CN116319630A - Message reply method and device, electronic equipment and readable storage medium - Google Patents
Message reply method and device, electronic equipment and readable storage medium Download PDFInfo
- Publication number
- CN116319630A CN116319630A CN202310252732.9A CN202310252732A CN116319630A CN 116319630 A CN116319630 A CN 116319630A CN 202310252732 A CN202310252732 A CN 202310252732A CN 116319630 A CN116319630 A CN 116319630A
- Authority
- CN
- China
- Prior art keywords
- message
- information
- reply
- expression
- user
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 61
- 230000014509 gene expression Effects 0.000 claims abstract description 140
- 238000004891 communication Methods 0.000 claims description 20
- 238000004590 computer program Methods 0.000 claims description 8
- 230000000694 effects Effects 0.000 abstract description 5
- 239000000049 pigment Substances 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 230000009471 action Effects 0.000 description 4
- 238000003062 neural network model Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 230000004044 response Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 230000003993 interaction Effects 0.000 description 3
- 238000013507 mapping Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L51/00—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
- H04L51/02—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L12/00—Data switching networks
- H04L12/02—Details
- H04L12/16—Arrangements for providing special services to substations
- H04L12/18—Arrangements for providing special services to substations for broadcast or conference, e.g. multicast
- H04L12/1813—Arrangements for providing special services to substations for broadcast or conference, e.g. multicast for computer conferences, e.g. chat rooms
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L51/00—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
- H04L51/07—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail characterised by the inclusion of specific contents
- H04L51/10—Multimedia information
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Multimedia (AREA)
- General Engineering & Computer Science (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The embodiment of the invention provides a message reply method, a device, electronic equipment and a readable storage medium, wherein the method comprises the steps of reading a target session message from a message queue, wherein the message queue is used for storing session messages sent by a first user in a chat group, and the first user is a user except a chat service machine in the chat group; determining a reply message according to the target session message, wherein the reply message comprises at least one of first text information, first expression information, first audio information and first video information; and sending the reply message in the chat group corresponding to the target session message. The message reply method provided by the embodiment of the invention improves the reply effect of the message reply method.
Description
Technical Field
The present invention relates to the field of artificial intelligence technologies, and in particular, to a message reply method, a device, an electronic apparatus, and a readable storage medium.
Background
In operation scenes such as before sales and after sales, operators are required to respond to the information sent by the user, so that the response of the information of the user is ensured, and the user obtains better experience. However, as the requirement of the user on the response speed is higher and higher, more operators need to be invested, which has higher labor cost, resulting in higher operation cost of network chat.
At present, in order to reduce the operation cost of network chat, an intelligent robot is introduced to answer the message of a user, but the method can only acquire corresponding text answers from a fixed question-answer pair according to specific text appearing in the message of the user in a one-to-one interaction scene, and the replied content is only text, so that the user experience is relatively bad. That is, the message reply method in the prior art has poor reply effect.
Disclosure of Invention
The embodiment of the invention aims to provide a message reply method, a device, electronic equipment and a readable storage medium, which improve the reply effect of the message reply method. The specific technical scheme is as follows:
in a first aspect of the present invention, there is provided a message reply method applied to a chat service machine, including:
reading a target session message from a message queue, wherein the message queue is used for storing session messages sent by a first user in a chat group, and the first user is a user except for the chat service machine in the chat group;
determining a reply message according to the target session message, wherein the reply message comprises at least one of first text information, first expression information, first audio information and first video information;
And sending the reply message in the chat group corresponding to the target session message.
In a second aspect of the present invention, there is also provided a message reply device, including:
the system comprises an acquisition module, a message queue and a chat service machine, wherein the acquisition module is used for reading a target session message from the message queue, and the message queue is used for storing session messages sent by a first user in a chat group, wherein the first user is a user except the chat service machine in the chat group;
the determining module is used for determining a reply message according to the target session message, wherein the reply message comprises at least one of first text information, first expression information, first audio information and first video information;
and the sending module is used for sending the reply message in the chat group corresponding to the target session message.
In yet another aspect of the present invention, there is also provided an electronic device including a processor, a communication interface, a memory, and a communication bus, where the processor, the communication interface, and the memory complete communication with each other through the communication bus;
a memory for storing a computer program;
and the processor is used for executing any one of the message replying methods when executing the program stored in the memory.
In yet another aspect of the present invention, there is also provided a computer readable storage medium having instructions stored therein, which when run on a computer, cause the computer to perform any of the above-described message reply methods.
In the embodiment of the invention, the message queue is used for storing session messages sent by a first user in the chat group, and the first user is a user except for a chat service machine in the chat group. The target session message is read from the message queue by the chat service machine and a reply message including at least one of the first text information, the first expression information, the first audio information, and the first video information is sent in the chat group. The method can make the form of the reply message more vivid and diversified, and improves the experience of the user, thereby improving the reply effect of the message reply method.
Drawings
In order to more clearly illustrate the embodiments of the present invention 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.
FIG. 1 is a flowchart of a message reply method according to an embodiment of the present invention;
FIG. 2 is a second flowchart of a message reply method according to an embodiment of the present invention;
Fig. 3 is a schematic structural diagram of a message reply device according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
For a better understanding of the present invention, a brief description of the background knowledge related to the present invention will be provided below.
With the development of internet technology, more and more operators and users choose to communicate over a network. In practical applications, users often communicate with operators in chat groups, such as users communicating with operators in chat groups about pre-sale and after-sale problems of products; also, for example, users communicate with other users in a chat group about the product's usage experience.
At present, in the scenes of operations such as before sales, after sales and the like, operators are required to respond to the information sent by the user, so that the response of the information of the user is ensured, and the user obtains better experience. However, as the requirement of the user on the response speed is higher and higher, more operators need to be invested, which has higher labor cost, resulting in higher operation cost of network chat.
To solve this problem, the present invention provides a message reply method, and the applicable scenario of the method includes, but is not limited to, the scenario that operators and users are in network chat (such as chat group). The method provided by the invention uses the chat service machine to execute the reply work of operators, and uses the machine to replace the manual work, thereby reducing the labor cost and further reducing the operation cost of network chat, and is described in detail below.
The technical solutions in the embodiments of the present invention will be described below with reference to the accompanying drawings in the embodiments of the present invention.
Referring to fig. 1, fig. 1 is a flowchart of a message reply method according to an embodiment of the present invention, which is applied to a chat service machine, and includes the following steps:
in particular implementations, the specific form of the target session message is not limited herein, and in an alternative embodiment, the target session message includes at least one of second text information, second expression information, second audio information, and second video information.
The target session message may be all session messages in the message queue, and the chat service machine replies to all session messages; the target session message may also be a partial session message in a message queue, and the chat service machine replies only to the partial session message.
Each chat group has at least two first users, and the session message may be a chat message between the first users, such as a message exchanged between the first users regarding the product's use experience. The session message may also be a question message sent by the first user to the operator, such as a user asking the operator for a pre-sale question of the price, parameters, etc. of the product, or a user asking the operator for an after-sale question of the product, such as a return of the product.
In the case that the target session message is a part of the session messages in the message queue, the part of the session messages may be a question message sent by the first user to the operator in the message queue, and in this scenario one, the chat service machine replies only to the question message sent by the first user to the operator.
When the target session message is all session messages in the message queue, the chat service machine replies the questioning message and participates in the chat process between the first users, for example, when the use experience of the product is discussed between the first users, the chat service machine can make comments on the use experience of the product and timely publicize the product.
in particular, when the reply message is the first text message, the chat service machine determines the reply message according to the specific content of the target session message.
Under the condition that the reply message comprises at least one of first expression information, first audio information and first video information, the chat service machine firstly determines first text information corresponding to the reply message, and then determines the first expression information and/or the first audio information and/or the first video information according to the first text information. Specifically, the chat service machine determines first expression information according to the first text information and a mapping relation between the pre-stored text information and the expression information; the chat service machine determines first audio information according to the first text information and a mapping relation between the pre-stored text information and the audio information; the chat service machine determines the first video information according to the first text information and the mapping relation between the pre-stored text information and the video information.
In particular, only any one of the first text information, the first expression information, the first audio information and the first video information may be transmitted in the chat group; any of the first text information, the first expression information, the first audio information, and the first video information may also be transmitted in the chat group.
In one embodiment, the first text information and the first expression information are sent in a chat group. In the embodiment, the first text information is sent to clearly reply the question of the first user, and the chat service machine can reply more vividly by sending the first expression information, so that the experience of the user is improved.
It should be noted that the chat group corresponding to the target session message may be one or more. In particular, the chat group includes a plurality of chat groups, the target conversation message may include a plurality of conversation messages, each conversation message corresponds to one chat group, in the case that the target conversation message includes a plurality of conversation messages, each conversation message corresponds to a set of reply messages, the set of reply messages being replies to the one conversation message, and the set of reply messages may include one or more messages. When the target session message includes multiple session messages, a group of reply messages corresponding to each session message may be determined in sequence according to the sequence of the sending time of the session messages, and each group of reply messages in the multiple groups of reply messages may be sent in the corresponding chat group according to the sequence of the sending time of the session messages.
