Method and system for implementing intelligent dialogue

Abstract

To provide a method and system for introducing an intelligent dialogue.SOLUTION: A system includes a cloud server that executes an intelligent dialogue introduction method using a processing circuit. The processing circuit is configured to initiate an online dialogue program, introduce a first chatbot, receive content input by a user through a dialogue interface, and acquire semantic features of the content input by the user, user data, and real-time environment information acquired from an external system. According to the information, a second chatbot corresponding to a specific domain is introduced into the dialogue interface. A natural language model and a generative artificial intelligence technology executed in the second chatbot generate dialogue content that matches the semantic features of the user, the preference of the user, and the real-time environment information. The dialogue content is output via the dialogue interface.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to a chatbot, and particularly to an intelligent dialogue introduction method and system for introducing a chatbot in a specific area of dynamics based on the semantic meaning of dialogue content.

Background Art

[0002] Currently, artificial intelligence (AI) in each field is developing rapidly. Among them, there is a natural language chatbot that can process natural language and automatically generate content, such as the Chat Generative Pre-trained Transformer developed by OpenAI, namely ChatGPT (Chat Generative Pre-trained Transformer) in English. Such a natural language chatbot can learn a large amount of data using generative artificial intelligence (generative AI) technology and then generate new data related to the original data, and build a smart model through deep learning (for example, generative adversarial networks (GAN)).

[0003] Taking ChatGPT as an example, ChatGPT can learn a large amount of network information and respond to users in a natural language manner. However, the general content answered to users is a standard answer due to being learned, and it cannot provide a response corresponding to the user's current state in real time. Although it is called a natural language chatbot, it lacks content related to the user and suitable for the real-time situation.

[0004] Furthermore, in addition to the shortcomings mentioned above, the services provided by conventional natural language chatbots are limited to general discussions and cannot address the needs of all domains, leaving significant room for improvement. It should be understood that for specific domains, it is possible to train a chatbot for that specific domain using data from that domain and provide dialogue services for that domain. However, conventional technology still lacks a chatbot that integrates these domains and effectively solves the needs of businesses and users. [Overview of the project] [Problems that the invention aims to solve]

[0005] This invention was made to improve upon the shortcomings of the prior art described above. [Means for solving the problem]

[0006] To improve upon the shortcomings of conventional chatbots, this invention proposes an intelligent dialogue implementation method and system that can introduce a chatbot with a corresponding domain based on the meaning of the dialogue content. Furthermore, by realizing this chatbot using natural language processing (NLP) and generative artificial intelligence (generative AI) technologies, it is possible to further refer to the user's preferences and real-time environmental information during the dialogue process with the user, and provide dialogue content that is appropriate to the user's personal needs and current situation.

[0007] The intelligent dialogue deployment system includes a cloud server, on which a processing circuit executes an intelligent dialogue deployment method. In this method, an online dialogue program is launched and a first chatbot is deployed. Content entered by the user is received through the dialogue interface, and semantic features of the user-entered content, user data, and real-time environmental information are obtained. Based on this, a second chatbot can be deployed based on the semantic features of the user-entered content, user preferences obtained from user data, real-time environmental information, or a combination of these pieces of information. Next, dialogue content is generated through a natural language model executed by the domain chatbot, the dialogue content is deployed to the online dialogue program, and the dialogue content is output through the dialogue interface. [Brief explanation of the drawing]

[0008] [Figure 1] This is a diagram illustrating an embodiment of a system architecture that implements an intelligent dialogue implementation method. [Figure 2] This is a diagram illustrating an embodiment showing the data configuration for implementing an intelligent dialogue system. [Figure 3] This is a diagram illustrating an embodiment of a multi-domain bot database. [Figure 4] This is one flowchart illustrating an embodiment of the intelligent dialogue implementation method. [Figure 5] This is flowchart 2 illustrating an embodiment of the intelligent dialogue implementation method. [Figure 6] This is a diagram illustrating an embodiment of the development flow for a domain chatbot. [Figure 7] This is a diagram illustrating an embodiment of the domain client report generation flow. [Figure 8] This figure shows an example of a graphical user interface provided by an intelligent dialogue system. [Figure 9] This figure shows an example of a graphical user interface provided by an intelligent dialogue system. [Figure 10] This figure shows an example of a graphical user interface provided by an intelligent dialogue system. [Figure 11] This figure shows an example of a graphical user interface provided by an intelligent dialogue system. [Figure 12] This figure shows an example of a graphical user interface provided by an intelligent dialogue system. [Figure 13] This figure shows an embodiment of the graphical user interface for related applications when introducing a domain chatbot. [Figure 14] This figure shows an embodiment of the graphical user interface for related applications when introducing a domain chatbot. [Figure 15] This figure shows an embodiment of the graphical user interface for related applications when introducing a domain chatbot. [Figure 16] This figure shows an embodiment of the graphical user interface for related applications when introducing a domain chatbot. [Figure 17] This figure shows an embodiment of the graphical user interface for related applications when introducing a domain chatbot. [Modes for carrying out the invention]

