CN113051405A - Dialog scene-based intelligent outbound knowledge graph construction method and device - Google Patents
Dialog scene-based intelligent outbound knowledge graph construction method and device Download PDFInfo
- Publication number
- CN113051405A CN113051405A CN202110214277.4A CN202110214277A CN113051405A CN 113051405 A CN113051405 A CN 113051405A CN 202110214277 A CN202110214277 A CN 202110214277A CN 113051405 A CN113051405 A CN 113051405A
- Authority
- CN
- China
- Prior art keywords
- conversation
- dialogue
- determining
- topic
- content
- 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
- 238000010276 construction Methods 0.000 title claims abstract description 17
- 238000000034 method Methods 0.000 claims abstract description 59
- 230000008569 process Effects 0.000 claims abstract description 21
- 238000012545 processing Methods 0.000 claims description 20
- 238000010586 diagram Methods 0.000 description 12
- 230000000694 effects Effects 0.000 description 11
- 230000005540 biological transmission Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000005034 decoration Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 2
- 239000010931 gold Substances 0.000 description 2
- 229910052737 gold Inorganic materials 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/42—Systems providing special services or facilities to subscribers
- H04M3/50—Centralised arrangements for answering calls; Centralised arrangements for recording messages for absent or busy subscribers ; Centralised arrangements for recording messages
- H04M3/51—Centralised call answering arrangements requiring operator intervention, e.g. call or contact centers for telemarketing
- H04M3/5166—Centralised call answering arrangements requiring operator intervention, e.g. call or contact centers for telemarketing in combination with interactive voice response systems or voice portals, e.g. as front-ends
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Animal Behavior & Ethology (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Signal Processing (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Machine Translation (AREA)
- Telephonic Communication Services (AREA)
Abstract
The application discloses a dialogue scene-based intelligent outbound knowledge graph construction method and device, wherein the method comprises the following steps: acquiring a script file related to an outbound process, wherein the script file comprises a plurality of conversation topics and a plurality of conversation contents corresponding to the plurality of conversation topics, and the plurality of conversation contents comprise conversation contents related to a calling party and conversation contents related to a called party; determining a connection relation among a plurality of conversation topics according to the script file; determining a plurality of dialog contents according to the script file; and constructing a knowledge graph related to the outbound flow according to the determined connection relation among the plurality of conversation topics and the plurality of conversation contents. The knowledge graph related to the outbound flow can be constructed according to the script file provided by the user. And further solves the technical problem that the prior art lacks a knowledge graph related to the outbound flow aiming at each outbound script file.
Description
Technical Field
The application relates to the field of knowledge graphs, in particular to an intelligent outbound knowledge graph construction method and device based on a conversation scene.
Background
In the call center, the outbound system is used for organizing a batch of subscriber numbers according to projects and carrying out Interactive Voice Response (IVR) according to a preset strategy, thereby achieving the purposes of market investigation, product marketing, customer return visit and care saving. The outbound system generally controls the business process executed by the outbound project by means of questionnaires, and one questionnaire comprises a plurality of functions of question and logic judgment and the like. The script file may be provided based on the user, and the voice corresponding to the contents of the dialog related to the caller in the script file may be generated and played to the user.
A knowledge graph (knowledgegraph) refers to a semantic network that takes entities and concepts as nodes and semantic relationships as edges. The knowledge graph enables knowledge to be acquired more directly, so that the knowledge graph can provide semantic associated knowledge for the outbound flow based on script files provided by users, and convenience, intelligence and humanization of outbound are achieved. However, the current Chinese knowledge graph still belongs to the construction stage and is a general knowledge graph. Therefore, we need to build a knowledge graph of the outbound flow domain for each script file.
Aiming at the technical problem that the prior art lacks a knowledge graph related to an outbound flow aiming at each outbound script file, an effective solution is not provided at present.
Disclosure of Invention
The embodiment of the disclosure provides a method and a device for constructing an intelligent outbound knowledge graph based on a conversation scene, so as to at least solve the technical problem that the knowledge graph related to an outbound flow is lacked for each outbound script file in the prior art.
According to an aspect of the disclosed embodiments, there is provided a method for constructing an intelligent outbound knowledge graph based on a conversation scene, including: acquiring a script file related to an outbound process, wherein the script file comprises a plurality of conversation topics and a plurality of conversation contents corresponding to the plurality of conversation topics, and the plurality of conversation contents comprise conversation contents related to a calling party and conversation contents related to a called party; determining a connection relation among a plurality of conversation topics according to the script file; determining a plurality of dialog contents according to the script file; establishing a knowledge graph related to the outbound flow according to the determined connection relation among the plurality of conversation topics and the plurality of conversation contents; and wherein the operation of determining a connection relationship between the plurality of conversation topics from the script file comprises: determining first dialogue content related to a calling party and a first dialogue theme corresponding to the first dialogue content; determining a category of a first dialogue topic according to a first keyword extracted from the first dialogue content; determining a category of second dialogue content related to the first dialogue topic according to the category of the first dialogue topic; and determining second dialogue content related to the first dialogue subject according to the category of the second dialogue content, thereby determining the second dialogue subject and determining the connection relation between the first dialogue subject and the second dialogue subject.
According to another aspect of the embodiments of the present disclosure, there is also provided a storage medium including a stored program, wherein the method of any one of the above is performed by a processor when the program is executed.
According to another aspect of the disclosed embodiments, there is also provided an intelligent outbound knowledge graph building apparatus based on conversation scenarios, including: the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring a script file related to an outbound process, the script file comprises a plurality of conversation themes and a plurality of conversation contents corresponding to the plurality of conversation themes, and the plurality of conversation contents comprise conversation contents related to a calling party and conversation contents related to a called party; the first determining module is used for determining the connection relation among a plurality of conversation topics according to the script file; the second determining module is used for determining a plurality of conversation contents according to the script file; the building module is used for building a knowledge graph related to the outbound flow according to the determined connection relation among the plurality of conversation topics and the plurality of conversation contents; and wherein the operation of determining a connection relationship between the plurality of conversation topics from the script file comprises: determining first dialogue content related to a calling party and a first dialogue theme corresponding to the first dialogue content; determining a category of a first dialogue topic according to a first keyword extracted from the first dialogue content; determining a category of second dialogue content related to the first dialogue topic according to the category of the first dialogue topic; and determining second dialogue content related to the first dialogue subject according to the category of the second dialogue content, thereby determining the second dialogue subject and determining the connection relation between the first dialogue subject and the second dialogue subject.