In the embodiment of the invention, the message queue is used for storing session messages sent by a first user in the chat group, and the first user is a user except for a chat service machine in the chat group. The target session message is read from the message queue by the chat service machine and a reply message including at least one of the first text information, the first expression information, the first audio information, and the first video information is sent in the chat group. The method can make the form of the reply message more vivid and diversified, and improves the experience of the user, thereby improving the reply effect of the message reply method.
In addition, in the embodiment of the application, by setting the message queue and storing the session message sent by the first user in the chat group, the chat robot can reply the messages of a plurality of users at the same time, and the method can be applied to one-to-many interaction scenes, so that the message reply method is not limited to be applied to one-to-one interaction scenes.
In an embodiment, before step 101, the method further comprises:
receiving the session message and storing the session message into the message queue under the condition that the chat service machine has receiving authority;
Or under the condition that the chat service machine does not have receiving authority, acquiring the session message through an application programming interface API, and storing the session message into the message queue.
In particular, in the case where the chat server has authority to receive session messages from the chat group, the session messages may be received from the chat group and all session messages received from the chat group may be stored in the message queue. In the first scenario, the chat service machine may also store only a portion of the session messages received from the chat group in the message queue, where the portion of the session messages are query messages sent from the first user in the message queue to the operator, as described above.
For example, in the case where the chat group is a chat group within a company, the chat server has authority to receive conversation messages from the chat group, and conversation messages within the chat group can be posted to a message queue through the chat service.
In the event that the chat service machine does not have receiving authority to receive conversation messages from the chat group, the chat service machine may obtain the conversation messages through the application programming interface API and store the conversation messages in the message queue. Similarly, in the first scenario, the chat service machine may store only a portion of the session messages received from the chat group in the message queue, where the portion of the session messages are query messages sent from the first user to the operator in the message queue, as described above.
For example, in the case where the chat group is a micro-community, a third party community, the chat service machine does not have the receiving authority to receive the session message from the chat group, but may use an API provided by the micro-community, the third party community to post the session message to the message queue.
After the session message is posted to the message queue, the chat service machine may listen to the message queue to obtain the target session message.
In this embodiment, by storing the session messages of the chat group in the message queue, the chat service machine can be facilitated to monitor the message queue, thereby obtaining the target session message.
At present, in order to reduce the operation cost of network chat, an intelligent robot is introduced to answer the message of the user, but the method can only obtain the corresponding answer from the fixed question-answer pair according to the specific text when the specific text appears in a one-to-one scene and the problem of the user, if the message of the user is text except the specific text or is in a form except the text form, the message of the user cannot be replied, that is, the reply success rate of the message reply method in the prior art is lower.
In order to improve the reply success rate of the message reply method, in an embodiment, the target session message includes at least one of the second expression information, the second audio information, and the second video information, and determining a reply message according to the target session message includes:
determining third text information corresponding to the target session message according to the target session message;
and determining the reply message according to the third text information.
When the method is specifically implemented, the chat service machine firstly determines third text information according to the specific content of the target session message, and then determines first expression information, and/or first audio information and/or first video information according to the third text information.
And under the condition that the target session message comprises the second expression information, the chat service machine acquires third text information consistent with the second expression information by understanding the expression. For example, in the case that the target session message includes the second expression information, characters displayed on the expression image in the second expression information may be recognized by a character recognition method, and the obtained characters are determined as the third character information; in case the target session message includes the second audio information, the second audio information may be converted into third Text information through Text To Speech (TTS); in the case that the target session message includes the second video information, the voice in the second video information may be converted into the third text information through TTS, or the subtitle in the second video information may be recognized through a text recognition method, and the acquired subtitle may be determined as the third text information.
After the third text information is obtained, the third text information with the semantics can be input into a pre-trained model to generate corresponding reply information, wherein the reply information can comprise character information or content information for indicating the expression meaning. For example, according to the third text information, corresponding reply information is generated through a relevant neural network model, the relevant neural network model is a pre-trained model, text information is input to the relevant neural network model, and the neural network model can output the reply information for replying the text information. For example, the third text information may be "how do today weather? ", its corresponding reply message includes character information: "sunny day".
When the reply information comprises character information, the chat service machine can determine the expression image displayed with the character information as first expression information from a database storing the expression image according to the character information in the reply information; alternatively, in the case where the reply information includes content information for indicating the meaning of the expression, the expression image corresponding to the content information in the reply information is read from a database storing the correspondence relationship between the content information and the expression image, and is determined as the first expression information.
In the case that the reply message includes character information, a voice corresponding to the character information may be determined as first audio information; alternatively, in the case where the reply message includes content information for indicating the meaning of the expression, a voice corresponding to the content information may be determined as the first audio information.
When the reply information includes character information, generating an expression image corresponding to the character information and voice corresponding to the character information, taking the expression image as an image frame, taking the character information as a subtitle, taking the voice corresponding to the character information as a video of background audio, and determining the video as first video information; alternatively, in the case where the reply message includes content information for indicating the meaning of the expression, the expression image corresponding to the content information and the voice corresponding to the content information may be generated as video with the expression image as an image frame, the content information as a subtitle, and the voice corresponding to the content information as a background audio, and determined as the first video information.
In this embodiment, by determining the third text information corresponding to the target session message according to the target session message and determining the reply message according to the third text information, the chat service machine can reply to the message of the user when the message of the user is in a form other than text, thereby improving the reply success rate of the message reply method.
In an optional embodiment, the target session message includes the second expression information, where the second expression information includes an expression image, and a specific manner of the chat service machine obtaining, by understanding the expression, third text information consistent with the second expression information may be:
identifying the expression image, and determining characters displayed in the expression image as the third text information;
or determining content information corresponding to the expression image obtained from a preset database as the third text information, wherein the content information is used for indicating expression meaning.
In the specific implementation, characters displayed in the expression image and coordinates corresponding to the characters can be obtained from the expression image in a character recognition OCR mode. Since the common writing manner is from left to right and from top to bottom, after the characters are acquired, the distance between the coordinates of each character and the origin (i.e. the upper left corner of the expression image) can be determined first, and the characters are arranged into a consistent sentence in the order from small to large, wherein the sentence is the third text information.
Or, a preset database stores a large number of expression images and content information corresponding to each expression image, wherein the content information can be characters displayed in the expression images or classification information capable of representing the meaning of the expression images.
In the case where the content information is a character displayed in the emoticon, the content information such as "evening" is determined as the third text information; in the case that the content information is classification information representing the meaning of the expression image, the classification information such as large-class information: "emotion class", subclass information: the subclass information in the "happy" is determined as the third text information.
In this embodiment, by recognizing the emoji image, the character displayed in the emoji image is determined as the third text information; or, the content information corresponding to the expression image is determined as the third text information, semantic analysis can be performed on the expression image, an analysis result (namely the third text information) is obtained, and the chat service machine can reply based on the analysis result, so that the function of replying of the chat service machine based on the second expression information in the target session message can be realized. In an embodiment, the determining the reply message according to the third text information includes:
deleting forbidden words in the third text information according to preset forbidden words, and obtaining fourth text information, wherein the forbidden words comprise a plurality of forbidden words;
And determining the reply message according to the fourth text information.
In particular implementations, the forbidden words include, but are not limited to, special characters that do not have practical significance, illegal words that do not comply with law, morals, and sensitive words that affect harmonious communications. The forbidden phrase may be determined according to legal regulations, moral customs, etc. The forbidden phrase can be stored in the storage medium of the chat service machine, so that the forbidden phrase can be directly read from the storage medium of the chat service machine when the forbidden phrase is needed, and the time consumption for acquiring the forbidden phrase is shortened.
And deleting the forbidden words in the third text information under the condition that the forbidden words appear in the third text information, obtaining fourth text information, and determining a reply message according to the fourth text information.
In this embodiment, by setting the forbidden word group to delete the forbidden word in the third text information, fourth text information without illegal sensitive information and without actual meaning information can be obtained, and the reply message is determined according to the fourth text information, so that the illegal sensitive information or the interference of the information without actual meaning can be avoided, thereby simplifying the process of determining the reply message and ensuring that the determined reply message is more reasonable.
In the first scenario, the target session message is a part of session messages in the message queue, where the part of session messages are query messages sent by the first user to the operator in the message queue, and the chat service machine replies to the query messages sent by the first user to the operator only. In a first scenario, to facilitate the chat service machine to more quickly distinguish a target session message from all session messages, in an embodiment, the target session message includes the second text information, and determining a reply message according to the target session message includes:
judging whether a preset trigger word exists in the second text information or not, wherein the trigger word is used for indicating that the chat service machine needs to reply to the second text information;
and under the condition that the trigger word exists in the second text information, determining the reply message according to the second text information.
In specific implementation, the trigger words are words set according to actual conditions, and the trigger words can be words or symbols. The chat service machine may store a trigger word library in advance, compare the second text information with a plurality of trigger words stored in the trigger word library one by one after the second text information is acquired, and if the trigger words in the trigger word library are the same as characters appearing in the second text information, determine that preset trigger words exist in the second text information. For example, in the first scenario, the trigger word is set to "ask" and if the second text information is "ask for the price of the product, it may be determined that the second text information" ask for the price of the product "needs to be replied according to the" ask for the price "in the second text information.
For another example, in scene one, the trigger word is set to "? "who is you? "in the case of" can be based on "? ", determine what is you needed to" who is? "this second text message is replied".