[0009] This invention discloses an intelligent dialogue implementation method and system, the intelligent dialogue implementation method being executed on a cloud server and providing an intelligent dialogue service using natural language processing technology. Furthermore, the cloud server provides social media services via the network, and users can share text content, image content, and video content after joining. The cloud server also provides chatbots in multiple domains, and users engage in dialogues through the services provided by the cloud server, and further provides dialogue services in corresponding domains based on the characteristics of the user's dialogue. The use of artificial intelligence technology includes a chatbot that learns data in each domain using machine learning algorithms and natural language processing technology to provide dialogue services, learns the user's activities on social media to obtain the user's preferences, and based on the meaning of the user's dialogue and the user's preferences, adds environmental information obtained in real time to provide dialogue content that is more suited to the individual user's needs and current environmental characteristics.

[0010] The system implemented by the above-mentioned cloud server will be described with reference to a diagram of an embodiment showing the system configuration for implementing the intelligent dialog introduction method shown in Figure 1.

[0011] The cloud server 100 shown in the figure is realized by a computer system, database, and network. Various functional modules realized through the cooperation of software and hardware include a natural language processing module 101, a machine learning module 103, an external system interface module 105, and a user interface module 107, as shown in the figure. The natural language processing module 101 is a module for performing natural language processing. The natural language processing module 101 realizes a chatbot with natural language information processing capabilities. The machine learning module 103 executes machine learning algorithms and, in addition to learning natural language models, can learn the user's activities on the network using deep learning methods to obtain information preferred by the user and provide the chatbot with dialogue content that suits the user's preferences. The external system interface module 105 provided by the cloud server 100 executes connections with external systems (e.g., a first external system 111, a second external system 112) (e.g., via network 10), circuits for obtaining data via an application program interface (API), and related usage software. The user interface module 107 provided by the cloud server 100 allows the user device 150 to connect to the cloud server 100 via the network connection function of the user interface module 107 and run a server that can provide network services. The user device 150 can then run an application program (for example, a social media application program) that corresponds to and acquires the services provided by the cloud server 100.

[0012] According to the configuration shown in the diagram, the cloud server 100 has an internal or externally connected database and provides data services. The video database 110 shown in the diagram provides video content that each end user uploads and shares, stored via the network 10 by the user device 150. The content uploaded and shared by users may also include text content and image content. The user database 120 stores user data, including personal user data, uploaded text content, image content, and video content. It also acquires user activity data from the network services provided by the cloud server 100, such as content viewed, following, likes, shares, and subscriptions, thereby forming a user profile. When dialogue content is continuously generated over time, the user database 120 can store and update user data, including a record of the user's history of dialogues, in chronological order so that it becomes a dialogue record that can be provided to a natural language model for machine learning algorithms to learn from. The vector database 130 is a database for recording structured information obtained by performing vector algorithm calculations on various text content, image content, and video content. This structured information is used to compare various data tailored to the user's personalization. The data provided by the system that executes the intelligent dialogue introduction method also includes the multi-domain bot database 140. Referring to the embodiment shown in Figure 3, when a domain model is used in the intelligent dialogue introduction method in the multi-domain bot database 140, the system can determine a domain chatbot that corresponds to the user's needs based on the semantic features in the dialogue message provided by the user. For example, if the user mentions a need related to exercise in the dialogue, the natural language processing module 101 processes it and, upon obtaining semantic related to exercise, introduces an exercise-related domain chatbot from the multi-domain bot database 140, allowing the user to obtain information about exercise from the exercise domain chatbot during the chat.As a result, the system can provide better dialog services in multiple regions.

[0013] According to the system configuration schematic diagram shown in the figure, the cloud server 100 acquires data of external systems such as the first external system 111 and the second external system 112 schematically shown in the figure through a connection in the network 10 or a specific protocol. The first external system 111 and the second external system 112 are, for example, servers installed by a government or a company for providing open data. The cloud server 100 can acquire real-time information that meets needs, such as real-time weather, real-time road conditions, real-time news, and network information related to real-time location, through the application program interfaces provided by the external systems via the external system interface module 105.

[0014] An application program capable of acquiring the services provided by the cloud server 100 in the user device 150, for example, runs the social media service provided by the cloud server 100. The user device 150 runs the corresponding social media application program and acquires the social media service through the user interface module 107. In particular, the cloud server 100 provides a natural language chatbot through the natural language processing module 101, and the user can have a dialog with the chatbot through the dialog interface 115. On the other hand, the cloud server 100 can learn the activity data of the user using various services of the cloud server 100 through the machine learning module 103, and the machine learning module 103 can learn the user's interest characteristics and construct user data. The activity data includes the activity data acquired by the user using the social media application program and the dialog interface 115.

[0015] Here, it should be noted that various text contents, image contents, and video contents obtained by the cloud server 100 are unstructured data, and may be converted into vectorized data by an encoder method so as to facilitate obtaining the meanings of various text contents, image contents, and video contents and to be advantageous for data search. Furthermore, the vectorized vectorized data is used for comparison of a user's keyword search, and the distance between the search keyword and the vectorized data in the database is calculated by a distance function, and the closer the distance is, the more similar the data is. Thereby, the user can search for data by the vector database 130. Similarly, the semantic meaning can be discriminated based on the keyword of the user dialog, and the corresponding area chatbot can be automatically introduced.

