Robot intelligent chat system and method based on artificial intelligence

Abstract

The invention discloses a robot intelligent chat system and method based on artificial intelligence. The robot intelligent chat system comprises an information data storage module, a man-machine binding module, a face recognition module, an image acquisition module, a voice recognition module, an infrared distance measurement module, a wireless network communication module, a mobile terminal positioning module, a consumption record calling module, a scene analysis recognition module and a robot intelligent control module. The beneficial effects of the invention lie in that by acquiring the image signal and the voice signal, whether the current person is an acquaintance or a stranger is judged according to the face recognition and voice recognition results, and then different dialogue modes are adopted for the acquaintance or the stranger according to the preset dialogue mode, so that the system is more intelligent, and the system can be bound with the mobile terminal, thereby improving the user experience. Different dialogue contents can be generated according to the real-time geographic position and the consumption record of the mobile terminal, and the bound user can be helped to know the daily journey of the user corresponding to the mobile terminal.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to an artificial intelligence-based robot intelligent chat system and method. Background Art

[0002] An intelligent chatbot is a computer program that communicates through dialogue or text and can simulate human conversation. Chatbots can also be used for practical purposes, such as customer service or consultation. Some chatbots are equipped with natural language processing systems, but most simple systems only find the most appropriate response sentence from the database based on the input keywords. Currently, chatbots are part of virtual assistants and can be connected to many organizations' applications, websites, and instant messaging platforms. Artificial intelligence refers to a branch of computer science that attempts to understand the essence of intelligence and produce a new type of intelligent machine that can respond in a similar way to human intelligence.

[0003] However, the existing robot intelligent chat technology still has many shortcomings. Due to the immaturity of the technology, chat robots cannot completely achieve the same chat method as humans. Although they can all chat, on the whole, most chat robots answer questions irrelevantly, resulting in the actual use effect being far below public expectations. In addition, the contextual semantic understanding ability of multiple rounds of interactions is poor, resulting in a low fluency of user experience. The existing robot intelligent chat technology is mostly in the stage where humans actively communicate with robots, and it is impossible for robots to actively communicate with humans. In addition, the number of lonely elderly people is gradually increasing. Their children are too busy at work to give them timely care. The elderly want to know about their children's recent situation but are afraid of disturbing their work, which leads to the lack of contact between the elderly and their children.

[0004] Based on the above problems, it is urgent to propose a robot intelligent chat system and method based on artificial intelligence. By collecting image signals and voice signals, it is judged whether the current person is an acquaintance or a stranger according to the results of face recognition and voice recognition, and then different conversation methods are adopted for acquaintances or strangers according to the pre-set conversation mode, making it more intelligent and capable of binding to mobile terminals. Different conversation contents can be generated according to the real-time geographic location and consumption records of the mobile terminal, which can help bound users understand the daily itinerary of the corresponding user of the mobile terminal. Summary of the invention

[0005] The purpose of the present invention is to provide a robot intelligent chat system and method based on artificial intelligence to solve the problems raised in the above background technology.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: A robot intelligent chat system based on artificial intelligence, the robot intelligent chat system includes an information data storage module, a human-machine binding module, a face recognition module, an image acquisition module, a voice recognition module, an infrared ranging module, a wireless network communication module, a mobile terminal positioning module, a consumption record retrieval module, a scenario analysis and recognition module, and a robot intelligent control module. The information data storage module is used to store basic personal information, which includes facial information and voice information. When storing basic personal information, the information data storage module also stores the collection time node of the basic personal information. The information data storage module is also used to store the conversation data between the user and others according to the time information. The human-machine binding module is used to establish a binding relationship between the user and the robot, and store the user information bound to the robot in the information data storage module. The image acquisition module is used to collect video images in the surrounding environment. The face recognition module is used to recognize the facial information in the collected image. The voice recognition module is used to recognize the voice information in the surrounding environment. The infrared ranging module is used to measure the distance between the person and the robot. The wireless network communication module Used to establish communication between the robot and the mobile terminal, the mobile terminal positioning module is used to obtain the real-time position of the mobile terminal bound to the robot, the consumption record retrieval module is used to obtain the consumption record of the mobile terminal at the position according to the real-time position of the mobile terminal, if the consumption record of the mobile terminal is not obtained within a certain time interval when the mobile terminal position is obtained, then the previous consumption record of the mobile terminal at the position is obtained, the scenario analysis and recognition module is used to perform scenario analysis based on the collected voice signals, video images and the real-time position of the mobile terminal, the robot intelligent control module is used to control the communication between the robot and the user according to the analysis and recognition results of the scenario analysis and recognition module, and the robot intelligent control module is also used to generate multiple dialogue modes based on the daily conversations between the bound user and others.