According to another aspect of the disclosed embodiments, there is also provided an intelligent outbound knowledge graph building apparatus based on conversation scenarios, including: a processor; and a memory coupled to the processor for providing instructions to the processor for processing the following processing steps: acquiring a script file related to an outbound process, wherein the script file comprises a plurality of conversation topics and a plurality of conversation contents corresponding to the plurality of conversation topics, and the plurality of conversation contents comprise conversation contents related to a calling party and conversation contents related to a called party; determining a connection relation among a plurality of conversation topics according to the script file; determining a plurality of dialog contents according to the script file; establishing a knowledge graph related to the outbound flow according to the determined connection relation among the plurality of conversation topics and the plurality of conversation contents; and wherein the operation of determining a connection relationship between the plurality of conversation topics from the script file comprises: determining first dialogue content related to a calling party and a first dialogue theme corresponding to the first dialogue content; determining a category of a first dialogue topic according to a first keyword extracted from the first dialogue content; determining a category of second dialogue content related to the first dialogue topic according to the category of the first dialogue topic; and determining second dialogue content related to the first dialogue subject according to the category of the second dialogue content, thereby determining the second dialogue subject and determining the connection relation between the first dialogue subject and the second dialogue subject.
In the embodiment of the disclosure, the server determines the connection relationship among the plurality of conversation topics and determines the plurality of conversation contents corresponding to the plurality of conversation topics according to the script file, so as to construct a knowledge graph related to the outbound flow according to the determined connection relationship among the plurality of conversation topics and the plurality of conversation contents. The knowledge graph related to the outbound flow can be constructed according to the script file provided by the user. And further solves the technical problem that the prior art lacks a knowledge graph related to the outbound flow aiming at each outbound script file.
Drawings
The accompanying drawings, which are included to provide a further understanding of the disclosure and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the disclosure and together with the description serve to explain the disclosure and not to limit the disclosure. In the drawings:
fig. 1 is a block diagram of a hardware structure of a computer terminal for implementing the method according to embodiment 1 of the present disclosure;
FIG. 2 is a schematic diagram of a system of an intelligent outbound knowledge graph construction method based on dialog scenarios according to embodiment 1 of the present disclosure;
fig. 3 is a flowchart of a dialog scenario-based intelligent outbound knowledge graph construction method according to the first aspect of embodiment 1 of the present disclosure;
fig. 4A is a schematic diagram of a connection relationship between a plurality of conversation topics according to the first aspect of embodiment 1 of the present disclosure;
FIG. 4B is a schematic diagram of a constructed knowledge-graph according to the first aspect of example 1 of the present disclosure;
FIG. 5 is yet another schematic diagram of a constructed knowledge-graph according to the first aspect of example 1 of the present disclosure;
FIG. 6 is yet another schematic diagram of a constructed knowledge-graph according to the first aspect of example 1 of the present disclosure;
fig. 7 is a schematic diagram of an intelligent outbound knowledge graph construction apparatus based on dialog scenarios according to embodiment 2 of the present disclosure; and
fig. 8 is a schematic diagram of an intelligent outbound knowledge graph building apparatus based on dialog scenarios according to embodiment 3 of the present disclosure.
Detailed Description
In order to make those skilled in the art better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the drawings in the embodiments of the present disclosure. It is to be understood that the described embodiments are merely exemplary of some, and not all, of the present disclosure. All other embodiments, which can be derived by a person skilled in the art from the embodiments disclosed herein without making any creative effort, shall fall within the protection scope of the present disclosure.
It should be noted that the terms "first," "second," and the like in the description and claims of the present disclosure and in the above-described drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the disclosure described herein are capable of operation in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Example 1
In accordance with the present embodiment, there is provided a method embodiment of an intelligent callout knowledge graph building method based on dialog scenarios, it is noted that the steps illustrated in the flowchart of the figure may be performed in a computer system, such as a set of computer-executable instructions, and that while a logical order is illustrated in the flowchart, in some cases the steps illustrated or described may be performed in an order different than here.
The method provided by the embodiment can be executed in a mobile terminal, a computer terminal or a similar operation device. Fig. 1 shows a hardware configuration block diagram of a computer terminal (or mobile device) for implementing an intelligent outbound knowledge graph construction method based on a dialog scenario. As shown in fig. 1, the computer terminal 10 (or mobile device 10) may include one or more (shown as 102a, 102b, … …, 102 n) processors 102 (the processors 102 may include, but are not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA, etc.), a memory 104 for storing data, and a transmission module 106 for communication functions. Besides, the method can also comprise the following steps: a display, an input/output interface (I/O interface), a Universal Serial Bus (USB) port (which may be included as one of the ports of the I/O interface), a network interface, a power source, and/or a camera. It will be understood by those skilled in the art that the structure shown in fig. 1 is only an illustration and is not intended to limit the structure of the electronic device. For example, the computer terminal 10 may also include more or fewer components than shown in FIG. 1, or have a different configuration than shown in FIG. 1.
It should be noted that the one or more processors 102 and/or other data processing circuitry described above may be referred to generally herein as "data processing circuitry". The data processing circuitry may be embodied in whole or in part in software, hardware, firmware, or any combination thereof. Further, the data processing circuit may be a single stand-alone processing module, or incorporated in whole or in part into any of the other elements in the computer terminal 10 (or mobile device). As referred to in the disclosed embodiments, the data processing circuit acts as a processor control (e.g., selection of a variable resistance termination path connected to the interface).
The memory 104 may be used to store software programs and modules of application software, such as program instructions/data storage devices corresponding to the intelligent call-out knowledge graph construction method based on dialog scenarios in the embodiment of the present disclosure, and the processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, implements the above-mentioned intelligent call-out knowledge graph construction method based on dialog scenarios of application programs. The memory 104 may include high speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include memory located remotely from the processor 102, which may be connected to the computer terminal 10 via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The transmission device 106 is used for receiving or transmitting data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider of the computer terminal 10. In one example, the transmission device 106 includes a Network adapter (NIC) that can be connected to other Network devices through a base station to communicate with the internet. In one example, the transmission device 106 can be a Radio Frequency (RF) module, which is used to communicate with the internet in a wireless manner.
The display may be, for example, a touch screen type Liquid Crystal Display (LCD) that may enable a user to interact with a user interface of the computer terminal 10 (or mobile device).
It should be noted here that in some alternative embodiments, the computer device (or mobile device) shown in fig. 1 described above may include hardware elements (including circuitry), software elements (including computer code stored on a computer-readable medium), or a combination of both hardware and software elements. It should be noted that fig. 1 is only one example of a particular specific example and is intended to illustrate the types of components that may be present in the computer device (or mobile device) described above.
Fig. 2 is a schematic diagram of a system of the intelligent outbound knowledge graph construction method based on dialog scenarios according to the embodiment. Referring to fig. 2, the system includes: a server 100 and a database 200. The database 200 may be configured in the server 100, or may be configured in another server. The server 100 may acquire the script file related to the outbound flow from the database 200, or may acquire the script file related to the outbound flow from the terminal of the user. And then constructing a knowledge graph related to the outbound flow based on the acquired script file. It should be noted that the server 100 in the system may be adapted to the above-described hardware configuration.
Under the above operating environment, according to the first aspect of the present embodiment, there is provided a method for constructing an intelligent outbound knowledge graph based on a dialog scenario, which is implemented by the server 100 shown in fig. 2. Fig. 3 shows a flow diagram of the method, which, with reference to fig. 3, comprises:
s302: acquiring a script file related to an outbound flow, wherein the script file comprises a plurality of conversation themes and a plurality of conversation contents corresponding to the plurality of conversation themes;
s304: determining a connection relation among a plurality of conversation topics according to the script file;
s306: determining a plurality of dialog contents according to the script file; and
s308: and constructing a knowledge graph related to the outbound flow according to the determined connection relation among the plurality of conversation topics and the plurality of conversation contents.
As described in the background, a knowledge graph (knowledgegraph) refers to a semantic network with entities and concepts as nodes and semantic relationships as edges. The knowledge graph enables knowledge to be acquired more directly, so that the knowledge graph can provide semantic associated knowledge for the outbound flow based on script files provided by users, and convenience, intelligence and humanization of outbound are achieved. However, the current Chinese knowledge graph still belongs to the construction stage and is a general knowledge graph. Therefore, we need to build a knowledge graph of the outbound flow domain for each script file.
In view of the technical problem of the prior art that the knowledge graph related to the outbound flow is lacking for each outbound script file, as shown in fig. 2, the server 100 provided in this embodiment first obtains the script file related to the outbound flow. Wherein the script file includes a plurality of conversation topics and a plurality of conversation contents corresponding to the plurality of conversation topics. Specifically, the server 100 may obtain the script file from the database 200, for example, but not limited to, or from a terminal of the user.
With respect to an example of a script file, referring to FIG. 4A, a script associated with an outbound flow according to an embodiment of the present disclosure is shown in FIG. 4A. And a plurality of dialog topics are included in the script. And in fig. 4 the different dialog topics are shown by means of dashed boxes.
It can be seen that in fig. 4A, the script basically describes the outbound flow associated with the gold card service.
Further, the server 100 determines a connection relationship between a plurality of conversation topics according to the script file. Specifically, referring to fig. 4A, for example: the first dialog title in the script file is ' inquire whether the called party is the owner of the caller ', the second dialog title is ' introduce the activity to the called party when the called party is the owner ' and ' the called party is not the owner ' to introduce the activity and request the called party to inform the caller of the content of the activity '. At this time, the server 100 may determine that the connection relationship between the first conversation topic and the two second conversation topics is an upstream-downstream relationship, and the connection relationship between the two second conversation topics is a parallel relationship. As shown with reference to the knowledge-graph shown in fig. 4B.
Further, the server 100 determines a plurality of dialog contents from the script file. Specifically, referring to fig. 4A, the first conversation contents corresponding to the first conversation topic are "caller: do you well, i am the person who is the king card in Tencent asking for your owner of the mobile phone with the tail number 6066? "; the second conversation contents corresponding to a second conversation topic are "called party: is the owner. Calling party: kay, it is such that the Wang card introduced a preference to charge 100 for 100 calls, ending at 12 am. Advising you to recharge as soon as possible. "; the second conversation contents corresponding to another second conversation topic are "called party: the owner is not. Calling party: kah-kah, a time-limited preferential activity of 100 charges, by 12 o' clock this night, trouble you report to the owner, ask him to participate as soon as possible, do you look good? ".
Further, the server 100 constructs a knowledge graph related to the outbound process according to the determined connection relationship among the plurality of conversation topics and the plurality of conversation contents. Thus, a knowledge graph as shown in fig. 4B is formed.
Thus, in the above manner, the server 100 determines the connection relationship between the plurality of conversation topics and determines the plurality of conversation contents corresponding to the plurality of conversation topics according to the script file, so as to construct a knowledge graph related to the outbound flow according to the determined connection relationship between the plurality of conversation topics and the plurality of conversation contents. The knowledge graph related to the outbound flow can be constructed according to the script file provided by the user. And further solves the technical problem that the prior art lacks a knowledge graph related to the outbound flow aiming at each outbound script file.
Optionally, the operation of determining a connection relationship between the plurality of conversation topics according to the script file includes: determining first dialogue content related to a calling party and a first dialogue theme corresponding to the first dialogue content; extracting a first keyword in the first dialogue content; determining second dialogue content corresponding to the first keyword and relevant to the called party according to the outbound flow; determining a second conversation topic corresponding to the second conversation content; and determining a connection relationship between the first dialogue topic and the second dialogue topic.
In particular, the plurality of dialog contents includes a dialog content associated with the calling party and a dialog content associated with the called party. And the operation of the server 100 determining the connection relationship between the plurality of conversation topics according to the script file includes: first, the server 100 determines first dialogue content related to a caller and a first dialogue topic corresponding to the first dialogue content according to the dialogue content related to the caller included in the script file. For example: referring to fig. 4A, the first dialog contents related to the caller are:
'do you, i are the workers of the oriental gold card, ask you the owner of the mobile phone with the tail number 6066'
It follows that the first topic of conversation, which is uttered by the caller, is mainly "ask if the owner is. The server 100 then extracts the first keyword in the first dialog content. For example: the first keywords extracted from the first dialog content by the server 100 are "mobile phone end number", "owner", and "do", thereby indicating that the called party is asked whether it is the owner.
Then, the server 100 determines second dialogue content related to the calling party corresponding to the first keyword according to the outbound flow in the script. For example, the server 100 may determine the corresponding second content by querying the script with keywords such as "owner", "is owner", or "owner" according to the first keyword "owner". Referring to fig. 4A, the second contents of the dialog related to the called party are "the owner is" or "the owner is not present".
The server 100 then determines a second conversation topic corresponding to the second conversation content. For example: a second dialogue topic corresponding to the second dialogue content is 'introduction of the activity to the called party when the called party is the owner'; and a second call title corresponding to another second call contents is 'introduce the present activity and request the called party to inform the owner of the present activity content in case the called party is absent'.