[0016] According to an embodiment, the vector database 130 of the cloud server 100 can support multi-mode search services such as text content and image content. The vector database 130 provides structured data. For example, after various text contents, image contents, and video contents are texturized, vectorized data is obtained by the operation of a vector algorithm, and the vectorized data can be applied to a search service and can be used in a natural language processing program. The natural language processing program uses a natural language model to correspond the vectorized data to a vector space. Taking the word input by the user as an example, a word vector is obtained by the operation of a vector algorithm.

[0017] In one embodiment, the intelligent dialogue implementation method provided herein is actually a multi-domain chatbot that runs on a cloud server 100. The chatbot can interact with the user in natural language, including text and voice, and in addition to responding to information entered by the user, it may also acquire user data in advance via the cloud server 100 before the dialogue, and obtain the user's personality and habits from this user data. It may also obtain real-time information from external systems (first external system 111, second external system 112), for example, by obtaining the weather and news for the user's location. As a result, the content that the chatbot responds to can reflect not only the user's preferences but also the real-world situation.

[0018] The dialog service provided by the system described above can be offered as a function that runs on social media. A user's activity on social media is data for the system to learn the user's preferences and forms structured data within the system. Referring to Figure 2, which is a diagram illustrating an embodiment of the data structure for implementing the intelligent dialog implementation method, the data is divided into social media platform data 21, user data (e.g., user description file 23, user activity data (user profile data) 25).

[0019] Social media platform data 21 is data that is not made public within the system. The system, which implements the intelligent dialogue implementation method, acquires viewer data 211 of users who access various content provided by the cloud server 100, and creator data 212 of users who provide various content to the system. Social media platform data 21 further includes business data 213 for the system to provide companies with built company data for advertising, and various location data 214 related to acquiring geographical locations so that the system can provide appropriate services.

[0020] User data 23 is data that can be made public within the system and includes data edited by the user themselves. The data edited by the user themselves includes viewer data 231 obtained from various user activity data. Viewer data 231 may include user preference data as a viewer obtained through machine learning, such as recent preference data, past preference data (interest data), and location preference data (location interest).

[0021] In user data 23, creator data 232 is data related to the user as a creator, and includes the types preferred by the creator and location-related data of the creator, as determined by the system through machine learning. Creator data 232 may include, for example, data of the user as a creator, and the types preferred by the creator obtained through learning, as well as geographical location or a specific location within a single place.

[0022] The business data 233 in user data 23 includes the company business type and product characteristics obtained by the system through machine learning, when the user is a company.

[0023] User activity data 25 is data that is not made public within the system and includes statistical data on user activities in various services provided by the cloud server 100, as well as data obtained through machine learning. User activity data 25 mainly includes viewer data 251, creator data 252, and business data 253.

[0024] Viewer data 251 consists of user activity data such as viewing rate, viewing time, following, preferences, comments, and subscriptions when users use the services provided on the cloud server 100. Creator data 252 consists of statistical data of users as creators, such as channel or account followers, number of views of created content, and account viewing rate. Business data 253 consists of data obtained when the user is a company, such as followers, number of content views, and overall impression data.

[0025] The social media platform data 21, user data 23, and user activity data 25 collected and learned by the cloud server 100 form the basis of the dialogue service implemented using natural language processing and generative artificial intelligence as described herein. By performing calculations on the above various data using processing circuits in the cloud server 100, it becomes possible to provide a chatbot that is tailored to the user's personal and real-time needs.

[0026] In the data configuration for implementing the intelligent dialogue implementation method shown in Figure 2, if the user belongs to a company, specific organization, or individual that provides business services or products, the intelligent dialogue implementation system can use the business data 213 of the social media platform data 21 to train domain chatbots in the relevant domain and provide support for the company, organization, or individual to conduct business promotions. In another embodiment, the intelligent dialogue implementation system can use data from various specialized domains to train domain bots in different domains and provide specialized dialogue content on specific domains according to the user's needs.

[0027] Based on the diagram illustrating the embodiment of the multi-domain bot database shown in Figure 3, the multi-domain bot database 140 is connected to an external cloud server 100 or is built into the cloud server 100. The multi-domain bot database 140 contains multiple chatbots, including a main chatbot 300 that provides general dialog services to the user. This may be used as the default chatbot at the start of a dialog, and it uses natural language processing technology to perform natural language dialogs and user Content entered by The semantic features of the words are analyzed. Furthermore, by referring to real-time environmental information at the time of the dialogue, it is possible to determine whether it is necessary to introduce a chatbot for a specific domain.

[0028] The multi-domain bot database 140 shown in the figure provides multiple domain chatbots trained to learn different domain data. Examples include a first domain chatbot 301, a second domain chatbot 302, and a third domain chatbot 303. When in use, it is also possible to integrate different domain chatbots to form a different domain chatbot. For example, a motor domain bot can provide specialized dialogue capabilities regarding various motor activities, and the system can also provide domain chatbots trained for specific motor items. The intelligent dialogue deployment system can also train domain chatbots to suit the user's needs upon user request, and these chatbots can support dialogue services for specific product promotions. The multi-domain bot database 140 provides a bot import interface 30 connected to a cloud server 100, and based on instructions from the cloud server 100, one of the domain chatbots can be selected and deployed to the cloud server 100 via the bot import interface 30.

[0029] As an embodiment, the natural language model executed on the cloud server 100 may generate dialogue content that matches the user's preferences and real-time environment information by executing a vector algorithm on the content entered by the user through the dialog interface, the user's preferences, and real-time environment information, tagging the acquired text, calculating the vector of each word, and obtaining relevant content after searching the database based on the vector distance between words. In the online dialog process, the natural language model executed behind the chatbot may execute a program to perform machine translation, document summarization, document generation, etc., on the data that has been transcribed using a transformation model. Referring to the flow description of the embodiment shown in Figure 4, the chatbot (for example, the main chatbot 300, the first domain chatbot 301, the second domain chatbot 302, and the third domain chatbot 303 shown in Figure 3) may generate dialogue content by obtaining the meaning of words in the user's dialog.

[0030] The flow for implementing the intelligent dialogue deployment method in a system using a cloud server architecture can be seen by referring to the flowcharts illustrating the embodiments shown in Figures 4 to 7. Furthermore, in describing the flow, you can also refer to the diagrams showing examples of graphical user interfaces provided by the intelligent dialogue deployment system, shown in Figures 8 to 12, and the diagrams showing embodiments of graphical user interfaces for applications related to the deployment of domain chatbots, shown in Figures 13 to 17. These examples are not intended to limit the actual operation method.

[0031] In the flow shown in Figure 4, the user first connects to the cloud server 100 using an application program running on the user device and uses the provided services to view its content. The graphical user interface for manipulating and viewing text content, image content, and video content provided by the cloud server 100 (for example, by the user interface module 107 shown in Figure 1) is a map interface 80 with an electronic map background, which is launched after the application program is executed on the user device, as shown in Figure 5. Figure 8 schematically shows how the link icon for each video content is displayed on the map interface 80 according to the geographical information associated with it. The link points associated with multiple geographical locations as shown in the figure may include one or more video link points, and in the figure, video link points 801, 802, and 803 are shown as examples. Depending on the embodiment, the multiple video link points displayed on the map interface 80 may include one or more video content related to points of interest (POIs) within this geographical area recommended by the system.

[0032] According to the embodiment, taking social media as an example, when the corresponding social media application program is executed on the user's device, a page is launched, and as shown in the map interface 80 of Figure 8, the user may launch an online dialog program by clicking (touching or using a specific hand gesture) the dialog link icon for dialog 812 or by clicking the link point for providing a dialog in the map interface 80, using the link icons such as Play 811, Dialog 812, Help 813, Search 814, and User Main Page 815 shown below (step S401).

[0033] On the other hand, Figure 9 provides a schematic diagram of another linking method for launching an online dialog program. For example, after a user selects one of the video link points (video link points 801, 802, or 803) on the map interface 80, the screen launches a video playback page 90 that plays a video shared or created by a user, as shown in Figure 9. In Figure 9, the geographical location 901 of the video is further displayed, and several link icons such as preferences 903, dialogs 904, collections 905, and shares 906 are displayed in the sidebar. The user may also launch an online dialog program by clicking the dialog link icon for dialog 904 (step S401).

[0034] Next, the dialog interface is launched, and the user inputs text content, image content, or specific video content through the dialog interface (for example, inputting a link to share video content), and the cloud server 100 may receive the content input by the user via the user interface module 107 (step S403). According to the embodiment, the online dialog program is actually a chatbot that uses a natural language model (referring to the multi-domain bot database 140 shown in Figure 3, the default main chatbot 300 can be introduced first). This allows the chatbot to communicate with the user via the dialog interface, receive the dialog content input by the user, and perform natural language processing on each input content from the user.

[0035] Examples of dialog interfaces include the dialog interface 1000 shown in Figure 10, the dialog interface 1110 shown in Figure 11, and the dialog interface 1200 shown in Figure 12. Each example of a dialog interface provides an input field for the user to enter content, dialog content to be output by the chatbot, and a dialog display area to display the content entered by the user.

[0036] At this time, the cloud server 100 acquires the content entered by the user via the user interface module 107. The content received via the dialog interface may be text content, audio content, or video content. If the received content is audio content or video content, the audio content or video content may be converted into text content using a text conversion program, and then semantic analysis may be performed using a natural language processing module to acquire semantic features (step S405). While the above programs are running, the cloud server 100 acquires user data from the user database 120 and acquires real-time environment information from an external system (via the external system interface module 105 shown in Figure 1) (step S407).