[0007] Furthermore, the face recognition module is connected to the image acquisition module, the information data storage module and the infrared ranging module. When the image acquisition module acquires an image, the face information in the image is recognized by the face recognition module, and the face information is the first face information. The information data storage module is used to obtain the stored second face information. The scenario analysis and recognition module further compares the first face information with the second face information, that is, determines whether the first face information currently exists in the information data storage module. If the first facial information currently exists in the information data storage module, further obtaining a collection time node related to the first facial information, calculating the shortest time interval between the collection time node and the current time node, and the robot intelligent control module selecting a corresponding dialogue mode according to the time interval; If the first facial information does not currently exist in the information data storage module, the image acquisition module is further used to collect a video image of another person within a certain range corresponding to the first face. The image acquisition module also obtains the third facial information of the user bound to the robot through the information data storage module, and determines whether the bound user appears within the certain range according to the third facial information, and further records the residence time and number of appearances of the bound user within the certain range. The robot can determine whether the current visitor is an acquaintance or a stranger according to the result of face recognition. The dialogue mode for acquaintances and strangers is also different. Acquaintances can be greeted, and strangers can be asked about the reason for their visit. In addition, the storage of facial information also needs to be judged. According to the actual scene, it is determined whether the two people are currently chatting. Moreover, according to the distance between the two people and the time and number of conversations, the person corresponding to the facial information stored in the information data storage module can be regarded as an acquaintance of the user bound to the robot. In this way, when the bound user is not at home or cannot greet the visitor in the first time, the robot can perform face recognition to determine whether it is an acquaintance or a stranger, and actively greet the visitor or the reason for the visit, referring to different dialogue modes.

[0008] Furthermore, the scene analysis and recognition module records the user's stay time and number of appearances within the certain range through the image acquisition module and the face recognition module, and the scene analysis and recognition module records the number of appearances as , , ,..., , , and record each stay time corresponding to the number of occurrences as , , ,..., , , further calculate the total number of occurrences and the total residence time, When the total number of occurrences is greater than or equal to a first preset value, the information data storage module stores the first face information; When the total stay time is greater than or equal to a second preset value, the information data storage stores the first facial information.

[0009] Further, the scenario analysis and recognition module is connected to a speech recognition module, the speech recognition module collects speech signals within the certain range, and recognizes the collected speech signals, which are first speech signals, and obtains the stored second speech signals through the information data storage module. The scene analysis and recognition module further compares the first voice signal with the second voice signal, that is, determines whether the first voice signal currently exists in the information data storage module. If the first voice signal currently exists in the information data storage module, further obtaining a collection time node related to the first voice signal, calculating the shortest time interval between the collection time node and the current time node, and the robot intelligent control module selecting a corresponding dialogue mode according to the time interval; If the first voice signal does not exist in the information data storage module, the voice signal is further collected through the voice recognition module. The scenario analysis and recognition module obtains the distance between the bound user and others through the image acquisition module, the face recognition module and the infrared ranging module. If the voice recognition module collects the voice signal, the voice signal is stored through the data storage module, and a corresponding relationship is established between the voice signal and the face information, and the collection time node is stored at the same time. It can also be judged whether the current person is an acquaintance or a stranger based on the recognition of the voice signal. The dialogue mode for acquaintances and strangers is also different. Acquaintances can be greeted and strangers can be asked about the reason for their visit. The storage of voice information also needs to be judged. It is judged according to the actual scene whether the two people are currently chatting. Moreover, according to the distance between the two people and the time and number of conversations, the person corresponding to the face information stored in the information data storage module can be regarded as an acquaintance of the user bound to the robot. In this way, when the bound user is not at home or cannot greet the visitor in the first time, the robot can perform face recognition to judge whether it is an acquaintance or a stranger, and actively greet them or ask the reason for the visit, referring to different dialogue modes.

[0010] Furthermore, the scenario analysis and recognition module is connected to the infrared distance measurement module, and the scenario analysis and recognition module obtains the distance between other people and the robot through the face recognition module, the voice recognition module and the infrared distance measurement module. If face information or voice signal is collected, the scenario analysis and recognition module obtains the current number of people according to the collected face information or voice signal, and further measures the distance between each person and the robot through the infrared ranging module. The scenario analysis and recognition module obtains the stored information data through the information data storage module, and determines whether the currently collected face information or voice signal exists in the information data storage module. Determine the current number of acquaintances and strangers, the facial information and voice information of acquaintances, i.e., the other party, exists in the information data storage module, and the facial information and voice information of strangers, i.e., the other party, does not exist in the information data storage module, The robot intelligent control module selects corresponding dialogue modes one by one according to the measured distance, and adopts different dialogue modes for acquaintances and strangers. When multiple facial information or voice signals are collected, it means that multiple people are currently present, and it is judged whether the multiple people are acquaintances of the bound user, or strangers, or both acquaintances and strangers. Then, different dialogue modes can be selected one by one according to the distance and the judgment result, and they can be greeted or chatted with.

[0011] Furthermore, the wireless network communication module establishes communication between the bound user and other people's mobile terminals, the mobile terminal positioning module obtains the real-time location of the mobile terminal, and the mobile terminal user can turn on and off the positioning function by himself. The robot intelligent control module further obtains the consumption record at the corresponding real-time location based on the acquired real-time location of the mobile terminal through the consumption record, and the robot intelligent control module further generates the travel trajectory of the mobile terminal user based on the consumption record. The robot intelligent control module generates the conversation content about the mobile terminal user based on the travel trajectory of the corresponding mobile terminal user. The robot intelligent control module can recognize the voice of the bound user through the voice recognition module, extract the voice content keywords, match the corresponding mobile terminal user, and so on. The above-mentioned conversation between the robot intelligent control module and the bound user about the mobile terminal user is a common social phenomenon nowadays. Children are too busy with work to take care of the elderly all the time, and the elderly are unable to express their longing for their children for fear of disturbing their children's work. Therefore, it is a common phenomenon that there is little contact between children and the elderly, but the elderly want to know about their children's recent situation, perhaps where they go and what they do every day. Therefore, the children's mobile terminal can be bound to obtain the real-time location based on the real-time positioning of the mobile terminal. The positioning of the mobile terminal can also be turned on or off by itself. The robot can also analyze what the customer corresponding to the current mobile terminal is doing based on the consumption records and consumption locations. The robot can generate corresponding dialogue content based on the results of the analysis and chat with the elderly.