Finally, the server 100 finally determines that the connection relationship between the first dialogue topic and the two second dialogue topics is an upstream-downstream relationship through the above operations. And, the relationship between the two second conversation topics is a parallel relationship. Thus, in this way, the connection relationship between a plurality of conversation topics can be determined quickly and accurately, as shown in fig. 4B. Therefore, through the method, the server can determine the connection relation among all conversation topics according to the keywords in the conversation contents of the calling party and the called party in different conversation topics, and accordingly the corresponding knowledge graph can be determined more accurately according to the script.
Alternatively, the server 100 can determine a category of the first conversation topic based on the first keyword extracted from the first conversation content, then determine a category of the second conversation content related to the first conversation topic based on the category of the first conversation topic, and determine the second conversation content related to the first conversation topic based on the category of the second conversation content, thereby determining the second conversation topic and determining the connection relationship between the first conversation topic and the second conversation topic.
For example, the server 100 determines that the category of the first dialogue topic is "ask whether the owner is the owner" by using the existing semantic analysis model according to the first keywords "mobile phone end number", "owner", and "do" extracted from the first dialogue content of the first dialogue topic. The server 100 then determines that the category corresponding to the second dialogue content related to the first dialogue topic should be "confirm as to the owner or not" according to the category of the first dialogue topic. The server 100 then searches the script for second dialog content corresponding to the category. For example, the server 100 searches the script for the second dialogue content "is the owner" or "the owner is not present". Then, the server 100 determines a second conversation topic corresponding to the second conversation content according to the second conversation content, and further determines a connection relationship between the first conversation topic and the second conversation topic.
Therefore, the technical scheme of the embodiment can determine the connection relation between the conversation topics based on semantic analysis and classification modes, and can more accurately determine the connection relation between the conversation topics by utilizing a deep learning algorithm.
As for the specific semantic analysis and classification model, the existing NLP processing algorithm or other semantic analysis models can be used. Are not described in detail herein.
Optionally, the operation of constructing a knowledge graph related to the outbound procedure according to the determined connection relationship among the plurality of conversation topics and the plurality of conversation contents further includes: and retrieving contents related to the outbound flow from a preset database, and adding the contents to the knowledge graph, wherein the database is prestored with conversation contents related to a plurality of outbound flows.
Specifically, the operation of the server 100 constructing a knowledge graph related to the outbound flow according to the determined connection relationship among the conversation topics and the conversation contents further includes: the server 100 retrieves content related to the outbound flow from a pre-set database (e.g., database 200) and adds to the knowledge-graph. Wherein the database 200 is pre-stored with session contents associated with a plurality of outbound procedures. Thus, in this way, the constructed knowledge-graph can be further supplemented and refined.
Optionally, the operations of retrieving content related to the outbound flow from a preset database and adding the content to the knowledge graph include: retrieving a third conversation topic corresponding to the first keyword on the outbound flow from the database; and determining a connection relation between the first conversation topic and the third conversation topic, and adding the conversation content of the third conversation topic to the knowledge graph.
Specifically, the operations of the server 100 for retrieving the content related to the outbound flow from the preset database 200 and adding the content to the knowledge graph include: the server 100 first retrieves from the database 200 a third conversation topic corresponding to the first keyword on the outbound flow. For example: the first keyword is "do owner", thereby indicating that the called party is asked whether or not the called party is an owner. The server 100 then retrieves from the database 200 a third conversation topic corresponding to the first keyword, which is "introduce this activity to the called party if the called party is the owner but busy". The server 100 then determines that the connection relationship between the first conversation topic and the third conversation topic is an upstream-downstream relationship, and adds the conversation content of the third conversation topic to the knowledge-graph. Wherein figure 5 shows a schematic diagram after adding dialog content of a third dialog topic to the knowledge-graph. Therefore, by the method, other conversation topics related to the outbound flow and corresponding conversation contents can be retrieved from the preset database 200, and the retrieved conversation topics and the conversation contents are added to the constructed knowledge graph, so that the integrity of data in the knowledge graph is guaranteed.
Optionally, the operation of retrieving the content related to the outbound flow from a preset database and adding the content to the knowledge graph further includes: based on the first conversation content of the caller in the first conversation topic and the third conversation content of the caller in the second conversation topic, a fourth conversation topic subsequent to the second conversation topic is retrieved from the database and added to the knowledge-graph.
Specifically, the server 100 determines that the first content of the calling party in the first dialogue theme is "ask whether the owner is the owner" and determines that the third content of the calling party in the second dialogue theme is "introduce the service in a case where the owner is busy".
The server 100 then determines the subsequent topic content of the second topic from the database according to the first topic and the second topic connected with the first topic, so as to be added to the knowledge graph as the subsequent conversation topic of the second topic.
For example, the server 100 searches a plurality of knowledge-graphs in the database, thereby retrieving knowledge-graph contents according to the following connection relations: the first topic is a conversation topic in which "ask whether the owner is the owner" and the subsequent second topic is "introduce a service in the case where the owner is busy". The server 100 then determines from the database a subsequent conversation topic that is connected to the second conversation topic in the retrieved knowledge-graph content.
For example, the server 100 first searches the database 200 for a conversation topic entitled "ask whether or not the owner is the same", and determines it as the first conversation topic. The server 100 then searches the database 200 for a subsequent second conversation topic that is connected to the first conversation topic. Then, the server 100 further determines a conversation subject corresponding to the subject "introduction of service in case of busy owner" from among the subsequent second conversation subjects searched, thereby searching the database 200 for the second conversation subject corresponding to the subject.
Further, the server 100 queries, in the database 200, further according to the second topic of conversation, subsequent other topics corresponding to the second topic of conversation, for example, the server 100 further searches the database 200 for subsequent topics of conversation:
"called party: do not want to participate in
Calling party: a very sorry bothers you, this activity, today was the last day, advising you to attend as soon as they have time, otherwise you would not have such an advantage to charge next after the mistake. Do you look good? "
And
"called party: at busy/inconvenient/other
Calling party: the call is interrupted, the call is used for informing a user of an activity of charging 100 and sending 100, and the call can participate in the call today. Then I do not disturb you on the side, congratulate you for pleasure, see again! "
Then, the server 100 adds the queried follow-up topic to the knowledge-graph, thereby obtaining the knowledge-graph shown in fig. 6. Thus, in this way, the server 100 can further expand the script in the longitudinal direction and the depth direction of each score according to the knowledge graph generated by the existing script, thereby further ensuring the integrity of the data in the knowledge graph.