[0037] When a dialogue is performed, the intelligent dialogue deployment software program running on the cloud server can determine in real time whether to deploy a domain chatbot for a specific domain based on the semantic features of the dialogue, user preferences, and real-time environmental information, or a combination of these pieces of information. If a domain chatbot is deployed (step S409), the database is queried to obtain content that matches the semantic features of the content entered by the user, the user preferences obtained from user data, and the real-time environmental information (step S411). The online dialogue program generates dialogue content using the natural language model running in the domain chatbot (step S413). Subsequently, the dialogue content is introduced into the online dialogue program and output through the dialogue interface (step S415). The embodiment flow described above, such as step S403, is then continued.

[0038] Furthermore, when the natural language model of the cloud server 100 is running, multidimensional information is recorded using a database or system memory, and this multidimensional information may include the history of dialogues in the same online dialogue program. This allows the chatbot to consider, in addition to the semantic features in the user's dialogue, user preferences, and real-time environmental information, as in step S411, before generating a dialogue (step S417), the history of dialogues in the user's current online dialogue program. As a result, the dialogue content generated by the natural language model (step S411) will have dialogue content that is appropriate to the current situation.

[0039] For example, since the current situation often exists in the history of a user's online dialog program that can reflect the user's current emotions and needs, as shown in the embodiment in Figure 1, the natural language processing module 101 in the cloud server 100 uses a natural language model to communicate the user's current emotions and needs. Content entered by Meaning of the word Features It can simultaneously consider user preferences, real-time environmental information, and historical dialogue records, and can continue the same dialogue situation when generating dialogue content. For example, when it can continuously generate dialogues in natural language on the same dialogue theme, the terminology may have the same tone as previous dialogue content (reflecting the user's emotions such as joy, anger, sadness, etc.), and the chatbot may learn the user's emotional expression style from historical dialogue records.

[0040] See Figure 10 for a related diagram. As shown in Figure 10, the dialog interface 1000 has dialog contents 1001, 1002, and 1003 between the user and the chatbot. The chatbot further searches the database based on user semantic features obtained from dialog content 1002 to provide recommended video content 1004, and below the dialog interface 1000 is an input field 1005 where the user can further input dialog content.

[0041] Another mode is the dialog interface 1110 shown in Figure 11. As shown in this example, when an online dialog program is launched, the system may directly provide natural language dialog content 1111, 1112, and 1114 based on user preferences and real-time information, and directly provide recommended video content 1113, after which the user may respond to the dialog content using the input field 1115 in the dialog interface 1110.

[0042] In another embodiment, the dialogue content generated by a natural language model executed in the chatbot based on semantic features of user-input content, user preferences, and real-time environmental information may further include providing multiple recommendation options, multiple recommendation video content, and / or multiple recommendation friend links, as can be seen in the example in Figure 12.

[0043] In an online dialog program, the dialog interface 1200 shown in Figure 12 allows the chatbot to communicate with the user. Content entered byThe system includes dialogue content 1201 generated based on the semantic features of the words. Furthermore, if a program that processes natural language within the system determines that the semantic features of a particular dialogue are related to content concerning a particular domain, the system will, in real time, introduce the corresponding domain chatbot from the multi-domain bot database 140, initiate a dialogue with the user, and provide information related to the domain until it is determined whether to return to the main chatbot or introduce another domain chatbot. In subsequent dialogues, the semantics in this example cause the chatbot to determine that the user has selected a specific item, and therefore multiple recommendation options 1202 are provided. In particular, the chatbot provides recommendation options to the user based on real-time environmental information obtained by the system from an external system. For example, the chatbot may provide recommendation options 1202 based on real-time weather, road conditions, time, and the user's location. If it is mealtime, the system will provide meal options from restaurants that are open near the user's location, taking into account the user's eating habits.

[0044] Furthermore, if the user expresses a desire to watch video content, the recommendation option 1202 above may include multiple recommended video content. If the user expresses a desire to find friends with similar interests, the recommendation option 1202 above may include multiple recommended friend links.

[0045] Furthermore, when the user then uses the input field 1206 to input dialog content 1203 in response to several recommendation options 1202, the chatbot will respond with dialog content 1204 based on the meaning of the dialog content 1203, and then provide several more recommendation contents 1205 based on the meaning of the above dialog contents. Following the above example, when the user responds that they would like one of the meals, the chatbot will provide restaurant options that correspond to the meal the user wants to eat, based on real-time weather, road conditions, and the user's location obtained by the system from an external system, and if the weather is bad or the roads are congested, it will recommend restaurant options that are easier for the user to get to.

[0046] Next, we refer to the flowchart of another embodiment of the intelligent dialogue implementation method shown in Figure 5. In this flowchart, the first chatbot or the second chatbot is an automated dialogue program that runs within an online dialogue program and can refer to any of the main chatbot and / or multiple domain chatbots included in the multi-domain chatbot database provided by the system.

[0047] In the flow shown in Figure 5, the user launches an online dialog program through an application program and deploys the first chatbot. Based on the embodiment, the system default main chatbot can be deployed first when the online dialog program starts (step S501). The first chatbot can either automatically generate dialog content or wait for the user to input content and then receive the dialog content entered by the user (step S503), thereby allowing the user to interact with the chatbot. Content entered by Further semantic features are obtained. Based on the embodiment, the cloud server 100 uses a natural language processing module to perform transformation operations and vector algorithm operations to obtain semantic features (step S505).

[0048] In this context, an embodiment of the intelligent dialogue implementation method provided by the present invention involves using artificial intelligence technology to learn natural language, and after understanding natural language (natural language understanding), text classification and grammatical analysis are performed. When processing the dialogue content entered by the user, a transformation model (Google Translate, 2017) is used. TM The deep learning method (submitted by the brain team) may be used to process user input with chronologically ordered natural language content, and if the input content is not text content, it needs to be converted to text before obtaining the text. Thus, in an online dialogue program, this conversion model may be used to perform machine translation, document summarization, document generation, etc.

[0049] After acquiring the semantic features of the user dialog content, the system analyzes the user's preferences and current location, or the locations the user is interested in from the dialog content, and acquires real-time environmental information from an external system in real time based on that location (step S507). The real-time environmental information may include information acquired in real time from one or more external systems, such as real-time weather, real-time road conditions, real-time news, and real-time location-related network information (POIs (points of interface) on a map, POI evaluations, etc.), or any combination thereof.

[0050] At this time, the system executes a software program to introduce the chatbot (connecting to the bot import interface 30 of the multi-domain bot database 140 shown in Figure 3), and the user Content entered by Based on the semantic characteristics of the user, user preferences, and real-time environmental information, or any combination thereof, it is determined whether to deploy a second chatbot (step S509). The software program that deploys the chatbot determines whether to deploy a second chatbot. Content entered by Meaning of the word Features It is a region chatbot that corresponds to a specific area determined based on user preferences and real-time environmental information, or a combination thereof.

[0051] If, in the above steps, it is decided not to introduce a second chatbot (no), the user will continue to interact with the original chatbot (e.g., the default main chatbot or any domain chatbot). The system uses a vector database to calculate the closest response based on user semantic features, user preferences, and real-time environment information, or by adding historical dialogue records (step S511). It should be noted that the data in the vector database is structured information obtained using a vector algorithm, and the system may obtain words with relatively similar semantics from content obtained by vector distance. For example, the vector distance between the word "computer" in the dialogue content and the word "calculate" in the database is relatively close, while the vector distance between the word "computer" and the word "run" is relatively far.

[0052] Furthermore, the system further searches the video database 110 based on the above information to obtain suitable video content (step S513), the main chatbot or domain chatbot generates dialogue content using natural language processing and generative artificial intelligence technology (step S515), and outputs the dialogue content to the dialogue interface (step S517). In addition, in the embodiment, during the chat process, the system may continue the above steps, and the chatbot may communicate with the user in natural language (text or voice) and provide real-time content (video content, text content) that the user is interested in.

[0053] On the other hand, if the decision in step S509 determines that a domain chatbot for a specific domain should be introduced under the conditions at the time (yes), the domain chatbot is introduced through the bot import interface 30 in the multi-domain bot database 140 (step S519). The domain chatbot generates a dialogue using the natural language model running on it and engages in a dialogue with the user about the specific domain (step S521). Similarly, the system may acquire semantic features in the dialogue through the natural language processing module (step S523), and further acquire real-time environmental information, and continue executing the dialogue content generation steps, for example, steps S511 to S517. The flow repeats steps such as step S503, generating dialogue content based on semantic features, user preferences, and real-time environmental information acquired in real time, and performing steps such as determining whether other domain chatbots should be introduced.

[0054] Related applications can refer to the diagram in Figure 13, which shows an embodiment of the graphical user interface of an application related to the introduction of a domain chatbot. Here, a domain chatbot provided by a manufacturer is used as an example. If the system determines from the user-chatbot dialogue content that a service or product provided by a certain manufacturer is relevant to the topic, it automatically introduces the domain chatbot of that specific manufacturer. At this time, the manufacturer's logo 1301 may be displayed in the dialogue interface 1300 shown in Figure 13. The domain chatbot may use a natural language model to generate dialogue content with the user, such as dialogue content 1303 and 1305 in the example of Figure 13, while querying a video database (e.g., video database 110 in Figure 1) to introduce recommended video content and embed it on the dialogue interface 1300. For example, in the example of Figure 13, a recommended product video 1304 is displayed, and the user can respond to the dialogue content 1306.

[0055] Figure 14 shows another embodiment of a graphical user interface that introduces recommended manufacturers. In this example, the domain chatbot interacts with the user during the dialogue process. Content entered by Meaning of the word Features Based on the user's preferences and location, the system can determine whether a service or product offered by a specific manufacturer meets the user's requirements and display one or more location-based recommendation contents on the dialog interface 1400 for geographic locations 1401 related to the user's location, such as a first recommended manufacturer 1403 and a second recommended manufacturer 1405 related to the geographic location 1401. In this way, a chatbot tailored to the user's needs in a specific domain can be provided through the domain chatbot.

[0056] Another embodiment can be seen in Figure 15, which shows an embodiment of a graphical user interface for a corporate page. In this example, the intelligent dialog system provides a user with the ability to create their own homepage, for example, the corporate page 1500 shown in Figure 15, through a user-side application program. The corporate page 1500 can provide corporate users with the ability to create and manage content. For example, a domain chatbot may be customized, and in this embodiment, the corporate page 1500 is provided with a domain bot construction link 1501.

[0057] Based on the embodiment, the intelligent dialogue deployment system provides enterprise users with the ability to create domain chatbots tailored to their enterprise needs. Specifically, using a machine learning module (e.g., machine learning module 103 shown in Figure 1) on the intelligent dialogue deployment system's cloud server, the trained domain chatbot learns from the content provided by the enterprise and can then provide users with dialogue content about the enterprise's services or products in natural language. For information on how to create a domain chatbot, refer to the flowchart illustrating an embodiment shown in Figure 6.

[0058] In the intelligent dialogue implementation system, corporate users belong to domain clients and can first join a specific social media platform (step S601). As shown in the corporate page 1500 in Figure 15, domain clients can upload video content and descriptive text to create their own homepage (step S603). In creating a domain chatbot belonging to a domain client, the system utilizes machine learning algorithms to learn data from each domain provided by the domain client and learn the characteristics of each domain (step S605). Then, natural language processing and generative artificial intelligence technologies are used to create a domain chatbot specifically for the domain client (step S607).

[0059] Furthermore, for business users, the system offers paid services that allow domain clients to set conditions for using the domain chatbot. For example, they can set the number of dialogs and budget daily, weekly, or monthly (step S609). Figure 17 shows an embodiment of the graphical user interface of the budget setting page, where various paid plans are offered and domain users can refer to the settings.

[0060] Once a domain client has completed creating its domain chatbot and associated settings, the dedicated domain chatbot created by each domain client is built in the multi-domain bot database 140 provided by the cloud server 100 shown in Figure 1. When the system executes the intelligent dialog deployment method, the software program that executes the intelligent dialog deployment method is used by the user Content entered by Meaning of the word Features The system analyzes the data and introduces a domain chatbot into the online dialogue program to address user needs (step S611).

[0061] Furthermore, the intelligent dialogue system can provide usage data for the domain chatbot when providing services to each domain client. Refer to the diagram illustrating an embodiment of the domain client report generation flow shown in Figure 7 and the diagram illustrating an embodiment of the graphical user interface for the statistics report page shown in Figure 16.

[0062] Each domain chatbot running in the intelligent dialogue deployment system can generate statistical data for itself, and domain clients can evaluate its effectiveness through the statistical data built into the system. The intelligent dialogue deployment system statistically collects statistics on the number of deployments, execution time, and number of dialogues of domain chatbots through a software program on a cloud server (step S701), statistically collects the number of clicks and time spent on content recommended by the domain chatbots (step S703), and further obtains the number of new followers (step S705) and the number of views of client data (step S707), and provides domain client reports so that domain clients can evaluate the effectiveness of the domain chatbots (step S709).

[0063] You can refer to the diagram showing an embodiment of the graphical user interface of the statistics report page shown in Figure 16, which shows the statistics report page 1600 provided to the domain client. In one embodiment, the domain client may interact with the system's chatbot in a dialog format and request the system to submit a report, such as a statistics report 1602, to which the system responds, using, for example, the schematically shown dialog contents 1601 and 1603. It is noteworthy that, in addition to providing the domain client with a general statistics report, the domain client can also obtain statistics data of their own domain chatbot through the dialog in the online dialog program. In the process of the dialog, the system communicates to the user through the chatbot. Content entered by Meaning of the word FeaturesBased on user preferences and real-time environmental information, we will continue to provide recommendation activities 1604. [Explanation of Symbols]

[0064] 10 Networks 100 Cloud Servers 101 Natural Language Processing Module 103 Machine Learning Modules 105 External System Interface Module 107 User Interface Module 110 Video Database 120 User Databases 130 Vector Databases 140 Multi-domain Bot Databases 111 First external system 112 Second external system 150 User Devices 115 Dialog Interface 21 Social Media Platform Data 211 Viewer Data 212 Creator Data 213 Business Data 214 Location data 23 User Data 231 Viewer Data 232 Creator Data 233 Business Data 25. User Activity Data 251 Viewer Data 252 Creator Data 253 Business Data 30 Bot Import Interface 300 Main Chatbots 301 First Domain Chatbot 302 Second Domain Chatbot 303 Third Domain Chatbot 80 Map Interface 801, 802, 803 Video Link Points 811 Playback 812 Dialog 813 Help 814 Search 815 User Main Page 90 Video Playback Page 901 Geographic location 903 Preference 904 Dialog 905 Collection 906 shares 1000 Dialog Interfaces 1001, 1002, 1003 Dialogue Content 1004 Recommended Video Content 1005 Input field 1110 Dialog Interface 1111, 1112, 1114 Dialogue Content 1113 Recommended Video Content 1115 Input field 1200 Dialog Interface 1201, 1203, 1204 Dialogue Content 1202 Recommendation Options 1205 Recommended Content 1206 Input field 1300 Dialog Interface 1301 Manufacturer Logo Dialogue content 1303, 1305, 1306 1304 Recommended Product Video 1400 Dialog Interface 1401 Geographic location 1403 Top Recommended Manufacturer 1405 Second Recommended Manufacturer 1500 company pages 1501 Domain Bot Construction Link 1600 Statistical Report Pages Dialogue content 1601, 1603 1602 Statistical Report 1604 Recommendation activities 1700 Budget Setting Page S401~S417 Steps in the Intelligent Dialogue Implementation Flow S501~S523 Steps in the Intelligent Dialogue Implementation Flow S601~S611 Steps in the Domain Bot Construction Flow Steps in the S701-S709 Area Client Report Generation Flow

Claims

1. A method for introducing intelligent dialogs that run on a cloud server, The online dialog program is launched, the first chatbot is introduced, and content entered by the user is received through the dialog interface. The process involves obtaining semantic features of the content entered by the user, To acquire user data and real-time environment information, A second chatbot is introduced based on any of the following information, or any combination thereof: the semantic characteristics of the content entered by the user, the user's preferences obtained from the user data, and the real-time environmental information. The second chatbot generates dialogue content through a natural language model, The dialog content is introduced into the online dialog program, and the dialog interface outputs the dialog content. including A method for introducing intelligent dialogue, characterized by the following features.

2. The intelligent dialog introduction method according to claim 1, wherein, in addition to the first chatbot or the second chatbot generating the dialog content, one or more video contents are introduced into the dialog interface based on the semantic characteristics of the content entered by the user, the user's preferences, and the real-time environment information, and one or more location-based recommendation contents related to the user's location are displayed in the dialog interface.

3. The intelligent dialog introduction method according to claim 1, wherein the cloud server runs social media, the user device runs a corresponding social media application program, and the user clicks a dialog link icon on a page within the social media application program to enter the online dialog program.

4. The intelligent dialog introduction method according to claim 1, wherein the natural language model executed in the cloud server performs machine translation, document summarization, and document generation processing on the data converted into text using the conversion model, generates the dialog content, and further executes a vector algorithm on the content entered by the user, the user's preferences, and the real-time environment information, tags the acquired text, calculates the vector of each word, and acquires relevant content based on the vector distance between words to generate the dialog content that is suitable for the user's preferences and the real-time environment information.

5. The first chatbot is the default main chatbot in the online dialog program, The intelligent dialogue introduction method according to any one of claims 1 to 4, wherein the second chatbot is a domain chatbot determined by the cloud server executing a software program for introducing the chatbot, based on the semantic characteristics of the content entered by the user, the user's preferences, and the real-time environment information, or any combination thereof.

6. The processing circuit, Launch the online dialog program, install the first chatbot, and receive content entered by the user through the dialog interface. The semantic features of the content entered by the user are obtained, Acquire user data and real-time environment information, A second chatbot is introduced based on the semantic characteristics of the content entered by the user, the user's preferences obtained from the user data, and any information or any combination of the real-time environmental information. Using the natural language model executed by the second chatbot described above, dialogue content is generated. The system includes a cloud server that loads the aforementioned dialog content into the online dialog program and outputs the aforementioned dialog content through the dialog interface. An intelligent dialogue introduction system characterized by the following features.

7. The intelligent dialogue deployment system according to claim 6, wherein the cloud server provides an external system interface for connecting to one or more external systems to acquire the real-time environmental information, which includes one or any combination of network information relating to real-time weather, real-time traffic conditions, real-time news, and real-time location.

8. The intelligent dialogue system according to claim 6, wherein the natural language model, which is executed within the cloud server, generates the dialogue content through the processes of machine translation, document summarization, and document generation on the data that has been transcribed into text using the transformation model, and further generates the dialogue content that is suitable for the user's preferences and the real-time environment information by executing a vector algorithm on the content entered by the user, the user's preferences, and the real-time environment information, tagging the acquired text, calculating the vector for each word, and acquiring relevant content based on the vector distance between words.

9. The first chatbot is the default main chatbot in the online dialog program, The second chatbot is a domain chatbot that is determined by the cloud server executing a software program to implement the chatbot, based on any of the following information, or any combination thereof: the semantic characteristics of the content entered by the user, the user's preferences, and the real-time environment information. The aforementioned cloud server provides a multi-domain bot database, and the domain chatbots are provided from the multi-domain bot database. The aforementioned multi-domain bot database includes multiple domain models that have been trained by learning expertise in various domains using machine learning algorithms. The intelligent dialogue introduction system according to any one of claims 6 to 8, wherein the multiple domain models realize multiple domain chatbots having natural language processing capabilities using natural language processing technology and generative artificial intelligence technology.

10. The intelligent dialogue deployment system according to claim 9, wherein the cloud server statistically collects statistics on the number of deployments, execution time, and number of dialogues of the domain chatbot, and statistically collects statistics on the number of clicks and time spent on content recommended by the domain chatbot, and provides a domain client report.

Images