[0012] Furthermore, the robot intelligent control module records the conversation data between the bound user and others, stores the conversation data through the information data storage module, and obtains the time interval between each stored conversation data. The robot intelligent control module further extracts the conversation content according to the conversation data, and establishes different conversation content databases according to different people. The robot intelligent control module classifies the conversation contents whose time interval difference is within a certain range into one category according to the time interval, and classifies and stores the conversation contents belonging to one category. The robot intelligent control module generates several conversation modes according to the time interval, and establishes a corresponding relationship between the conversation mode and other people. The robot intelligent control module recognizes the facial information or the voice information through the facial recognition module or the voice recognition module, and further selects a corresponding dialogue mode according to the corresponding relationship between the dialogue mode and others.

[0013] Furthermore, a robot intelligent chat method based on artificial intelligence comprises the following steps: S1: Set the corresponding dialogue mode; S2: Perform face recognition and control the robot's actions according to the face recognition results; S3: Perform voice signal recognition and control the robot's actions according to the voice signal recognition results; S4: According to the distance measurement between the human and the robot, the robot is controlled to adopt the corresponding dialogue mode; S5: Generate corresponding dialogue content according to the real-time location of the bound mobile terminal, and control the robot to communicate with the bound user.

[0014] Furthermore, the intelligent chatting method further comprises the following steps: S1-1: The robot intelligent control module records the conversation data between the bound user and others, stores the conversation data through the information data storage module, and obtains the time interval between each stored conversation data. The robot intelligent control module further extracts the conversation content based on the conversation data, and establishes different conversation content databases according to different people. The robot intelligent control module classifies the conversation content with a time interval difference within a certain range into one category according to the time interval, and classifies and stores the conversation content belonging to one category. The robot intelligent control module generates several conversation modes according to the time interval, and establishes the corresponding relationship between the conversation mode and others. The robot intelligent control module recognizes the face information or voice information through the face recognition module or the voice recognition module, and further selects the corresponding dialogue mode according to the corresponding relationship between the dialogue mode and others; S2-1: The face recognition module is connected to the image acquisition module, the information data storage module and the infrared ranging module. When the image acquisition module acquires an image, the face recognition module identifies the face information in the image, which is the first face information, and obtains the stored second face information through the information data storage module. The scenario analysis and recognition module further compares the first face information with the second face information, that is, determines whether the current first face information exists in the information data storage module. If the current first face information exists in the information data storage module, further obtaining the collection time node related to the first face information, calculating the shortest time interval between the collection time node and the current time node, and the robot intelligent control module selecting the corresponding dialogue mode according to the time interval; If the current first face information does not exist in the information data storage module, the image acquisition module is further used to collect a video image of another person within a certain range corresponding to the first face. The image acquisition module also obtains the third face information of the user bound to the robot through the information data storage module, and determines whether the bound user appears within the certain range based on the third face information, and further records the stay time and number of appearances of the bound user within the certain range; The scene analysis and recognition module records the user's stay time and appearance times within a certain range through the image acquisition module and the face recognition module. The scene analysis and recognition module records the appearance times as , , ,..., , , and record each stay time corresponding to the number of occurrences as , , ,..., , , further calculate the total number of occurrences and the total residence time, When the total number of occurrences is greater than or equal to a first preset value, the information data storage module stores the first face information; When the total stay time is greater than or equal to a second preset value, the information data storage stores the first face information; S3-1: The scenario analysis and recognition module is connected to the speech recognition module. The speech recognition module collects speech signals within a certain range and recognizes the collected speech signals, which are first speech signals. The information data storage module obtains the stored second speech signals. The scenario analysis and recognition module further compares the first voice signal with the second voice signal, that is, determines whether the current first voice signal exists in the information data storage module. If the current first voice signal exists in the information data storage module, then further obtaining the collection time node related to the first voice signal, calculating the shortest time interval between the collection time node and the current time node, and the robot intelligent control module selecting the corresponding dialogue mode according to the time interval; If the current first voice signal does not exist in the information data storage module, the voice signal is further collected through the voice recognition module, and the scene analysis and recognition module obtains the distance between the bound user and others through the image acquisition module, the face recognition module and the infrared ranging module. If the voice recognition module collects the voice signal, the voice signal is stored through the data storage module, and a corresponding relationship is established between the voice signal and the face information, and the collection time node is stored at the same time; S4-1: The scenario analysis and recognition module is connected to the infrared distance measurement module. The scenario analysis and recognition module obtains the distance between other people and the robot through the face recognition module, voice recognition module and infrared distance measurement module. If face information or voice signals are collected, the scenario analysis and recognition module obtains the current number of people based on the collected face information or voice signals, and further measures the distance between each person and the robot through the infrared ranging module. The scenario analysis and recognition module obtains the stored information data through the information data storage module, and determines whether the currently collected face information or voice signals exist in the information data storage module. Determine the current number of acquaintances and strangers. The facial information and voice information of acquaintances, i.e., the other party, exist in the information data storage module, while the facial information and voice information of strangers, i.e., the other party, do not exist in the information data storage module. The robot intelligent control module selects the corresponding dialogue mode according to the measured distance, and adopts different dialogue modes for acquaintances and strangers; S5-1: The wireless network communication module establishes communication between the bound user and other mobile terminals. The mobile terminal positioning module obtains the real-time location of the mobile terminal. The mobile terminal user can turn the positioning function on and off by himself. The robot intelligent control module obtains the consumption record at the corresponding real-time location based on the obtained real-time location of the mobile terminal and the consumption record. The robot intelligent control module further generates the travel trajectory of the mobile terminal user based on the consumption record. The robot intelligent control module generates the conversation content about the mobile terminal user based on the travel trajectory of the corresponding mobile terminal user. The robot intelligent control module can recognize the voice of the bound user through the voice recognition module, extract the voice content keywords, match the corresponding mobile terminal user, and the robot intelligent control module conducts a conversation with the bound user about the mobile terminal user.

[0015] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: the present invention collects image signals and voice signals, determines whether the current person is an acquaintance or a stranger according to the results of face recognition and voice recognition, and then adopts different conversation methods for acquaintances or strangers according to the pre-set conversation mode, making it more intelligent, and can also bind to a mobile terminal, and generate different conversation contents according to the real-time geographic location and consumption records of the mobile terminal, which can help the bound user understand the daily itinerary of the user corresponding to the mobile terminal. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings: Figure 1 It is a module schematic diagram of a robot intelligent chat system based on artificial intelligence of the present invention; Figure 2 It is a schematic diagram of the steps of a robot intelligent chatting method based on artificial intelligence of the present invention. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0018] See also Figure 1-Figure 2 , the present invention provides a technical solution: A robot intelligent chat system based on artificial intelligence, the robot intelligent chat system includes an information data storage module, a human-machine binding module, a face recognition module, an image acquisition module, a voice recognition module, an infrared ranging module, a wireless network communication module, a mobile terminal positioning module, a consumption record retrieval module, a scenario analysis and recognition module, and a robot intelligent control module. The information data storage module is used to store basic personal information, including facial information and voice information. When storing basic personal information, the information data storage module also stores the collection time node of the basic personal information. The information data storage module is also used to store the conversation data between the user and others according to the time information. The human-machine binding module is used to establish a binding relationship between the user and the robot, and store the user information bound to the robot into the information data storage module. The image acquisition module is used to collect video images in the surrounding environment. The face recognition module is used to recognize the face information in the collected image. The voice recognition module is used to recognize the voice information in the surrounding environment. The infrared ranging module is used to measure the distance between the human and the robot. The wireless network communication module is used for the machine Communication is established between a person and a mobile terminal. The mobile terminal positioning module is used to obtain the real-time location of the mobile terminal bound to the robot. The consumption record retrieval module is used to obtain the consumption record of the mobile terminal at this location based on the real-time location of the mobile terminal. If the consumption record of the mobile terminal is not obtained within a certain time interval when the location of the mobile terminal is obtained, the previous consumption record of the mobile terminal at this location is obtained. The scenario analysis and recognition module is used to perform scenario analysis based on the collected voice signals, video images and the real-time location of the mobile terminal. The robot intelligent control module is used to control the communication between the robot and the user based on the analysis and recognition results of the scenario analysis and recognition module. The robot intelligent control module is also used to generate a variety of dialogue modes based on the daily conversations between the bound user and others.

[0019] The face recognition module is connected to the image acquisition module, the information data storage module and the infrared ranging module. When the image acquisition module acquires an image, the face information in the image is recognized by the face recognition module, and the face information is the first face information. The information data storage module is used to obtain the stored second face information. The scenario analysis and recognition module further compares the first face information with the second face information, that is, determines whether the current first face information exists in the information data storage module. If the current first face information exists in the information data storage module, further obtaining the collection time node related to the first face information, calculating the shortest time interval between the collection time node and the current time node, and the robot intelligent control module selecting the corresponding dialogue mode according to the time interval; If the current first facial information does not exist in the information data storage module, the image acquisition module is further used to collect video images of other people within a certain range corresponding to the first face. The image acquisition module also obtains the third facial information of the user bound to the robot through the information data storage module, and determines whether the bound user appears within a certain range based on the third facial information, and further records the bound user's stay time and number of appearances within a certain range.

[0020] The scene analysis and recognition module records the user's stay time and appearance times within a certain range through the image acquisition module and the face recognition module. The scene analysis and recognition module records the appearance times as , , ,..., , , and record each stay time corresponding to the number of occurrences as , , ,..., , , further calculate the total number of occurrences and the total residence time, When the total number of occurrences is greater than or equal to a first preset value, the information data storage module stores the first face information; When the total stay time is greater than or equal to a second preset value, the information data storage stores the first facial information.