The trigger word is a contract for sending a session message to the first user in the chat group, and the first user is informed of the trigger word in advance, so that the first user can join the trigger word in the session message when the first user needs to reply by 'operators' (i.e. the chat service machine), and the chat service machine can conveniently and rapidly distinguish the target session message from all the session messages.
In this embodiment, by setting the trigger word, if the trigger word exists in the second text information, the reply message is determined according to the second text information. The chat service machine can be facilitated to more quickly distinguish the targeted session message from the overall session message, thereby improving reply efficiency.
In an embodiment, the reply message includes first expression information, and the determining the reply message according to the target session message includes:
determining expression preference information of a target user according to historical session information of the target user, wherein the target user is the user who sends the target session information, and the historical session information is all session information sent by the target user in the message queue;
And determining the first expression information according to the target session message and the expression preference information.
In particular, personal information (such as age, sex, hobbies, etc.) and/or common expression information of the target user can be determined according to all session messages sent by the target user in the message queue, and expression preference information of the target user can be determined according to the personal information and/or the common expression information of the target user. The expression preference information includes at least one of a pigment character, a pictogram, an illustration expression, a cartoon expression, an animal and plant expression, a text expression, and a true human expression.
The pigment characters refer to patterns describing the expression actions of the figures formed by arranging the combination sequence by using computer characters.
Pictographic (Emoji) is an image character.
The pictorial expression refers to an expression drawn in a cartoon form.
The cartoon expression refers to an expression made of a screenshot and a video of the animation work.
The animal and plant expression refers to the expression made by the pictures, video and characters of the animal and plant.
The text expression refers to an expression made of text screenshot.
The expression of the real person refers to the expression made of screenshot and video in film and television and synthetic works.
For example, if the personal information of the target user is that the age of the target user is 16 years, the expression preference information of the target user may be determined to be a cartoon expression. Under the condition that the expression preference information is a cartoon expression, the specific form of the first expression information is the cartoon expression.
If the common expression information of the target user indicates that the target user generally uses the pigment, the expression preference information of the target user can be determined to be the pigment. In the case that the expression preference information is a pigment, the specific form of the first expression information is a pigment.
In this embodiment, the target user is the user who sent the target session message, and the history session message is all session messages sent by the target user in the message queue. According to the historical conversation information of the target user, the expression preference information of the target user is determined, and the first expression information is determined according to the historical conversation information and the expression preference information, so that the first expression information sent by the chat service machine is the expression preferred by the target user, and the experience sense of the user is improved.
Referring to fig. 2, for easy understanding, the message reply method provided by the present invention is described in the following with a complete embodiment.
1. Delivering session messages sent by a first user in each chat group to a message queue, and acquiring target session messages through a monitoring message queue;
2. the conversation messages in the message queue can be classified according to expressions, audios and characters, and conversation messages of expression classes and audios are converted into characters;
3. The forbidden words in the text-form target session message are deleted (message filtering), the reply message can be determined through the expression boring service and the encyclopedia question-answering service based on the target session message, and for the expressions in the reply message, the user personalized ranking service can be performed according to the expression preference information of the user, and the expressions preferred by the user are selected for reply (user portrait personalized processing).
4. And packaging the reply message determined in the steps into a message body, and sending the reply message to the chat group corresponding to the target session message through the speaking service. The reply message is packaged into a message body, and can be encrypted to prevent others from falsifying, so that the safety of the message reply method is improved.
Referring to fig. 3, fig. 3 is a message reply device 200 provided in an embodiment of the present invention, including:
an obtaining module 201, configured to read a target session message from a message queue, where the message queue is configured to store session messages sent by a first user in a chat group, where the first user is a user in the chat group except for the chat service machine;
a determining module 202, configured to determine a reply message according to the target session message, where the reply message includes at least one of first text information, first expression information, first audio information, and first video information;
And a sending module 203, configured to send the reply message in the chat group corresponding to the target session message.
Optionally, before the obtaining module 201, the apparatus 200 further includes:
the first storage module is used for receiving the session message and storing the session message into the message queue under the condition that the chat service machine has receiving authority;
or the second storage module is used for acquiring the session message through an application programming interface API and storing the session message into the message queue under the condition that the chat service machine does not have receiving authority.
Optionally, the target session message includes at least one of second text information, second expression information, second audio information, and second video information.
Optionally, the target session message includes at least one of the second expression information, the second audio information, and the second video information, and the determining module 202 includes:
the first determining unit is used for determining third text information corresponding to the target session message according to the target session message;
and the second determining unit is used for determining the reply message according to the third text information.
Optionally, the target session message includes the second expression information, the second expression information includes an expression image, and the first determining unit includes:
the recognition subunit is used for recognizing the expression image and determining characters displayed in the expression image as the third text information;
or the obtaining subunit is configured to determine content information corresponding to the expression image obtained from a preset database as the third text information, where the content information is used to indicate expression meaning.
Optionally, the second determining unit includes:
the first determining subunit is configured to delete a forbidden word in the third text information according to a preset forbidden word group, and obtain fourth text information, where the forbidden word group includes a plurality of forbidden words;
and the second determining subunit is used for determining the reply message according to the fourth text information.
Optionally, the target session message includes the second text information, and the determining module 202 includes:
the judging unit is used for judging whether a preset trigger word exists in the second text information or not, and the trigger word is used for indicating the chat service machine to reply the second text information;
And the third determining unit is used for determining the reply message according to the second text information under the condition that the trigger word exists in the second text information.
Optionally, the reply message includes first expression information, and the determining module 202 includes:
a fourth determining unit, configured to determine expression preference information of a target user according to a historical session message of the target user, where the target user is a user who sends the target session message, and the historical session message is all session messages sent by the target user in the message queue;
and a fifth determining unit, configured to determine the first expression information according to the target session message and the expression preference information.
The message reply device 200 provided in the embodiment of the present invention can implement each process that can be implemented in the embodiment of the message reply method of the present invention, and achieve the same beneficial effects, and in order to avoid repetition, a detailed description is omitted here.
The embodiment of the present invention further provides an electronic device, as shown in fig. 4, including a processor 301, a communication interface 302, a memory 303, and a communication bus 304, where the processor 301, the communication interface 302, and the memory 303 perform communication with each other through the communication bus 304,
A memory 303 for storing a computer program;
the processor 301 is configured to execute the program stored in the memory 303, and implement the following steps:
reading a target session message from a message queue, wherein the message queue is used for storing session messages sent by a first user in a chat group, and the first user is a user except for the chat service machine in the chat group;
determining a reply message according to the target session message, wherein the reply message comprises at least one of first text information, first expression information, first audio information and first video information;
and sending the reply message in the chat group corresponding to the target session message.
Optionally, the processor 301 is configured to execute the program stored in the memory 303, and further implement the following steps:
receiving the session message and storing the session message into the message queue under the condition that the chat service machine has receiving authority;
or under the condition that the chat service machine does not have receiving authority, acquiring the session message through an application programming interface API, and storing the session message into the message queue.
Optionally, the target session message includes at least one of second text information, second expression information, second audio information, and second video information.
Optionally, the processor 301 is configured to execute the program stored in the memory 303, and further implement the following steps:
determining third text information corresponding to the target session message according to the target session message;
and determining the reply message according to the third text information.
Optionally, the processor 301 is configured to execute the program stored in the memory 303, and further implement the following steps:
identifying the expression image, and determining characters displayed in the expression image as the third text information;
or determining content information corresponding to the expression image obtained from a preset database as the third text information, wherein the content information is used for indicating expression meaning.
Optionally, the processor 301 is configured to execute the program stored in the memory 303, and further implement the following steps:
deleting forbidden words in the third text information according to preset forbidden words, and obtaining fourth text information, wherein the forbidden words comprise a plurality of forbidden words;
And determining the reply message according to the fourth text information.
Optionally, the processor 301 is configured to execute the program stored in the memory 303, and further implement the following steps:
judging whether a preset trigger word exists in the second text information or not, wherein the trigger word is used for indicating that the chat service machine needs to reply to the second text information;
and under the condition that the trigger word exists in the second text information, determining the reply message according to the second text information.
Optionally, the processor 301 is configured to execute the program stored in the memory 303, and further implement the following steps:
determining expression preference information of a target user according to historical session information of the target user, wherein the target user is the user who sends the target session information, and the historical session information is all session information sent by the target user in the message queue;
and determining the first expression information according to the target session message and the expression preference information.
The communication bus mentioned by the above electronic device may be a peripheral component interconnect standard (Peripheral Component Interconnect, abbreviated as PCI) bus or an extended industry standard architecture (Extended Industry Standard Architecture, abbreviated as EISA) bus, or the like. The communication bus may be classified as an address bus, a data bus, a control bus, or the like. For ease of illustration, the figures are shown with only one bold line, but not with only one bus or one type of bus.
The communication interface is used for communication between the terminal and other devices.
The memory may include random access memory (Random Access Memory, RAM) or non-volatile memory (non-volatile memory), such as at least one disk memory. Optionally, the memory may also be at least one memory device located remotely from the aforementioned processor.
The processor may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU for short), a network processor (Network Processor, NP for short), etc.; but also digital signal processors (Digital Signal Processing, DSP for short), application specific integrated circuits (Application Specific Integrated Circuit, ASIC for short), field-programmable gate arrays (Field-Programmable Gate Array, FPGA for short) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.
In yet another embodiment of the present invention, a computer readable storage medium is provided, in which instructions are stored, which when run on a computer, cause the computer to perform the message reply method according to any one of the above embodiments.
In yet another embodiment of the present invention, there is also provided a computer program product containing instructions that, when run on a computer, cause the computer to perform the message reply method of any of the above embodiments.
In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, produces a flow or function in accordance with embodiments of the present invention, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in or transmitted from one computer-readable storage medium to another, for example, by wired (e.g., coaxial cable, optical fiber, digital Subscriber Line (DSL)), or wireless (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains an integration of one or more available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid State Disk (SSD)), etc.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
In this specification, each embodiment is described in a related manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for system embodiments, since they are substantially similar to method embodiments, the description is relatively simple, as relevant to see a section of the description of method embodiments.
The foregoing description is only of the preferred embodiments of the present invention and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention are included in the protection scope of the present invention.
Claims (11)
1. A message reply method, applied to a chat service machine, comprising:
reading a target session message from a message queue, wherein the message queue is used for storing session messages sent by a first user in a chat group, and the first user is a user except for the chat service machine in the chat group;
determining a reply message according to the target session message, wherein the reply message comprises at least one of first text information, first expression information, first audio information and first video information;
and sending the reply message in the chat group corresponding to the target session message.
2. The message reply method of claim 1 wherein prior to reading the target session message from the message queue, the method further comprises:
receiving the session message and storing the session message into the message queue under the condition that the chat service machine has receiving authority;
Or under the condition that the chat service machine does not have receiving authority, acquiring the session message through an application programming interface API, and storing the session message into the message queue.
3. The message reply method of claim 1 wherein the target session message includes at least one of second text information, second expression information, second audio information, and second video information.
4. The message reply method of claim 3 wherein the target session message includes at least one of the second expression information, the second audio information, and the second video information, the determining a reply message from the target session message comprising:
determining third text information corresponding to the target session message according to the target session message;
and determining the reply message according to the third text information.
5. The message reply method according to claim 4, wherein the target session message includes the second expression information, the second expression information includes an expression image, and the determining, according to the target session message, third text information corresponding to the target session message includes:
Identifying the expression image, and determining characters displayed in the expression image as the third text information;
or determining content information corresponding to the expression image obtained from a preset database as the third text information, wherein the content information is used for indicating expression meaning.
6. The message reply method of claim 4 wherein the determining the reply message according to the third text message comprises:
deleting forbidden words in the third text information according to preset forbidden words, and obtaining fourth text information, wherein the forbidden words comprise a plurality of forbidden words;
and determining the reply message according to the fourth text information.
7. The message reply method of claim 3 wherein the target session message includes the second text message, and wherein determining a reply message from the target session message comprises:
judging whether a preset trigger word exists in the second text information or not, wherein the trigger word is used for indicating that the chat service machine needs to reply to the second text information;
and under the condition that the trigger word exists in the second text information, determining the reply message according to the second text information.
8. The message reply method according to claim 1, wherein the reply message includes first expression information, and the determining the reply message according to the target session message includes:
determining expression preference information of a target user according to historical session information of the target user, wherein the target user is the user who sends the target session information, and the historical session information is all session information sent by the target user in the message queue;
and determining the first expression information according to the target session message and the expression preference information.
9. A message reply device, comprising:
the system comprises an acquisition module, a message queue and a chat service machine, wherein the acquisition module is used for reading a target session message from the message queue, and the message queue is used for storing session messages sent by a first user in a chat group, wherein the first user is a user except the chat service machine in the chat group;
the determining module is used for determining a reply message according to the target session message, wherein the reply message comprises at least one of first text information, first expression information, first audio information and first video information;
and the sending module is used for sending the reply message in the chat group corresponding to the target session message.
10. An electronic device, characterized in that the electronic device comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are in communication with each other through the communication bus;
a memory for storing a computer program;
a processor for implementing the method steps of any one of claims 1-8 when executing a program stored on a memory.
11. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the method according to any of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310252732.9A CN116319630A (en) | 2023-03-07 | 2023-03-07 | Message reply method and device, electronic equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310252732.9A CN116319630A (en) | 2023-03-07 | 2023-03-07 | Message reply method and device, electronic equipment and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116319630A true CN116319630A (en) | 2023-06-23 |
Family
ID=86797416
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310252732.9A Pending CN116319630A (en) | 2023-03-07 | 2023-03-07 | Message reply method and device, electronic equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116319630A (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101282314A (en) * | 2008-05-23 | 2008-10-08 | 中国移动通信集团北京有限公司 | Group communication method, equipment and system for instant communication |
| WO2018066935A2 (en) * | 2016-10-05 | 2018-04-12 | 심용주 | Method and system for providing quiz together with advertisement in instant message service (ims) chat room |
| CN109639828A (en) * | 2019-01-15 | 2019-04-16 | 腾讯科技（深圳）有限公司 | Conversation message treating method and apparatus |
| CN109688049A (en) * | 2018-12-24 | 2019-04-26 | 联想(北京)有限公司 | Information processing method and electronic equipment |
| 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 |
| CN110457445A (en) * | 2018-05-03 | 2019-11-15 | 微软技术许可有限责任公司 | Answer generation technique based on user's portrait and Context Reasoning |
| CN110581772A (en) * | 2019-09-06 | 2019-12-17 | 腾讯科技（深圳）有限公司 | Instant messaging message interaction method and device and computer readable storage medium |
| CN112202661A (en) * | 2020-09-11 | 2021-01-08 | 腾讯科技（深圳）有限公司 | Session message processing method and device, computer equipment and storage medium |
| CN113192505A (en) * | 2021-04-30 | 2021-07-30 | 中国工商银行股份有限公司 | Session information generation method and device and service robot |
-
2023
- 2023-03-07 CN CN202310252732.9A patent/CN116319630A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101282314A (en) * | 2008-05-23 | 2008-10-08 | 中国移动通信集团北京有限公司 | Group communication method, equipment and system for instant communication |
| WO2018066935A2 (en) * | 2016-10-05 | 2018-04-12 | 심용주 | Method and system for providing quiz together with advertisement in instant message service (ims) chat room |
| 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 |
| CN110457445A (en) * | 2018-05-03 | 2019-11-15 | 微软技术许可有限责任公司 | Answer generation technique based on user's portrait and Context Reasoning |
| CN109688049A (en) * | 2018-12-24 | 2019-04-26 | 联想(北京)有限公司 | Information processing method and electronic equipment |
| CN109639828A (en) * | 2019-01-15 | 2019-04-16 | 腾讯科技（深圳）有限公司 | Conversation message treating method and apparatus |
| CN110581772A (en) * | 2019-09-06 | 2019-12-17 | 腾讯科技（深圳）有限公司 | Instant messaging message interaction method and device and computer readable storage medium |
| CN112202661A (en) * | 2020-09-11 | 2021-01-08 | 腾讯科技（深圳）有限公司 | Session message processing method and device, computer equipment and storage medium |
| CN113192505A (en) * | 2021-04-30 | 2021-07-30 | 中国工商银行股份有限公司 | Session information generation method and device and service robot |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10404629B2 (en) | Automatic reply method, device, apparatus, and storage medium | |
| US8589235B2 (en) | Method of answering questions by trusted participants | |
| CN103080927A (en) | Automatic routing using search results | |
| CN111565143B (en) | Instant messaging method, equipment and computer readable storage medium | |
| CN112291423B (en) | Communication call intelligent response processing method and device, electronic equipment and storage medium | |
| US20180365552A1 (en) | Cognitive communication assistant services | |
| Tagg et al. | Polymedia repertoires of networked individuals: a day-in-the-life approach | |
| CN110209768B (en) | Question processing method and device for automatic question answering | |
| CN111611365A (en) | Flow control method, device, equipment and storage medium of dialog system | |
| CN109275036B (en) | Message reminding method, device and equipment for teaching live broadcast | |
| CN111369275B (en) | Group identification and description method, coordination device and computer readable storage medium | |
| KR20190058257A (en) | Chatbot trainer platform and method of operating the same | |
| CN116319630A (en) | Message reply method and device, electronic equipment and readable storage medium | |
| WO2023284630A1 (en) | Emoticon image adding method and apparatus, and device and storage medium | |
| KR100627853B1 (en) | A method for converting sms message to multimedia message and sending the multimedia message and text-image converting server | |
| CN106878761B (en) | Living broadcast interactive method, apparatus and server | |
| CN114363277A (en) | Intelligent chatting method and device based on social relationship and related products | |
| CN110995940A (en) | Harassment visitor identification method and device, electronic equipment and medium | |
| WO2020124444A1 (en) | Information processing method and related apparatus | |
| US20180270172A1 (en) | Information processing device, information processing method, and non-transitory computer readable storage medium | |
| CN114244791B (en) | Data processing method, device and readable storage medium | |
| US11902223B2 (en) | Intelligent assistant content generation | |
| CN114529845A (en) | Call information processing method, terminal and server | |
| CN114328870A (en) | Reply message generation method, system and device | |
| Sharonova et al. | Comparative Analysis of Instant Messaging Protocols and Technologies for Effective Communication in Computer-Mediated Environment. |
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 |