CN112579754A - Intelligent robot conversation interaction method and device, and computer equipment - Google Patents
Intelligent robot conversation interaction method and device, and computer equipment Download PDFInfo
- Publication number
- CN112579754A CN112579754A CN202011507312.3A CN202011507312A CN112579754A CN 112579754 A CN112579754 A CN 112579754A CN 202011507312 A CN202011507312 A CN 202011507312A CN 112579754 A CN112579754 A CN 112579754A
- Authority
- CN
- China
- Prior art keywords
- session
- message
- identifier
- conversation
- robot
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Theoretical Computer Science (AREA)
- Artificial Intelligence (AREA)
- Human Computer Interaction (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The application relates to a conversation interaction method and device of an intelligent robot, computer equipment and a storage medium. The method comprises the following steps: receiving a session message forwarded by a message system; the conversation message is a conversation message with the robot sent by the user terminal in a conversation group; determining a corresponding session context identifier according to a session group identifier, a user identifier and a robot identifier carried in the session message, and sending the session message carrying the session context identifier to an intelligent robot system; the session context identifier has a mapping relation with the multi-person session group identifier, the user identifier and the robot identifier information; and processing the conversation message carrying the conversation context identifier through the intelligent robot system to obtain a corresponding response message, and returning the response message to the message system. By adopting the method, the accuracy of the intelligent robot in processing the session information can be effectively improved.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a method and an apparatus for session interaction of an intelligent robot, a computer device, and a storage medium.
Background
With the development of computer technology and the coming of the 5G era, the appearance of the Internet brings great convenience to modern life, and more users can log in different application platforms to perform conversation interaction with various intelligent robots online.
However, in the current session interaction mode of the intelligent robot, the server can only perform individual conversations and maintain session context information with the intelligent robot based on the user dimensions, and cannot support maintaining the session context information of different users independent of each other in a plurality of multi-user conversation groups, so that the intelligent robot cannot perform semantic analysis accurately, and the accuracy of processing the session information by the intelligent robot is low.
Disclosure of Invention
In view of the foregoing, there is a need to provide an interaction method, an interaction apparatus, a computer device, and a storage medium for an intelligent robot in a complex context, which can improve accuracy of processing session information by the intelligent robot.
A conversation interaction method of an intelligent robot, the method comprising:
receiving a session message forwarded by a message system; the conversation message is a conversation message with the robot sent by the user terminal in a conversation group;
determining a corresponding session context identifier according to a session group identifier, a user identifier and a robot identifier carried in the session message, and sending the session message carrying the session context identifier to an intelligent robot system; the session context identifier has a mapping relation with the multi-person session group identifier, the user identifier and the robot identifier information;
and processing the conversation message carrying the conversation context identifier through the intelligent robot system to obtain a corresponding response message, and returning the response message to the message system.
In one embodiment, before receiving the session message forwarded by the message system, the method further includes:
acquiring a server address where each intelligent robot is located, and storing the server address in a local database;
the sending the session message carrying the session context identifier to the intelligent robot system comprises:
acquiring a robot identifier carried in the session message;
inquiring a corresponding server address from the local database according to the robot identifier;
and after carrying out format conversion and encryption on the session message carrying the session context identifier, sending the session message to the server address.
In one embodiment, the determining the corresponding session context identifier according to the session group identifier, the user identifier, and the robot identifier carried in the session message includes:
acquiring a conversation group identifier, a user identifier and robot identifier information carried in the conversation message;
combining identification variables of three dimensions of the session group identification, the user identification and the robot identification according to a preset rule to obtain an updated variable identification;
and marking the updated variable identification as a corresponding session context identification.
In one embodiment, the method further comprises:
setting failure time corresponding to the session context identifier, wherein the failure time is used for judging whether to update the session context identifier;
when detecting that the session context identifier is invalid, re-acquiring the session message forwarded by the message system;
and generating a new session context identifier according to the identification information of the multiple dimensions carried in the session message.
In one embodiment, the processing, by the intelligent robot system, the session message carrying the session context identifier to obtain a corresponding response message includes:
recognizing the session context identification carried by the session message through an intelligent robot system, and searching session context information corresponding to the session context identification;
and performing semantic analysis according to the session context information to obtain a corresponding response message.
In one embodiment, after returning the response message to the message system, the method further comprises:
and pushing the response message to a session group corresponding to the session group identifier through the message system, and sending a corresponding session message aiming at a message receiver corresponding to the user identifier.
A conversation interaction apparatus of an intelligent robot, the apparatus comprising:
a receiving module, for receiving the session message forwarded by the message system; the conversation message is a conversation message with the robot sent by the user terminal in a conversation group;
the sending module is used for determining a corresponding session context identifier according to the session group identifier, the user identifier and the robot identifier carried in the session message, and sending the session message carrying the session context identifier to the intelligent robot system; the session context identifier has a mapping relation with the multi-person session group identifier, the user identifier and the robot identifier information;
and the processing module is used for processing the conversation message carrying the conversation context identifier through the intelligent robot system to obtain a corresponding response message and returning the response message to the message system.
A computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program:
receiving a session message forwarded by a message system; the conversation message is a conversation message with the robot sent by the user terminal in a conversation group;
determining a corresponding session context identifier according to a session group identifier, a user identifier and a robot identifier carried in the session message, and sending the session message carrying the session context identifier to an intelligent robot system; the session context identifier has a mapping relation with the multi-person session group identifier, the user identifier and the robot identifier information;
and processing the conversation message carrying the conversation context identifier through the intelligent robot system to obtain a corresponding response message, and returning the response message to the message system.
A computer-readable storage medium, on which a computer program is stored which, when executed by a processor, carries out the steps of:
receiving a session message forwarded by a message system; the conversation message is a conversation message with the robot sent by the user terminal in a conversation group;
determining a corresponding session context identifier according to a session group identifier, a user identifier and a robot identifier carried in the session message, and sending the session message carrying the session context identifier to an intelligent robot system; the session context identifier has a mapping relation with the multi-person session group identifier, the user identifier and the robot identifier information;
and processing the conversation message carrying the conversation context identifier through the intelligent robot system to obtain a corresponding response message, and returning the response message to the message system.
A conversational interaction system, comprising:
a message system for receiving a session message; the conversation message is a conversation message with the robot sent by the user terminal in a conversation group;
the adaptive system is used for determining a corresponding session context identifier according to the session group identifier, the user identifier and the robot identifier carried in the session message, and sending the session message carrying the session context identifier to the intelligent robot system; the session context identifier has a mapping relation with the multi-person session group identifier, the user identifier and the robot identifier information;
and the intelligent robot system is used for processing the conversation message carrying the conversation context identifier to obtain a corresponding response message and returning the response message to the message system.
The intelligent robot conversation interaction method, the intelligent robot conversation interaction device, the computer equipment and the storage medium receive conversation messages forwarded through the message system, and the conversation messages are conversation messages which are sent by the user terminal in the conversation group and are sent by the robot. And determining a corresponding session context identifier according to the session group identifier, the user identifier and the robot identifier carried in the session message, and sending the session message carrying the session context identifier to the intelligent robot system, wherein the session context identifier has a mapping relation with the multi-person session group identifier, the user identifier and the robot identifier information. And processing the conversation message carrying the conversation context identifier through the intelligent robot system to obtain a corresponding response message, and returning the response message to the message system. Therefore, the third-party intelligent robot system can judge whether the conversation context is the same or not only by identifying the conversation context identification, and through the context information maintained uniformly, when different users have conversations with different intelligent robots in different multi-user groups, the independent conversation context can be maintained, so that the intelligent robot can perform more accurate semantic analysis aiming at different conversation contexts, a more intelligent effect is achieved, the intelligent robot is prevented from giving out answers of discordant texts due to different confused conversations, and the accuracy of processing the conversation information by the intelligent robot is effectively improved.
Drawings
FIG. 1 is a diagram of an application environment of a session interaction method of an intelligent robot in one embodiment;
FIG. 2 is a flow diagram that illustrates a method for session interaction of an intelligent robot, in accordance with an embodiment;
FIG. 3A is a flowchart illustrating steps of sending a session message with a session context identifier to an intelligent robot system in one embodiment;
FIG. 3B is a system architecture diagram of intelligent robot session interactions in one embodiment;
fig. 4 is a schematic flowchart of a step of determining a corresponding session context identifier according to a session group identifier, a user identifier, and a robot identifier carried in a session message in an embodiment;
FIG. 5 is a flowchart of the step of generating a new session context identification in one embodiment;
fig. 6A is a schematic flowchart illustrating a step of processing, by an intelligent robot system, a session message with a session context identifier to obtain a corresponding response message in one embodiment;
FIG. 6B is a diagram illustrating an interface for displaying messages of a conversation between a user and a robot in a conversation group, in accordance with an embodiment;
FIG. 7 is a block diagram of a conversational interaction device of an intelligent robot in one embodiment;
FIG. 8 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The conversation interaction method of the intelligent robot can be applied to the application environment shown in fig. 1. Wherein the terminal 102 communicates with the server 104 via a network. The server 104 receives a conversation message forwarded through the messaging system, the conversation message being a conversation message with the robot sent by the user terminal 102 in a conversation group. The server 104 determines a corresponding session context identifier according to the session group identifier, the user identifier and the robot identifier carried in the session message, the server 104 sends the session message carrying the session context identifier to the intelligent robot system, and the session context identifier has a mapping relation with the multi-person session group identifier, the user identifier and the robot identifier information. The server 104 processes the session message carrying the session context identifier through the intelligent robot system to obtain a corresponding response message, and returns the response message to the message system. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices, and the server 104 may be implemented by an independent server or a server cluster formed by a plurality of servers.
