

[0021] Match the preprocessed group chat message with the keyword library. Each command type corresponds to a keyword library;

[0022] Output the matching result, and determine the command type corresponding to the group chat message according to the matching result.

[0023] As a further solution of the present invention: the step of having a conversation according to the last N group chat messages specifically includes:

[0024] Summarize the last N group chat messages, determine the summary message type, and the summary message type is inquiry query, topic discussion or undetermined;

[0025] When it is an inquiry query, determine the corresponding query question, and input the query question into the AI big data model to obtain the conversation reply content;

[0026] When it is a topic discussion, determine the topic phrase to be discussed, and input the topic phrase into the AI big data model to obtain the conversation reply content;

[0027] When it cannot be determined, obtain the social hot topic and conduct a guided interaction based on the social hot topic.

[0028] As a further solution of the present invention: The steps of conducting a guided interaction based on the social hot topic specifically include:

[0029] Determine the group chat interested tags based on all the historical topic phrases, and screen the social hot topics according to the group chat interested tags;

[0030] Retrieve the article titles of the screened social hot topics, and input the article titles into the group chat dialog box.

[0031] Another object of the present invention is to provide an AI robot dialogue control system based on big data search, and the system includes:

[0032] A control parameter determination module, which is used to receive group chat robot control information, and the group chat robot control information includes the autonomous dialogue frequency and the pause time;

[0033] A group chat robot startup module, which is used to process and identify group chat messages. When there is a call signal, the autonomous dialogue frequency is reached, or the pause time is reached, the group chat robot is enabled to conduct a dialogue;

[0034] A call signal trigger module, which is used to collect the group chat message corresponding to the call signal when there is a call signal, and conduct a dialogue according to the command type of the group chat message. The command type is inquiry query, statistical classification, or text summary;

[0035] A dialogue frequency trigger module, which is used to collect the latest N group chat messages when the autonomous dialogue frequency is reached, and conduct an interactive dialogue according to the latest N group chat messages;

[0036] A pause time trigger module, which is used to collect the latest group chat message when the pause time is reached, and input the group chat message into the AI big data model to obtain the conversation reply content.

[0037] As a further solution of the present invention: The group chat robot startup module includes:

[0038] A call signal determination unit, which is used to determine whether a group chat robot call character appears in the group chat message. When it appears, it is determined that there is a call signal;

[0039] A conversation frequency determination unit, which is used to count the number of messages after the last group chat robot conversation in the group chat messages, and delete duplicate messages during the counting. When the number of messages reaches a preset number, it is determined that the autonomous conversation frequency is reached;

[0040] A pause time determination unit, which is used to determine whether the latest group chat message is an interrogative sentence. When it is, the sending time of the latest group chat message is timed to obtain a timing duration. When the timing duration reaches a preset duration, it is determined that the pause time is reached.

[0041] As a further solution of the present invention: The call signal trigger module includes:

[0042] A command type determination unit, which is used to collect the group chat message corresponding to the call signal and determine the command type corresponding to the group chat message;

[0043] An inquiry query reply unit, which is used to input the group chat message into the AI big data model to obtain a conversation reply content when it is an inquiry query;

[0044] A statistical classification reply unit, which is used to perform message backtracking when it is statistical classification, determine the chat topic and the topic reply to the chat topic, and perform statistics based on the topic reply to obtain statistical classification information;

[0045] A text summary reply unit, which is used to perform message backtracking when it is text summary, determine the chat topic and the topic reply to the chat topic, and integrate the topic reply based on the AI big data model to obtain text summary information.

[0046] As a further solution of the present invention: The command type determination unit includes:

[0047] A message preprocessing subunit, which is used to preprocess the group chat message, and the preprocessing includes word segmentation and stop word removal;

[0048] A keyword matching subunit, which is used to match the preprocessed group chat message with a keyword library, and each command type corresponds to a keyword library;

[0049] A command type determination subunit, which is used to output a matching result and determine the command type corresponding to the group chat message according to the matching result.