In addition, the server 100 may retrieve other keywords associated with the first keyword from the preset database 200. For example: the first keyword is "the owner himself", and the other keywords retrieved may be "i me", "right", "i me", "do nothing", and so on. Specifically, as shown with reference to fig. 6, the server 100 may add the retrieved other keywords to the first dialog content corresponding to the first keyword.
Optionally, the operation of constructing a knowledge graph related to the outbound process according to the determined connection relationship among the plurality of conversation topics and the plurality of conversation contents includes: and drawing a knowledge graph according to the determined connection relation among the plurality of conversation topics and the plurality of conversation contents based on a preset graph database. In this way, the constructed knowledge-graph may be graphically presented to the user. The experience effect of the user is greatly increased.
Optionally, the method further comprises: and updating the knowledge graph. By continuously updating the knowledge graph, the real-time performance and the integrity of data in the knowledge graph are guaranteed.
Optionally, the operation of updating the knowledge-graph includes: acquiring map data related to the knowledge map, wherein the map data is historical data generated in the application process of the knowledge map; and updating the knowledge graph according to the graph data. Specifically, the operation of the server 100 to update the knowledge graph includes: first, the server 100 acquires profile data related to a knowledge profile. Wherein the atlas data is historical data generated by the knowledge atlas in the application process. The server 100 then updates the knowledge-graph based on the acquired graph data. Therefore, by the method, the real-time performance and the integrity of the data in the knowledge graph are guaranteed, and the reliability of the updated data is also guaranteed.
Further, referring to fig. 1, according to a second aspect of the present embodiment, a storage medium 104 is provided. The storage medium 104 comprises a stored program, wherein the method of any of the above is performed by a processor when the program is run.
It should be noted that, for simplicity of description, the above-mentioned method embodiments are described as a series of acts or combination of acts, but those skilled in the art will recognize that the present invention is not limited by the order of acts, as some steps may occur in other orders or concurrently in accordance with the invention. Further, those skilled in the art should also appreciate that the embodiments described in the specification are preferred embodiments and that the acts and modules referred to are not necessarily required by the invention.
Through the above description of the embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but the former is a better implementation mode in many cases. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.
Example 2
Fig. 7 shows an intelligent callout knowledge-graph building apparatus 700 based on dialog scenarios according to the first aspect of the present embodiment, which apparatus 700 corresponds to the method according to the first aspect of embodiment 1. Referring to fig. 7, the apparatus 700 includes: an obtaining module 710, configured to obtain a script file related to an outbound flow, where the script file includes a plurality of conversation topics and a plurality of conversation contents corresponding to the plurality of conversation topics; a first determining module 720, configured to determine, according to the script file, a connection relationship between the plurality of dialog topics; a second determining module 730, configured to determine a plurality of session contents according to the script file; and a construction module 740, configured to construct a knowledge graph related to the outbound flow according to the determined connection relationship among the plurality of conversation topics and the plurality of conversation contents.
Optionally, the plurality of dialog contents includes a dialog content related to a calling party and a dialog content related to a called party, and the first determining module 720 includes: a first determining sub-module for determining first dialogue content related to a calling party and a first dialogue theme corresponding to the first dialogue content; the extraction sub-module is used for extracting a first keyword in the first dialogue content; the second determining submodule is used for determining second dialogue content which corresponds to the first keyword and is related to the called party according to the outbound flow; a third determining sub-module, configured to determine a second conversation topic corresponding to the second conversation content; and a fourth determining sub-module for determining a connection relationship between the first dialogue topic and the second dialogue topic.
Optionally, the first determining module 720 further includes: and the retrieval submodule is used for retrieving contents related to the outbound flow from a preset database and adding the contents to the knowledge graph, wherein the database is prestored with conversation contents related to a plurality of outbound flows.
Optionally, the retrieval submodule includes: the first retrieval unit is used for retrieving a third conversation topic corresponding to the first keyword in the outbound flow from the database; and the first determining unit is used for determining the connection relation between the first conversation topic and the third conversation topic and adding the conversation content of the third conversation topic to the knowledge graph.
Optionally, the retrieving sub-module further includes: a second determining unit, configured to determine third dialog content related to the calling party in the first dialog topic, and extract a second keyword from the third dialog content; the second retrieval unit is used for retrieving a third conversation theme corresponding to the first keyword in the outbound flow from a preset database according to the first keyword, the second keyword and the relation between the third conversation content and the first conversation content in the outbound flow, wherein the database is pre-stored with conversation contents related to a plurality of outbound flows; and a third determining unit, configured to determine a connection relationship between the first conversation topic and a third conversation topic, and add the conversation content of the third conversation topic to the knowledge graph.
Optionally, the building module 740 comprises: and the drawing submodule is used for drawing a knowledge graph according to the determined connection relation among the plurality of conversation topics and the plurality of conversation contents based on a preset graph database.
Optionally, the method further comprises: and the updating module is used for updating the knowledge graph.
Optionally, the update module includes: the acquisition submodule is used for acquiring map data related to the knowledge map, wherein the map data is historical data generated in the application process of the knowledge map; and the updating submodule is used for updating the knowledge graph according to the graph data.
Thus, according to the present embodiment, the apparatus 700 first determines a connection relationship between a plurality of conversation topics and determines a plurality of conversation contents corresponding to the plurality of conversation topics according to the script file, so as to construct a knowledge graph related to the outbound flow according to the determined connection relationship between the plurality of conversation topics and the plurality of conversation contents. The knowledge graph related to the outbound flow can be constructed according to the script file provided by the user. And further solves the technical problem that the prior art lacks a knowledge graph related to the outbound flow aiming at each outbound script file.
Example 3
Fig. 8 shows an intelligent callout knowledge-graph building apparatus 800 based on dialog scenarios according to the first aspect of the present embodiment, which apparatus 800 corresponds to the method according to the first aspect of embodiment 1. Referring to fig. 8, the apparatus 800 includes: a processor 810; and a memory 820 coupled to the processor 810 for providing instructions to the processor 810 to process the following process steps: acquiring a script file related to an outbound flow, wherein the script file comprises a plurality of conversation themes and a plurality of conversation contents corresponding to the plurality of conversation themes; determining a connection relation among a plurality of conversation topics according to the script file; determining a plurality of dialog contents according to the script file; and constructing a knowledge graph related to the outbound flow according to the determined connection relation among the plurality of conversation topics and the plurality of conversation contents.
Optionally, the operation of determining a connection relationship between the plurality of conversation topics according to the script file includes: determining first dialogue content related to a calling party and a first dialogue theme corresponding to the first dialogue content; extracting a first keyword in the first dialogue content; determining second dialogue content corresponding to the first keyword and relevant to the called party according to the outbound flow; determining a second conversation topic corresponding to the second conversation content; and determining a connection relationship between the first dialogue topic and the second dialogue topic.
Optionally, the operation of constructing a knowledge graph related to the outbound procedure according to the determined connection relationship among the plurality of conversation topics and the plurality of conversation contents further includes: and retrieving contents related to the outbound flow from a preset database, and adding the contents to the knowledge graph, wherein the database is prestored with conversation contents related to a plurality of outbound flows.
Optionally, the operations of retrieving content related to the outbound flow from a preset database and adding the content to the knowledge graph include: retrieving a third conversation topic corresponding to the first keyword on the outbound flow from the database; and determining a connection relation between the first conversation topic and the third conversation topic, and adding the conversation content of the third conversation topic to the knowledge graph.
Optionally, the operation of retrieving the content related to the outbound flow from a preset database and adding the content to the knowledge graph further includes: determining third conversation content related to the calling party in the first conversation topic, and extracting a second keyword from the third conversation content; searching a third conversation theme corresponding to the first keyword in the outbound flow from a preset database according to the first keyword, the second keyword and the relation between the third conversation content and the first conversation content in the outbound flow, wherein the database is prestored with conversation contents related to a plurality of outbound flows; and determining a connection relation between the first conversation topic and the third conversation topic, and adding the conversation content of the third conversation topic to the knowledge graph.
Optionally, the operation of constructing a knowledge graph related to the outbound process according to the determined connection relationship among the plurality of conversation topics and the plurality of conversation contents includes: and drawing a knowledge graph according to the determined connection relation among the plurality of conversation topics and the plurality of conversation contents based on a preset graph database.
Optionally, the memory 820 is further configured to provide the processor 810 with instructions for processing the following processing steps: and updating the knowledge graph.
Optionally, the operation of updating the knowledge-graph includes: acquiring map data related to the knowledge map, wherein the map data is historical data generated in the application process of the knowledge map; and updating the knowledge graph according to the graph data.
Thus, according to the present embodiment, the apparatus 800 determines the connection relationship between a plurality of conversation topics and determines a plurality of conversation contents corresponding to the plurality of conversation topics, according to the script file, so as to construct a knowledge graph related to the outbound flow according to the determined connection relationship between the plurality of conversation topics and the plurality of conversation contents. The knowledge graph related to the outbound flow can be constructed according to the script file provided by the user. And further solves the technical problem that the prior art lacks a knowledge graph related to the outbound flow aiming at each outbound script file.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
In the above embodiments of the present invention, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
In the embodiments provided in the present application, it should be understood that the disclosed technology can be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one type of division of logical functions, and there may be other divisions when actually implemented, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, units or modules, and may be in an electrical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic disk, or an optical disk, which can store program codes.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.
Claims (10)
1. A dialogue scene-based intelligent outbound knowledge graph construction method is characterized by comprising the following steps:
acquiring a script file related to an outbound process, wherein the script file comprises a plurality of conversation topics and a plurality of conversation contents corresponding to the plurality of conversation topics, and the plurality of conversation contents comprise conversation contents related to a calling party and conversation contents related to a called party;
determining a connection relation among the plurality of conversation topics according to the script file;
determining the plurality of dialog contents according to the script file; and
constructing a knowledge graph related to an outbound process according to the determined connection relation among the plurality of conversation topics and the plurality of conversation contents; and wherein
Determining a connection relationship between the plurality of conversation topics according to the script file, including:
determining first dialogue content related to a calling party and a first dialogue theme corresponding to the first dialogue content;
determining a category of a first dialogue topic according to a first keyword extracted from the first dialogue content;
determining a category of second dialogue content related to the first dialogue topic according to the category of the first dialogue topic; and
and determining second dialogue content related to the first dialogue topic according to the category of the second dialogue content, thereby determining the second dialogue topic, and determining the connection relation between the first dialogue topic and the second dialogue topic.
2. The method of claim 1, wherein the operation of determining a connection relationship between the plurality of conversation topics from the script file further comprises:
determining first dialogue content related to a calling party and a first dialogue theme corresponding to the first dialogue content;
extracting a first keyword in the first dialogue content;
determining second dialogue content corresponding to the first keyword and related to a called party according to the outbound flow;
determining a second conversation topic corresponding to the second conversation content; and
determining a connection relationship between the first conversation topic and the second conversation topic.
3. The method of claim 2, wherein the operation of constructing a knowledge graph related to the outbound flow according to the determined connection relationship between the conversation topics and the conversation contents further comprises:
and retrieving contents related to the outbound flow from a preset database, and adding the contents to the knowledge graph, wherein the database is prestored with conversation contents related to a plurality of outbound flows.
4. The method of claim 3,
the operation of retrieving the content related to the outbound procedure from a preset database and adding the content to the knowledge graph comprises the following steps: retrieving a third conversation topic corresponding to the first keyword on the outbound flow from the database; determining a connection relation between the first conversation topic and the third conversation topic, and adding the conversation content of the third conversation topic to the knowledge graph; or
The operation of retrieving the content related to the outbound procedure from the preset database and adding the content to the knowledge graph comprises the following steps: determining third conversation content related to the calling party in the first conversation topic, and extracting a second keyword from the third conversation content; searching a third conversation theme corresponding to the first keyword in the outbound flow from a preset database according to the first keyword, the second keyword and the relation between the third conversation content and the first conversation content in the outbound flow, wherein the database is prestored with conversation contents related to a plurality of outbound flows; and determining a connection relation between the first conversation topic and the third conversation topic, and adding the conversation content of the third conversation topic to the knowledge graph.
5. The method of claim 1, wherein the operation of constructing a knowledge graph related to the outbound flow according to the determined connection relationship between the conversation topics and the conversation contents comprises:
and drawing the knowledge graph according to the determined connection relation among the plurality of conversation topics and the plurality of conversation contents based on a preset graphic database.
6. The method of claim 1, further comprising: and updating the knowledge graph.
7. The method of claim 6, wherein the act of updating the knowledge-graph comprises:
acquiring map data related to the knowledge map, wherein the map data is historical data generated in the application process of the knowledge map; and
and updating the knowledge graph according to the graph data.
8. A storage medium comprising a stored program, wherein the method of any one of claims 1 to 7 is performed by a processor when the program is run.
9. An intelligent outbound knowledge graph construction device based on conversation scenes is characterized by comprising the following components:
the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring a script file related to an outbound process, the script file comprises a plurality of conversation themes and a plurality of conversation contents corresponding to the conversation themes, and the conversation contents comprise conversation contents related to a calling party and conversation contents related to a called party;
the first determining module is used for determining the connection relation among the plurality of conversation themes according to the script file;
the second determining module is used for determining the plurality of conversation contents according to the script file; and
the building module is used for building a knowledge graph related to the outbound flow according to the determined connection relation among the plurality of conversation topics and the plurality of conversation contents; and wherein
Determining a connection relationship between the plurality of conversation topics according to the script file, including:
determining first dialogue content related to a calling party and a first dialogue theme corresponding to the first dialogue content;
determining a category of a first dialogue topic according to a first keyword extracted from the first dialogue content;
determining a category of second dialogue content related to the first dialogue topic according to the category of the first dialogue topic; and
and determining second dialogue content related to the first dialogue topic according to the category of the second dialogue content, thereby determining the second dialogue topic, and determining the connection relation between the first dialogue topic and the second dialogue topic.
10. An intelligent outbound knowledge graph construction device based on conversation scenes is characterized by comprising the following components:
a processor; and
a memory coupled to the processor for providing instructions to the processor for processing the following processing steps:
acquiring a script file related to an outbound process, wherein the script file comprises a plurality of conversation topics and a plurality of conversation contents corresponding to the plurality of conversation topics, and the plurality of conversation contents comprise conversation contents related to a calling party and conversation contents related to a called party;
determining a connection relation among the plurality of conversation topics according to the script file;
determining the plurality of dialog contents according to the script file; and
constructing a knowledge graph related to an outbound process according to the determined connection relation among the plurality of conversation topics and the plurality of conversation contents; and wherein
Determining a connection relationship between the plurality of conversation topics according to the script file, including:
determining first dialogue content related to a calling party and a first dialogue theme corresponding to the first dialogue content;
determining a category of a first dialogue topic according to a first keyword extracted from the first dialogue content;
determining a category of second dialogue content related to the first dialogue topic according to the category of the first dialogue topic; and
and determining second dialogue content related to the first dialogue topic according to the category of the second dialogue content, thereby determining the second dialogue topic, and determining the connection relation between the first dialogue topic and the second dialogue topic.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110214277.4A CN113051405A (en) | 2019-04-30 | 2019-04-30 | Dialog scene-based intelligent outbound knowledge graph construction method and device |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110214277.4A CN113051405A (en) | 2019-04-30 | 2019-04-30 | Dialog scene-based intelligent outbound knowledge graph construction method and device |
| CN201910363800.2A CN110138986B (en) | 2019-04-30 | 2019-04-30 | Method, device and storage medium for constructing knowledge graph related to outbound process |
Related Parent Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910363800.2A Division CN110138986B (en) | 2019-04-30 | 2019-04-30 | Method, device and storage medium for constructing knowledge graph related to outbound process |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113051405A true CN113051405A (en) | 2021-06-29 |
Family
ID=67576164
Family Applications (3)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110215235.2A Active CN112911073B (en) | 2019-04-30 | 2019-04-30 | Intelligent knowledge graph construction method and device for outbound flow dialogue content |
| CN201910363800.2A Active CN110138986B (en) | 2019-04-30 | 2019-04-30 | Method, device and storage medium for constructing knowledge graph related to outbound process |
| CN202110214277.4A Pending CN113051405A (en) | 2019-04-30 | 2019-04-30 | Dialog scene-based intelligent outbound knowledge graph construction method and device |
Family Applications Before (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110215235.2A Active CN112911073B (en) | 2019-04-30 | 2019-04-30 | Intelligent knowledge graph construction method and device for outbound flow dialogue content |
| CN201910363800.2A Active CN110138986B (en) | 2019-04-30 | 2019-04-30 | Method, device and storage medium for constructing knowledge graph related to outbound process |
Country Status (1)
| Country | Link |
|---|---|
| CN (3) | CN112911073B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114708047A (en) * | 2022-06-06 | 2022-07-05 | 上海荣数信息技术有限公司 | Outbound strategy operation method and system based on knowledge graph |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110995945B (en) * | 2019-11-29 | 2021-05-25 | 中国银行股份有限公司 | Data processing method, device, equipment and system for generating outbound flow |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103795876A (en) * | 2012-10-29 | 2014-05-14 | 殷程 | Intelligent voice script |
| US20150142704A1 (en) * | 2013-11-20 | 2015-05-21 | Justin London | Adaptive Virtual Intelligent Agent |
| CN107247726A (en) * | 2017-04-28 | 2017-10-13 | 北京神州泰岳软件股份有限公司 | Suitable for the implementation method and device of the intelligent robot of multi-service scene |
| CN108509617A (en) * | 2018-04-04 | 2018-09-07 | 上海智臻智能网络科技股份有限公司 | Construction of knowledge base, intelligent answer method and device, storage medium, the terminal in knowledge based library |
| CN108810296A (en) * | 2018-04-28 | 2018-11-13 | 上海车音智能科技有限公司 | A kind of intelligence calling-out method and device |
| CN109672794A (en) * | 2018-12-04 | 2019-04-23 | 天津深思维科技有限公司 | A kind of outer paging system of intelligent sound |
Family Cites Families (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20140145018A (en) * | 2013-06-12 | 2014-12-22 | 한국전자통신연구원 | Knowledge index system and method thereof |
| US10509889B2 (en) * | 2014-11-06 | 2019-12-17 | ezDI, Inc. | Data processing system and method for computer-assisted coding of natural language medical text |
| CN105931638B (en) * | 2016-04-26 | 2019-12-24 | 北京光年无限科技有限公司 | Intelligent robot-oriented dialogue system data processing method and device |