In one embodiment, as shown in fig. 2, a session interaction method for an intelligent robot is provided, which is described by taking the method as an example applied to the server in fig. 1, and includes the following steps:
The adaptation system, i.e. the adaptation server, may receive a session message forwarded by the messaging system, the session message being a session message with the robot sent by the user terminal in a session group. The message system refers to a server for processing different types of messages, and can be deployed locally or in other server platforms. The session group refers to a group having a multi-person session function. For example, the current applications such as WeChat, Skype, etc. all have a multi-person group session function. The types of messages that a conversation group may support include text, pictures, voice, video, geographic location, files, notifications, prompts, intelligent conversation robots, custom messages, and the like. And meanwhile, the offline message, roaming message, multi-terminal synchronization, cloud history record and message pushing capability are provided. The adaptation server is an adaptation system adapted to the third-party intelligent robot system, and is used for searching the intelligent robot system correspondingly adapted according to the received message forwarded by the message system and forwarding the corresponding message to the third-party robot system. When interacting with the intelligent robot, namely when a user calls the intelligent robot, firstly creating a corresponding session context in an intelligent robot system, and updating the timeout time corresponding to the session context; the second is to send information to the intelligent robotic system and the request parameters need to be accompanied by the ID of the session context. For example, a user may send a message of an @ intelligent robot providing a service in a conversation group in a specific scenario, and the conversation message is processed by a series of logics of a message system, and the message system forwards the conversation message to an adaptation system (xt-robot) by calling an internal interface of the adaptation system (xt-robot).
And 204, determining a corresponding session context identifier according to the session group identifier, the user identifier and the robot identifier carried in the session message, and sending the session message carrying the session context identifier to the intelligent robot system, wherein the session context identifier has a mapping relation with the multi-person session group identifier, the user identifier and the robot identifier information.
After the adaptation system receives the session message forwarded by the message system, the adaptation system can determine a corresponding session context identifier according to the session group identifier, the user identifier and the robot identifier carried in the session message, and send the session message carrying the session context identifier to the intelligent robot system, wherein the session context identifier has a mapping relation with the multi-person session group identifier, the user identifier and the robot identifier information. The session group identification is used for identifying the unique session group, the user identification is used for identifying the unique user, and the robot identification is used for identifying the unique robot. The session context identifier is used to identify unique session context information. The purpose of establishing the conversation context information is to provide context information before and after the conversation in the conversation process, so that the intelligent robot can correlate the previous conversation content when answering questions to form a coherent conversation process. The mapping relation means that the adaptation system can combine ID variables of three dimensions of a session group identifier, a user identifier and a robot identifier carried in a session message to form a new variable, namely a session context identifier, and the new variable changes along with the change of the ID variables of the three dimensions. For example, if the three dimensional variables are userid _ xxx, group _ vvv, and robotid _ bbb, respectively, the adaptation system may generate a corresponding new variable according to the three dimensional variables, that is, the ID of the generated session context is userid _ xxx-group _ vvv-robotid _ bbb. If any variable changes, a new session context ID is generated, for example, the group dimension group _ vvv changes to group _ VYY, and the corresponding session context ID generated by the adaptation system is updated to userid _ xxx-group _ VYY-robotid _ bbb.
And step 206, processing the session message carrying the session context identifier through the intelligent robot system to obtain a corresponding response message, and returning the response message to the message system.
The adaptation system determines a corresponding session context identifier according to a session group identifier, a user identifier and a robot identifier carried in the session message, sends the session message carrying the session context identifier to the intelligent robot system, processes the session message carrying the session context identifier through the intelligent robot system to obtain a corresponding response message, and returns the response message to the message system. The intelligent robot system is a robot system capable of performing semantic analysis for different conversation contexts. For example, the robots may include different-function smart robots deployed on different servers, such as cloudlets, canopies, and the like. Specifically, the adaptation system determines a corresponding session context identifier according to a session group identifier, a user identifier and a robot identifier carried in a session message, and forwards the session message to a third-party intelligent robot system after formatting and encryption, and the third-party intelligent robot performs intelligent semantic analysis processing on the session message to obtain a corresponding response message. After the adaptation system receives the response message returned by the intelligent robot, the adaptation system carries out format arrangement on the response message, pushes the response message to the message system, displays the response message in the corresponding conversation group through the message system, and sends the corresponding conversation message to the corresponding message receiver.
In a traditional mode of interacting with an intelligent robot, based on the dimensionality of users, the intelligent robot carries out conversation with the intelligent robot and maintains conversation context information, namely each user only has one conversation context information and cannot support the maintenance of mutually independent conversation context information in a plurality of multi-person conversation groups, the intelligent robot cannot accurately carry out semantic analysis on the conversation information in the multi-person conversation groups, namely the users in different multi-person groups share one conversation context information, when the intelligent robot answers the problem of the same user in different groups, the related conversation context information is the same, and different conversations are easily confused to give out answers of non-answer to the question.
