CN109190114B - Method and device for generating reply information - Google Patents
Method and device for generating reply information Download PDFInfo
- Publication number
- CN109190114B CN109190114B CN201810917669.5A CN201810917669A CN109190114B CN 109190114 B CN109190114 B CN 109190114B CN 201810917669 A CN201810917669 A CN 201810917669A CN 109190114 B CN109190114 B CN 109190114B
- Authority
- CN
- China
- Prior art keywords
- information
- target
- reply information
- node
- reply
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Abstract
The embodiment of the application discloses a method and a device for generating reply information. One embodiment of the method comprises: receiving input information sent by a user through a terminal; performing semantic analysis on the input information to obtain a semantic analysis result of the input information, wherein the semantic analysis result comprises a target intention category and a confidence coefficient corresponding to the target intention category; matching the input information with question information of question-answer pair information in a question-answer pair information set established in advance to obtain a matching result, wherein the question-answer pair information comprises question information and answer information; determining a target reply information generation mode from at least one preset reply information generation mode based on the semantic analysis result and the matching result; and generating reply information according to the target reply information generation mode, and sending the reply information to the terminal. The embodiment enables the generated reply information to be more targeted.
Description
Technical Field
The embodiment of the application relates to the technical field of computers, in particular to a method and a device for generating reply information.
Background
With the development of human-computer interaction technology, the human-computer interaction technology based on language is also widely applied, for example, services can be provided for users through intelligent interaction robots such as intelligent online customer service robots and mobile phone assistants. Generally, after a user inputs information in a chat window, the intelligent interactive robot automatically gives related statements in the chat window according to a certain logic based on the input information of the user.
In practice, different reply logics need to be set for the intelligent interactive robot aiming at different service scenes so as to meet service requirements of users in different service scenes.
Disclosure of Invention
The embodiment of the application provides a method and a device for generating reply information.
In a first aspect, an embodiment of the present application provides a method for generating a reply message, where the method includes: receiving input information sent by a user through a terminal; performing semantic analysis on the input information to obtain a semantic analysis result of the input information, wherein the semantic analysis result comprises a target intention type and a confidence degree corresponding to the target intention type; matching the input information with question information of question-answer pair information in a question-answer pair information set established in advance to obtain a matching result, wherein the question-answer pair information comprises question information and answer information; determining a target reply information generation mode from at least one preset reply information generation mode based on the semantic analysis result and the matching result; and generating reply information according to the target reply information generation mode, and sending the reply information to the terminal.
In some embodiments, the at least one reply information generation manner includes: the directed graph comprises a root node, a judgment node, an action node and an extension node, wherein the root node corresponds to the intention category one to one, the judgment node is predefined with a judgment rule, the action node is predefined with a reply information generation rule, and the extension node is predefined with a rule of requesting data.
In some embodiments, when the target reply information is generated in a first manner, the generating a reply information according to the target reply information generation manner and sending the reply information to the terminal includes: determining a root node corresponding to the target intention category as a first target root node; and generating reply information according to the first target root node and the directed graph, and sending the reply information to the terminal.
In some embodiments, when the target reply information generation method is the second method, the generating reply information according to the target reply information generation method, and sending the reply information to the terminal includes: acquiring an intention type of a previous sentence of the input information sent by the terminal from a dialogue information set as a historical intention type, wherein the dialogue information set is used for recording information generated by interaction with the terminal; determining the root node corresponding to the historical intention category as a second target root node; and generating reply information according to the second target root node and the directed graph, and sending the reply information to the terminal.
In some embodiments, when the target reply information generation method is the third method, the generating reply information according to the target reply information generation method, and sending the reply information to the terminal includes: according to information recorded in a session information set, determining an action node corresponding to a previous statement of the input information sent by the terminal as a historical action node, and in response to determining that the historical action node has a next node, taking the next node of the historical action node as a target node, wherein the session information set is used for recording information generated by interaction with the terminal; and generating reply information according to the target node and the directed graph, and sending the reply information to the terminal.
In some embodiments, when the target reply information generation method is the fourth method, the generating a reply information according to the target reply information generation method, and sending the reply information to the terminal includes: and selecting target question-answer pair information from the question-answer pair information set according to the matching result, and sending answer information in the target question-answer pair information to the terminal as reply information.
In some embodiments, the determining, based on the semantic analysis result and the matching result, a target reply information generation manner from at least one preset reply information generation manner includes: and determining one of the first mode, the second mode, the third mode, the fourth mode and the fifth mode as a target reply information generation mode according to the confidence of the target intention type, the matching result and a preset scheduling rule.
In a second aspect, an embodiment of the present application provides an apparatus for generating a reply message, where the apparatus includes: a receiving unit configured to receive input information transmitted by a user through a terminal; an analysis unit configured to perform semantic analysis on the input information to obtain a semantic analysis result of the input information, wherein the semantic analysis result includes a target intention type and a confidence corresponding to the target intention type; the matching unit is configured to match the input information with question information of question-answer pair information in a question-answer pair information set established in advance to obtain a matching result, wherein the question-answer pair information comprises question information and answer information; a determining unit configured to determine a target reply information generation manner from at least one preset reply information generation manner based on the semantic analysis result and the matching result; and the generating unit is configured to generate reply information according to the target reply information generating mode and send the reply information to the terminal.
In some embodiments, the at least one reply information generation manner includes: the method comprises a first mode of generating reply information based on a root node corresponding to the target intention category and a directed graph, a second mode of generating reply information based on a root node corresponding to the history intention category and the directed graph, a third mode of generating reply information based on a history action node and the directed graph, a fourth mode of generating a reply information set based on the question-answer pair information set and a fifth mode of generating a preset information set, wherein the directed graph comprises the root node, a judgment node, an action node and an extension node, the root node corresponds to the intention category one by one, the judgment node is predefined with a judgment rule, the action node is predefined with a reply information generation rule, and the extension node is predefined with a rule of requesting data.