| US10009466B2 (en) * | 2016-07-12 | 2018-06-26 | International Business Machines Corporation | System and method for a cognitive system plug-in answering subject matter expert questions |
| US10026092B2 (en) * | 2016-12-09 | 2018-07-17 | Nuance Communications, Inc. | Learning and automating agent actions |
| US10740373B2 (en) * | 2017-02-08 | 2020-08-11 | International Business Machines Corporation | Dialog mechanism responsive to query context |
| CN107135247B (en) * | 2017-02-16 | 2019-11-29 | 江苏南大电子信息技术股份有限公司 | A kind of service system and method for the intelligent coordinated work of person to person's work |
| US10044862B1 (en) * | 2017-04-28 | 2018-08-07 | International Business Machines Corporation | Dynamic topic guidance in the context of multi-round conversation |
| CN108132966A (en) * | 2017-11-28 | 2018-06-08 | 北京洪泰同创信息技术有限公司 | Knowledge mapping generation method and device |
| CN108170792B (en) * | 2017-12-27 | 2021-12-28 | 北京百度网讯科技有限公司 | Question and answer guiding method and device based on artificial intelligence and computer equipment |
| CN108491491B (en) * | 2018-03-14 | 2021-04-09 | 广州杰赛科技股份有限公司 | Method and system for constructing intelligent customer service knowledge graph |
| CN108932278B (en) * | 2018-04-28 | 2021-05-18 | 厦门快商通信息技术有限公司 | Man-machine conversation method and system based on semantic framework |
| CN109002434A (en) * | 2018-05-31 | 2018-12-14 | 青岛理工大学 | Customer service question and answer matching process, server and storage medium |
| CN109509002A (en) * | 2018-06-15 | 2019-03-22 | 中国建设银行股份有限公司 | Automatically configure the system and method for realizing conversation process, storage medium |
| CN109102809B (en) * | 2018-06-22 | 2021-06-15 | 北京光年无限科技有限公司 | Dialogue method and system for intelligent robot |
| CN109213854A (en) * | 2018-09-05 | 2019-01-15 | 平安科技（深圳）有限公司 | Knowledge mapping approaches to IM, device, computer equipment and storage medium |
| CN109145102B (en) * | 2018-09-06 | 2021-02-09 | 杭州安恒信息技术股份有限公司 | Intelligent question answering method and knowledge graph system construction method, device and equipment thereof |
| CN109145123B (en) * | 2018-09-30 | 2020-11-17 | 国信优易数据股份有限公司 | Knowledge graph model construction method, intelligent interaction method and system and electronic equipment |
| CN109446305A (en) * | 2018-10-10 | 2019-03-08 | 长沙师范学院 | The construction method and system of intelligent tour customer service system |
| CN109471947A (en) * | 2018-11-06 | 2019-03-15 | 北京锐安科技有限公司 | A kind of knowledge spectrogram construction method, device, equipment and the storage medium of data |
| CN109616108B (en) * | 2018-11-29 | 2022-05-31 | 出门问问创新科技有限公司 | Multi-turn dialogue interaction processing method and device, electronic equipment and storage medium |
| CN109614476A (en) * | 2018-12-11 | 2019-04-12 | 平安科技（深圳）有限公司 | Customer service system answering method, device, computer equipment and storage medium |
| CN110008326B (en) * | 2019-04-01 | 2020-11-03 | 苏州思必驰信息科技有限公司 | Knowledge abstract generation method and system in session system |
| CN112291423B (en) * | 2020-10-23 | 2023-09-26 | 腾讯科技（深圳）有限公司 | Communication call intelligent response processing method and device, electronic equipment and storage medium |
-
2019
- 2019-04-30 CN CN202110215235.2A patent/CN112911073B/en active Active
- 2019-04-30 CN CN201910363800.2A patent/CN110138986B/en active Active
- 2019-04-30 CN CN202110214277.4A patent/CN113051405A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103795876A (en) * | 2012-10-29 | 2014-05-14 | 殷程 | Intelligent voice script |
| US20150142704A1 (en) * | 2013-11-20 | 2015-05-21 | Justin London | Adaptive Virtual Intelligent Agent |
| CN107247726A (en) * | 2017-04-28 | 2017-10-13 | 北京神州泰岳软件股份有限公司 | Suitable for the implementation method and device of the intelligent robot of multi-service scene |
| CN108509617A (en) * | 2018-04-04 | 2018-09-07 | 上海智臻智能网络科技股份有限公司 | Construction of knowledge base, intelligent answer method and device, storage medium, the terminal in knowledge based library |
| CN108810296A (en) * | 2018-04-28 | 2018-11-13 | 上海车音智能科技有限公司 | A kind of intelligence calling-out method and device |
| CN109672794A (en) * | 2018-12-04 | 2019-04-23 | 天津深思维科技有限公司 | A kind of outer paging system of intelligent sound |
Non-Patent Citations (1)
| Title |
|---|
| 李亚梦: ""智能外呼系统研究及设计"", 《邮电设计技术》, no. 12, pages 77 - 82 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114708047A (en) * | 2022-06-06 | 2022-07-05 | 上海荣数信息技术有限公司 | Outbound strategy operation method and system based on knowledge graph |
| CN114708047B (en) * | 2022-06-06 | 2022-09-09 | 上海荣数信息技术有限公司 | Outbound strategy operation method and system based on knowledge graph |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112911073A (en) | 2021-06-04 |
| CN110138986A (en) | 2019-08-16 |
| CN112911073B (en) | 2023-04-25 |
| CN110138986B (en) | 2021-01-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102510551B (en) | Method and device for automatic recommendation of friends in mobile communication tool | |
| AU2012238229A1 (en) | Multi-modal customer care system | |
| CN112084315A (en) | Question-answer interaction method, device, storage medium and equipment | |
| CN110138986B (en) | Method, device and storage medium for constructing knowledge graph related to outbound process | |
| CN107450725B (en) | Man-machine interaction application platform, method and storage medium | |
| US20190196705A1 (en) | Mobile terminal and method for implementing custom applications using the same | |
| CN105373619A (en) | User big data based user group analysis method and system | |
| CN110704045A (en) | Method and device for constructing decision flow and storage medium | |
| CN113434844A (en) | Intelligent scene building method and device, storage medium and electronic equipment | |
| CN110175240A (en) | Construction method, device and the storage medium of knowledge mapping relevant to outgoing call process | |
| CN103078782A (en) | Friend note recommendation note implementation method and system | |
| CN113934299A (en) | Equipment interaction method and device, smart home equipment and processor | |
| CN110489519A (en) | The session method and Related product of dialogue-based prediction model | |
| CN105721289A (en) | Display method of function module in message communication accessory column | |
| CN110209904B (en) | Information classification method and device and storage medium | |
| CN111651989A (en) | Named entity recognition method and device, storage medium and electronic device | |
| CN105323391A (en) | Method and device for automatically broadcasting voice menu | |
| CN115270743A (en) | Form data processing method and device | |
| CN113392175A (en) | Method, apparatus and storage medium for predicting dialect combinations | |
| CN106125956A (en) | A kind of information-pushing method based on input method and system | |
| CN110276658A (en) | Processing method, device and the storage medium of information | |
| CN111897441A (en) | Expression adding method and device and electronic equipment | |
| CN113313507A (en) | Method, device and storage medium for improving marketing precision of telephone operation | |
| CN110351603B (en) | Method, device and storage medium for viewing reply video of concerned user | |
| CN112053273B (en) | Method and device for guiding case analysis and storage 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 |