In this embodiment, a session message forwarded by the message system is received, where the session message is a session message with the robot sent by the user terminal in the session group. And determining a corresponding session context identifier according to the session group identifier, the user identifier and the robot identifier carried in the session message, and sending the session message carrying the session context identifier to the intelligent robot system, wherein the session context identifier has a mapping relation with the multi-person session group identifier, the user identifier and the robot identifier information. And processing the conversation message carrying the conversation context identifier through the intelligent robot system to obtain a corresponding response message, and returning the response message to the message system. Therefore, the third-party intelligent robot system can judge whether the conversation context is the same or not only by identifying the conversation context identification, the whole conversation context information does not need to be stored, the complexity of the third-party intelligent robot system is simplified, meanwhile, the context information is maintained in a unified manner, when different users carry out conversation with different intelligent robots in different multi-user groups, the independent conversation context can be maintained, the intelligent robot can carry out more accurate semantic analysis on different conversation contexts, a more intelligent effect is achieved, the intelligent robot is prevented from giving out answers without answer to the questions due to confusion of different conversations, and the accuracy of processing the conversation information by the intelligent robot is effectively improved.
In one embodiment, before receiving the session message forwarded by the messaging system, the method further includes a step of storing the server address in a local database, specifically including:
and acquiring the address of a server where each intelligent robot is located, and storing the server address in a local database.
Before the adaptation system receives the session message forwarded by the message system, the adaptation system may store the server addresses corresponding to the different robot systems in a local database. Specifically, the adaptation system may obtain a server address where each intelligent robot is located, and store the server address in the local database. That is, the server addresses corresponding to the intelligent robots providing different services are all written in the database corresponding to the adaptation system, and the adaptation system can support the inquiry of the server address according to the robot identification, that is, the robot ID. Therefore, the adaptation system is added between the message system and the third-party robot system, and the adaptation system performs unified maintenance on the server address corresponding to the third-party robot system, so that the server address corresponding to the robot identification can be inquired according to the robot identification, and the complexity of the third-party intelligent robot system is simplified. Particularly, under the condition that a plurality of third-party intelligent robot systems need to be docked, corresponding conversation context information does not need to be maintained for each user by each intelligent robot system, the workload is reduced, and the integration of the plurality of intelligent robot systems is facilitated.
In one embodiment, as shown in fig. 3A, the step of sending the session message carrying the session context identifier to the intelligent robot system includes:
And step 304, inquiring a corresponding server address from a local database according to the robot identification.
After the adaptation system receives the session message forwarded by the message system, the adaptation system can determine a corresponding session context identifier according to the session group identifier, the user identifier and the robot identifier carried in the session message, and send the session message carrying the session context identifier to the intelligent robot system. Specifically, as shown in fig. 3B, a system architecture diagram of intelligent robot conversational interaction is shown. And the adaptation system acquires the robot identification carried in the conversation message according to the received conversation message. Further, the adaptation system can query a corresponding server address from a local database according to the robot identifier, perform format conversion and encryption on the session message carrying the session context identifier, and then send the session message to the queried corresponding server address. The adaptation system can perform format conversion and encryption on the received session information according to a preset protocol, and then forwards the session information to the third-party robot system. For example, the message format messaging protocol may be as follows: HTTP HEADER are as follows:
HTTP BODY is as follows:
where sign denotes the signature value and sessionId denotes the session context ID. The adaptation system can perform format conversion and encryption on the received session information in various ways according to a preset protocol. For example, when a sign signature value is calculated, the adaptation system may use digest information in the parameters and appsert (i.e., an application key) of the robot as a signature string, calculate a signature using the hmac sha256 algorithm, and then perform Base64encode, that is, encode using a Base64encode function, to obtain a final signature value. Therefore, the corresponding server address can be inquired according to the robot identifier, namely, the session message can be forwarded to the server where the robot is located for processing according to the configuration information (the server address where the robot service is located) corresponding to the intelligent robot, and the complexity of a third-party intelligent robot system is simplified. Particularly, under the condition that a plurality of third-party intelligent robot systems need to be docked, corresponding conversation context information does not need to be maintained for each user by each intelligent robot system, the workload is reduced, and the integration of the plurality of intelligent robot systems is facilitated.
In an embodiment, as shown in fig. 4, the step of determining a corresponding session context identifier according to a session group identifier, a user identifier, and a robot identifier carried in a session message includes:
And 404, combining identification variables of three dimensions of the session group identification, the user identification and the robot identification according to a preset rule to obtain an updated variable identification.
After the adaptation system receives the session message forwarded by the message system, the adaptation system can determine a corresponding session context identifier according to the session group identifier, the user identifier and the robot identifier carried in the session message. Specifically, the adaptation system may obtain a session group identifier, a user identifier, and robot identifier information carried in the session message. The adaptation system combines identification variables of three dimensions of the session group identification, the user identification and the robot identification according to a preset rule, namely a generation rule of the session context identification to obtain an updated variable identification, and marks the updated variable identification as the corresponding session context identification. For example, the session group identifier, the user identifier, and the robot identifier are userid _ xxx, group _ vvv, robotid _ bbb, respectively. The adaptation system may generate a corresponding new variable according to the three dimensional variables, that is, the ID of the generated session context is userid _ xxx-group _ vvv-robotid _ bbb. If any variable changes, a new session context ID is generated, for example, the group dimension group _ vvv changes to group _ VYY, and the corresponding session context ID generated by the adaptation system is updated to userid _ xxx-group _ VYY-robotid _ bbb. When the session context information corresponding to the user is integrally maintained in the adaptation system and the third-party intelligent robot carries out a conversation, the adaptation system only needs to send the session information to the third-party intelligent robot system, the session context ID is attached to the request parameter, and the third-party intelligent robot system only needs to identify the session context ID to judge whether the session context information is the same. Compared with the traditional method, the conversation context ID has only one dimension, namely the dimension of the user ID. For example, if the user ID is userid _ xxx, then the session context ID is also userid _ xxx, which is still userid _ xxx even though the robot is talking in a different team. In the embodiment, an adaptation system adapted to a third-party intelligent robot system is added between a message system of a multi-person conversation group and the intelligent robot system, and the adaptation system is utilized to maintain corresponding conversation contexts according to three dimensional information (multi-person conversation group ID, user ID and robot ID), so that when different users have conversations with different intelligent robots in different multi-person groups, independent conversation contexts can be maintained, the intelligent robot can perform more accurate semantic analysis on different conversation contexts, a more intelligent effect is achieved, the intelligent robot is prevented from giving out answers without answer to questions due to confusion of different conversations, and the accuracy of the intelligent robot in processing conversation information is effectively improved.
In one embodiment, as shown in fig. 5, the step of generating a new session context identifier includes:
After the adaptation system receives the session message forwarded by the message system, the adaptation system can generate a unique session context identifier according to the current user ID, the current session group ID and the current intelligent robot ID, and store the expiration time corresponding to the session context identifier. Specifically, the adaptation system may preset expiration time corresponding to the session context identifier, where the expiration time is used to determine whether to update the session context identifier. When the adaptation system detects that the session context identifier is invalid, the adaptation system acquires the session message forwarded by the message system again, and generates a new session context identifier according to the identifier information of multiple dimensions carried in the session message. For example, the user 1 sends a message to the robot a at 8:00 am, and then has no continuous conversation, until 19:00 pm, the user 1 sends a message to the robot a again, because the adaptation system sets the expiration time corresponding to the session context, when the user 1 sends a message at 19:00 pm, the session context of the message sent before is expired, and therefore, the adaptation system generates a corresponding new session context identifier according to the session group identifier, the user identifier, and the robot identifier carried in the session message received at 19:00 pm. Therefore, the problem that the conversation time interval between the user and the robot is too long can be solved by setting the failure time corresponding to the session context, a more intelligent effect is achieved, and convenience is brought to the user.
In an embodiment, as shown in fig. 6A, the step of processing, by the intelligent robot system, the session message carrying the session context identifier to obtain a corresponding response message includes:
And step 604, performing semantic analysis according to the session context information to obtain a corresponding response message.
The adaptation system sends the session message carrying the session context identifier to the intelligent robot system, and the intelligent robot system processes the session message carrying the session context identifier to obtain a corresponding response message. Specifically, the intelligent robot system can directly identify the session context identifier carried by the session message, and find the session context information corresponding to the session context identifier. And the intelligent robot system performs semantic analysis according to the session context information to obtain a corresponding response message, and the response message is returned to the adaptation system. Therefore, the third-party intelligent robot system can judge whether the conversation contexts are the same only by identifying the conversation context ID without storing the whole conversation context information, and the complexity of the third-party intelligent robot system is simplified. Particularly, under the condition that a plurality of third-party intelligent robot systems need to be docked simultaneously, unpredictable errors caused by different standards of the third-party robot systems for conversation contexts can be avoided, each third-party intelligent robot can perform more accurate semantic analysis aiming at different conversation contexts, a more intelligent effect is achieved, the intelligent robot is prevented from giving out answers of the texts without answering questions due to the fact that different conversations are mixed up, and therefore the accuracy of the intelligent robot in processing conversation information is effectively improved.
In one embodiment, after the response message is returned to the message system, the method further includes a step of sending a corresponding session message to a message recipient corresponding to the user identifier, which specifically includes:
and pushing the response message to the session group corresponding to the session group identifier through the message system, and sending the corresponding session message aiming at the message receiver corresponding to the user identifier.
The intelligent robot system processes the session message carrying the session context identification to obtain a corresponding response message, and after the adaptive system returns the response message to the message system, the message system sends the corresponding session message to the message receiver corresponding to the user identification. Specifically, after the adaptation system forwards the received response message returned by the robot system to the message system, the message system may push the response message to the session group corresponding to the session group identifier, and send the corresponding session message to the message receiver corresponding to the user identifier. For example, after receiving the response message of the intelligent robot, the adaptation system sorts the response message by message format and sends the response message to the message system, and finally pushes the response message of the intelligent robot to the corresponding multi-person group session by the message system, and @ the corresponding message receiver. As shown in fig. 6B, the response message of the intelligent robot adopts the @ receiving mode (meanwhile, a dialog message is attached), and this mode enables the independent session context information of each user to be well distinguished in the multi-user session group. Therefore, when the message replied by the robot is displayed, which replied message and which user ID replied can be clearly displayed, as shown in fig. 6B, which is a schematic view of a display interface of the messages of the conversation between the user and the robot in a certain conversation group. Is more clearly shown on the display. Meanwhile, the adaptation system stores all session context information into a database and provides a function of inquiring according to the session ID, thereby bringing convenience to users.
It should be understood that although the various steps in the flow charts of fig. 1-6 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 1-6 may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed in turn or alternately with other steps or at least some of the other steps.
In one embodiment, as shown in fig. 7, there is provided a conversation interaction apparatus of an intelligent robot, including: a receiving module 702, a sending module 704, and a processing module 706, wherein:
a receiving module 702, configured to receive a session message forwarded by a message system, where the session message is a session message with a robot sent by a user terminal in a session group.
A sending module 704, configured to determine a corresponding session context identifier according to the session group identifier, the user identifier, and the robot identifier carried in the session message, and send the session message carrying the session context identifier to the intelligent robot system, where the session context identifier has a mapping relationship with the multi-person session group identifier, the user identifier, and the robot identifier information.
And the processing module 706 is configured to process the session message carrying the session context identifier through the intelligent robot system to obtain a corresponding response message, and return the response message to the message system.
In one embodiment, the apparatus further comprises: the device comprises an acquisition module and a query module.
The acquisition module is used for acquiring the address of a server where each intelligent robot is located and storing the server address in a local database; and acquiring the robot identification carried in the conversation message. And the query module is used for querying the corresponding server address from the local database according to the robot identifier. And the sending module is used for carrying out format conversion and encryption on the session message carrying the session context identifier and then sending the session message to the server address.
In one embodiment, the apparatus further comprises: a combination module and a marking module.
The acquisition module is further used for acquiring the conversation group identification, the user identification and the robot identification information carried in the conversation message. The combination module is used for combining identification variables of three dimensions of the session group identification, the user identification and the robot identification according to a preset rule to obtain an updated variable identification. The marking module is used for marking the updated variable identification as the corresponding session context identification.
In one embodiment, the apparatus further comprises: the device comprises a setting module and a detection module.
The setting module is used for setting the failure time corresponding to the session context identifier, and the failure time is used for judging whether to update the session context identifier. The detection module is used for re-acquiring the session message forwarded by the message system when detecting that the session context identifier is invalid, and generating a new session context identifier according to the identifier information of multiple dimensions carried in the session message.
In one embodiment, the apparatus further comprises: the device comprises a searching module and an analyzing module.
The searching module is used for identifying the session context identification carried by the session message through the intelligent robot system and searching the session context information corresponding to the session context identification. The analysis module is used for carrying out semantic analysis according to the session context information to obtain a corresponding response message.
In one embodiment, the sending module is further configured to push the response message to the session group corresponding to the session group identifier through the message system, and send the corresponding session message to the message recipient corresponding to the user identifier.
The specific definition of the intelligent robot session interaction device can refer to the above definition of the intelligent robot session interaction method, which is not described herein again. The modules in the conversation interaction device of the intelligent robot can be wholly or partially realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in fig. 8. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing the conversation interaction data of the intelligent robot. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a conversational interaction method for an intelligent robot.
Those skilled in the art will appreciate that the architecture shown in fig. 8 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the steps of the above-described method embodiments being implemented when the computer program is executed by the processor.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database or other medium used in the embodiments provided herein can include at least one of non-volatile and volatile memory. Non-volatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical storage, or the like. Volatile Memory can include Random Access Memory (RAM) or external cache Memory. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A conversation interaction method of an intelligent robot, the method comprising:
receiving a session message forwarded by a message system; the conversation message is a conversation message with the robot sent by the user terminal in a conversation group;
determining a corresponding session context identifier according to a session group identifier, a user identifier and a robot identifier carried in the session message, and sending the session message carrying the session context identifier to an intelligent robot system; the session context identifier has a mapping relation with the multi-person session group identifier, the user identifier and the robot identifier information;
and processing the conversation message carrying the conversation context identifier through the intelligent robot system to obtain a corresponding response message, and returning the response message to the message system.
2. The method of claim 1, wherein prior to receiving the session message forwarded through the messaging system, the method further comprises:
acquiring a server address where each intelligent robot is located, and storing the server address in a local database;
the sending the session message carrying the session context identifier to the intelligent robot system comprises:
acquiring a robot identifier carried in the session message;
inquiring a corresponding server address from the local database according to the robot identifier;
and after carrying out format conversion and encryption on the session message carrying the session context identifier, sending the session message to the server address.
3. The method of claim 1, wherein the determining the corresponding session context identifier according to the session group identifier, the user identifier, and the robot identifier carried in the session message comprises:
acquiring a conversation group identifier, a user identifier and robot identifier information carried in the conversation message;
combining identification variables of three dimensions of the session group identification, the user identification and the robot identification according to a preset rule to obtain an updated variable identification;
and marking the updated variable identification as a corresponding session context identification.
4. The method of claim 3, further comprising:
setting failure time corresponding to the session context identifier, wherein the failure time is used for judging whether to update the session context identifier;
when detecting that the session context identifier is invalid, re-acquiring the session message forwarded by the message system;
and generating a new session context identifier according to the identification information of the multiple dimensions carried in the session message.
5. The method according to claim 1, wherein the processing, by the intelligent robot system, the session message carrying the session context identifier to obtain a corresponding response message comprises:
recognizing the session context identification carried by the session message through an intelligent robot system, and searching session context information corresponding to the session context identification;
and performing semantic analysis according to the session context information to obtain a corresponding response message.
6. The method of claim 1, wherein after returning the response message to the messaging system, the method further comprises:
and pushing the response message to a session group corresponding to the session group identifier through the message system, and sending a corresponding session message aiming at a message receiver corresponding to the user identifier.
7. A conversational interaction system, comprising:
a message system for receiving a session message; the conversation message is a conversation message with the robot sent by the user terminal in a conversation group;
the adaptive system is used for determining a corresponding session context identifier according to the session group identifier, the user identifier and the robot identifier carried in the session message, and sending the session message carrying the session context identifier to the intelligent robot system; the session context identifier has a mapping relation with the multi-person session group identifier, the user identifier and the robot identifier information;
and the intelligent robot system is used for processing the conversation message carrying the conversation context identifier to obtain a corresponding response message and returning the response message to the message system.
8. A conversation interaction apparatus of an intelligent robot, the apparatus comprising:
a receiving module, for receiving the session message forwarded by the message system; the conversation message is a conversation message with the robot sent by the user terminal in a conversation group;
the sending module is used for determining a corresponding session context identifier according to the session group identifier, the user identifier and the robot identifier carried in the session message, and sending the session message carrying the session context identifier to the intelligent robot system; the session context identifier has a mapping relation with the multi-person session group identifier, the user identifier and the robot identifier information;
and the processing module is used for processing the conversation message carrying the conversation context identifier through the intelligent robot system to obtain a corresponding response message and returning the response message to the message system.
9. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 6 when executing the computer program.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011507312.3A CN112579754B (en) | 2020-12-18 | 2020-12-18 | Conversation interaction method and device of intelligent robot and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011507312.3A CN112579754B (en) | 2020-12-18 | 2020-12-18 | Conversation interaction method and device of intelligent robot and computer equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112579754A true CN112579754A (en) | 2021-03-30 |
| CN112579754B CN112579754B (en) | 2024-09-27 |
Family
ID=75136125
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011507312.3A Active CN112579754B (en) | 2020-12-18 | 2020-12-18 | Conversation interaction method and device of intelligent robot and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112579754B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113452598A (en) * | 2021-04-14 | 2021-09-28 | 阿里巴巴新加坡控股有限公司 | Data processing method and computer program product |