[0021] The scenario analysis recognition module is connected to the speech recognition module. The speech recognition module collects speech signals within a certain range and recognizes the collected speech signals, which are first speech signals. The information data storage module obtains the stored second speech signals. The scenario analysis and recognition module further compares the first voice signal with the second voice signal, that is, determines whether the current first voice signal exists in the information data storage module. If the current first voice signal exists in the information data storage module, then further obtaining the collection time node related to the first voice signal, calculating the shortest time interval between the collection time node and the current time node, and the robot intelligent control module selecting the corresponding dialogue mode according to the time interval; If the current first voice signal does not exist in the information data storage module, the voice signal is further collected through the voice recognition module, and the scene analysis and recognition module obtains the distance between the bound user and others through the image acquisition module, the face recognition module and the infrared ranging module. If the voice recognition module collects the voice signal, the voice signal is stored through the data storage module, and a corresponding relationship between the voice signal and the face information is established, and the collection time node is stored at the same time.

[0022] The scenario analysis and recognition module is connected to the infrared distance measurement module. The scenario analysis and recognition module obtains the distance between other people and the robot through the face recognition module, voice recognition module and infrared distance measurement module. If face information or voice signals are collected, the scenario analysis and recognition module obtains the current number of people based on the collected face information or voice signals, and further measures the distance between each person and the robot through the infrared ranging module. The scenario analysis and recognition module obtains the stored information data through the information data storage module, and determines whether the currently collected face information or voice signals exist in the information data storage module. Determine the current number of acquaintances and strangers. The facial information and voice information of acquaintances, i.e., the other party, exist in the information data storage module, while the facial information and voice information of strangers, i.e., the other party, do not exist in the information data storage module. The robot's intelligent control module selects the corresponding dialogue mode according to the measured distance, and adopts different dialogue modes for acquaintances and strangers.

[0023] The wireless network communication module establishes communication between the bound user and other mobile terminals. The mobile terminal positioning module obtains the real-time location of the mobile terminal. The mobile terminal user can turn the positioning function on and off by himself. The robot intelligent control module obtains the consumption record at the corresponding real-time location based on the acquired real-time location of the mobile terminal and through the consumption record. The robot intelligent control module further generates the travel trajectory of the mobile terminal user based on the consumption record. The robot intelligent control module generates the conversation content about the mobile terminal user based on the travel trajectory of the corresponding mobile terminal user. The robot intelligent control module can recognize the voice of the bound user through the voice recognition module, extract the voice content keywords, match the corresponding mobile terminal user, and the robot intelligent control module conducts a conversation with the bound user about the mobile terminal user.

[0024] The robot intelligent control module records the conversation data between the bound user and others, stores the conversation data through the information data storage module, and obtains the time interval between each stored conversation data. The robot intelligent control module further extracts the conversation content based on the conversation data, and establishes different conversation content databases according to different people. The robot intelligent control module classifies the conversation content with a time interval difference within a certain range into one category according to the time interval, and classifies and stores the conversation content belonging to one category. The robot intelligent control module generates several conversation modes according to the time interval, and establishes the corresponding relationship between the conversation mode and others. The robot intelligent control module recognizes the face information or voice information through the face recognition module or the voice recognition module, and further selects the corresponding dialogue mode according to the corresponding relationship between the dialogue mode and others.

[0025] A robot intelligent chat method based on artificial intelligence, the intelligent chat method comprising the following steps: S1: Set the corresponding dialogue mode; S2: Perform face recognition and control the robot's actions according to the face recognition results; S3: Perform voice signal recognition and control the robot's actions according to the voice signal recognition results; S4: According to the distance measurement between the human and the robot, the robot is controlled to adopt the corresponding dialogue mode; S5: Generate corresponding dialogue content according to the real-time location of the bound mobile terminal, and control the robot to communicate with the bound user.

[0026] The intelligent chatting method also includes the following steps: S1-1: The robot intelligent control module records the conversation data between the bound user and others, stores the conversation data through the information data storage module, and obtains the time interval between each stored conversation data. The robot intelligent control module further extracts the conversation content based on the conversation data, and establishes different conversation content databases according to different people. The robot intelligent control module classifies the conversation content with a time interval difference within a certain range into one category according to the time interval, and classifies and stores the conversation content belonging to one category. The robot intelligent control module generates several conversation modes according to the time interval, and establishes the corresponding relationship between the conversation mode and others. The robot intelligent control module recognizes the face information or voice information through the face recognition module or the voice recognition module, and further selects the corresponding dialogue mode according to the corresponding relationship between the dialogue mode and others; S2-1: The face recognition module is connected to the image acquisition module, the information data storage module and the infrared ranging module. When the image acquisition module acquires an image, the face recognition module identifies the face information in the image, which is the first face information, and obtains the stored second face information through the information data storage module. The scenario analysis and recognition module further compares the first face information with the second face information, that is, determines whether the current first face information exists in the information data storage module. If the current first face information exists in the information data storage module, further obtaining the collection time node related to the first face information, calculating the shortest time interval between the collection time node and the current time node, and the robot intelligent control module selecting the corresponding dialogue mode according to the time interval; If the current first face information does not exist in the information data storage module, the image acquisition module is further used to collect a video image of another person within a certain range corresponding to the first face. The image acquisition module also obtains the third face information of the user bound to the robot through the information data storage module, and determines whether the bound user appears within the certain range based on the third face information, and further records the stay time and number of appearances of the bound user within the certain range; The scene analysis and recognition module records the user's stay time and appearance times within a certain range through the image acquisition module and the face recognition module. The scene analysis and recognition module records the appearance times as , , ,..., , , and record each stay time corresponding to the number of occurrences as , , ,..., , , further calculate the total number of occurrences and the total residence time, When the total number of occurrences is greater than or equal to a first preset value, the information data storage module stores the first face information; When the total stay time is greater than or equal to a second preset value, the information data storage stores the first face information; S3-1: The scenario analysis and recognition module is connected to the speech recognition module. The speech recognition module collects speech signals within a certain range and recognizes the collected speech signals, which are first speech signals. The information data storage module obtains the stored second speech signals. The scenario analysis and recognition module further compares the first voice signal with the second voice signal, that is, determines whether the current first voice signal exists in the information data storage module. If the current first voice signal exists in the information data storage module, then further obtaining the collection time node related to the first voice signal, calculating the shortest time interval between the collection time node and the current time node, and the robot intelligent control module selecting the corresponding dialogue mode according to the time interval; If the current first voice signal does not exist in the information data storage module, the voice signal is further collected through the voice recognition module, and the scene analysis and recognition module obtains the distance between the bound user and others through the image acquisition module, the face recognition module and the infrared ranging module. If the voice recognition module collects the voice signal, the voice signal is stored through the data storage module, and a corresponding relationship is established between the voice signal and the face information, and the collection time node is stored at the same time; S4-1: The scenario analysis and recognition module is connected to the infrared distance measurement module. The scenario analysis and recognition module obtains the distance between other people and the robot through the face recognition module, voice recognition module and infrared distance measurement module. If face information or voice signals are collected, the scenario analysis and recognition module obtains the current number of people based on the collected face information or voice signals, and further measures the distance between each person and the robot through the infrared ranging module. The scenario analysis and recognition module obtains the stored information data through the information data storage module, and determines whether the currently collected face information or voice signals exist in the information data storage module. Determine the current number of acquaintances and strangers. The facial information and voice information of acquaintances, i.e., the other party, exist in the information data storage module, while the facial information and voice information of strangers, i.e., the other party, do not exist in the information data storage module. The robot intelligent control module selects the corresponding dialogue mode according to the measured distance, and adopts different dialogue modes for acquaintances and strangers; S5-1: The wireless network communication module establishes communication between the bound user and other mobile terminals. The mobile terminal positioning module obtains the real-time location of the mobile terminal. The mobile terminal user can turn the positioning function on and off by himself. The robot intelligent control module obtains the consumption record at the corresponding real-time location based on the obtained real-time location of the mobile terminal and the consumption record. The robot intelligent control module further generates the travel trajectory of the mobile terminal user based on the consumption record. The robot intelligent control module generates the conversation content about the mobile terminal user based on the travel trajectory of the corresponding mobile terminal user. The robot intelligent control module can recognize the voice of the bound user through the voice recognition module, extract the voice content keywords, match the corresponding mobile terminal user, and the robot intelligent control module conducts a conversation with the bound user about the mobile terminal user.

[0027] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device 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 device.

[0028] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A robot intelligent chat system based on artificial intelligence, characterized by: The robot intelligent chat system includes an information data storage module, a human-machine binding module, a face recognition module, an image acquisition module, a voice recognition module, an infrared distance measurement module, a wireless network communication module, a mobile terminal positioning module, a consumption record retrieval module, a scenario analysis and recognition module, and a robot intelligent control module. The information data storage module is used to store basic personal information, which includes facial information and voice information. When storing basic personal information, the information data storage module also stores the collection time node of the basic personal information. The information data storage module is also used to store the conversation data between the user and others according to the time information. The human-machine binding module is used to establish a binding relationship between the user and the robot, and store the user information bound to the robot in the information data storage module. The image acquisition module is used to collect video images in the surrounding environment. The face recognition module is used to recognize the facial information in the collected image. The voice recognition module is used to recognize the voice information in the surrounding environment. The infrared ranging module is used to measure the distance between the person and the robot. The wireless network communication module Used to establish communication between the robot and the mobile terminal, the mobile terminal positioning module is used to obtain the real-time position of the mobile terminal bound to the robot, the consumption record retrieval module is used to obtain the consumption record of the mobile terminal at the position according to the real-time position of the mobile terminal, if the consumption record of the mobile terminal is not obtained within a certain time interval when the mobile terminal position is obtained, then the previous consumption record of the mobile terminal at the position is obtained, the scenario analysis and recognition module is used to perform scenario analysis based on the collected voice signals, video images and the real-time position of the mobile terminal, the robot intelligent control module is used to control the communication between the robot and the user according to the analysis and recognition results of the scenario analysis and recognition module, and the robot intelligent control module is also used to generate multiple dialogue modes based on the daily conversations between the bound user and others.

2. The robot intelligent chat system based on artificial intelligence according to claim 1, characterized in that: The face recognition module is connected to the image acquisition module, the information data storage module and the infrared ranging module. When the image acquisition module acquires an image, the face information in the image is recognized by the face recognition module, and the face information is the first face information. The information data storage module is used to obtain the stored second face information. The scene analysis and recognition module further compares the first face information with the second face information, that is, determines whether the first face information currently exists in the information data storage module. If the first facial information currently exists in the information data storage module, further obtaining a collection time node related to the first facial information, calculating the shortest time interval between the collection time node and the current time node, and the robot intelligent control module selecting a corresponding dialogue mode according to the time interval; If the first facial information currently does not exist in the information data storage module, the image acquisition module is further used to collect video images of other people within a certain range corresponding to the first face. The image acquisition module also obtains the third facial information of the user bound to the robot through the information data storage module, and determines whether the bound user appears in the certain range based on the third facial information, and further records the bound user's stay time and number of appearances in the certain range.

3. The robot intelligent chat system based on artificial intelligence according to claim 2, characterized in that: The scene analysis and recognition module records the user's stay time and number of appearances within the certain range through the image acquisition module and the face recognition module. The scene analysis and recognition module records the number of appearances as , , ,..., , , and record each stay time corresponding to the number of occurrences as , , ,..., , , further calculate the total number of occurrences and the total residence time, When the total number of occurrences is greater than or equal to a first preset value, the information data storage module stores the first face information; When the total stay time is greater than or equal to a second preset value, the information data storage stores the first facial information.

4. The robot intelligent chat system based on artificial intelligence according to claim 1, characterized in that: The scenario analysis and recognition module is connected to the voice recognition module, the voice recognition module collects the voice signal within the certain range, and recognizes the collected voice signal, which is the first voice signal, and obtains the stored second voice signal through the information data storage module, The scene analysis and recognition module further compares the first voice signal with the second voice signal, that is, determines whether the first voice signal currently exists in the information data storage module. If the first voice signal currently exists in the information data storage module, further obtaining a collection time node related to the first voice signal, calculating the shortest time interval between the collection time node and the current time node, and the robot intelligent control module selecting a corresponding dialogue mode according to the time interval; If the first voice signal does not currently exist in the information data storage module, the voice signal is further collected through the voice recognition module, and the scene analysis and recognition module obtains the distance between the bound user and others through the image acquisition module, the face recognition module and the infrared ranging module. If the voice recognition module collects the voice signal, the voice signal is stored through the data storage module, and a corresponding relationship between the voice signal and the face information is established, and the collection time node is stored at the same time.

5. The robot intelligent chat system based on artificial intelligence according to claim 1, characterized in that: The scene analysis and recognition module is connected to the infrared distance measurement module, and the scene analysis and recognition module obtains the distance between other people and the robot through the face recognition module, the voice recognition module and the infrared distance measurement module. If face information or voice signal is collected, the scenario analysis and recognition module obtains the current number of people according to the collected face information or voice signal, and further measures the distance between each person and the robot through the infrared ranging module. The scenario analysis and recognition module obtains the stored information data through the information data storage module, and determines whether the currently collected face information or voice signal exists in the information data storage module. Determine the current number of acquaintances and strangers, the facial information and voice information of acquaintances, i.e., the other party, exists in the information data storage module, and the facial information and voice information of strangers, i.e., the other party, does not exist in the information data storage module, The robot intelligent control module selects corresponding dialogue modes one by one according to the measured distance, and adopts different dialogue modes for acquaintances and strangers.

6. The robot intelligent chat system based on artificial intelligence according to claim 1, characterized in that: The wireless network communication module establishes communication between the bound user and other mobile terminals, the mobile terminal positioning module obtains the real-time location of the mobile terminal, and the mobile terminal user can turn the positioning function on and off by himself. The robot intelligent control module further obtains the consumption record at the corresponding real-time location based on the acquired real-time location of the mobile terminal and the consumption record, and the robot intelligent control module further generates the travel trajectory of the mobile terminal user based on the consumption record. The robot intelligent control module generates the conversation content about the mobile terminal user based on the travel trajectory of the corresponding mobile terminal user. The robot intelligent control module can recognize the voice of the bound user through the voice recognition module, extract the voice content keywords, match the corresponding mobile terminal user, and the robot intelligent control module conducts a conversation with the bound user about the mobile terminal user.

7. The robot intelligent chat system based on artificial intelligence according to claim 1, characterized in that: The robot intelligent control module records the conversation data between the bound user and others, stores the conversation data through the information data storage module, and obtains the time interval between each stored conversation data. The robot intelligent control module further extracts the conversation content according to the conversation data, and establishes different conversation content databases according to different people. The robot intelligent control module classifies the conversation contents whose time interval difference is within a certain range into one category according to the time interval, and classifies and stores the conversation contents belonging to one category. The robot intelligent control module generates several conversation modes according to the time interval, and establishes a corresponding relationship between the conversation mode and other people. The robot intelligent control module recognizes the facial information or the voice information through the facial recognition module or the voice recognition module, and further selects a corresponding dialogue mode according to the corresponding relationship between the dialogue mode and others.

8. A robot intelligent chat method based on artificial intelligence, characterized in that: The intelligent chatting method comprises the following steps: S1: Set the corresponding dialogue mode; S2: Perform face recognition and control the robot's actions according to the face recognition results; S3: Perform voice signal recognition and control the robot's actions according to the voice signal recognition results; S4: According to the distance measurement between the human and the robot, the robot is controlled to adopt the corresponding dialogue mode; S5: Generate corresponding dialogue content according to the real-time location of the bound mobile terminal, and control the robot to communicate with the bound user.

9. The method for robot intelligent chat based on artificial intelligence according to claim 8, characterized in that: The intelligent chatting method further comprises the following steps: S1-1: The robot intelligent control module records the conversation data between the bound user and others, stores the conversation data through the information data storage module, and obtains the time interval between each stored conversation data. The robot intelligent control module further extracts the conversation content based on the conversation data, and establishes different conversation content databases according to different people. The robot intelligent control module classifies the conversation content with a time interval difference within a certain range into one category according to the time interval, and classifies and stores the conversation content belonging to one category. The robot intelligent control module generates several conversation modes according to the time interval, and establishes the corresponding relationship between the conversation mode and others. The robot intelligent control module recognizes the face information or voice information through the face recognition module or the voice recognition module, and further selects the corresponding dialogue mode according to the corresponding relationship between the dialogue mode and others; S2-1: The face recognition module is connected to the image acquisition module, the information data storage module and the infrared ranging module. When the image acquisition module acquires an image, the face recognition module identifies the face information in the image, which is the first face information, and obtains the stored second face information through the information data storage module. The scenario analysis and recognition module further compares the first face information with the second face information, that is, determines whether the current first face information exists in the information data storage module. If the current first face information exists in the information data storage module, further obtaining the collection time node related to the first face information, calculating the shortest time interval between the collection time node and the current time node, and the robot intelligent control module selecting the corresponding dialogue mode according to the time interval; If the current first face information does not exist in the information data storage module, the image acquisition module is further used to collect a video image of another person within a certain range corresponding to the first face. The image acquisition module also obtains the third face information of the user bound to the robot through the information data storage module, and determines whether the bound user appears within the certain range based on the third face information, and further records the stay time and number of appearances of the bound user within the certain range; The scene analysis and recognition module records the user's stay time and appearance times within a certain range through the image acquisition module and the face recognition module. The scene analysis and recognition module records the appearance times as , , ,..., , , and record each stay time corresponding to the number of occurrences as , , ,..., , , further calculate the total number of occurrences and the total residence time, When the total number of occurrences is greater than or equal to a first preset value, the information data storage module stores the first face information; When the total stay time is greater than or equal to a second preset value, the information data storage stores the first face information; S3-1: The scenario analysis and recognition module is connected to the speech recognition module. The speech recognition module collects speech signals within a certain range and recognizes the collected speech signals, which are first speech signals. The information data storage module obtains the stored second speech signals. The scenario analysis and recognition module further compares the first voice signal with the second voice signal, that is, determines whether the current first voice signal exists in the information data storage module. If the current first voice signal exists in the information data storage module, then further obtaining the collection time node related to the first voice signal, calculating the shortest time interval between the collection time node and the current time node, and the robot intelligent control module selecting the corresponding dialogue mode according to the time interval; If the current first voice signal does not exist in the information data storage module, the voice signal is further collected through the voice recognition module, and the scene analysis and recognition module obtains the distance between the bound user and others through the image acquisition module, the face recognition module and the infrared ranging module. If the voice recognition module collects the voice signal, the voice signal is stored through the data storage module, and a corresponding relationship is established between the voice signal and the face information, and the collection time node is stored at the same time; S4-1: The scenario analysis and recognition module is connected to the infrared distance measurement module. The scenario analysis and recognition module obtains the distance between other people and the robot through the face recognition module, voice recognition module and infrared distance measurement module. If face information or voice signals are collected, the scenario analysis and recognition module obtains the current number of people based on the collected face information or voice signals, and further measures the distance between each person and the robot through the infrared ranging module. The scenario analysis and recognition module obtains the stored information data through the information data storage module, and determines whether the currently collected face information or voice signals exist in the information data storage module. Determine the current number of acquaintances and strangers. The facial information and voice information of acquaintances, i.e., the other party, are stored in the information data storage module, while the facial information and voice information of strangers, i.e., the other party, are not stored in the information data storage module. The robot intelligent control module selects the corresponding dialogue mode according to the measured distance, and adopts different dialogue modes for acquaintances and strangers; S5-1: The wireless network communication module establishes communication between the bound user and other mobile terminals. The mobile terminal positioning module obtains the real-time location of the mobile terminal. The mobile terminal user can turn the positioning function on and off by himself. The robot intelligent control module obtains the consumption record at the corresponding real-time location based on the obtained real-time location of the mobile terminal and the consumption record. The robot intelligent control module further generates the travel trajectory of the mobile terminal user based on the consumption record. The robot intelligent control module generates the conversation content about the mobile terminal user based on the travel trajectory of the corresponding mobile terminal user. The robot intelligent control module can recognize the voice of the bound user through the voice recognition module, extract the voice content keywords, match the corresponding mobile terminal user, and the robot intelligent control module conducts a conversation with the bound user about the mobile terminal user.

Images