In some embodiments, when the target reply message is generated in a first manner, the generating unit is further configured to: determining a root node corresponding to the target intention category as a first target root node; and generating reply information according to the first target root node and the directed graph, and sending the reply information to the terminal.
In some embodiments, when the target reply information is generated in the second manner, the generating unit is further configured to: acquiring an intention type of a previous sentence of the input information sent by the terminal from a dialogue information set as a historical intention type, wherein the dialogue information set is used for recording information generated by interaction with the terminal; determining the root node corresponding to the historical intention category as a second target root node; and generating reply information according to the second target root node and the directed graph, and sending the reply information to the terminal.
In some embodiments, when the target reply information is generated in a third manner, the generating unit is further configured to: according to information recorded in a session information set, determining an action node corresponding to a previous statement of the input information sent by the terminal as a historical action node, and in response to determining that the historical action node has a next node, taking the next node of the historical action node as a target node, wherein the session information set is used for recording information generated by interaction with the terminal; and generating reply information according to the target node and the directed graph, and sending the reply information to the terminal.
In some embodiments, when the target reply message is generated in a fourth manner, the generating unit is further configured to: and selecting target question-answer pair information from the question-answer pair information set according to the matching result, and sending answer information in the target question-answer pair information to the terminal as reply information.
In some embodiments, the determining unit is further configured to: and determining one of the first mode, the second mode, the third mode, the fourth mode and the fifth mode as a target reply information generation mode according to the confidence of the target intention type, the matching result and a preset scheduling rule.
In a third aspect, an embodiment of the present application provides a server, where the server includes: one or more processors; a storage device, on which one or more programs are stored, which, when executed by the one or more processors, cause the one or more processors to implement the method as described in any implementation manner of the first aspect.
In a fourth aspect, the present application provides a computer-readable medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the method as described in any implementation manner of the first aspect.
According to the method and the device for generating the reply information, firstly, semantic analysis is carried out on input information sent by a terminal to obtain a semantic analysis result of the input information, then the input information is matched with question information of question-answer pair information in a question-answer pair information set established in advance to obtain a matching result, then a target reply information generation mode is determined from at least one reply information generation mode based on the semantic analysis result and the matching result, finally, the reply information is generated according to the target reply information generation mode and sent to the terminal, and selection of the target reply information generation mode based on the semantic analysis result and the matching result is achieved, so that the generated reply information is more targeted, and user requirements can be met.
Drawings
Other features, objects and advantages of the present application will become more apparent upon reading of the following detailed description of non-limiting embodiments thereof, made with reference to the accompanying drawings in which:
FIG. 1 is an exemplary system architecture diagram in which one embodiment of the present application may be applied;
FIG. 2 is a flow diagram for one embodiment of a method for generating a reply message in accordance with the present application;
FIG. 3 is an exemplary diagram of nodes and wires of a directed graph according to the present application;
FIG. 4 is an exemplary diagram of a scheduling rule according to the present application;
FIG. 5 is a schematic diagram of one application scenario of a method for generating a reply message according to the present application;
FIG. 6 is a block diagram illustrating an embodiment of an apparatus for generating a reply message according to the present application;
FIG. 7 is a block diagram of a computer system suitable for use in implementing a server according to embodiments of the present application.
Detailed Description
The present application will be described in further detail with reference to the following drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the relevant invention and not restrictive of the invention. It should be noted that, for convenience of description, only the portions related to the related invention are shown in the drawings.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
Fig. 1 illustrates an exemplary system architecture 100 to which a method for generating reply information or an apparatus for generating reply information of an embodiment of the present application may be applied.
As shown in fig. 1, the system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 serves as a medium for providing communication links between the terminal devices 101, 102, 103 and the server 105. Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.
The user may use the terminal devices 101, 102, 103 to interact with the server 105 via the network 104 to receive or send messages or the like. The terminal devices 101, 102, 103 may have various communication client applications installed thereon, such as a web browser application, a shopping application, a search application, an instant messaging tool, a mailbox client, social platform software, and the like.
The terminal apparatuses 101, 102, and 103 may be hardware or software. When the terminal devices 101, 102, 103 are hardware, they may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, e-book readers, laptop portable computers, desktop computers, and the like. When the terminal apparatuses 101, 102, 103 are software, they can be installed in the electronic apparatuses listed above. It may be implemented as multiple pieces of software or software modules (e.g., to provide distributed services) or as a single piece of software or software module. And is not particularly limited herein.
The server 105 may be a server that provides various services, such as a background server that provides support for reply information received by the terminal devices 101, 102, 103. The background server may perform semantic analysis on the input information sent by the terminal devices 101, 102, and 103, perform matching with question information in question-answer pair information, and generate reply information according to the processing result, and send the reply information to the terminal device.
The server may be hardware or software. When the server is hardware, it may be implemented as a distributed server cluster formed by multiple servers, or may be implemented as a single server. When the server is software, it may be implemented as multiple pieces of software or software modules (e.g., to provide distributed services), or as a single piece of software or software module. And is not particularly limited herein.
It should be understood that the number of terminal devices, networks, and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
It should be noted that the method for generating the reply information provided in the embodiment of the present application is generally performed by the server 105, and accordingly, the apparatus for generating the reply information is generally disposed in the server 105.
With continued reference to FIG. 2, a flow 200 of one embodiment of a method for generating a reply message in accordance with the present application is shown. The method for generating the reply message comprises the following steps:
In the present embodiment, the execution subject of the method for generating reply information (e.g., the server 105 shown in fig. 1) may receive input information from a terminal (e.g., the terminal devices 101, 102, 103 shown in fig. 1) with which the user inputs information, through a wired connection manner or a wireless connection manner. In practice, the input information may include, but is not limited to, text information, voice information, picture information, and the like. Under the condition that the input information comprises picture information, the execution main body can carry out semantic recognition on the picture to generate character information related to the picture; when the input information includes voice information, the execution body may perform voice recognition on the voice information to generate character information related to the voice information.
In this embodiment, the execution subject may analyze the input information obtained in step 201 by using various semantic analysis means (e.g., word segmentation, part-of-speech tagging, named entity recognition, etc.), so as to obtain a semantic analysis result of the input information. Here, the semantic analysis result may include a target intention category and a confidence degree corresponding to the target intention category. The target intention category may be a category indicating an intention of the user to transmit the input information. In practice, different intention categories may be preset according to different service scenarios, that is, one service scenario corresponds to one intention category, for example, when the execution subject is used to provide customer service for an operator, the intention category may be set as "telephone charge inquiry" for the service scenario, "telephone charge recharge" for the service scenario, and the like.
As an example, the execution subject may first perform word segmentation on the input information to obtain a target word segmentation set. Then, the target intention category and the confidence corresponding to the target intention category are obtained by a direct word list matching method, wherein the word list may be a correspondence list which is preset by a technician based on statistics of a large number of word sets and intention categories and stores the correspondence between a plurality of word sets and intention categories. In this way, the execution main body may sequentially match the target participle set with the plurality of participle sets in the correspondence table, obtain an intention category corresponding to the participle set most similar to the target participle set in the correspondence table as a target intention category according to a matching result, and determine a confidence corresponding to the target intention category according to a similarity between the participle set and the target participle set.
As another example, the execution subject may import the input information into a pre-established intention classification model, and obtain a target intention category corresponding to the input information and a confidence corresponding to the target intention category. The intention classification model can be used for representing the corresponding relation between input information and intention categories and the confidence degrees of the intention categories. The intention classification Model may be obtained based on a Machine learning method, and specifically, the intention classification Model may be obtained based on a Naive Bayesian Model (NBM) or a Support Vector Machine (SVM) or other Model training for classification.
In this embodiment, the execution main body may store a question-answer pair information set in advance, where each piece of question-answer pair information in the question-answer pair information set may include question information and answer information stored in association. In this way, the executing entity may match the input information received in step 201 with the question information of the question-answer pair information in the question-answer pair information set, and obtain a matching result (e.g., similarity).
And 204, determining a target reply information generation mode from at least one preset reply information generation mode based on the semantic analysis result and the matching result.
In this embodiment, the execution body may be preset with at least one reply information generation manner for generating the reply information. The execution body may determine a target reply information generation manner from the at least one reply information generation manner based on the semantic analysis result and the matching result. As an example, the execution main body may store a scheduling rule in advance, and the scheduling rule may be used to represent a correspondence relationship between the semantic analysis result, the matching result, and the reply information generation manner. In this way, after obtaining the semantic analysis result and the matching result, the execution main body can determine the target reply information generation mode by inquiring the scheduling rule.
In some optional implementation manners of this embodiment, the at least one reply information generation manner may include the following several manners:
1) and generating reply information based on the root node and the directed graph corresponding to the target intention category.
Here, the directed graph may be pre-stored in the execution subject, and the directed graph may include a root node, a judgment node, an action node, and an extension node.
The root nodes may have a one-to-one correspondence with the intent categories, i.e., one root node may serve as an entry node for one traffic scenario.
In practice, the judgment node may set a plurality of judgment branches, and each judgment branch may judge data such as an intention category, user input information, an entity extracted in an interaction process, and a result requested by the expansion node. As an example, the decision operator used in deciding a node may include, but is not limited to ═ |! Examples of such factors include, but are not limited to, >, is null, is not null, contacts (inclusive), regex (regular expression class), and the like. In addition, a combined judgment, such as AND OR, is also supported in the judgment node. In practice, the multiple decision branches of the decision node may include an else (other) decision branch, which is a branch when all the decision conditions are not satisfied.
Reply information generation rules can be predefined in the action nodes, and the action nodes are set as one of the following: waiting for user input, manual transfer, and session termination. For example, if a reply message generated by an action node is used to ask a question to the user, the action node is set to "wait for user input". For another example, if the reply message generated by an action node is used to prompt the user to transfer to manual service, the action node is set to "transfer to manual". For another example, if a reply message generated by an action node is used to prompt the user that the session is ended, the action node is set to "session terminated".
The rule for requesting data may be predefined in the extension node. The extension node may initiate an http request to an external server during the interaction process, and may use information (e.g., an intention category, an entity, etc.) generated during the interaction process as an http parameter, and a value returned by the http request may be used for the action node to generate reply information.
In the directed graph, a connection relationship may exist among the root node, the judgment node, the action node, and the extension node. Wherein the root node may comprise an exit point. The judging node may comprise an entry point and at least one exit point, wherein the number of exit points is the same as the number of judging branches set by the judging node. An action node may include an entry point and an exit point. An extension node may include an entry point and an exit point. Here, the exit point is a starting point of a connecting line, i.e., a starting point of a directed connecting line connecting from one node to the next node. An entry point is the end point of a connecting line, i.e. the point at which a directed connecting line from one node to the next is directed. The exit point can not be connected with the connecting line, the entry point can not be connected with the connecting line, the exit point can be connected with only one line, and the entry point can be connected with a plurality of lines. As an example, an example graph of nodes and connecting lines of a directed graph may be as shown in fig. 3, where fig. 3 includes root nodes 1, 2, decision nodes 1, 2, 3, action nodes 1, 2, 3, 4, 5 and extension node 1, where "∘" represents an entry point and "●" represents an exit point. It should be noted that the number of various nodes, the number of exit points in the judgment node, and the like in fig. 3 are merely illustrative, and are not limited to the number of various nodes, the number of exit points in the judgment node, and the like. In actual use, the setting can be performed according to the needs of the actual service scene.
2) And generating reply information based on the root node corresponding to the historical intention category and the directed graph. Here, if a sentence is transmitted before the user transmits the input information, the execution body may set an intention category corresponding to a last sentence transmitted before the user transmits the input information as a history intention category.
3) And generating reply information based on the historical action nodes and the directed graph. Here, if a sentence is transmitted before the user transmits the input information, the execution body may set an action node corresponding to a previous sentence transmitted between the user and the input information as a history action node, and the action node corresponding to the previous sentence may be an action node for generating reply information with respect to the previous sentence.
4) And a fourth mode of information collection based on the question and answer pairs.
5) And a fifth mode based on a preset information set. Here, the preset information set may be preset with words indicating that the user intention is not understood, for example, "sorry, did i not understand what you say? ".
In some alternative implementations, the step 204 may be specifically performed as follows: and determining one of the first mode, the second mode, the third mode, the fourth mode and the fifth mode as a target reply information generation mode according to the confidence of the target intention type, the matching result and a preset scheduling rule. Here, the scheduling rule may be set by a technician according to an actual service requirement, and is not limited herein.
Referring to fig. 4, as an example, one scheduling rule may be as follows:
step S1, determine whether the confidence of the target intent category is greater than a preset threshold and the target intent category has a corresponding root node.
Step S2, in response to determining that the confidence of the target intention category is greater than the preset threshold and that the target intention category has a corresponding root node, setting the reply information generation manner to the first manner.
In step S3, it is determined whether the user input is requested by the historical action node corresponding to the previous sentence input by the user before the input information is input.
In response to determining that the above-described historical action node requires user input, step S4 is performed.
In step S4, it is determined whether there is a subsequent node in the history action node.
In step S5, in response to determining that there is a subsequent node in the history action node, the reply information generation mode is set to mode three.
Step S6, in response to determining that the above-mentioned historical action node has no subsequent node and determining that the reply information generation manner is vacant, setting the reply information generation manner to manner two.
In response to determining that the above-described historical action node does not require user input and that the reply information generation manner is empty, step S7 is performed.
Step S7, determining whether there is matching question-answer pair information in the question-answer pair information set.
Step S8, in response to determining that there is matching question-answer information, sets the reply information generation manner to manner four.
In step S9, in response to determining that there is no matching question-answer information, the reply information generation manner is set to manner five.
In response to determining that the confidence of the target intention category is not greater than the preset threshold and/or the target intention category does not have a corresponding root node, step S10 is executed.
Step S10, it is determined whether the user input information is an initial dialog. If so, go to step S7; if not, step S3 is performed.
And step 205, generating the reply information according to the target reply information generation mode, and sending the reply information to the terminal.
In this embodiment, the executing entity may generate reply information according to the target reply information generation manner determined in step 204, and send the generated reply information to the terminal, so that the terminal presents the reply information to the user.
In some optional implementation manners, when the target reply message generation manner is a first manner, the step 205 may specifically include the following: first, the execution subject may determine a root node corresponding to the target intention category as a first target root node. Then, the executing body may generate reply information according to the first target root node and the directed graph, and send the reply information to the terminal for presentation by the terminal. As an example, the executing agent may start with the first target root node, and execute downward according to the connection relationship between the nodes in the directed graph until the reply information is generated.
In some optional implementation manners, when the target reply information generation manner is the second manner, the step 205 may specifically include the following contents: first, an intention type of a previous sentence of the input information transmitted by the terminal is acquired from a dialogue information set as a history intention type. Here, the dialog information set may be used to record information generated by interaction with the terminal. As an example, various information generated during a multi-turn dialog process between the terminal and the execution subject may be stored in the dialog information set, such as an extracted entity, an intention category of a previous sentence input by the user, an action node generating reply information for the previous sentence, and the like. In practice, when the terminal sends a piece of information to the executing agent, the executing agent will determine whether the information includes a session identifier (sessionID), if not, the executing agent will generate a session identifier for the information, and store various information generated in the session process and the session identifier in a session information set in an associated manner; if included, and the included session identifier is not expired, the dialog information set corresponding to the session identifier may be used directly, e.g., stored information, invoked information, etc. Next, the execution subject may determine a root node corresponding to the historical intent category as a second target root node. And finally, the execution main body can generate reply information according to the second target root node and the directed graph, and send the reply information to the terminal so that the terminal can present the reply information to a user.
In some optional implementation manners, when the target reply information generation manner is a third manner, the step 205 may specifically include the following contents: first, the execution body may determine, from information recorded in the dialog information set, an action node corresponding to a previous sentence of the input information transmitted by the terminal as a history action node, and may determine, in response to determining that the history action node has a next node, the next node of the history action node as a target node, where the action node corresponding to the previous sentence may be an action node that generates reply information for the previous sentence. The dialog information set may be used to record information resulting from interaction with the terminal. And finally, the execution main body can generate reply information according to the target node and the directed graph, and send the reply information to the terminal for the terminal to present. As an example, the executing agent may start with the target node, and execute downward according to the connection relationship between the nodes in the directed graph until the reply information is generated.
In some optional implementation manners, when the target reply information generation manner is a fourth manner, the step 205 may specifically include the following: the executing body may select target question-answer pair information from the question-answer pair information set according to the matching result, and may select question-answer pair information with the highest matching degree as the target question-answer pair information according to the matching result. And sending answer information in the target question-answer pair information as reply information to the terminal so that the terminal can present the reply information to the user.
In addition, when the target reply information generation manner is the fifth manner, the execution main body may select (e.g., randomly select) one piece of information from the preset information set as the reply information.
With continued reference to fig. 5, fig. 5 is a schematic diagram of an application scenario of the method for generating reply information according to the present embodiment. In the application scenario of fig. 5, the user sends input information "i want to inquire about the call charge" through the terminal device 501. Then, the server 502 may perform semantic analysis on the input information "i want to inquire the call charge" to obtain a semantic analysis result. The server 502 may also match the input information "i want to inquire the telephone charge" with question information of question-answer pair information in the question-answer pair information set, to obtain a matching result. Then, the server 502 may determine, based on the semantic analysis result and the matching result, the first mode as the target reply information generation mode from among preset 5 reply information generation modes "mode one, mode two, mode three, mode four, and mode five". Finally, reply information is generated according to the mode, and the reply information is sent to the terminal 501 for the terminal 501 to present to the user.
The method provided by the embodiment of the application realizes the selection of the target reply information generation mode based on the semantic analysis result and the matching result, so that the generated reply information is more targeted and can better meet the user requirements.
With further reference to fig. 6, as an implementation of the method shown in the above-mentioned figures, the present application provides an embodiment of an apparatus for generating reply information, where the embodiment of the apparatus corresponds to the embodiment of the method shown in fig. 2, and the apparatus may be applied to various electronic devices.
As shown in fig. 6, the apparatus 600 for generating reply information of the present embodiment includes: a receiving unit 601, an analyzing unit 602, a matching unit 603, a determining unit 604 and a generating unit 605. Wherein, the receiving unit 601 is configured to receive input information sent by a user through a terminal; the analysis unit 602 is configured to perform semantic analysis on the input information to obtain a semantic analysis result of the input information, where the semantic analysis result includes a target intention category and a confidence corresponding to the target intention category; the matching unit 603 is configured to match the input information with question information of question-answer pair information in a question-answer pair information set established in advance to obtain a matching result, wherein the question-answer pair information includes question information and answer information; the determining unit 604 is configured to determine a target reply information generation manner from at least one preset reply information generation manner based on the semantic analysis result and the matching result; the generating unit 605 is configured to generate a reply message according to the target reply message generation manner, and transmit the reply message to the terminal.
In this embodiment, specific processes of the receiving unit 601, the analyzing unit 602, the matching unit 603, the determining unit 604, and the generating unit 605 of the apparatus 600 for generating the reply message and technical effects thereof may refer to related descriptions of step 201, step 202, step 203, step 204, and step 205 in the corresponding embodiment of fig. 2, which are not described herein again.
In some optional implementation manners of this embodiment, the at least one reply information generation manner includes: the directed graph comprises a root node, a judgment node, an action node and an extension node, wherein the root node corresponds to the intention category one to one, the judgment node is predefined with a judgment rule, the action node is predefined with a reply information generation rule, and the extension node is predefined with a rule of requesting data.
In some optional implementations of this embodiment, when the target reply information is generated in a first manner, the generating unit 605 is further configured to: determining a root node corresponding to the target intention category as a first target root node; and generating reply information according to the first target root node and the directed graph, and sending the reply information to the terminal.
In some optional implementations of this embodiment, when the target reply information generation manner is a second manner, the generating unit 605 is further configured to: acquiring an intention type of a previous sentence of the input information sent by the terminal from a dialogue information set as a historical intention type, wherein the dialogue information set is used for recording information generated by interaction with the terminal; determining the root node corresponding to the historical intention category as a second target root node; and generating reply information according to the second target root node and the directed graph, and sending the reply information to the terminal.
In some optional implementations of this embodiment, when the target reply information generation manner is a third manner, the generating unit 605 is further configured to: according to information recorded in a session information set, determining an action node corresponding to a previous statement of the input information sent by the terminal as a historical action node, and in response to determining that the historical action node has a next node, taking the next node of the historical action node as a target node, wherein the session information set is used for recording information generated by interaction with the terminal; and generating reply information according to the target node and the directed graph, and sending the reply information to the terminal.
In some optional implementations of this embodiment, when the target reply information is generated in a fourth manner, the generating unit 605 is further configured to: and selecting target question-answer pair information from the question-answer pair information set according to the matching result, and sending answer information in the target question-answer pair information to the terminal as reply information.
In some optional implementations of the present embodiment, the determining unit 604 is further configured to: and determining one of the first mode, the second mode, the third mode, the fourth mode and the fifth mode as a target reply information generation mode according to the confidence of the target intention type, the matching result and a preset scheduling rule.
Referring now to FIG. 7, shown is a block diagram of a computer system 700 suitable for use in implementing a server according to embodiments of the present application. The server shown in fig. 7 is only an example, and should not bring any limitation to the function and the use range of the embodiment of the present application.
As shown in fig. 7, the computer system 700 includes a Central Processing Unit (CPU)701, which can perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM) 702 or a program loaded from a storage section 706 into a Random Access Memory (RAM) 703. In the RAM 703, various programs and data necessary for the operation of the system 700 are also stored. The CPU 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An Input/Output (I/O) interface 705 is also connected to the bus 704.
The following components are connected to the I/O interface 705: a storage portion 706 including a hard disk and the like; and a communication section 707 including a Network interface card such as a LAN (Local Area Network) card, a modem, or the like. The communication section 707 performs communication processing via a network such as the internet. A drive 708 is also connected to the I/O interface 705 as needed. A removable medium 709 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 708 as necessary, so that a computer program read out therefrom is mounted into the storage section 706 as necessary.
In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 707 and/or installed from the removable medium 709. The computer program, when executed by a Central Processing Unit (CPU)701, performs the above-described functions defined in the method of the present application.
It should be noted that the computer readable medium described herein can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this application, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In this application, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for aspects of the present application may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units described in the embodiments of the present application may be implemented by software or hardware. The described units may also be provided in a processor, which may be described as: a processor includes a receiving unit, an analyzing unit, a matching unit, a determining unit, and a generating unit. The names of these units do not constitute a limitation to the unit itself in some cases, and for example, the receiving unit may also be described as a "unit that receives input information transmitted by a user through a terminal".
As another aspect, the present application also provides a computer-readable medium, which may be contained in the apparatus described in the above embodiments; or may be present separately and not assembled into the device. The computer readable medium carries one or more programs which, when executed by the apparatus, cause the apparatus to: receiving input information sent by a user through a terminal; performing semantic analysis on the input information to obtain a semantic analysis result of the input information, wherein the semantic analysis result comprises a target intention type and a confidence degree corresponding to the target intention type; matching the input information with question information of question-answer pair information in a question-answer pair information set established in advance to obtain a matching result, wherein the question-answer pair information comprises question information and answer information; determining a target reply information generation mode from at least one preset reply information generation mode based on the semantic analysis result and the matching result; and generating reply information according to the target reply information generation mode, and sending the reply information to the terminal.
The above description is only a preferred embodiment of the application and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention herein disclosed is not limited to the particular combination of features described above, but also encompasses other arrangements in which any combination of the features described above or their equivalents does not depart from the spirit of the invention disclosed above. For example, the above features may be replaced with (but not limited to) features having similar functions disclosed in the present application.
Claims (14)
1. A method for generating a reply message, comprising:
receiving input information sent by a user through a terminal;
performing semantic analysis on the input information to obtain a semantic analysis result of the input information, wherein the semantic analysis result comprises a target intention category and a confidence degree corresponding to the target intention category;
matching the input information with question information of question-answer pair information in a question-answer pair information set established in advance to obtain a matching result, wherein the question-answer pair information comprises question information and answer information;
determining a target reply information generation mode from at least one preset reply information generation mode based on the semantic analysis result and the matching result, wherein the target reply information generation mode comprises the following steps: determining a target reply information generation mode from at least one preset reply information generation mode based on the semantic analysis result, the matching result and a preset scheduling rule;
wherein, the preset scheduling rule comprises: judging whether the confidence of the target intention type is greater than a preset threshold value or not and whether the target intention type has a corresponding root node or not; setting a reply information generation mode to be a mode one in response to the fact that the confidence degree of the target intention type is larger than a preset threshold value and the target intention type has a corresponding root node; determining whether the historical action node corresponding to the last sentence input by the user before inputting the input information requires the user to input; in response to determining that the historical action node requires user input, determining whether the historical action node has a subsequent node; setting a reply information generation mode to be a mode three in response to the fact that the historical action node is determined to have subsequent nodes; in response to the fact that the historical action node is determined to have no subsequent node and the reply information generation mode is determined to be vacant, setting the reply information generation mode to be a second mode; in response to determining that the historical action node does not require user input and determining that a reply information generation mode is vacant, determining whether the question-answer pair information set has matched question-answer pair information; responding to the question and answer information which is determined to be matched, and setting a reply information generation mode to be a mode four; responding to the question and answer information which is determined not to be matched, and setting a reply information generation mode to be a mode five;
and generating reply information according to the target reply information generation mode, and sending the reply information to the terminal.
2. The method of claim 1, wherein the at least one reply message generation comprises:
the method comprises a first mode of generating reply information based on a root node corresponding to the target intention category and a directed graph, a second mode of generating reply information based on a root node corresponding to the historical intention category and a directed graph, a third mode of generating reply information based on a historical action node and a directed graph, a fourth mode of generating a reply information set based on a question-answer pair information set and a fifth mode of generating a preset information set based on a preset information set, wherein the directed graph comprises the root node, a judgment node, an action node and an extension node, the root node corresponds to the intention category one by one, a judgment rule is predefined in the judgment node, a reply information generation rule is predefined in the action node, and a rule of requesting data is predefined in the extension node.
3. The method according to claim 2, wherein when the target reply information is generated in a first mode, the generating of the reply information according to the target reply information generation mode and the sending of the reply information to the terminal includes:
determining a root node corresponding to the target intention category as a first target root node;
and generating reply information according to the first target root node and the directed graph, and sending the reply information to the terminal.
4. The method according to claim 2, wherein when the target reply information generation mode is a second mode, the generating reply information according to the target reply information generation mode and sending the reply information to the terminal includes:
acquiring an intention category of a last statement of the input information sent by the terminal from a dialogue information set as a historical intention category, wherein the dialogue information set is used for recording information generated by interaction with the terminal;
determining a root node corresponding to the historical intention category as a second target root node;
and generating reply information according to the second target root node and the directed graph, and sending the reply information to the terminal.
5. The method according to claim 2, wherein when the target reply information generation manner is a third manner, the generating reply information according to the target reply information generation manner and sending the reply information to the terminal includes:
according to information recorded in a session information set, determining an action node corresponding to a previous statement of the input information and sent by the terminal as a historical action node, and in response to determining that the historical action node has a next node, taking the next node of the historical action node as a target node, wherein the session information set is used for recording information generated by interaction with the terminal;
and generating reply information according to the target node and the directed graph, and sending the reply information to the terminal.
6. The method according to claim 2, wherein when the target reply information is generated in a fourth manner, the generating reply information according to the target reply information generation manner and sending the reply information to the terminal includes:
and selecting target question-answer pair information from the question-answer pair information set according to the matching result, and sending answer information in the target question-answer pair information to the terminal as reply information.
7. An apparatus for generating reply information, comprising:
a receiving unit configured to receive input information transmitted by a user through a terminal;
the analysis unit is configured to perform semantic analysis on the input information to obtain a semantic analysis result of the input information, wherein the semantic analysis result comprises a target intention category and a confidence degree corresponding to the target intention category;
the matching unit is configured to match the input information with question information of question-answer pair information in a question-answer pair information set established in advance to obtain a matching result, wherein the question-answer pair information comprises question information and answer information;
a determining unit configured to determine a target reply information generation manner from at least one preset reply information generation manner based on the semantic analysis result and the matching result, and further configured to: determining a target reply information generation mode from at least one preset reply information generation mode based on the semantic analysis result, the matching result and a preset scheduling rule;
wherein, the preset scheduling rule comprises: judging whether the confidence of the target intention type is greater than a preset threshold value or not and whether the target intention type has a corresponding root node or not; setting a reply information generation mode to be a mode one in response to the fact that the confidence degree of the target intention type is larger than a preset threshold value and the target intention type has a corresponding root node; determining whether the historical action node corresponding to the last sentence input by the user before inputting the input information requires the user to input; in response to determining that the historical action node requires user input, determining whether the historical action node has a subsequent node; setting a reply information generation mode to be a mode three in response to the fact that the historical action node is determined to have subsequent nodes; in response to the fact that the historical action node is determined to have no subsequent node and the reply information generation mode is determined to be vacant, setting the reply information generation mode to be a second mode; in response to determining that the historical action node does not require user input and determining that a reply information generation mode is vacant, determining whether the question-answer pair information set has matched question-answer pair information; responding to the question and answer information which is determined to be matched, and setting a reply information generation mode to be a mode four; responding to the question and answer information which is determined not to be matched, and setting a reply information generation mode to be a mode five;
and the generating unit is configured to generate reply information according to the target reply information generating mode and send the reply information to the terminal.
8. The apparatus of claim 7, wherein the at least one reply message generation comprises:
the method comprises a first mode of generating reply information based on a root node corresponding to the target intention category and a directed graph, a second mode of generating reply information based on a root node corresponding to the historical intention category and a directed graph, a third mode of generating reply information based on a historical action node and a directed graph, a fourth mode of generating a reply information set based on a question-answer pair information set and a fifth mode of generating a preset information set based on a preset information set, wherein the directed graph comprises the root node, a judgment node, an action node and an extension node, the root node corresponds to the intention category one by one, a judgment rule is predefined in the judgment node, a reply information generation rule is predefined in the action node, and a rule of requesting data is predefined in the extension node.
9. The apparatus of claim 8, wherein when the target reply message is generated in a manner one, the generating unit is further configured to:
determining a root node corresponding to the target intention category as a first target root node;
and generating reply information according to the first target root node and the directed graph, and sending the reply information to the terminal.
10. The apparatus according to claim 8, wherein when the target reply message is generated in a second manner, the generating unit is further configured to:
acquiring an intention category of a last statement of the input information sent by the terminal from a dialogue information set as a historical intention category, wherein the dialogue information set is used for recording information generated by interaction with the terminal;
determining a root node corresponding to the historical intention category as a second target root node;
and generating reply information according to the second target root node and the directed graph, and sending the reply information to the terminal.
11. The apparatus of claim 8, wherein when the target reply message is generated in a manner three, the generating unit is further configured to:
according to information recorded in a session information set, determining an action node corresponding to a previous statement of the input information and sent by the terminal as a historical action node, and in response to determining that the historical action node has a next node, taking the next node of the historical action node as a target node, wherein the session information set is used for recording information generated by interaction with the terminal;
and generating reply information according to the target node and the directed graph, and sending the reply information to the terminal.
12. The apparatus according to claim 8, wherein when the target reply message is generated in a fourth manner, the generating unit is further configured to:
and selecting target question-answer pair information from the question-answer pair information set according to the matching result, and sending answer information in the target question-answer pair information to the terminal as reply information.
13. A server, comprising:
one or more processors;
a storage device having one or more programs stored thereon,
when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-6.
14. A computer-readable medium, on which a computer program is stored, wherein the program, when executed by a processor, implements the method of any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810917669.5A CN109190114B (en) | 2018-08-13 | 2018-08-13 | Method and device for generating reply information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810917669.5A CN109190114B (en) | 2018-08-13 | 2018-08-13 | Method and device for generating reply information |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109190114A CN109190114A (en) | 2019-01-11 |
| CN109190114B true CN109190114B (en) | 2022-06-07 |
Family
ID=64921658
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810917669.5A Active CN109190114B (en) | 2018-08-13 | 2018-08-13 | Method and device for generating reply information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109190114B (en) |
Families Citing this family (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109753561B (en) * | 2019-01-16 | 2021-04-27 | 长安汽车金融有限公司 | Automatic reply generation method and device |
| CN109948155B (en) * | 2019-03-12 | 2023-06-30 | 广东小天才科技有限公司 | Multi-intention selection method and device and terminal equipment |
| CN110008050B (en) * | 2019-04-11 | 2023-06-30 | 北京百度网讯科技有限公司 | Method and device for processing information |
| CN110008314B (en) * | 2019-04-12 | 2022-07-26 | 广东小天才科技有限公司 | Intention analysis method and device |
| CN111881266A (en) * | 2019-07-19 | 2020-11-03 | 马上消费金融股份有限公司 | Response method and device |
| CN110445707B (en) * | 2019-07-23 | 2022-05-13 | 北京秒针人工智能科技有限公司 | Message processing method and device |
| CN110532440A (en) * | 2019-08-21 | 2019-12-03 | 深圳追一科技有限公司 | Information processing method, device, equipment and storage medium |
| CN110929027B (en) * | 2019-09-30 | 2022-08-12 | 珠海格力电器股份有限公司 | Prompting system, prompting method, computer and waste accommodating device |
| CN113761138B (en) * | 2020-06-02 | 2024-02-02 | 阿里巴巴集团控股有限公司 | Dialogue system, dialogue method, dialogue device, electronic equipment and computer readable storage medium |
| CN113010654A (en) * | 2021-03-17 | 2021-06-22 | 北京十一贝科技有限公司 | Question reply method and device applied to insurance industry, electronic equipment and medium |
| CN117196035A (en) * | 2023-08-31 | 2023-12-08 | 摩尔线程智能科技(北京)有限责任公司 | Reply content processing method and device, electronic equipment and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105050103A (en) * | 2015-07-20 | 2015-11-11 | 大唐移动通信设备有限公司 | Signalling process identification method and signalling process identification device |
| CN105068661A (en) * | 2015-09-07 | 2015-11-18 | 百度在线网络技术（北京）有限公司 | Man-machine interaction method and system based on artificial intelligence |
| CN105094315A (en) * | 2015-06-25 | 2015-11-25 | 百度在线网络技术（北京）有限公司 | Method and apparatus for smart man-machine chat based on artificial intelligence |
| CN105589848A (en) * | 2015-12-28 | 2016-05-18 | 百度在线网络技术（北京）有限公司 | Dialog management method and device |
| CN105845137A (en) * | 2016-03-18 | 2016-08-10 | 中国科学院声学研究所 | Voice communication management system |
| CN106486120A (en) * | 2016-10-21 | 2017-03-08 | 上海智臻智能网络科技股份有限公司 | Interactive voice response method and answering system |
| WO2017041370A1 (en) * | 2015-09-07 | 2017-03-16 | 百度在线网络技术（北京）有限公司 | Human-computer chatting method and device based on artificial intelligence |
| CN108090177A (en) * | 2017-12-15 | 2018-05-29 | 上海智臻智能网络科技股份有限公司 | The generation methods of more wheel question answering systems, equipment, medium and take turns question answering system more |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9495331B2 (en) * | 2011-09-19 | 2016-11-15 | Personetics Technologies Ltd. | Advanced system and method for automated-context-aware-dialog with human users |
| US20180174055A1 (en) * | 2016-12-19 | 2018-06-21 | Giridhar S. Tirumale | Intelligent conversation system |
-
2018
- 2018-08-13 CN CN201810917669.5A patent/CN109190114B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105094315A (en) * | 2015-06-25 | 2015-11-25 | 百度在线网络技术（北京）有限公司 | Method and apparatus for smart man-machine chat based on artificial intelligence |
| CN105050103A (en) * | 2015-07-20 | 2015-11-11 | 大唐移动通信设备有限公司 | Signalling process identification method and signalling process identification device |
| CN105068661A (en) * | 2015-09-07 | 2015-11-18 | 百度在线网络技术（北京）有限公司 | Man-machine interaction method and system based on artificial intelligence |
| WO2017041370A1 (en) * | 2015-09-07 | 2017-03-16 | 百度在线网络技术（北京）有限公司 | Human-computer chatting method and device based on artificial intelligence |
| CN105589848A (en) * | 2015-12-28 | 2016-05-18 | 百度在线网络技术（北京）有限公司 | Dialog management method and device |
| CN105845137A (en) * | 2016-03-18 | 2016-08-10 | 中国科学院声学研究所 | Voice communication management system |
| CN106486120A (en) * | 2016-10-21 | 2017-03-08 | 上海智臻智能网络科技股份有限公司 | Interactive voice response method and answering system |
| CN108090177A (en) * | 2017-12-15 | 2018-05-29 | 上海智臻智能网络科技股份有限公司 | The generation methods of more wheel question answering systems, equipment, medium and take turns question answering system more |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109190114A (en) | 2019-01-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109190114B (en) | Method and device for generating reply information | |
| CN108229704B (en) | Method and device for pushing information | |
| WO2020215914A1 (en) | Information processing method, information processing device, and information processing system | |
| CN109117378B (en) | Method and apparatus for displaying information | |
| US11706172B2 (en) | Method and device for sending information | |
| CN109829164B (en) | Method and device for generating text | |
| CN116644145B (en) | Session data processing method, device, equipment and storage medium | |
| US20200328990A1 (en) | Intelligent Scheduler for Chatbot Sessions | |
| CN109522399B (en) | Method and apparatus for generating information | |
| CN107885872B (en) | Method and device for generating information | |
| CN113779346A (en) | Method and device for identifying one person with multiple accounts | |
| CN110223694B (en) | Voice processing method, system and device | |
| CN107622766B (en) | Method and apparatus for searching information | |
| CN113051381B (en) | Information quality inspection method, information quality inspection device, computer system and computer readable storage medium | |
| CN111131354B (en) | Method and apparatus for generating information | |
| CN112163078A (en) | Intelligent response method, device, server and storage medium | |
| CN111414566A (en) | Method and device for pushing information | |
| CN111782776A (en) | Method and device for realizing intention identification through slot filling | |
| CN111259697A (en) | Method and apparatus for transmitting information | |
| CN113656573B (en) | Text information generation method, device and terminal equipment | |
| CN115905490B (en) | Man-machine interaction dialogue method, device and equipment | |
| CN112860962B (en) | Method, device, electronic equipment and medium for processing questioning information | |
| CN112308166B (en) | Method and device for processing tag data | |
| KR102505259B1 (en) | Call center operating system based on cloud service | |
| CN113722449A (en) | Information processing method, device, electronic equipment and computer readable medium |
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 |