CN108509591B - Information question-answer interaction method and system, storage medium, terminal and intelligent knowledge base - Google Patents
Information question-answer interaction method and system, storage medium, terminal and intelligent knowledge base Download PDFInfo
- Publication number
- CN108509591B CN108509591B CN201810273945.9A CN201810273945A CN108509591B CN 108509591 B CN108509591 B CN 108509591B CN 201810273945 A CN201810273945 A CN 201810273945A CN 108509591 B CN108509591 B CN 108509591B
- Authority
- CN
- China
- Prior art keywords
- information
- information processing
- processing flow
- target
- user
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides an information question-answer interaction method and system, a storage medium, a terminal and an intelligent knowledge base. The method comprises the following steps: creating a plurality of information processing flows in advance; performing a first interaction with a user, comprising: acquiring first request information of a user; performing first matching processing on the plurality of information processing flows according to the first request information, and taking the matched information processing flows as target information processing flows; providing first reply information to a user according to a target information processing flow; and performing a second interaction with the user, comprising: acquiring second request information of the user; when the second request information is matched with the target information processing flow, second reply information is provided for the user according to the target information processing flow; and when the second request information is not matched with the target information processing flow but is matched with the associated information of the corresponding step, providing second reply information for the user according to the associated information. The invention shortens the processing time and has higher accuracy.
Description
Technical Field
The invention relates to the technical field of information processing, in particular to an information question-answer interaction method, an information question-answer interaction system, a storage medium, a terminal and an intelligent knowledge base.
Background
With the development of information technology, in a customer service system, a knowledge base system for solving the problem of customer visiting gradually turns from passive business content retrieval to an automatic and collaborative business support system which is more active and more suitable for the business service process. According to the manual participation degree of interactive question answering, the information question answering interactive technology can be divided into two types of manual customer service question answering interaction and automatic question answering interaction.
Currently, for service support of manual customer service question and answer interaction (such as seat customer service, online customer service and the like), a knowledge base in a document type file storage and retrieval form is mainly used as a support tool, and a knowledge content base based on a common question type knowledge form and a question and answer knowledge form is partially mixed and used as a content support tool of the customer service.
Taking the example of manual customer service question-answer interaction, the existing information question-answer interaction method comprises the following steps:
step 1, a plurality of information processing flows are created in advance, each information processing flow comprises a plurality of step nodes, and each step node corresponds to a target, a flow step description, a reference operation and an operation description. And storing each flow chart in a directory mode according to the function. The current knowledge content is built into a single 'document storage type knowledge' and 'question-answer dialogue type knowledge'.
And 2, the client personnel acquires the request information of the user.
And 3, selecting a service flow chart corresponding to the request information of the user by the customer service staff according to experience, and displaying the service flow chart and the information corresponding to each step node in an excel table form.
And 4, the customer service personnel interacts with the user according to the displayed information and responds correspondingly according to the prompt of the reference speech.
And 5, when the user's question is not included in the information processing flow, the customer service staff needs to re-open another information processing flow according to experience and repeat the steps.
However, the above technique has the following problems:
firstly, all the client problems are solved by uniform service content, common questions and answers and customer service skills. The technology can solve most of the same and standardized customer problems, but the user problems of common problems are more in different problem scenes and backgrounds, customer service personnel are still required to perform self-service aiming at specific service scenes, and the service efficiency and the service quality are difficult to manage and control.
Second, the solidified content cannot be flexibly and intelligently supported for service. The single service problem point can not effectively support the client problem of the deep and complex scene. Meanwhile, the problems are difficult to process in a robot question-answering mode, and the problems still need to be solved by means of business understanding of customer service staff.
Thirdly, selecting the correct service flow chart from the massive service flow charts needs to be according to experience of customer service staff, that is, time for the customer service staff with more experience to find the correct service flow chart is short, while time for the customer service staff with less experience to find the correct service flow chart is long, even no way to find the correct service flow chart is available, so that different user experience effects are greatly different, average reply time is long, and reply accuracy is low.
Fourthly, the service data of the user needs to be queried by a customer service person logging in the service data platform in real time, so that the reply time is prolonged.
Fifthly, when the user requirements are processed, no recommendation and association are made, and customer service personnel are required to manually select and switch among different service flow charts, so that the response time is further prolonged, and the response accuracy is reduced.
Disclosure of Invention
The invention aims to provide a more intelligent information question-answer interaction method and system, a storage medium, a terminal and an intelligent knowledge base.
In order to solve the above problem, an embodiment of the present invention provides an information question-answer interaction method, including:
the method comprises the steps of creating a plurality of information processing flows in advance, wherein each information processing flow comprises a plurality of steps, at least part of the steps comprise associated information, and the associated information comprises associated knowledge points and/or associated information processing flows;
performing a first interaction with a user, comprising: acquiring first request information of a user; performing first matching processing on the plurality of information processing flows according to the first request information, and taking the matched information processing flow as a target information processing flow; providing first reply information to a user according to the target information processing flow;
and performing a second interaction with the user, comprising: acquiring second request information of the user; when the second request information is matched with the target information processing flow, second reply information is provided for a user according to the target information processing flow; and when the second request information is not matched with the target information processing flow but is matched with the associated information of the corresponding step, providing second reply information for the user according to the associated information.
Optionally, the method further comprises: when the second request information is not matched with the target information processing flow and is not matched with the associated information of the corresponding step, performing second matching processing on the plurality of information processing flows according to the second request information, and taking the matched information processing flow as a new target information processing flow; and providing second reply information to the user according to the new target information processing flow.
Optionally, each information processing flow corresponds to a topic knowledge point, the topic knowledge point includes a topic question and a topic answer, and the topic answer is used for establishing a connection between the topic knowledge point and the corresponding information processing flow; the matching process includes:
calculating semantic similarity between the request information and each topic question;
and when the calculated highest semantic similarity is larger than a preset threshold value, taking the topic knowledge point corresponding to the highest semantic similarity as a target topic knowledge point, and taking an information processing flow corresponding to the target topic knowledge point as a target information processing flow through the topic answer of the target topic knowledge point.
Optionally, the association information is obtained by training and learning the generated interaction data.
Optionally, the request information is voice information, and the method further includes: converting the voice information into text information before the matching process is performed.
Optionally, the method is used for manual customer service question-answer interaction, and the reply information is responded correspondingly by a manual customer service reference speech prompt.
Optionally, at least part of the steps are associated with one or more service data platforms, so as to actively acquire service data information related to the steps according to user information.
In order to solve the above technical problem, an embodiment of the present invention further provides an information question-answer interaction system, including:
the storage module is used for storing a plurality of pre-created information processing flows and associated information, each information processing flow comprises a plurality of steps, at least part of the steps comprise associated information, and the associated information comprises associated knowledge points and/or associated information processing flows;
the first interaction module is used for carrying out first interaction with a user and comprises: the first input unit is used for acquiring first request information of a user; a first matching unit, configured to perform first matching processing on the multiple information processing flows according to the first request information, and use a matched information processing flow as a target information processing flow; the first output unit is used for providing first reply information for a user according to the target information processing flow;
the second interaction module is used for carrying out second interaction with the user and comprises: the second input unit is used for acquiring second request information of the user; the second matching unit is used for judging whether the second request information is matched with the target information processing flow or not and further judging whether the second request information is matched with the associated information of the corresponding step or not when the second request information is not matched with the target information processing flow; and the second output unit is used for providing second reply information to the user according to the target information processing flow when the second request information is matched with the target information processing flow, and providing second reply information to the user according to the associated information when the second request information is not matched with the target information processing flow but is matched with the associated information of the corresponding step.
Optionally, when the second request information does not match the target information processing flow and does not match the associated information of the corresponding step, the second matching unit is further configured to perform second matching processing on the plurality of information processing flows according to the second request information, and use the matched information processing flow as a new target information processing flow; and the second output unit provides second reply information to the user according to the new target information processing flow.
Optionally, each information processing flow corresponds to a topic knowledge point, the topic knowledge point includes a topic question and a topic answer, and the topic answer is used for establishing a connection between the topic knowledge point and the corresponding information processing flow; the matching process includes:
calculating semantic similarity between the request information and each topic question;
and when the calculated highest semantic similarity is larger than a preset threshold value, taking the topic knowledge point corresponding to the highest semantic similarity as a target topic knowledge point, and taking an information processing flow corresponding to the target topic knowledge point as a target information processing flow through the topic answer of the target topic knowledge point.
Optionally, the system further comprises: and the training module is used for training and learning the generated interactive data to obtain the associated information.
Optionally, the system further comprises: and the conversion module is used for converting the voice information into text information when the request information is the voice information.
Optionally, the system further comprises: and the external data reading module is used for being associated with one or more service data platforms so as to actively acquire the service data information related to the steps according to the user information.
In order to solve the above technical problem, an embodiment of the present invention further provides a storage medium, on which computer instructions are stored, and the computer instructions execute the steps of the above information question-answer interaction method when running.
In order to solve the above technical problem, an embodiment of the present invention further provides a terminal, including a memory and a processor, where the memory stores computer instructions executable on the processor, and the processor executes the steps of the above information question-answer interaction method when executing the computer instructions.
In order to solve the above technical problem, an embodiment of the present invention further provides an intelligent knowledge base, including:
a plurality of question-answer knowledge points, wherein each question-answer knowledge point comprises a question-answer question and a question-answer;
a plurality of information processing flows, each of the information processing flows comprising a plurality of steps, at least some of the steps comprising associated information, the associated information comprising associated knowledge points and/or associated information processing flows;
each topic knowledge point corresponds to one information processing flow, each topic knowledge point comprises a topic question and a topic answer, and the topic answer is used for establishing the relation between the topic knowledge point and the corresponding information processing flow.
Compared with the prior art, the technical scheme of the invention has the following advantages:
the invention creates a plurality of information processing flows and also creates the associated information for at least part of the steps, thereby in the subsequent interaction with the user, when the user request information can not be matched with the current target information processing flow, the corresponding reply information can be provided for the user through the associated information automatic matching, the difference caused by different experiences of customer service staff is overcome, the times of carrying out additional retrieval are reduced, the processing time is greatly shortened, and the accuracy is higher.
Furthermore, the seamless connection with the service data platform autonomously acquires the corresponding service data platform, reduces the interaction times with the user, improves the accuracy of the acquired service data, shortens the interaction time with the user, and is beneficial to more accurately providing a proper answer for the user in a shorter time.
Drawings
Fig. 1 is a schematic flow chart of an information question-answer interaction method according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of step S2 in FIG. 1;
FIG. 3 is a schematic flow chart of step S3 in FIG. 1;
fig. 4 is a schematic structural diagram of an information question-answer interaction system according to an embodiment of the present invention.
Detailed Description
As described in the background, the prior art has a great difference in the interactive experience of the user due to the different experience of the customer service staff. Therefore, the construction of knowledge content needs to gradually change from single "document storage type knowledge" and "question-and-answer dialogue type knowledge" to "scene type knowledge facing customer service", and in the application form of knowledge, the service scene knowledge of a stream program can be associated and communicated with user identification information, channel type information, business background information, other associated information and the like in the existing CRM (customer relationship management system) system, so that the service type judgment and support of customer service are realized, and finally, the service prediction type and intelligent auxiliary manual customized service is realized.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in detail below.
Referring to fig. 1, the present embodiment provides an information question-answer interaction method, including the following steps:
step S1, a plurality of information processing flows are created in advance, each information processing flow comprises a plurality of steps, at least part of the steps comprise associated information, and the associated information comprises associated knowledge points and/or associated information processing flows;
step S2, performing a first interaction with the user, including: acquiring first request information of a user; performing first matching processing on the plurality of information processing flows according to the first request information, and taking the matched information processing flow as a target information processing flow; providing first reply information to a user according to the target information processing flow;
step S3, performing a second interaction with the user, including: acquiring second request information of the user; when the second request information is matched with the target information processing flow, second reply information is provided for a user according to the target information processing flow; and when the second request information is not matched with the target information processing flow but is matched with the associated information of the corresponding step, providing second reply information for the user according to the associated information.
In the embodiment, the associated information is created for at least part of steps while a plurality of information processing flows are created, so that in the subsequent interaction with the user, when the user request information cannot be matched with the current target information processing flow, the corresponding reply information can be provided for the user through the automatic matching of the associated information, the difference caused by different experiences of customer service staff is overcome, the times of carrying out additional retrieval are reduced, the processing time is greatly shortened, and the accuracy is higher.
The method of the embodiment can be used for manual customer service question and answer interaction, such as: telephone customer service, seat customer service, network customer service, etc.
Step S1 is first executed to create a plurality of information processing flows in advance.
In this embodiment, a plurality of business process diagrams (i.e., information processing flows) may be created for a specific field, product, service, or the like, so as to implement any business request such as consultation and retrieval of a user for the field, product, or service.
Each business flow chart comprises a plurality of steps, and each step can correspond to: flow step descriptions, system operation, reference techniques, description of the techniques, associated knowledge, associated attachments, and associated flows (i.e., associated business flow diagrams).
It should be noted that, in this embodiment, corresponding associated information may be established for each step, or corresponding associated information may be established for only some steps, where the associated information includes associated knowledge points and/or associated information processing flows.
In addition, each step can be associated with one or more service data platforms, so that service data information related to the user can be actively acquired.
Each business flow diagram also corresponds to a topic knowledge point, and the topic knowledge point reflects the function of the flow diagram. The topic knowledge points comprise topic questions and topic answers, the topic questions can comprise a topic standard question and a topic expansion question, the topic standard question and the topic expansion question are different expression forms of the same semantic meaning and can be represented by semantic expressions, and the answers are used for establishing the relation between the topic knowledge points and the business flow chart, namely when the request information of a user is matched with the topic questions of one topic knowledge point, the business flow chart is displayed to the manual customer service personnel through the topic answers of the topic knowledge points.
The associated knowledge points may include one or more question-answer knowledge points, each question-answer knowledge point includes a question-answer question and a question-answer, each question-answer question may include a question-answer standard question and a plurality of question-answer expanded questions, the question-answer expanded questions and the question-answer standard questions are different expression forms of the same semantic, and may be represented by semantic expressions, and when the request information of the user is the same as the semantic of the question-answer question of one question-answer knowledge point, the customer service may reply the answer of the question-answer knowledge point to the user.
The association process may be one or more, which is another one or more business process flow diagrams that may be called in order to reply to the user's request information during the interaction with the user.
The associated knowledge and the associated process are in interaction with the user in the step, and the user is most likely to ask about related contents, which can be obtained by training and learning in the generated interaction data.
It should be noted that the flowchart and the related information at this time may be stored in an excel table format, or may not be stored in the excel table format, so that the selectivity of the storage manner is wider.
Before information question-answer interaction, an intelligent knowledge base needs to be established, and the intelligent knowledge base specifically includes:
a plurality of question-answer knowledge points, wherein each question-answer knowledge point comprises a question-answer question and a question-answer;
a plurality of information processing flows, each of the information processing flows comprising a plurality of steps, at least some of the steps comprising associated information, the associated information comprising associated knowledge points and/or associated information processing flows;
each topic knowledge point corresponds to one information processing flow, each topic knowledge point comprises a topic question and a topic answer, and the topic answer is used for establishing the relation between the topic knowledge point and the corresponding information processing flow.
The information processing flow, the topic knowledge point, and the associated information may be constructed in step S1.
Step S2 is then performed for a first interaction with the user.
Referring to fig. 2, the first interaction specifically includes the following steps:
and S21, acquiring the first request information of the user.
The first request message may be a text message or a non-text message such as a voice message.
When the first request message is a non-text message, the non-text message may be converted into a text message.
And S22, performing first matching processing on the plurality of information processing flows according to the first request information, and taking the matched information processing flow as a target information processing flow.
The first matching process includes:
calculating semantic similarity between the first request information and each topic question;
and when the calculated highest semantic similarity is larger than or equal to a preset threshold, taking the topic knowledge point corresponding to the highest semantic similarity as a target topic knowledge point, and taking the information processing flow corresponding to the target topic knowledge point as a target information processing flow through the topic answer of the target topic knowledge point.
Wherein, the semantic similarity may adopt a combination of one or more of the following methods: the method comprises a semantic similarity calculation method based on ontology distance, a semantic similarity calculation method based on ontology content, a semantic similarity calculation method based on ontology attributes and a mixed semantic similarity calculation method.
In this embodiment, by calculating the semantic similarity of the first request information and the topic problem corresponding to each information processing flow, a maximum value (i.e., the highest semantic similarity) is extracted from the obtained multiple semantic similarities, and then the maximum value is compared with a preset threshold value, when the calculated maximum value is greater than the preset threshold value, it is indicated that the semantics of the information processing flow corresponding to the first request information and the maximum value are very relevant, and a customer service person can search for the step corresponding to the first request information in the information processing flow, and accordingly provide first recovery information to a user.
The embodiment may also automatically acquire a step corresponding to the first request information, specifically: and respectively matching the first request information with each step of the target information processing flow through semantic similarity calculation, taking the step with the highest semantic similarity as the step corresponding to the first request information, and further performing special labeling (such as labeling with different colors) on the step corresponding to the first request information in the target information processing flow, so that customer service personnel can conveniently provide first recovery information for users according to the contents of reference terms and the like of the step.
And obtaining a target information processing flow, wherein the target information processing flow is matched with the first request information.
Step S3 is then performed to perform a second interaction with the user.
Referring to fig. 3, the second interaction specifically includes the following steps:
and S31, acquiring the second request information of the user.
The second request message may be a text message or a non-text message such as a voice message.
When the second request message is a non-text message, the non-text message may be converted into a text message.
And S32, judging whether the second request information is matched with the target information flow.
Specifically, calculating semantic similarity between the second request information and a target topic knowledge point, and judging whether the semantic similarity is greater than a preset threshold, wherein when the semantic similarity is greater than or equal to the preset threshold, the second request information is matched with the target information flow; otherwise, when the semantic similarity is smaller than or equal to the preset threshold, the second request information is not matched with the target information process, so that automatic matching judgment of the second request information and the target information process is realized.
In this embodiment, the customer service staff may also directly determine whether the second request information matches the target information flow.
When the second request message matches the target message processing flow, the step S33 is executed continuously, and a second reply message is provided to the user according to the target message processing flow.
Specifically, the second request information is respectively matched with each step of the target information processing flow through semantic similarity calculation, the step with the highest semantic similarity is taken as the step corresponding to the second request information, and further the step corresponding to the second request information can be specially marked (such as marking with different colors) in the target information processing flow, so that a customer service staff can conveniently provide second reply information for a user according to the contents of reference terms and the like of the step.
In this embodiment, the customer service person may also search for a step corresponding to the second request information in the target information processing flow, and accordingly provide the second reply information to the user.
When the second request information does not match the target information processing flow, the processing continues to step S34, and it is determined whether the second request information matches the associated information of the corresponding step.
The associated information of the corresponding step is preset, and may correspond to M question-answering knowledge points and N topic knowledge points (i.e., N information processing flows), where: m and N are integers which are greater than or equal to 0, and M and N in the same step can be the same or different. For convenience of description, the M question-answer knowledge points and the N topic knowledge points corresponding to the associated information of the corresponding step are collectively referred to as knowledge points (i.e., M + N knowledge points) below.
It should be noted that M and N corresponding to different steps may be wholly or partially different or may be the same.
And judging whether the second request information is matched with the associated information of the corresponding step is to judge whether the second request information is matched with the M + N knowledge points of the corresponding step. Specifically, calculating semantic similarity between the second request information and M + N knowledge points, and determining whether a maximum semantic similarity is greater than a preset threshold, where when the maximum semantic similarity is greater than or equal to the preset threshold, the second request information is matched with the knowledge point corresponding to the maximum semantic similarity, that is, the second request information is matched with the associated information of the corresponding step; otherwise, when the maximum semantic similarity is smaller than or equal to the preset threshold, the second request information is not matched with the associated information of the corresponding step, so that automatic matching judgment of the second request information and the associated information of the corresponding step is realized.
In this embodiment, the customer service staff may also directly determine whether the second request information matches the associated information of the corresponding step.
When the second request information matches the associated information of the corresponding step, the step S35 is continuously executed, and second reply information is provided to the user according to the associated information.
When the second request information does not match the associated information of the corresponding step, step S36 is executed, the second matching processing is performed on the plurality of information processing flows according to the second request information, the matched information processing flow is used as a new target information processing flow, and second reply information is provided to the user according to the new target information processing flow.
The step S36 may refer to the step S22 described above.
It should be noted that, when the above steps are executed, the service data information related to the steps can be actively acquired according to the user information, so that inquiry acquisition from the user is not required, and thus, seamless connection with the service data platform is achieved, the corresponding service data platform is autonomously acquired, the number of times of interaction with the user is reduced, the accuracy of the acquired service data is improved, the interaction time with the user is shortened, and a suitable answer can be provided for the user more accurately in a shorter time. Because the service data related to the step nodes can be actively acquired, the steps of the current flow chart are simpler, the acquired service data are more accurate and quicker, the reply accuracy is finally improved, and the reply time is reduced.
In addition, when the first reply information and/or the second reply information are provided for the user in the above steps, the method may further include: and converting the acquired reply information into voice and sending the voice to the user. In other words, in order to ensure consistency with the user interaction, when the user interacts using a modality such as voice, the optimal answer fed back to the user is also voice. Therefore, when the optimal answer is in a text form, the optimal answer is converted into voice and then output to the user.
Continuing to execute the subsequent steps, and performing a third interaction with the user, reference may be made to step S3, which is not described herein again.
And continuously executing the step of interacting with the user until the interaction process with the current user is finished.
The embodiment can reduce the times of additional retrieval, shorten the processing time and improve the accuracy, thereby greatly improving the user experience effect of manual customer service question-answer interaction.
Referring to fig. 4, this embodiment further provides an information question-answer interaction system, which may include:
a storage module 41, configured to store a plurality of information processing flows and associated information created in advance, where each information processing flow includes a plurality of steps, at least some of the steps include associated information, and the associated information includes associated knowledge points and/or associated information processing flows;
a first interaction module 42, configured to perform a first interaction with the user, including: the first input unit is used for acquiring first request information of a user; a first matching unit, configured to perform first matching processing on the multiple information processing flows according to the first request information, and use a matched information processing flow as a target information processing flow; the first output unit is used for providing first reply information for a user according to the target information processing flow;
a second interaction module 43, configured to perform a second interaction with the user, including: the second input unit is used for acquiring second request information of the user; the second matching unit is used for judging whether the second request information is matched with the target information processing flow or not and further judging whether the second request information is matched with the associated information of the corresponding step or not when the second request information is not matched with the target information processing flow; and the second output unit is used for providing second reply information to the user according to the target information processing flow when the second request information is matched with the target information processing flow, and providing second reply information to the user according to the associated information when the second request information is not matched with the target information processing flow but is matched with the associated information of the corresponding step.
When the second request information does not match the target information processing flow and does not match the associated information of the corresponding step, the second matching unit is further configured to perform second matching processing on the plurality of information processing flows according to the second request information, and use the matched information processing flow as a new target information processing flow; and the second output unit provides second reply information to the user according to the new target information processing flow.
Each information processing flow corresponds to a theme knowledge point, the theme knowledge points comprise theme questions and theme answers, and the theme answers are used for establishing the relation between the theme knowledge points and the corresponding information processing flows; the matching process includes:
calculating semantic similarity between the request information and each topic question;
and when the calculated highest semantic similarity is larger than a preset threshold value, taking the topic knowledge point corresponding to the highest semantic similarity as a target topic knowledge point, and taking an information processing flow corresponding to the target topic knowledge point as a target information processing flow through the topic answer of the target topic knowledge point.
Wherein the system may further comprise: and the training module (not shown in the figure) is used for training and learning the generated interaction data to obtain the association information.
Wherein the system may further comprise: a conversion module (not shown in the figure) for converting the voice information into text information when the request information is voice information.
Wherein the system may further comprise: and the external data reading module (not shown in the figure) is used for being associated with one or more service data platforms so as to actively acquire service data information related to the step according to the user information.
It should be understood that each module or unit described in the information question-answering interaction system provided in the above embodiments corresponds to one of the method steps described above. Therefore, the operations and features described in the foregoing method steps are also applicable to the information question-answering interaction system and the corresponding modules and units included therein, and repeated contents are not described herein again.
An embodiment of the present invention further provides a terminal, which includes a memory, a processor, and computer instructions stored in the memory and executed by the processor, where the processor executes the computer instructions to implement the steps of the information question-answer interaction method described in any of the foregoing embodiments.
An embodiment of the present invention further provides a storage medium, on which computer instructions are stored, and the computer instructions, when executed by a processor, implement the steps of the information question-answer interaction method described in any one of the foregoing embodiments. The storage medium may be any tangible medium, such as a floppy disk, a CD-ROM, a DVD, a hard drive, even a network medium, etc.
It should be understood that although one implementation form of the embodiments of the present invention described above may be a computer program product, the method or apparatus of the embodiments of the present invention may be implemented in software, hardware, or a combination of software and hardware. The hardware portion may be implemented using dedicated logic; the software portions may be stored in a memory and executed by a suitable instruction execution system, such as a microprocessor or specially designed hardware. It will be appreciated by those of ordinary skill in the art that the methods and apparatus described above may be implemented using computer executable instructions and/or embodied in processor control code, such code provided, for example, on a carrier medium such as a disk, CD or DVD-ROM, programmable memory such as read only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The methods and apparatus of the present invention may be implemented in hardware circuitry, such as very large scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, or programmable hardware devices such as field programmable gate arrays, programmable logic devices, or in software for execution by various types of processors, or in a combination of hardware circuitry and software, such as firmware.
It should be understood that although several modules or units of the apparatus are mentioned in the above detailed description, such division is merely exemplary and not mandatory. Indeed, according to exemplary embodiments of the invention, the features and functions of two or more modules/units described above may be implemented in one module/unit, whereas the features and functions of one module/unit described above may be further divided into implementations by a plurality of modules/units. Furthermore, some of the modules/units described above may be omitted in some application scenarios.
It is to be understood that the description has described only some of the key, not necessarily essential, techniques and features, and may not have described features that could be implemented by those skilled in the art, in order not to obscure the embodiments of the invention.
Although the present invention is disclosed above, the present invention is not limited thereto. Various changes and modifications may be effected therein by one skilled in the art without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (13)
1. An information question-answer interaction method is characterized by comprising the following steps:
the method comprises the steps of creating a plurality of information processing flows in advance, wherein each information processing flow comprises a plurality of steps, at least part of the steps comprise associated information, and the associated information comprises associated knowledge points and/or associated information processing flows;
performing a first interaction with a user, comprising: acquiring first request information of a user; performing first matching processing on the plurality of information processing flows according to the first request information, and taking the matched information processing flow as a target information processing flow; providing first reply information to a user according to the target information processing flow;
and performing a second interaction with the user, comprising: acquiring second request information of the user; when the second request information is matched with the target information processing flow, second reply information is provided for a user according to the target information processing flow; when the second request information is not matched with the target information processing flow but is matched with the associated information of the corresponding step, second reply information is provided for the user according to the associated information; when the second request information is not matched with the target information processing flow and is not matched with the associated information of the corresponding step, performing second matching processing on the plurality of information processing flows according to the second request information, and taking the matched information processing flow as a new target information processing flow; providing second reply information to the user according to the new target information processing flow;
the method is used for manual customer service question-answer interaction.
2. The method of claim 1, wherein each information processing flow corresponds to a topic knowledge point, the topic knowledge point comprises a topic question and a topic answer, and the topic answer is used for establishing a connection between the topic knowledge point and the corresponding information processing flow; the matching process includes:
calculating semantic similarity between the request information and each topic question;
and when the calculated highest semantic similarity is larger than a preset threshold value, taking the topic knowledge point corresponding to the highest semantic similarity as a target topic knowledge point, and taking an information processing flow corresponding to the target topic knowledge point as a target information processing flow through the topic answer of the target topic knowledge point.
3. The method of claim 1, wherein the association information is obtained by training learning the generated interaction data.
4. The method of claim 1, wherein the requested information is voice information, the method further comprising: converting the voice information into text information before the matching process is performed.
5. The method of claim 1, wherein the reply message is answered by human customer service with reference to a verbal prompt.
6. The method of claim 1, wherein at least some of the steps are associated with one or more service data platforms to proactively obtain service data information related to the steps based on user information.
7. An information question-answer interaction system, comprising:
the storage module is used for storing a plurality of pre-created information processing flows and associated information, each information processing flow comprises a plurality of steps, at least part of the steps comprise associated information, and the associated information comprises associated knowledge points and/or associated information processing flows;
the first interaction module is used for carrying out first interaction with a user and comprises: the first input unit is used for acquiring first request information of a user; a first matching unit, configured to perform first matching processing on the multiple information processing flows according to the first request information, and use a matched information processing flow as a target information processing flow; the first output unit is used for providing first reply information for a user according to the target information processing flow;
the second interaction module is used for carrying out second interaction with the user and comprises: the second input unit is used for acquiring second request information of the user; the second matching unit is used for judging whether the second request information is matched with the target information processing flow or not and further judging whether the second request information is matched with the associated information of the corresponding step or not when the second request information is not matched with the target information processing flow; the second output unit is used for providing second reply information for the user according to the target information processing flow when the second request information is matched with the target information processing flow; when the second request information is not matched with the target information processing flow but is matched with the associated information of the corresponding step, second reply information is provided for the user according to the associated information; when the second request information is not matched with the target information processing flow and is not matched with the associated information of the corresponding step, the second matching unit is further used for performing second matching processing on the plurality of information processing flows according to the second request information, and taking the matched information processing flow as a new target information processing flow; the second output unit provides second reply information to the user according to the new target information processing flow;
the system is used for manual customer service question and answer interaction.
8. The system of claim 7, wherein each of the information processing flows corresponds to a topic knowledge point, the topic knowledge point comprises a topic question and a topic answer, and the topic answer is used for establishing a connection between the topic knowledge point and the corresponding information processing flow; the matching process includes:
calculating semantic similarity between the request information and each topic question;
and when the calculated highest semantic similarity is larger than a preset threshold value, taking the topic knowledge point corresponding to the highest semantic similarity as a target topic knowledge point, and taking an information processing flow corresponding to the target topic knowledge point as a target information processing flow through the topic answer of the target topic knowledge point.
9. The system of claim 7, further comprising: and the training module is used for training and learning the generated interactive data to obtain the associated information.
10. The system of claim 7, further comprising: and the conversion module is used for converting the voice information into text information when the request information is the voice information.
11. The system of claim 7, further comprising: and the external data reading module is used for being associated with one or more service data platforms so as to actively acquire the service data information related to the steps according to the user information.
12. A storage medium having stored thereon computer instructions, wherein the computer instructions are operable to perform the steps of the information question-answer interaction method according to any one of claims 1 to 6.
13. A terminal comprising a memory and a processor, the memory having stored thereon computer instructions executable on the processor, wherein the processor executes the computer instructions to perform the steps of the information question-answer interaction method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810273945.9A CN108509591B (en) | 2018-03-29 | 2018-03-29 | Information question-answer interaction method and system, storage medium, terminal and intelligent knowledge base |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810273945.9A CN108509591B (en) | 2018-03-29 | 2018-03-29 | Information question-answer interaction method and system, storage medium, terminal and intelligent knowledge base |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108509591A CN108509591A (en) | 2018-09-07 |
| CN108509591B true CN108509591B (en) | 2020-12-08 |
Family
ID=63377965
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810273945.9A Active CN108509591B (en) | 2018-03-29 | 2018-03-29 | Information question-answer interaction method and system, storage medium, terminal and intelligent knowledge base |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108509591B (en) |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111382236A (en) * | 2018-12-27 | 2020-07-07 | 上海智臻智能网络科技股份有限公司 | Switching method and device between interactive processes |
| CN109710939B (en) * | 2018-12-28 | 2023-06-09 | 北京百度网讯科技有限公司 | Method and device for determining theme |
| CN109840802B (en) * | 2018-12-29 | 2023-04-28 | 深圳巨湾科技有限公司 | Communication method and device, real estate system, computer and readable storage medium |
| CN111723183B (en) * | 2019-03-20 | 2023-05-23 | 上海智臻智能网络科技股份有限公司 | Method and device for adjusting dialogue flow in intelligent question and answer |
| CN110555100A (en) * | 2019-09-06 | 2019-12-10 | 北京讯鸟软件有限公司 | Multi-product demand matching method and system based on graph generation free dialogue |
| CN111241246B (en) * | 2020-01-17 | 2023-08-22 | 苏州研途教育科技有限公司 | Autonomous learning method, device, intelligent customer service robot and storage medium |
| CN111311186A (en) * | 2020-02-19 | 2020-06-19 | 杭州朗和科技有限公司 | Work order creating method, medium, device and computing equipment |
| CN111984773A (en) * | 2020-03-31 | 2020-11-24 | 北京来也网络科技有限公司 | Information processing method, device, equipment and storage medium combining RPA and AI |
| CN111556096B (en) * | 2020-04-01 | 2023-02-28 | 深圳壹账通智能科技有限公司 | Information pushing method, device, medium and electronic equipment |
| CN113392324B (en) * | 2021-06-17 | 2023-11-10 | 北京京东振世信息技术有限公司 | Information pushing method, device, equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106294341A (en) * | 2015-05-12 | 2017-01-04 | 阿里巴巴集团控股有限公司 | A kind of Intelligent Answer System and theme method of discrimination thereof and device |
| CN106528613A (en) * | 2016-05-26 | 2017-03-22 | 中科鼎富（北京）科技发展有限公司 | Intelligent question-answer (Q&A) method and device |
| CN106649825A (en) * | 2016-12-29 | 2017-05-10 | 上海智臻智能网络科技股份有限公司 | Voice interaction system, establishment method and device thereof |
| CN107220380A (en) * | 2017-06-27 | 2017-09-29 | 北京百度网讯科技有限公司 | Question and answer based on artificial intelligence recommend method, device and computer equipment |
| 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 |
| CN107807949A (en) * | 2017-09-11 | 2018-03-16 | 远光软件股份有限公司 | Intelligent interactive method, equipment and storage medium |
-
2018
- 2018-03-29 CN CN201810273945.9A patent/CN108509591B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106294341A (en) * | 2015-05-12 | 2017-01-04 | 阿里巴巴集团控股有限公司 | A kind of Intelligent Answer System and theme method of discrimination thereof and device |
| CN106528613A (en) * | 2016-05-26 | 2017-03-22 | 中科鼎富（北京）科技发展有限公司 | Intelligent question-answer (Q&A) method and device |
| CN106649825A (en) * | 2016-12-29 | 2017-05-10 | 上海智臻智能网络科技股份有限公司 | Voice interaction system, establishment method and device thereof |
| 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 |
| CN107220380A (en) * | 2017-06-27 | 2017-09-29 | 北京百度网讯科技有限公司 | Question and answer based on artificial intelligence recommend method, device and computer equipment |
| CN107807949A (en) * | 2017-09-11 | 2018-03-16 | 远光软件股份有限公司 | Intelligent interactive method, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108509591A (en) | 2018-09-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108509591B (en) | Information question-answer interaction method and system, storage medium, terminal and intelligent knowledge base | |
| CN110795543B (en) | Unstructured data extraction method, device and storage medium based on deep learning | |
| CN106534548B (en) | Voice error correction method and device | |
| US9946511B2 (en) | Method for user training of information dialogue system | |
| US20190108273A1 (en) | Data Processing Method, Apparatus and Electronic Device | |
| CN111708869B (en) | Processing method and device for man-machine conversation | |
| US8972265B1 (en) | Multiple voices in audio content | |
| JP2017037588A (en) | Information processor and information processing program | |
| CN111666006B (en) | Method and device for drawing question and answer, drawing question and answer system and readable storage medium | |
| CN114757176B (en) | Method for acquiring target intention recognition model and intention recognition method | |
| JPH02302876A (en) | Conversational language analyzer | |
| CN110610698B (en) | Voice labeling method and device | |
| CN112685550B (en) | Intelligent question-answering method, intelligent question-answering device, intelligent question-answering server and computer readable storage medium | |
| CN104572852A (en) | Recommendation method and recommendation device for recourses | |
| CN111553138B (en) | Auxiliary writing method and device for standardizing content structure document | |
| CN117216212A (en) | Dialogue processing method, dialogue model training method, device, equipment and medium | |
| CN115640386A (en) | Method and apparatus for conducting dialogs based on recommended dialogs | |
| JP5258056B2 (en) | Question sentence candidate presentation device | |
| CN111723559B (en) | Real-time information extraction method and device | |
| CN117273167A (en) | Training method, medical method, device, equipment and storage medium for medical model | |
| CN116860938A (en) | Voice question-answering construction method, device and medium based on large language model | |
| CN116204615A (en) | Question generation model training method and device | |
| JP2017021245A (en) | Language learning support device, language learning support method, and language learning support program | |
| KR20190070682A (en) | System and method for constructing and providing lecture contents | |
| CN113468306A (en) | Voice conversation method, device, electronic equipment 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |