CN114363277A - Intelligent chatting method and device based on social relationship and related products - Google Patents
Intelligent chatting method and device based on social relationship and related products Download PDFInfo
- Publication number
- CN114363277A CN114363277A CN202111533248.0A CN202111533248A CN114363277A CN 114363277 A CN114363277 A CN 114363277A CN 202111533248 A CN202111533248 A CN 202111533248A CN 114363277 A CN114363277 A CN 114363277A
- Authority
- CN
- China
- Prior art keywords
- reply
- intelligent
- conversation
- message
- conversation message
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Information Transfer Between Computers (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The application discloses an intelligent chatting method, an intelligent chatting device and related products based on social relations, wherein the method comprises the following steps: determining a first identity of a user, extracting attribute information corresponding to the first identity, and generating a social relationship graph according to the attribute information; receiving a conversation message through instant messaging software, and intelligently identifying and determining whether intelligent reply is needed or not according to the conversation message and the social relationship map; and when the intelligent reply to the conversation message is determined to be needed, starting an intelligent chat assistant to carry out intelligent reply to the conversation message. The technical scheme provided by the application has the advantage of high user experience.
Description
Technical Field
The application relates to the field of internet, in particular to an intelligent chatting method and device based on social relations and a related product.
Background
Instant Messaging (IM) refers to a service capable of instantly sending and receiving internet messages and the like. Since 1998, particularly with the rapid development in recent years, the functions of instant messaging are becoming more and more abundant, and various functions such as e-mail, blog, music, television, game, and search are gradually integrated. Instant messaging is not a simple chat tool, and has been developed into a comprehensive information platform integrating communication, information, entertainment, search, e-commerce, office collaboration, enterprise customer service and the like.
The existing instant messaging software cannot realize intelligent chat, and the user experience is influenced.
Disclosure of Invention
The embodiment of the application provides an intelligent chatting method and device based on social relations and a related product, which can carry out intelligent chatting on instant messaging software and improve user experience.
In a first aspect, an embodiment of the present application provides an intelligent chat method based on social relationships, where the method is applied to an electronic device, and the method includes the following steps:
determining a first identity of a user, extracting attribute information corresponding to the first identity, and generating a social relationship graph according to the attribute information;
receiving a conversation message through instant messaging software, and intelligently identifying and determining whether intelligent reply is needed or not according to the conversation message and the social relationship map;
and when the intelligent reply to the conversation message is determined to be needed, starting an intelligent chat assistant to carry out intelligent reply to the conversation message.
In a second aspect, an intelligent chat apparatus based on social relationships is provided, where the intelligent chat assistant based on social relationships is applied to an electronic device, and specifically includes:
a determining unit for determining a first identity of a user;
the processing unit is used for extracting attribute information corresponding to the first identity and generating a social relationship map according to the attribute information; receiving a conversation message through instant messaging software, and intelligently identifying and determining whether intelligent reply is needed or not according to the conversation message and the social relationship map; and when the intelligent reply to the conversation message is determined to be needed, starting the intelligent chat assistant to carry out intelligent reply to the conversation message.
In a third aspect, an embodiment of the present application provides an electronic device, including a processor, a memory, a communication interface, and one or more programs, where the one or more programs are stored in the memory and configured to be executed by the processor, and the program includes instructions for executing the steps in the first aspect of the embodiment of the present application.
In a fourth aspect, the present application provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program for electronic data exchange, where the computer program makes a computer perform part or all of the steps described in any one of the methods in the second aspect of the present application.
In a fifth aspect, the present application provides a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to perform some or all of the steps described in any one of the methods of the second aspect of the present application. The computer program product may be a software installation package.
According to the technical scheme, the electronic equipment determines the first identity of the user, extracts attribute information corresponding to the first identity and generates the social relationship map; receiving a conversation message through instant messaging software, and intelligently identifying and determining whether intelligent reply is needed or not according to the conversation message and a social relationship map; and when the intelligent reply to the conversation message is determined to be needed, the intelligent chat assistant is started to carry out intelligent reply to the conversation message. By the technical scheme, whether intelligent reply is needed or not can be intelligently identified through the social relationship map and the session message, intelligent chat is realized, and user experience is improved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a flow chart of an intelligent chat method based on social relationships according to an embodiment of the present application;
FIG. 2 is a schematic flow diagram of the intelligent reply function provided herein;
FIG. 3 is a flow chart illustrating an implementation of an intelligent chat assistant provided by the present application;
FIG. 4 is a schematic diagram of a security proctoring provided by the present application;
fig. 5 is a schematic structural diagram of an electronic device provided in an embodiment of the present application;
fig. 6 is a schematic structural diagram of an intelligent chat assistant based on social relationships provided in the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be described below with reference to the accompanying drawings.
In order to better understand the scheme of the embodiments of the present application, the following first introduces the related terms and concepts that may be involved in the embodiments of the present application.
The terms "first," "second," and the like in the description and claims of the present application and in the above-described drawings are used for distinguishing between different objects and not for describing a particular order. Furthermore, the terms "include" and "have," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.
In order to make the technical solutions of the present application better understood, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The electronic device described in the embodiment of the present application may include a smart Phone (e.g., an Android Phone, an iOS Phone, a Windows Phone, etc.), a tablet computer, a palm computer, a notebook computer, a video matrix, a monitoring platform, a Mobile Internet Device (MID), a wearable device, or the like, which are examples and not exhaustive, and include but are not limited to the foregoing devices, and of course, the electronic device may also be a server, for example, a cloud server.
Referring to fig. 1, fig. 1 provides an intelligent social relationship-based chat method applied to an electronic device, and the method is as shown in fig. 1, and the intelligent social relationship-based chat method may include the following steps:
101. determining a first identity of a user, extracting attribute information corresponding to the first identity, and generating a social relationship graph according to the attribute information.
In this embodiment, the first identity may include at least one of the following: name, username, IP address, physical address, etc., without limitation. The electronic device can determine a first identity of the user, determine attribute information corresponding to the first identity according to a preset mapping relationship between the identity and the attribute information, and generate a social relationship graph according to the attribute information.
In an alternative, the determining the first identity of the user may include:
and identifying and determining the first identity for the first picture of the collected first picture of the user. I.e. the user identity can be obtained by means of image recognition.
102. And receiving a conversation message through instant messaging software, and intelligently identifying and determining whether intelligent reply is needed or not according to the conversation message and the social relationship map.
In a specific implementation, the electronic device may receive a session message through the instant messaging software, perform semantic recognition based on the session message to determine whether the session message needs to be replied, and/or determine the importance of the session message according to the social relationship graph, and determine whether the session message needs to be replied according to the importance, and further determine whether the session message itself and the social relationship graph need to be intelligently replied.
103. And when the intelligent reply to the conversation message is determined to be needed, starting an intelligent chat assistant to carry out intelligent reply to the conversation message.
In the specific implementation, when it is determined that the intelligent reply is required to the session message, the intelligent chat assistant is started, and further, an interface of the intelligent chat assistant can be opened, and the intelligent reply is performed to the session message through the intelligent chat assistant.
According to the technical scheme, the electronic equipment determines a first identity of a user, extracts attribute information corresponding to the first identity and generates a social relationship map; receiving a conversation message through instant messaging software, and intelligently identifying and determining whether intelligent reply is needed or not according to the conversation message and a social relationship map; and when the intelligent reply to the conversation message is determined to be needed, the intelligent chat assistant is started to carry out intelligent reply to the conversation message. By the technical scheme, whether intelligent reply is needed or not can be intelligently identified through the social relationship map and the session message, intelligent chat is realized, and user experience is improved.
In an optional scheme, the attribute information may specifically include: the generating of the social relationship map according to the attribute information may specifically include:
and determining whether the first identity has a direct label relationship according to the attribute information, establishing a first-layer map after grouping the direct label relationship, acquiring an indirect relation person in the first-layer map if the first identity has an indirect label relationship, and setting the indirect label relationship in a second-layer map under the relation person.
Direct or indirect relations among different people can be combed based on the attribute information, and finally the social relation graph is formed.
In specific implementation, for the social relationship graph, the personal relationship model may be calculated according to the friend tag relationship of the individual, or the personal relationship model may be calculated according to the group relationship in which the individual is added, or the personal relationship model may be calculated according to the key information in the daily chat process; or, the personal relation model can be calculated according to the organization structure and the work function in the work; alternatively, the individual's tendencies may be calculated and incorporated into the relationship model based on the user tags and interests, as well as the individual's chat data.
In an optional aspect, the method may further include:
and when the conversation message is determined to need manual reply, sending a prompt message to the user to prompt the user to manually reply.
When the electronic device determines that the conversation message contains the preset keyword, it determines that a manual reply is required, and the preset keyword may be preset or default to the system, for example, the preset keyword may be "manual", "worship", "do not want to use robot", and the like, which is not limited herein. Of course, the electronic device may also perform semantic recognition on the session message, and if the session message cannot be correctly replied, may also send a prompt message to the user to prompt the user to reply manually.
In an optional scheme, the determining whether an intelligent reply is required according to the conversation message and the social relationship graph intelligent recognition specifically includes:
according to the extracted conversation mark and the conversation content corresponding to the conversation message, if the conversation mark belongs to the social relationship map, a first group of the conversation mark in the social relationship map is obtained, the conversation content is searched in the historical information of the first group, if the historical reply information of the conversation content exists, intelligent reply is determined, and if the historical reply information of the conversation content does not exist, manual reply is determined.
In an optional aspect, the method may further include:
and determining the reply style of the intelligent chat assistant, generating a reply message matched with the conversation message according to the reply style, and replying the reply message.
In a specific implementation, different reply styles may have different reply messages, and the setting of the reply style may be preset or default to the system, for example, a personality parameter of the intelligent chat assistant may be set, and the intelligent chat assistant may have different reply styles based on different personality parameters.
The above reply mode is specifically shown in fig. 2, and may include: response style, response scope, and content collection.
The response style may be, for example, a hot service type, a apathy answer type, an expression-only type, a vocalization-only type, or the like.
And (4) calculating the intimacy and the attention according to the social relationship graph of the individual, and if the individual who needs to carry out the intelligent response range finds you to chat, automatically entering an intelligent response mode by the system. If the interlocutor and you are in close relationship, the manual conversation mode will be entered. Of course, the user can set which persons respond automatically and which persons respond manually by setting the tags.
Content collection, the user can automatically collect and feed back the content by setting the keywords of the concerned content. The intelligent chat assistant pushes the contents with important attention to the user in a mode of summary and conversation interception.
In an optional scheme, after receiving the session message, the method may further include:
and extracting the chat content of the session message, retrieving the chat content in a security risk knowledge base to obtain a retrieval result, if the retrieval result confirms that a risk problem exists, sending a risk prompt, and sending warning information to the opposite side of the session message.
For example, the embodiment of the present application may have a risk prompt system function, and may identify various risks in the automatic reply process of the conversation robot and the active conversation process of the user. The system helps users to improve network security awareness and prevent related risks.
Furthermore, the risk prompting system mainly depends on various personal behaviors in the social relationship network and the corpus related to common risk conversations, and helps a user to improve risk awareness and prevent crisis through big data analysis and calculation.
In an optional aspect, the method may further include:
and configuring a specified list, and adding the initiator of the session message into the specified list if the other party breaks rules for a long time or multiple times.
In a specific implementation, the number of the designated lists may be one or more, and the initiator of the session message may be added to the designated list when the number of times of violation accumulation of the other party reaches a certain number of times or the number of times of violation in a period of time reaches a certain number of times.
In an optional aspect, the method may further include:
and adding the specified list into the social relationship map.
In specific implementation, the designated list can be added into the social relationship map, so that the social relationship map is updated.
For example, in the embodiment of the present application, a speaker chat mode may be simulated according to data of a user typing chat and a voice chat, so as to perform an automatic response.
By way of further example, the user may set a scenario that requires an automatic response, such as a chat by a stranger, or a related advertising promotion-like message. If the intelligent chat assistant identifies information useful to the user, it will report it together to the user.
For example, in the embodiment of the present application, the conversation of the key relatives can be pushed to the user according to the social relationship graph of the user, and the user is helped to answer some simple questions quickly in the conversation. Fast answers rely on long-term accumulated knowledge bases and knowledge maps. For the strategy needing automatic answering and manual taking over, the strategy can be set according to the personal relationship map, and different conversation modes can be set for the interlocutors with different intimacy levels. Meanwhile, the method can also be set according to the conversation mode of the opposite side to the user, so that the adaptability is adjusted, and the improvement of interpersonal relationship is promoted.