| CN113965535A (en) * | 2021-10-21 | 2022-01-21 | 深圳前海微众银行股份有限公司 | Message push optimization method, apparatus, device and readable storage medium |
| CN114422576A (en) * | 2022-01-24 | 2022-04-29 | 深圳壹账通智能科技有限公司 | Session cleaning method and device, computer equipment and readable storage medium |
| CN114979045A (en) * | 2022-04-28 | 2022-08-30 | 北京百度网讯科技有限公司 | Group chat robot communication method, device, equipment and medium |
| CN115294988A (en) * | 2022-07-20 | 2022-11-04 | 北方民族大学 | A collaboration-oriented voice interaction system and method |
| WO2024140549A1 (en) * | 2022-12-30 | 2024-07-04 | 华为技术有限公司 | Communication method and related apparatus |
| WO2025098500A1 (en) * | 2023-11-08 | 2025-05-15 | 北京字跳网络技术有限公司 | Method and apparatus for conversation interaction, device, and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101635672A (en) * | 2008-07-21 | 2010-01-27 | 中兴通讯股份有限公司 | Device and method for realizing convergence service session in group mode |
| CN103236968A (en) * | 2013-05-16 | 2013-08-07 | 百度在线网络技术（北京）有限公司 | Session management method, device and system for mass texting messages |
| CN109639828A (en) * | 2019-01-15 | 2019-04-16 | 腾讯科技（深圳）有限公司 | Conversation message treating method and apparatus |
| CN110636106A (en) * | 2019-08-15 | 2019-12-31 | 平安普惠企业管理有限公司 | Information pushing method and device, computer equipment and storage medium |
-
2020
- 2020-12-18 CN CN202011507312.3A patent/CN112579754B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101635672A (en) * | 2008-07-21 | 2010-01-27 | 中兴通讯股份有限公司 | Device and method for realizing convergence service session in group mode |
| CN103236968A (en) * | 2013-05-16 | 2013-08-07 | 百度在线网络技术（北京）有限公司 | Session management method, device and system for mass texting messages |
| CN109639828A (en) * | 2019-01-15 | 2019-04-16 | 腾讯科技（深圳）有限公司 | Conversation message treating method and apparatus |
| CN110636106A (en) * | 2019-08-15 | 2019-12-31 | 平安普惠企业管理有限公司 | Information pushing method and device, computer equipment and storage medium |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113452598A (en) * | 2021-04-14 | 2021-09-28 | 阿里巴巴新加坡控股有限公司 | Data processing method and computer program product |
| CN113452598B (en) * | 2021-04-14 | 2022-10-28 | 阿里巴巴新加坡控股有限公司 | Data processing method |
| CN113965535A (en) * | 2021-10-21 | 2022-01-21 | 深圳前海微众银行股份有限公司 | Message push optimization method, apparatus, device and readable storage medium |
| CN113965535B (en) * | 2021-10-21 | 2023-04-18 | 深圳前海微众银行股份有限公司 | Message push optimization method, device, equipment and readable storage medium |
| CN114422576A (en) * | 2022-01-24 | 2022-04-29 | 深圳壹账通智能科技有限公司 | Session cleaning method and device, computer equipment and readable storage medium |
| CN114422576B (en) * | 2022-01-24 | 2024-02-06 | 深圳壹账通智能科技有限公司 | Session cleaning method and device, computer equipment and readable storage medium |
| CN114979045A (en) * | 2022-04-28 | 2022-08-30 | 北京百度网讯科技有限公司 | Group chat robot communication method, device, equipment and medium |
| CN115294988A (en) * | 2022-07-20 | 2022-11-04 | 北方民族大学 | A collaboration-oriented voice interaction system and method |
| WO2024140549A1 (en) * | 2022-12-30 | 2024-07-04 | 华为技术有限公司 | Communication method and related apparatus |
| WO2025098500A1 (en) * | 2023-11-08 | 2025-05-15 | 北京字跳网络技术有限公司 | Method and apparatus for conversation interaction, device, and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112579754B (en) | 2024-09-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112579754B (en) | Conversation interaction method and device of intelligent robot and computer equipment | |
| CN108449405B (en) | Event reminding method and device, computer equipment and storage medium | |
| JP2009540435A (en) | Email address verification | |
| US9065788B2 (en) | Method, device and system for voice communication | |
| US20190065498A1 (en) | System and method for rich conversation in artificial intelligence | |
| CN105827459B (en) | Method and device for calling maintenance center by intelligent equipment | |
| US20140280464A1 (en) | Intermediary api for providing presence data to requesting clients | |
| CN105553831B (en) | Message delivery method and system | |
| CN112612595A (en) | Method and device for establishing micro-service calling relationship, computer equipment and storage medium | |
| CN107948242A (en) | More service number template message sending methods and system | |
| US20100082757A1 (en) | Address quality engine | |
| CN111447136B (en) | Message pushing method and device, computer equipment and storage medium | |
| EP2974159A1 (en) | Method, device and system for voice communication | |
| CN113014446B (en) | Abnormal offline user detection method, device, server, storage medium and system | |
| CN112671636B (en) | Group message pushing method and device, computer equipment and storage medium | |
| CN110572358A (en) | Data leakage processing method and device, electronic equipment and storage medium | |
| CN105376279A (en) | Contact recommending method and device | |
| CN111182117A (en) | Call processing method and device, computer equipment and computer readable storage medium | |
| WO2019242279A1 (en) | Message processing method and device | |
| WO2018214795A1 (en) | Call indication method, device and system | |
| US11539650B2 (en) | System and method for alerts for missing coverage of chatbot conversation messages | |
| CN113691595A (en) | Interactive interface generation method and device, computer equipment and storage medium | |
| CN115695345A (en) | Message processing method, device, computer equipment and storage medium | |
| CN112291420A (en) | Message display method and terminal equipment | |
| US20240378622A1 (en) | Systems and methods for automated silent inference of client interaction |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |