WO2018000277A1

WO2018000277A1 - Question and answer method and system, and robot

Info

Publication number: WO2018000277A1
Application number: PCT/CN2016/087767
Authority: WO
Inventors: 邱楠; 杨新宇; 王昊奋
Original assignee: 深圳狗尾草智能科技有限公司
Priority date: 2016-06-29
Filing date: 2016-06-29
Publication date: 2018-01-04
Also published as: CN106663130A

Abstract

A question and answer method, comprising: obtaining question information (S101); inputting the question information into a mapping knowledge domain to search for an answer (S102); inputting the question information into community data to search for the answer if the answer is not found in the mapping knowledge domain (S103); and inputting the question information into internet data to search for the answer if the answer is not found in the community data (S104). The method can combine the following features, i.e., the question and answer based on the mapping knowledge domain is high in accuracy, the question and answer based on community data is high in coverage rate, and the question and answer based on internet data is higher in coverage rate, thus improving question and answer coverage rate and accuracy and enlarging the application scope and universality of the question and answer method.

Description

Question and answer method, system and robot

Technical field

The invention relates to the field of robot interaction technology, in particular to a question and answer method, a system and a robot.

Background technique

With the development of society and science and technology, more and more robots are applied to communicate with humans' work and life. Humans can ask questions to robots. After a series of processes, robots return results to humans, similar to human-to-human communication. the process of. In order to make the robot more anthropomorphic in the process of communicating with people, and to simulate the real scene of communication with people, people have explored many methods. However, in the existing question and answer system, there are cases where the answer answer accuracy is not high. .

Therefore, how to provide a question and answer method with a higher correct answer rate becomes a technical problem that needs to be solved.

Summary of the invention

It is an object of the present invention to provide a question and answer method, system and robot for answering a question answering method with a higher correct answer rate.

The object of the present invention is achieved by the following technical solutions:

A question and answer method, including:

Get question information;

Enter the question information into the knowledge map to query the answer;

If the answer is not found in the knowledge map, the question information is input into the community data to query the answer;

If the answer is not found in the community data, enter the question information into the Internet data to query the answer.

Preferably, the method further comprises:

If the answer is found in the knowledge map, the query is terminated.

Preferably, the method further comprises:

If the answer is found in the community data, the query is terminated.

Preferably, the step of inputting the question information into the knowledge map to query the answer specifically includes:

Divide the question information;

Find the intermediate results in the knowledge map by dividing the results;

Enter the intermediate results into the database to get emotional bias and get answers based on emotional bias.

Preferably, the step of inputting the question information into the community data to query the answer specifically includes:

Divide the question information;

Find the intermediate results in the community data by dividing the results;

The intermediate result is compared with the preset feature information, and the answer is obtained according to the comparison result.

Preferably, the step of inputting the question information into the Internet data to query the answer specifically includes:

Divide the question information;

Find the intermediate results in the Internet data by dividing the results;

The intermediate results are combined according to the language rules to get the answer.

The invention discloses a question answering system, comprising:

Obtaining a module for obtaining question information;

a knowledge map module for inputting question information into a knowledge map to query an answer;

The community data module is configured to input the question information into the community data to query the answer if the answer is not found in the knowledge map;

The Internet data module is used to input the question information into the Internet data to query the answer if the answer is not found in the community data.

Preferably, the system includes a first termination module for terminating the query if an answer is found in the knowledge map.

Preferably, the system includes a second termination module that terminates the query if an answer is found in the community data.

Preferably, the knowledge map module is specifically configured to:

Divide the question information;

Find the intermediate results in the knowledge map by dividing the results;

Preferably, the community data module is specifically configured to:

Divide the question information;

Find the intermediate results in the community data by dividing the results;

Preferably, the internet data module is specifically configured to:

Divide the question information;

Find the intermediate results in the Internet data by dividing the results;

The intermediate results are combined according to the language rules to get the answer. .

The invention discloses a robot comprising a question answering system as described in any of the above.

Compared with the prior art, the present invention has the following advantages: a question and answer method disclosed by the present invention includes: obtaining question information; inputting question information into a knowledge map to query an answer; if an answer is not found in the knowledge map, a question will be asked The information is input into the community data to query the answer; if the answer is not found in the community data, the question information is input into the Internet data to query the answer. In this way, the question information can be first input into the knowledge map to query the answer. If the query is received, it is feedback to the user. If there is no query, then the query will continue to the community data. If the query is received, the user will be fed back to the user. If it is queried, it will continue to query the Internet data if it is queried and fed back to the user. This can be combined with the high accuracy of question-and-answer based on knowledge maps, the high coverage rate based on community data, and the higher coverage rate based on question and answer of Internet data to improve the coverage and accuracy of question and answer. Rate, expand the scope and versatility of the question and answer method.

DRAWINGS

1 is a flowchart of a method for generating interactive content of a robot according to Embodiment 1 of the present invention;

2 is a schematic diagram of a system for generating interactive content of a robot according to a second embodiment of the present invention.

detailed description

Although the flowcharts describe various operations as a sequential process, many of the operations can be implemented in parallel, concurrently or concurrently. The order of the operations can be rearranged. Processing may be terminated when its operation is completed, but may also have additional steps not included in the figures. Processing can correspond to methods, functions, procedures, subroutines, subroutines, and the like.

Computer devices include user devices and network devices. The user equipment or the client includes but is not limited to a computer, a smart phone, a PDA, etc.; the network device includes but is not limited to a single network server, a server group composed of multiple network servers, or a cloud computing-based computer or network server. cloud. The computer device can operate alone to carry out the invention, and can also access the network and implement the invention through interoperation with other computer devices in the network. The network in which the computer device is located includes, but is not limited to, the Internet, a wide area network, a metropolitan area network, a local area network, a VPN network, and the like.

The terms "first", "second", etc. may be used herein to describe each unit, but These elements should not be limited by these terms, and these terms are used only to distinguish one element from another. The term "and/or" used herein includes any and all combinations of one or more of the associated listed items. When a unit is referred to as being "connected" or "coupled" to another unit, it can be directly connected or coupled to the other unit, or an intermediate unit can be present.

The terminology used herein is for the purpose of describing the particular embodiments, The singular forms "a", "an", It is also to be understood that the terms "comprising" and """ Other features, integers, steps, operations, units, components, and/or combinations thereof.

The invention will now be further described with reference to the drawings and preferred embodiments.

Embodiment 1

As shown in FIG. 1, a method for answering and answering is disclosed in this embodiment, including:

S101. Acquire question information.

S102. Enter the question information into the knowledge map to query the answer;

S103. If the answer is not found in the knowledge map, input the question information into the community data to query the answer;

S104. If the answer is not found in the community data, input the question information into the Internet data to query the answer.

A question and answer method disclosed by the present invention includes: obtaining question information; inputting the question information into the knowledge map to query the answer; if the answer is not found in the knowledge map, inputting the question information into the community data to query the answer; if in the community If the answer is not found in the data, the question information is input into the Internet data to query the answer. In this way, the question information can be first input into the knowledge map to query the answer. If the query is received, it is feedback to the user. If there is no query, then the query will continue to the community data. If the query is received, the user will be fed back to the user. If it is queried, it will continue to query the Internet data if it is queried and fed back to the user. This can be combined with the high accuracy of question-and-answer based on knowledge maps, the high coverage rate based on community data, and the higher coverage rate based on question and answer of Internet data to improve the coverage and accuracy of question and answer. Rate, expand the scope and versatility of the question and answer method.

In this embodiment, based on the Internet data question answer (WEB-QA, web question answering), based on community data answering (C-QA, community question answering), KB-QA is characterized by the highest accuracy rate but the lowest coverage rate in the three question-and-answer methods and systems based on KB-QA (knowledge based question answering). C-QA is characterized by the highest accuracy. However, the coverage rate is higher. WEB-QA is characterized by the lowest accuracy rate but the highest coverage rate. In this embodiment, the accuracy and coverage of the question and answer can be increased by effectively combining the three.

According to one of the examples, the method further comprises terminating the query if the answer is queried in the knowledge map. In this way, the query can be terminated after the answer is found to save resources and time, and the user can get the answer in time.

According to one of the examples, the method further comprises terminating the query if the answer is queried in the community data. In this way, the query can be terminated after the answer is found to save resources and time, and the user can get the answer in time.

According to another example, the step of inputting the question information into the knowledge map to query the answer specifically includes:

Divide the question information;

Find the intermediate results in the knowledge map by dividing the results;

This makes it quick and easy to find answers in the knowledge map.

According to another example, the step of inputting the question information into the community data to query the answer specifically includes:

Divide the question information;

Find the intermediate results in the community data by dividing the results;

This makes it quick and easy to find answers in community data such as "Baidu knows" and "Know" communities.

According to another example, the step of inputting the question information into the Internet data to query the answer specifically includes:

Divide the question information;

Find the intermediate results in the Internet data by dividing the results;

This makes it quick and easy to find answers in the knowledge map.

For example, the user asked a question "Do I wear this dress look good?"

Then Step1: Query in KB-QA, "I" hobbies, moods, styles of clothes, beauty Color, etc., and then according to the acquired person's preferences and the characteristics of the clothes, to judge whether it is good-looking or ugly, and get the answer.

Step2: If you can't find it in KB-QA, query it in C-QA. For example, knowing whether there is "I" preference information, and whether there is clothing information, the purpose is to get the characteristics of "I", the characteristics of "clothing", and then judge whether it is good-looking or ugly, and get the answer.

Step3: As far as this question is concerned, it is obvious that web-QA is not suitable. Because web-QA does not have "I" information, it will not be queried in web-QA.

Embodiment 2

As shown in FIG. 2, this embodiment discloses a question and answer system, including:

The obtaining module 201 is configured to obtain question information.

The knowledge map module 202 is configured to input the question information into the knowledge map to query the answer;

The community data module 203 is configured to input the question information into the community data to query an answer if the answer is not found in the knowledge map;

The Internet data module 204 is configured to input the question information into the Internet data to query an answer if the answer is not found in the community data.

In this way, the question information can be first input into the knowledge map to query the answer. If the query is received, it is feedback to the user. If there is no query, then the query will continue to the community data. If the query is received, the user will be fed back to the user. If it is queried, it will continue to query the Internet data if it is queried and fed back to the user. This can be combined with the high accuracy of question-and-answer based on knowledge maps, the high coverage rate based on community data, and the higher coverage rate based on question and answer of Internet data to improve the coverage and accuracy of question and answer. Rate, expand the scope and versatility of the question and answer method.

In this embodiment, based on the Internet data question and answer (WEB-QA, web question answering), based on community data answering (C-QA, community question answering), knowledge based question answering (KB-QA, knowledge based question answering) Among the three question and answer methods and systems, KB-QA is characterized by the highest accuracy, but the coverage rate is the lowest. C-QA is characterized by the highest accuracy, but the coverage rate is high. WEB-QA is characterized by accuracy. Lowest, but the highest coverage. In this embodiment, the accuracy and coverage of the question and answer can be increased by effectively combining the three.

According to one of the examples, the system includes a first termination module for terminating the query if an answer is queried in the knowledge map. This will terminate the query after finding the answer. Save resources and time, so that users can get answers in time.

According to another example, the system includes a second termination module that terminates the query if an answer is queried in the community data. In this way, the query can be terminated after the answer is found to save resources and time, and the user can get the answer in time.

According to another example, the knowledge map module is specifically configured to:

Divide the question information;

Find the intermediate results in the knowledge map by dividing the results;

This makes it quick and easy to find answers in the knowledge map.

According to another example, the community data module is specifically configured to:

Divide the question information;

Find the intermediate results in the community data by dividing the results;

According to another example, the internet data module is specifically configured to:

Divide the question information;

Find the intermediate results in the Internet data by dividing the results;

This makes it quick and easy to find answers in the knowledge map.

For example, the user asked a question "Do I wear this dress look good?"

Then Step1: Query in KB-QA, "I" hobbies, moods, styles of clothes, colors, etc., and then judge whether it is good-looking or ugly according to the preferences of the acquired people and the characteristics of the clothes, so as to get an answer.

The above is a further detailed description of the present invention in connection with the specific preferred embodiments, and the specific embodiments of the present invention are not limited to the description. For the technology of the present invention A person skilled in the art can make some simple deductions or substitutions without departing from the inventive concept, and should be considered as belonging to the scope of the present invention.

Claims

A question and answer method, characterized in that it comprises:

Get question information;

Enter the question information into the knowledge map to query the answer;

If the answer is not found in the knowledge map, the question information is input into the community data to query the answer;

If the answer is not found in the community data, enter the question information into the Internet data to query the answer.
The question and answer method according to claim 1, wherein the method further comprises:

If the answer is found in the knowledge map, the query is terminated.
The question and answer method according to claim 1, wherein the method further comprises:

If the answer is found in the community data, the query is terminated.
The question and answer method according to claim 1, wherein the step of inputting the question information into the knowledge map to query the answer comprises:

Divide the question information;

Find the intermediate results in the knowledge map by dividing the results;

Enter the intermediate results into the database to get emotional bias and get answers based on emotional bias.
The question and answer method according to claim 1, wherein the step of inputting the question information into the community data to query the answer comprises:

Divide the question information;

Find the intermediate results in the community data by dividing the results;

The intermediate result is compared with the preset feature information, and the answer is obtained according to the comparison result.
The question and answer method according to claim 1, wherein the step of inputting the question information into the internet data to query the answer comprises:

Divide the question information;

Find the intermediate results in the Internet data by dividing the results;

The intermediate results are combined according to the language rules to get the answer.
A question and answer system, characterized in that it comprises:

Obtaining a module for obtaining question information;

a knowledge map module for inputting question information into a knowledge map to query an answer;

The community data module is configured to input the question information into the community data to query the answer if the answer is not found in the knowledge map;

The Internet data module is used to input the question information into the Internet data to query the answer if the answer is not found in the community data.
The question answering system of claim 7, wherein the system includes a first termination module for terminating the query if the answer is queried in the knowledge map.
The question answering system according to claim 7, wherein said system comprises a second termination module that terminates the query if an answer is found in the community data.
The question answering system according to claim 7, wherein the knowledge map module is specifically configured to:

Divide the question information;

Find the intermediate results in the knowledge map by dividing the results;

Enter the intermediate results into the database to get emotional bias and get answers based on emotional bias.
The question answering system according to claim 7, wherein the community data module is specifically configured to:

Divide the question information;

Find the intermediate results in the community data by dividing the results;

The intermediate result is compared with the preset feature information, and the answer is obtained according to the comparison result.
The question answering system according to claim 7, wherein the internet data module is specifically configured to:

Divide the question information;

Find the intermediate results in the Internet data by dividing the results;

The intermediate results are combined according to the language rules to get the answer. .
A robot comprising a question answering system according to any one of claims 7 to 12.