In the embodiment of the application, the intelligent chat assistant can help a user to process daily communication chat contents according to dynamic relation change. Including automatic chat reply, automatic reply to promotional messages, etc. At the same time, the user is provided with a good answer by encountering difficult problems. In addition, when the automatic answering is carried out, the language and the speaking mode of the user can be simulated, and some key information which the user is interested in can be collected and gathered and pushed to the user on time. Especially under the condition of group chat, some key information is easy to miss, and the chat assistant can help to arrange the information.
In the embodiment of the application, the intelligent chat assistant can provide a risk prompt system for a user according to the continuous accumulation of the relationship graph and the risk dialogue corpus, and provides warning and preventing functions for various network risks. The social relationship graph can update a new state all the time according to the change of time and feed back the new state to the intelligent chat assistant, so that the intelligent chat assistant can judge conversation contents which are recommended and used by various scenes.
Example one
The embodiment of the application provides an intelligent chatting method based on social relations, which specifically comprises the following steps:
a social relationship graph.
The social relation graph carries out AI semantic analysis and big data reasoning from the perspective of each user, and calculates the relation graph which accords with personal habits, working role positioning and communication attention degrees according to the attributes of each user.
When another chat person chats with the current chat person, the two chat persons respectively calculate respective map relations and carry out relation fusion, so that the communication between the two chat persons is more in line with the communication expectation of the two chat persons.
For example, a is a life-oriented experience that is of interest for some luxury in communication software. B is a luxury buyer who can automatically reach the communication expectations of both and pull the relationship of both into intimate terms. The intelligent chat assistant can automatically help the two parties recommend some high-quality conversation contents, and prompts related risks according to the risk control strategy.
For the case of group chat, related conversation content recommendation can be performed according to topic content, group name subject and the like, if a person @ the person is, a relationship graph between the person and the group is calculated, and specific conversation content is recommended.
Intelligent chat assistant, intelligent answer function.
The answer styles comprise answer styles built in the system, such as a hot service type, a apathy type, an expression only type, a vocalization only type and the like. The method also comprises the steps of carrying out long-term AI training according to the social relationship graph of the individual, and carrying out automatic dialogue response according to the real chat situation of the individual.
And (4) calculating the intimacy and the attention according to the social relationship graph of the individual, and if the individual who needs to carry out the intelligent response range finds you to chat, automatically entering an intelligent response mode by the system. If the interlocutor and you are in close relationship, the manual conversation mode will be entered. Of course, the user can set which persons respond automatically and which persons respond manually by setting the tags.
Content collection, the user can automatically collect and feed back the content by setting the keywords of the concerned content. The intelligent chat assistant pushes the contents with important attention to the user in a mode of summary and conversation interception.
An intelligent chat assistant and a conversation assistant (shown in figure 3).
And screening out the situations needing manual response by the social relationship graph confirmed by the initiating conversation party, and entering a conversation mode which is dominated by the user and is cooperated by a conversation assistant.
If the conversation is actively initiated by the user, the conversation mode which is dominated by the user and is cooperated by the conversation assistant is also entered.
The intelligent chat assistant provides an intelligent AI conversation recommendation system composed of a strong knowledge base and a reply skill base aiming at different topics according to long-term corpus data and hot word data, and helps a user to carry out the content of a conversation link. Of course, the user may perform the conversation by himself without referring to the conversation contents recommended by the system.
The intelligent chat assistant can be turned on and off by the user under any condition.
A risk warning (as shown in fig. 4).
And searching the chat content in a safety risk knowledge base, and if a risk problem occurs, prompting a receiving party and warning a sending party.
And setting up a specified list, and if the issuing party breaks rules for a long time, strictly warning and adding the specified list.
When the social relationship graph is calculated, the specified list factor is also considered, and if a certain person frequently makes an illegal action, the opportunity of obtaining other people to chat actively is influenced. The system operator may perform special penalties if located on a designated list.
In accordance with the foregoing embodiments, please refer to fig. 5, fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application, and as shown in the drawing, the electronic device includes a processor, a memory, a communication interface, and one or more programs, where the one or more programs are stored in the memory and configured to be executed by the processor, and in an embodiment of the present application, the programs include instructions for performing the following steps:
determining a first identity of a user, extracting attribute information corresponding to the first identity, and generating a social relationship graph according to the attribute information;
receiving a conversation message through instant messaging software, and intelligently identifying and determining whether intelligent reply is needed or not according to the conversation message and the social relationship map;
and when the intelligent reply to the conversation message is determined to be needed, starting an intelligent chat assistant to carry out intelligent reply to the conversation message.
In an optional scheme, the attribute information specifically includes one or any combination of the following relationships:
friend label relationship, group label relationship, work label relationship, family label relationship.
In an alternative, in the generating of the social relationship graph according to the attribute information, the program includes instructions for performing the following steps:
and determining whether the first identity has a direct label relationship according to the attribute information, establishing a first-layer map after grouping the direct label relationship, acquiring an indirect relation person in the first-layer map if the first identity has an indirect label relationship, and setting the indirect label relationship in a second-layer map under the relation person.
In an alternative, the program further includes instructions for performing the steps of:
and when the conversation message is determined to need manual reply, sending a prompt message to the user to prompt the user to manually reply.
In an alternative arrangement, in said intelligently identifying whether an intelligent reply is required based on said conversation message and said social relationship graph, the program includes instructions for:
according to the extracted conversation mark and the conversation content corresponding to the conversation message, if the conversation mark belongs to the social relationship map, a first group of the conversation mark in the social relationship map is obtained, the conversation content is searched in the historical information of the first group, if the historical reply information of the conversation content exists, intelligent reply is determined, and if the historical reply information of the conversation content does not exist, manual reply is determined.
In an alternative, the program further includes instructions for performing the steps of:
and determining the reply style of the intelligent chat assistant, generating a reply message matched with the conversation message according to the reply style, and replying the reply message.
In an optional aspect, after receiving the session message, the program further includes instructions for performing the following steps:
and extracting the chat content of the session message, retrieving the chat content in a security risk knowledge base to obtain a retrieval result, if the retrieval result confirms that a risk problem exists, sending a risk prompt, and sending warning information to the opposite side of the session message.
In an alternative, the program further includes instructions for performing the steps of:
and configuring a specified list, and adding the initiator of the session message into the specified list if the other party breaks rules for a long time or multiple times.
It can be seen that, in the electronic device described in the present application, the first identity of the user is determined, and the attribute information corresponding to the first identity is extracted to generate the social relationship graph; receiving a conversation message through instant messaging software, and intelligently identifying and determining whether intelligent reply is needed or not according to the conversation message and a social relationship map; and when the intelligent reply to the conversation message is determined to be needed, the intelligent chat assistant is started to carry out intelligent reply to the conversation message. By the technical scheme, whether intelligent reply is needed or not can be intelligently identified through the social relationship map and the session message, intelligent chat is realized, and user experience is improved.
Referring to fig. 6, fig. 6 provides an intelligent chat device based on social relationships, where the intelligent chat device based on social relationships is applied to an electronic device, and specifically includes:
a determining unit 601, configured to determine a first identity of a user;
the processing unit 602 is configured to extract attribute information corresponding to the first identity, and generate a social relationship map according to the attribute information; receiving a conversation message through instant messaging software, and intelligently identifying and determining whether intelligent reply is needed or not according to the conversation message and the social relationship map; and when the intelligent reply to the conversation message is determined to be needed, starting the intelligent chat assistant to carry out intelligent reply to the conversation message.
The processing unit 602 may also perform a refinement or an alternative of the method embodiment shown in fig. 1, which is not described herein again.
In an optional scheme, the attribute information specifically includes one or any combination of the following relationships:
friend label relationship, group label relationship, work label relationship, family label relationship.
In an optional scheme, the generating a social relationship graph according to the attribute information specifically includes:
and determining whether the first identity has a direct label relationship according to the attribute information, establishing a first-layer map after grouping the direct label relationship, acquiring an indirect relation person in the first-layer map if the first identity has an indirect label relationship, and setting the indirect label relationship in a second-layer map under the relation person.
In an optional scheme, the intelligent chat device is further specifically configured to:
and when the conversation message is determined to need manual reply, sending a prompt message to the user to prompt the user to manually reply.
In an optional scheme, the determining whether an intelligent reply is required according to the conversation message and the social relationship graph intelligent recognition specifically includes:
according to the extracted conversation mark and the conversation content corresponding to the conversation message, if the conversation mark belongs to the social relationship map, a first group of the conversation mark in the social relationship map is obtained, the conversation content is searched in the historical information of the first group, if the historical reply information of the conversation content exists, intelligent reply is determined, and if the historical reply information of the conversation content does not exist, manual reply is determined.
In an optional scheme, the intelligent chat device is further specifically configured to:
and determining the reply style of the intelligent chat assistant, generating a reply message matched with the conversation message according to the reply style, and replying the reply message.
In an optional scheme, after receiving the session message, the method further includes:
and extracting the chat content of the session message, retrieving the chat content in a security risk knowledge base to obtain a retrieval result, if the retrieval result confirms that a risk problem exists, sending a risk prompt, and sending warning information to the opposite side of the session message.
In an optional scheme, the intelligent chat device is further specifically configured to:
and configuring a specified list, and adding the initiator of the session message into the specified list if the other party breaks rules for a long time or multiple times.
The intelligent chat assistant based on the social relationship described in the application can extract attribute information corresponding to a first identity to generate a social relationship map by determining the first identity of a user; receiving a conversation message through instant messaging software, and intelligently identifying and determining whether intelligent reply is needed or not according to the conversation message and a social relationship map; and when the intelligent reply to the conversation message is determined to be needed, the intelligent chat assistant is started to carry out intelligent reply to the conversation message. By the technical scheme, whether intelligent reply is needed or not can be intelligently identified through the social relationship map and the session message, intelligent chat is realized, and user experience is improved.
It will be appreciated that the electronic device, in order to implement the above-described functions, comprises corresponding hardware and/or software modules for performing the respective functions. The present application is capable of being implemented in hardware or a combination of hardware and computer software in conjunction with the exemplary algorithm steps described in connection with the embodiments disclosed herein. Whether a function is performed as hardware or computer software drives hardware depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, with the embodiment described in connection with the particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
In this embodiment, the electronic device may be divided into functional modules according to the above method example, for example, each functional module may be divided corresponding to each function, or two or more functions may be integrated into one processing module. The integrated module may be implemented in the form of hardware. It should be noted that the division of the modules in this embodiment is schematic, and is only a logic function division, and there may be another division manner in actual implementation.
The present embodiment also provides a computer storage medium, in which computer instructions are stored, and when the computer instructions are run on an electronic device, the electronic device executes the relevant method steps to implement the social relationship-based intelligent chat method in the above embodiments.
The embodiment also provides a computer program product, which when running on a computer, causes the computer to execute the above related steps to implement the social relationship-based intelligent chat method in the above embodiment.
In addition, embodiments of the present application also provide an apparatus, which may be specifically a chip, a component or a module, and may include a processor and a memory connected to each other; the memory is used for storing computer execution instructions, and when the device runs, the processor can execute the computer execution instructions stored in the memory, so that the chip can execute the intelligent chatting method based on social relations in the above method embodiments.
The electronic device, the computer storage medium, the computer program product, or the chip provided in this embodiment are all configured to execute the corresponding method provided above, so that the beneficial effects achieved by the electronic device, the computer storage medium, the computer program product, or the chip may refer to the beneficial effects in the corresponding method provided above, and are not described herein again.
Through the description of the above embodiments, those skilled in the art will understand that, for convenience and simplicity of description, only the division of the above functional modules is used as an example, and in practical applications, the above function distribution may be completed by different functional modules as needed, that is, the internal structure of the device may be divided into different functional modules to complete all or part of the above described functions.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described embodiments of the apparatus are merely illustrative, and for example, a module or a unit may be divided into only one logic function, and may be implemented in other ways, for example, a plurality of units or components may be combined or integrated into another apparatus, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
Units described as separate parts may or may not be physically separate, and parts displayed as units may be one physical unit or a plurality of physical units, may be located in one place, or may be distributed to a plurality of different places. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a readable storage medium. Based on such understanding, the technical solutions of the embodiments of the present application may be essentially or partially contributed to by the prior art, or all or part of the technical solutions may be embodied in the form of a software product, where the software product is stored in a storage medium and includes several instructions to enable a device (which may be a single chip, a chip, or the like) or a processor (processor) to execute all or part of the steps of the methods of the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (10)
1. An intelligent chatting method based on social relations is applied to electronic equipment, and the method comprises the following steps:
determining a first identity of a user, extracting attribute information corresponding to the first identity, and generating a social relationship graph according to the attribute information;
receiving a conversation message through instant messaging software, and intelligently identifying and determining whether intelligent reply is needed or not according to the conversation message and the social relationship map;
and when the intelligent reply to the conversation message is determined to be needed, starting an intelligent chat assistant to carry out intelligent reply to the conversation message.
2. The method according to claim 1, wherein the attribute information specifically includes one or any combination of the following relationships:
friend label relationship, group label relationship, work label relationship, family label relationship.
3. The method according to claim 2, wherein the generating a social relationship graph according to the attribute information specifically comprises:
and determining whether the first identity has a direct label relationship according to the attribute information, establishing a first-layer map after grouping the direct label relationship, acquiring an indirect relation person in the first-layer map if the first identity has an indirect label relationship, and setting the indirect label relationship in a second-layer map under the relation person.
4. The method of claim 1, further comprising:
and when the conversation message is determined to need manual reply, sending a prompt message to the user to prompt the user to manually reply.
5. The method of claim 1, wherein the intelligently identifying whether an intelligent reply is required based on the conversation message and the social relationship graph specifically comprises:
according to the extracted conversation mark and the conversation content corresponding to the conversation message, if the conversation mark belongs to the social relationship map, a first group of the conversation mark in the social relationship map is obtained, the conversation content is searched in the historical information of the first group, if the historical reply information of the conversation content exists, intelligent reply is determined, and if the historical reply information of the conversation content does not exist, manual reply is determined.
6. The method of claim 1, further comprising:
and determining the reply style of the intelligent chat assistant, generating a reply message matched with the conversation message according to the reply style, and replying the reply message.
7. The method of claim 1, further comprising, after receiving a session message:
and extracting the chat content of the session message, retrieving the chat content in a security risk knowledge base to obtain a retrieval result, if the retrieval result confirms that a risk problem exists, sending a risk prompt, and sending warning information to the opposite side of the session message.
8. The intelligent chat assistant based on social relations is applied to electronic equipment, and specifically comprises:
a determining unit for determining a first identity of a user;
the processing unit is used for extracting attribute information corresponding to the first identity and generating a social relationship map according to the attribute information; receiving a conversation message through instant messaging software, and intelligently identifying and determining whether intelligent reply is needed or not according to the conversation message and the social relationship map; and when the intelligent reply to the conversation message is determined to be needed, starting the intelligent chat assistant to carry out intelligent reply to the conversation message.
9. An electronic device comprising a processor, a memory for storing one or more programs and configured for execution by the processor, the programs comprising instructions for performing the steps of the method of any of claims 1-7.
10. A computer-readable storage medium, characterized in that a computer program for electronic data exchange is stored, wherein the computer program causes a computer to perform the method according to any one of claims 1-7.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011641731 | 2020-12-31 | ||
CN2020116417316 | 2020-12-31 |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114363277A true CN114363277A (en) | 2022-04-15 |
CN114363277B CN114363277B (en) | 2023-08-01 |
Family
ID=81099018
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111533248.0A Active CN114363277B (en) | 2020-12-31 | 2021-12-15 | Intelligent chat method and device based on social relationship and related products |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114363277B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115514728A (en) * | 2022-09-27 | 2022-12-23 | 平安科技(深圳)有限公司 | Message pushing method and device, computer equipment and storage medium |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108804698A (en) * | 2018-03-30 | 2018-11-13 | 深圳狗尾草智能科技有限公司 | Man-machine interaction method, system, medium based on personage IP and equipment |
CN110019824A (en) * | 2017-07-20 | 2019-07-16 | 苏州狗尾草智能科技有限公司 | Man-machine interaction method, the apparatus and system of knowledge based map |
CN110022258A (en) * | 2018-01-10 | 2019-07-16 | 腾讯科技(深圳)有限公司 | A kind of conversation controlling method and device, electronic equipment of instant messaging |
CN110502670A (en) * | 2019-08-29 | 2019-11-26 | 南京智慧光信息科技研究院有限公司 | Network social intercourse relationship knowledge mapping generation method and system based on artificial intelligence |
CN110597968A (en) * | 2019-04-28 | 2019-12-20 | 河北省讯飞人工智能研究院 | Reply selection method and device |
CN111883140A (en) * | 2020-07-24 | 2020-11-03 | 中国平安人寿保险股份有限公司 | Authentication method, device, equipment and medium based on knowledge graph and voiceprint recognition |
-
2021
- 2021-12-15 CN CN202111533248.0A patent/CN114363277B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110019824A (en) * | 2017-07-20 | 2019-07-16 | 苏州狗尾草智能科技有限公司 | Man-machine interaction method, the apparatus and system of knowledge based map |
CN110022258A (en) * | 2018-01-10 | 2019-07-16 | 腾讯科技(深圳)有限公司 | A kind of conversation controlling method and device, electronic equipment of instant messaging |
CN108804698A (en) * | 2018-03-30 | 2018-11-13 | 深圳狗尾草智能科技有限公司 | Man-machine interaction method, system, medium based on personage IP and equipment |
CN110597968A (en) * | 2019-04-28 | 2019-12-20 | 河北省讯飞人工智能研究院 | Reply selection method and device |
CN110502670A (en) * | 2019-08-29 | 2019-11-26 | 南京智慧光信息科技研究院有限公司 | Network social intercourse relationship knowledge mapping generation method and system based on artificial intelligence |
CN111883140A (en) * | 2020-07-24 | 2020-11-03 | 中国平安人寿保险股份有限公司 | Authentication method, device, equipment and medium based on knowledge graph and voiceprint recognition |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115514728A (en) * | 2022-09-27 | 2022-12-23 | 平安科技(深圳)有限公司 | Message pushing method and device, computer equipment and storage medium |
CN115514728B (en) * | 2022-09-27 | 2024-05-03 | 平安科技(深圳)有限公司 | Message pushing method, device, computer equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN114363277B (en) | 2023-08-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110581772B (en) | Instant messaging message interaction method and device and computer readable storage medium | |
CN109690526B (en) | Method, device and system for intelligent automatic chat | |
CN109416816B (en) | Artificial intelligence system supporting communication | |
AU2011235030B2 (en) | Conversational question and answer | |
USRE43031E1 (en) | Online interaction processing | |
US11488599B2 (en) | Session message processing with generating responses based on node relationships within knowledge graphs | |
CN110869969A (en) | Virtual assistant for generating personalized responses within a communication session | |
US20080046394A1 (en) | Knowledge extraction from online discussion forums | |
KR20190042337A (en) | Interactive chatbot operation method and system based on natural language processing for activation of messenger group chat room | |
US20090299932A1 (en) | System and method for providing a virtual persona | |
WO2020011043A1 (en) | Method, device and system for acquiring logistics object distribution information | |
CN111131005A (en) | Dialogue method, device, equipment and storage medium of customer service system | |
CN108306813B (en) | Session message processing method, server and client | |
CN108090170B (en) | A kind of intelligence inquiry method for recognizing semantics and visible intelligent interrogation system | |
CN116775815B (en) | Dialogue data processing method and device, electronic equipment and storage medium | |
CN114363277A (en) | Intelligent chatting method and device based on social relationship and related products | |
CN106874451A (en) | A kind of method of the personal exclusive corpus of automatic foundation | |
CN112685551A (en) | Corpus construction method, chat robot conversation method and related device | |
KR101986153B1 (en) | System and method for communication service using webtoon identification technology | |
CN106878761B (en) | Living broadcast interactive method, apparatus and server | |
CN113806620B (en) | Content recommendation method, device, system and storage medium | |
CN111683174B (en) | Incoming call processing method, device and system | |
CN114296547A (en) | Method, device and storage medium for initiating active dialogue | |
CN109299240B (en) | Chat robot knowledge display method and device | |
CN106331389A (en) | Short message addressee determining method, short message addressee determining device, and server |
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 |