[0050] Compared with the prior art, the beneficial effects of the present invention are:

[0051] In the present invention, when there is a summoning signal, the autonomous conversation frequency is reached, or the pause time is reached in the group chat message, the group chat robot will be triggered to have a conversation. The triggering conditions are diverse and can communicate and reply for various scenarios. And it will have a conversation according to the command type of the group chat message to achieve personalized conversation. This personalized conversation method can better meet the diverse needs of users and improve the user experience. When the autonomous conversation frequency is reached, it will have an interactive conversation according to the latest N group chat messages. In this way, the group chat robot can frequently join the group chat to interact with group members, making it more efficient and in-depth. When the pause time is reached, it will automatically collect the latest group chat messages, input the group chat messages into the AI big data model to obtain the conversation reply content, avoid the group chat from falling into a long silence, enhance the interactivity of the group chat, and also stimulate the enthusiasm of users to participate and improve the activity of the group chat. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 It is a flowchart of the AI robot conversation control method based on big data search.

[0053] Figure 2 It is a flowchart of processing group chat messages in the AI robot conversation control method based on big data search.

[0054] Figure 3 It is a flowchart of having a conversation according to the command type in the AI robot conversation control method based on big data search.

[0055] Figure 4 It is a flowchart of determining the command type in the AI robot conversation control method based on big data search.

[0056] Figure 5 It is a flowchart of having a conversation according to N messages in the AI robot conversation control method based on big data search.

[0057] Figure 6 It is a flowchart of conducting guided interaction in the AI robot conversation control method based on big data search.

[0058] Figure 7 It is a schematic structural diagram of the AI robot conversation control system based on big data search. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0059] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. 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.

[0060] The following describes in detail the specific implementation of the present invention with reference to specific embodiments.

[0061] As Figure 1 shown, an embodiment of the present invention provides an AI robot dialogue control method based on big data search. The method includes the following steps:

[0062] S100, receiving group chat robot control information, where the group chat robot control information includes the autonomous dialogue frequency and the pause time;

[0063] S200, processing and identifying group chat messages. When there is a call signal, the autonomous dialogue frequency is reached, or the pause time is reached in the group chat messages, the group chat robot is enabled to have a dialogue;

[0064] S300, when there is a call signal, collecting the group chat message corresponding to the call signal and having a dialogue according to the command type of the group chat message. The command type is inquiry query, statistical classification, or text summary;

[0065] S400, when the autonomous dialogue frequency is reached, collecting the most recent N group chat messages and having an interactive dialogue according to the most recent N group chat messages;

[0066] S500, when the pause time is reached, collecting the latest group chat message, and inputting the group chat message into the AI big data model to obtain the dialogue reply content.

[0067] In the embodiment of the present invention, first, the group owner or administrator needs to set parameters for the group chat robot and input the group chat robot control information. The set parameter items include the autonomous dialogue frequency and the pause time. Then, the group chat robot will process and identify the group chat messages. When there is a call signal, the autonomous dialogue frequency is reached, or the pause time is reached in the group chat messages, the group chat robot will be automatically triggered to have a dialogue. Specifically, when there is a call signal, the group chat message corresponding to the call signal is collected, and a dialogue is carried out according to the command type of the group chat message. The command type is inquiry query, statistical classification, or text summary. In this way, personalized dialogue can be carried out, and this personalized dialogue method can better meet the diverse needs of users and improve the user experience; when the autonomous dialogue frequency is reached, the most recent N group chat messages are collected, and an interactive dialogue is carried out according to the most recent N group chat messages. N is a preset fixed value. For example, N is 10. In this way, the group chat robot can frequently join the group chat to interact with group members, which is more efficient and in-depth; when the pause time is reached, the latest group chat message will be automatically collected, and the group chat message will be input into the AI big data model to obtain the dialogue reply content, avoiding the group chat from falling into a long silence. The AI big data model can be selected from ChatGPT, Wenxin Yiyan, Doubao, iFlytek Spark, etc. In this way, the triggering conditions of the group chat robot in the embodiment of the present invention are diverse, and it can communicate and reply for various scenarios. This can not only enhance the interactivity of the group chat, but also stimulate the enthusiasm of users to participate and improve the activity of the group chat.

[0068] As shown Figure 2 in the figure, as a preferred embodiment of the present invention, the steps of processing and identifying group chat messages specifically include:

[0069] S201, determine whether a group chat robot summoning character appears in the group chat message. When it appears, it is determined that there is a summoning signal;

[0070] S202, count the number of messages after the most recent group chat robot conversation in the group chat message. When counting, duplicate messages are deleted. When the number of messages reaches a preset number, it is determined that the autonomous conversation frequency is reached;

[0071] S203, determine whether the latest group chat message is an interrogative sentence. When it is, time the sending time of the latest group chat message to obtain a timing duration. When the timing duration reaches a preset duration, it is determined that the pause time is reached.

[0072] In the embodiment of the present invention, it is necessary to determine the trigger condition of the group chat robot. First, it is determined whether a group chat robot summoning character appears in the group chat message. For example, the summoning character is @group chat robot or the name of the group chat robot. When the summoning character appears, it is determined that there is a summoning signal. Then, the number of messages after the most recent group chat robot conversation in the group chat message is counted. When counting, duplicate messages need to be deleted. For example, if the content of five messages is all "Received", then these five messages are counted as one. When the number of messages reaches a preset number, it is defaulted that the autonomous conversation frequency is reached. In addition, it is also determined whether the latest group chat message is an interrogative sentence. When it is, then time the sending time of the latest group chat message to obtain a timing duration. When the timing duration reaches a preset duration, it is determined that the pause time is reached, indicating that at this time, a group member has asked a question and no one has answered. The group chat robot will intervene to reply, making the user experience better.

[0073] As shown Figure 3 in the figure, as a preferred embodiment of the present invention, the steps of collecting the group chat message corresponding to the summoning signal and having a conversation according to the command type of the group chat message specifically include:

[0074] S301, collect the group chat message corresponding to the summoning signal, and determine the command type corresponding to the group chat message;

[0075] S302, when it is an inquiry query, input the group chat message into the AI big data model to obtain a conversation reply content;

[0076] S303, when it is a statistical classification, perform message backtracking, determine the chat topic and the topic reply to the chat topic, and obtain statistical classification information based on the topic reply;

[0077] S304. When it is text summarization, message backtracking is performed to determine the chat topic and the topic responses to the chat topic. Based on the AI big data model, the topic responses are integrated to obtain text summary information.

[0078] In the embodiments of the present invention, the group chat messages corresponding to the call signal are determined, and the command type corresponding to the group chat messages is automatically determined. When the command type is inquiry query, the corresponding group chat messages are input into the AI big data model, and the conversation reply content can be directly obtained. When the command type is statistical classification, message backtracking is performed to determine the chat topic and the topic responses to the chat topic. For example, the chat topic is: "Vote on the team building plan. Press 1 for Plan 1 and 2 for Plan 2", and the topic responses are: "1", "2", "1", "1", "2", "1", "1", "2". Then, statistical classification information is obtained based on the topic responses. For example, the statistical classification information is that five people choose Plan 1 and three people choose Plan 2, which is more rapid and convenient compared with the traditional group voting. When the command type is text summarization, message backtracking is also performed to determine the chat topic and the topic responses to the chat topic. For example, the chat topic is: "Express opinions on the energy conservation and emission reduction project", and the topic responses are the reply contents of the group members to this topic. Finally, based on the AI big data model, the topic responses are integrated to obtain text summary information, and the reply content of each person is input into the AI big data model for optimization and summarization.

[0079] As Figure 4 shown, as a preferred embodiment of the present invention, the steps of determining the command type corresponding to the group chat message specifically include:

[0080] S3011. Preprocess the group chat message. The preprocessing includes word segmentation and stop word removal;

[0081] S3012. Match the preprocessed group chat message with the keyword library. Each command type corresponds to a keyword library;

[0082] S3013. Output the matching result, and determine the command type corresponding to the group chat message according to the matching result.

[0083] In the embodiments of the present invention, in order to better determine the command type, the group chat message is first preprocessed. The natural language processing (NLP) library (such as the jieba tokenizer) is used to tokenize the message text and remove common stop words (such as "de", "le", "zai", etc.) to reduce noise. Then, the preprocessed group chat message is matched with the keyword library. Each command type corresponds to a keyword library, and the keyword library needs to be constructed in advance. For example, the keyword library for inquiry contains "query", "?", "why", "ma", etc., the keyword library for statistics and classification contains "statistics", "classification", "proportion", etc., and the keyword library for text summary contains "summary", "generalize", "summarize", etc. The group chat message is character-matched with each keyword, and the matching result is output. According to the matching result, the command type corresponding to the group chat message can be automatically determined.

[0084] As Figure 5 shown, as a preferred embodiment of the present invention, the step of having a conversation based on the most recent N group chat messages specifically includes:

[0085] S401, Summarize the most recent N group chat messages to determine the type of the summarized message, where the type of the summarized message is inquiry, topic discussion, or undeterminable;

[0086] S402, When it is an inquiry, determine the corresponding query question, and input the query question into the AI big data model to obtain the conversation reply content;

[0087] S403, When it is a topic discussion, determine the topic phrase being discussed, and input the topic phrase into the AI big data model to obtain the conversation reply content;

[0088] S404, When it is undeterminable, obtain the current social hot topics and conduct guided interaction based on the social hot topics.

[0089] In the embodiments of the present invention, the most recent N group chat messages are summarized to determine the type of the summarized message, where the type of the summarized message is inquiry, topic discussion, or undeterminable. Specifically, when the group chat message contains an interrogative sentence, it is an inquiry; when a certain amount of messages in the group chat message are discussing a certain topic, it is a topic discussion; otherwise, it is undeterminable. When it is an inquiry, determine the corresponding query question, and input the query question into the AI big data model to obtain the conversation reply content. When it is a topic discussion, determine the topic phrase being discussed, and input the topic phrase into the AI big data model to obtain the conversation reply content. When it is undeterminable, obtain the current social hot topics and conduct guided interaction based on the social hot topics.

[0090] As Figure 6As shown in the figure, as a preferred embodiment of the present invention, the steps of guiding interaction based on social hot topics specifically include:

[0091] S4041, determining group chat interest tags based on all historical topic phrases, and screening social hot topics according to the group chat interest tags;

[0092] S4042, retrieving the article titles of the screened social hot topics, and inputting the article titles into the group chat dialog box.

[0093] In the embodiment of the present invention, the interest tags of the group chat will be determined according to all historical topic phrases. For example, the interest tags are football, games, and cars. Then, the social hot topics will be screened according to the group chat interest tags. The screened social hot topics conform to the tag content. Finally, the relevant article titles of the screened social hot topics will be retrieved and input into the group chat dialog box to trigger discussions among group members.

[0094] As Figure 7 shown in the figure, the embodiment of the present invention also provides an AI robot dialogue control system based on big data search. The system includes:

[0095] A control parameter determination module 100, configured to receive group chat robot control information, where the group chat robot control information includes an independent dialogue frequency and a pause time;

[0096] A group chat robot startup module 200, configured to process and identify group chat messages. When there is a summon signal, the independent dialogue frequency is reached, or the pause time is reached, the group chat robot is enabled to have a dialogue;

[0097] A summon signal trigger module 300, configured to collect the group chat messages corresponding to the summon signal when there is a summon signal, and have a dialogue according to the command type of the group chat messages. The command types are inquiry query, statistical classification, or text summary;

[0098] A dialogue frequency trigger module 400, configured to collect the most recent N group chat messages when the independent dialogue frequency is reached, and have an interactive dialogue according to the most recent N group chat messages;

[0099] A pause time trigger module 500, configured to collect the most recent group chat message when the pause time is reached, and input the group chat message into the AI big data model to obtain a dialogue reply content.

[0100] As a preferred embodiment of the present invention, the group chat robot startup module 200 includes:

[0101] A summon signal determination unit, configured to determine whether a group chat robot summon character appears in the group chat message. When it appears, it is determined that there is a summon signal;

[0102] A conversation frequency determination unit, which is used to count the number of messages after the last group chat robot conversation in the group chat messages, and delete duplicate messages during the counting. When the number of messages reaches a preset number, it is determined that the autonomous conversation frequency is reached;

[0103] A pause time determination unit, which is used to determine whether the latest group chat message is an interrogative sentence. When it is, the sending time of the latest group chat message is timed to obtain a timing duration. When the timing duration reaches a preset duration, it is determined that the pause time is reached.

[0104] As a preferred embodiment of the present invention, the call signal trigger module 300 includes:

[0105] A command type determination unit, which is used to collect the group chat message corresponding to the call signal and determine the command type corresponding to the group chat message;

[0106] An inquiry query reply unit, which is used to input the group chat message into the AI big data model to obtain a conversation reply content when it is an inquiry query;

[0107] A statistical classification reply unit, which is used to perform message backtracking when it is statistical classification, determine the chat topic and the topic reply to the chat topic, and obtain statistical classification information based on the topic reply for statistics;

[0108] A text summary reply unit, which is used to perform message backtracking when it is text summary, determine the chat topic and the topic reply to the chat topic, and integrate the topic reply based on the AI big data model to obtain text summary information.

[0109] As a preferred embodiment of the present invention, the command type determination unit includes:

[0110] A message preprocessing subunit, which is used to preprocess the group chat message, and the preprocessing includes word segmentation and stop word removal;

[0111] A keyword matching subunit, which is used to match the preprocessed group chat message with a keyword library, and each command type corresponds to a keyword library;

[0112] A command type determination subunit, which is used to output a matching result and determine the command type corresponding to the group chat message according to the matching result.

[0113] The above only describes the preferred embodiments of the present invention in detail, and does not limit the present invention. Any modifications, equivalent replacements, and improvements made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

[0114] It should be understood that although the steps in the flowcharts of the embodiments of the present invention are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this article, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, at least a part of the steps in each embodiment may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or sub-steps or stages of other steps.

[0115] Those of ordinary skill in the art can understand that all or part of the processes of implementing the methods in the above embodiments can be completed by instructing relevant hardware through a computer program. The program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database or other medium used in the embodiments provided in the present application can include non-volatile and / or volatile memories. Non-volatile memories can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memories can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0116] After considering the specification and the disclosure of the embodiments, those skilled in the art will readily think of other embodiments of the present disclosure. The present application aims to cover any variations, uses or adaptations of the present disclosure, which follow the general principles of the present disclosure and include common general knowledge or conventional technical means in the technical field not disclosed in the present disclosure. The specification and the embodiments are only regarded as exemplary, and the true scope and spirit of the present disclosure are pointed out by the claims.

Claims

1. An AI robot dialogue control method based on big data search, characterized in that: The method comprises the following steps: Receiving group chat robot control information, wherein the group chat robot control information includes autonomous conversation frequency and pause time; Process and identify group chat messages, and enable the group chat robot to have a conversation when there is a call signal in the group chat message, or when the autonomous conversation frequency or idle time is reached; When there is a call signal, the group chat message corresponding to the call signal is collected, and a conversation is conducted according to the command type of the group chat message, which is an inquiry query, statistical classification or text summary; When the autonomous conversation frequency is reached, the most recent N group chat messages are collected and interactive conversations are conducted based on the most recent N group chat messages; When the idle time is reached, the latest group chat message is collected and input into the AI ​​big data model to obtain the conversation reply content; Among them, the step of processing and identifying the group chat message specifically includes: determining whether a group chat robot summoning character appears in the group chat message, and when it appears, determining that there is a summoning signal; counting the number of messages after the most recent group chat robot conversation in the group chat message, deleting duplicate messages during the counting, and when the number of messages reaches a preset number, determining that the autonomous conversation frequency has been reached; determining whether the latest group chat message is a question sentence, and when it is, timing the sending time of the latest group chat message to obtain a timing duration, and when the timing duration reaches a preset duration, determining that the pause time has been reached.

2. The AI ​​robot dialogue control method based on big data search according to claim 1 is characterized in that: The step of collecting the group chat message corresponding to the call signal and conducting a conversation according to the command type of the group chat message specifically includes: Collecting a group chat message corresponding to the summon signal, and determining a command type corresponding to the group chat message; When it is an inquiry, the group chat message is input into the AI ​​big data model to obtain the conversation reply content; When it is statistical classification, message backtracking is performed to determine the chat topic and the topic replies to the chat topic, and statistical classification information is obtained based on the topic replies; When summarizing the text, message backtracking is performed to determine the chat topic and the topic replies to the chat topic, and the topic replies are integrated based on the AI ​​big data model to obtain text summary information.

3. The AI ​​robot dialogue control method based on big data search according to claim 2 is characterized in that: The step of determining the command type corresponding to the group chat message specifically includes: Preprocessing the group chat message, the preprocessing including word segmentation and removal of stop words; Match the pre-processed group chat messages with the keyword library. Each command type corresponds to a keyword library. The matching result is output, and the command type corresponding to the group chat message is determined according to the matching result.

4. The AI ​​robot dialogue control method based on big data search according to claim 1 is characterized in that: The step of conducting a conversation based on the most recent N group chat messages specifically includes: Summarize the most recent N group chat messages and determine the type of the summarized message, where the type of the summarized message is inquiry, topic discussion, or cannot be determined; When it is an inquiry query, determine the corresponding query question, and input the query question into the AI ​​big data model to obtain the dialogue response content; When it is a topic discussion, determine the topic phrase to be discussed, and input the topic phrase into the AI ​​big data model to obtain the dialogue reply content; When you are unsure, obtain social hot topics and conduct guided interactions based on them.

5. The AI ​​robot dialogue control method based on big data search according to claim 4 is characterized in that: The step of conducting guided interaction based on social hot topics specifically includes: Determine group chat interest tags based on all historical topic phrases, and filter social hot topics based on group chat interest tags; Retrieve the article titles of the filtered social hot topics, and input the article titles into the group chat dialog box.

6. AI robot dialogue control system based on big data search, characterized in that: The system comprises: A control parameter determination module, used to receive group chat robot control information, wherein the group chat robot control information includes autonomous conversation frequency and pause time; The group chat robot startup module is used to process and identify group chat messages. When the group chat message contains a call signal, reaches the autonomous conversation frequency or idle time, the group chat robot will have a conversation. A call signal trigger module is used to collect the group chat message corresponding to the call signal when there is a call signal, and conduct a conversation according to the command type of the group chat message, where the command type is inquiry query, statistical classification or text summary; The conversation frequency trigger module is used to collect the latest N group chat messages when the autonomous conversation frequency is reached, and conduct interactive conversations based on the latest N group chat messages; The idle time trigger module is used to collect the latest group chat messages when the idle time is reached, and input the group chat messages into the AI ​​big data model to obtain the dialogue reply content; Among them, the group chat robot startup module includes: a summoning signal determination unit, used to determine whether a group chat robot summoning character appears in the group chat message, and when it appears, it is determined that there is a summoning signal; a conversation frequency determination unit, used to count the number of messages after the most recent group chat robot conversation in the group chat message, and delete duplicate messages during the statistics. When the number of messages reaches a preset number, it is determined that the autonomous conversation frequency has been reached; a pause time determination unit, used to determine whether the latest group chat message is a question sentence. When it is, the sending time of the latest group chat message is timed to obtain the timing duration. When the timing duration reaches the preset duration, it is determined that the pause time has been reached.

7. The AI ​​robot dialogue control system based on big data search according to claim 6 is characterized in that: The calling signal triggering module comprises: A command type determination unit, used to collect a group chat message corresponding to the summon signal, and determine the command type corresponding to the group chat message; An inquiry and query reply unit, used for inputting the group chat message into the AI ​​big data model to obtain a dialogue reply content when it is an inquiry and query; A statistical classification reply unit, used for performing message backtracking, determining a chat topic and a topic reply to the chat topic, and obtaining statistical classification information based on statistics of the topic reply when statistical classification is performed; The text summary reply unit is used to perform message backtracking, determine the chat topic and the topic reply to the chat topic when summarizing the text, and integrate the topic reply based on the AI ​​big data model to obtain text summary information.

8. The AI ​​robot dialogue control system based on big data search according to claim 7 is characterized in that: The command type determination unit comprises: A message preprocessing subunit, used to preprocess the group chat message, the preprocessing including word segmentation and stop word removal; The keyword matching subunit is used to match the pre-processed group chat message with the keyword library. Each command type corresponds to a keyword library. The command type determination subunit is used to output a matching result and determine the command type corresponding to the group chat message according to the matching result.

Images