CN106843461B - Interactive output method for robot and robot - Google Patents
Interactive output method for robot and robot Download PDFInfo
- Publication number
- CN106843461B CN106843461B CN201611146822.6A CN201611146822A CN106843461B CN 106843461 B CN106843461 B CN 106843461B CN 201611146822 A CN201611146822 A CN 201611146822A CN 106843461 B CN106843461 B CN 106843461B
- Authority
- CN
- China
- Prior art keywords
- user
- sporting event
- event
- topic
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Human Computer Interaction (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Manipulator (AREA)
Abstract
The invention discloses an interactive output method for a robot and the robot. The method comprises the following steps: receiving and analyzing multi-modal input data, and judging whether a sports event which can be used as a topic exists at present; determining whether a sporting event has not been conducted or is being conducted but has not ended when there is a sporting event that can be a topic; obtaining multi-dimensional sample data related to the sporting event when the sporting event is not ongoing or ongoing but not yet finished; analyzing the sample data, and predicting the prediction result of the sports event by integrating the multi-dimensional analysis result of the sample data; and interacting with a user by taking the sports event as a topic, wherein the prediction result is output to the user in a multi-mode manner. Compared with the prior art, the method can greatly improve the interaction willingness of the user and improve the user experience of man-machine interaction.
Description
Technical Field
The invention relates to the field of robots, in particular to an interactive output method for a robot and the robot.
Background
With the continuous development of robot technology, more and more intelligent robots are applied to the daily production and life of human beings.
In the prior art, one of the most common human-computer interaction scenarios is that of a robot and a user chatting. However, in the existing human-computer interaction scenario, the chat between the robot and the user is usually initiated by the user and is dominated by the user, and the robot can only passively respond to the questions of the user in a targeted manner. This makes the whole chat process quite monotonous, and when the user obtains the answer that the user wants to know, the chat process is immediately stopped, and even in many cases, the user gives up the question after trying to ask the question once or twice, and the interaction is terminated unilaterally.
Therefore, in order to improve the interest of the robot in chatting with the user, improve the willingness of the user in chatting, and enhance the user experience of the robot, a better interactive output method is needed.
Disclosure of Invention
The invention provides an interactive output method for a robot, which comprises the following steps:
receiving and analyzing multi-modal input data, and judging whether a sports event which can be used as a topic exists at present;
determining whether a sporting event has not been conducted or is being conducted but has not ended when there is a sporting event that can be a topic;
obtaining multi-dimensional sample data related to the sporting event when the sporting event is not ongoing or ongoing but not yet finished;
analyzing the sample data, and predicting the prediction result of the sports event by integrating the multi-dimensional analysis result of the sample data;
and interacting with a user by taking the sports event as a topic, wherein the prediction result is output to the user in a multi-mode manner.
In one embodiment, whether a sports event which can be a topic exists currently is judged, wherein the first sports event is judged to be the topic when the output content of the user contains the first sports event in the process of man-machine interaction.
In one embodiment, it is determined whether there is a sporting event that can be a topic at present, wherein a user behavior of the user is detected and analyzed, and when the user behavior indicates that the user is focusing on a second sporting event, it is determined that the second sporting event can be a topic.
In one embodiment, multi-dimensional sample data related to the sporting event is obtained, wherein the sample data includes search data, social data, historical statistics of related events, and user data, including user feedback data for active questioning, user behavior data for online activities, and historical interaction records of users.
In an embodiment, multi-dimensional sample data related to the sporting event is obtained, wherein the sample data contains user preferences, the method further comprising:
capturing multi-modal behavior of the user for the sporting event;
analyzing the multi-modal behavior to obtain and save user preferences corresponding to the sporting event;
extracting the corresponding user preferences from the sporting event as a topic;
predicting a predicted outcome of the sporting event in conjunction with the user preference;
interacting with a user on the topic of the sporting event in conjunction with the user preferences.
In one embodiment:
predicting a predicted outcome for the sporting event, wherein a plurality of different predicted outcomes for the sporting event are obtained, each of the predicted outcomes corresponding to a respective probability of occurrence;
and outputting the prediction result to the user, wherein the plurality of different prediction results of the sports event, the occurrence probability corresponding to each prediction result, the prediction basis and the information source are output to the user in a multi-mode manner.
The invention also proposes an intelligent robot, comprising:
the current topic analyzing module is configured to receive and analyze the multi-modal input data and judge whether a sports event which can be used as a topic exists at present;
a sporting event progress analysis module configured to determine whether a sporting event that can be a topic is not ongoing or ongoing but not yet ended when there is the sporting event;
a sporting event data collection module configured to obtain multi-dimensional sample data relating to the sporting event when the sporting event is not yet in progress or is in progress but is not yet over;
an event result prediction module configured to analyze the sample data and predict a prediction result of the sporting event by integrating a multi-dimensional analysis result of the sample data;
an interaction output module configured to interact with a user on the topic of the sporting event, wherein the prediction result is multimodal output to the user.
In an embodiment, the current topic parsing module includes an interactive content parsing unit, and the interactive content parsing unit is configured to determine that a first sports event can be a topic when the output content of the user includes the first sports event during the human-computer interaction.
In an embodiment, the current topic parsing module includes a user behavior analysis unit configured to detect and analyze a user behavior of the user, and determine that a second athletic event may be a topic when the user behavior indicates that the user is paying attention to the second athletic event.
In one embodiment, the robot further comprises user data and a user preference collection module, the user preference collection module configured to:
acquiring multi-modal behaviors of the user for the sports event, analyzing the multi-modal behaviors, and acquiring and storing user preferences corresponding to the sports event;
extracting the corresponding user preferences from the sporting event as a topic.
The method of the present invention selects a sporting event as a topic entry point to interact with the user by predicting the outcome of the sporting event. Compared with the prior art, the method can greatly improve the interaction willingness of the user and improve the user experience of man-machine interaction.
Additional features and advantages of the invention will be set forth in the description which follows. Also, some of the features and advantages of the invention will be apparent from the description, or may be learned by practice of the invention. The objectives and some of the advantages of the invention may be realized and attained by the process particularly pointed out in the written description and claims hereof as well as the appended drawings.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a flow diagram of a method according to an embodiment of the invention;
FIGS. 2 and 3 are partial flow diagrams of methods according to embodiments of the invention;
FIG. 4 is a schematic illustration of a flow of information for predicting the outcome of a sporting event according to one embodiment of the present invention;
fig. 5 and 6 are block diagrams of a robot according to an embodiment of the present invention.
Detailed Description
The following detailed description will be provided for the embodiments of the present invention with reference to the accompanying drawings and examples, so that the practitioner of the present invention can fully understand how to apply the technical means to solve the technical problems, achieve the technical effects, and implement the present invention according to the implementation procedures. It should be noted that, as long as there is no conflict, the embodiments and the features of the embodiments of the present invention may be combined with each other, and the technical solutions formed are within the scope of the present invention.
In the prior art, one of the most common human-computer interaction scenarios is that of a robot and a user chatting. However, in the existing human-computer interaction scenario, the chat between the robot and the user is usually initiated by the user and is dominated by the user, and the robot can only passively respond to the questions of the user in a targeted manner. This makes the whole chat process quite monotonous, and when the user obtains the answer that the user wants to know, the chat process is immediately stopped, and even in many cases, the user gives up the question after trying to ask the question once or twice, and the interaction is terminated unilaterally.
Therefore, in order to improve the interest of the robot in chatting with the user, improve the chatting willingness of the user and enhance the user experience of the robot, the invention provides an interactive output method for the robot.
In the daily interactive scene between people, one of the keys for deciding the strength of the willingness of the two parties to talk is whether the current content of the talk matches the interests of the two parties. If both parties are interested in the current conversation content, the current conversation can be easily continued. The analysis is extended to a human-computer interaction scene, and the conversation interest of the user is only required to be improved as far as possible because the conversation interest of the robot is not required to be considered. Then, one of the key points to improving the user's willingness to chat is to keep the current topic content around the content the user is interested in.
Furthermore, in the human-computer interaction process, if the robot only performs simple information pushing on a specific topic, the whole interaction process is tedious (completely becomes an information query process, and cannot show the interaction feeling). Therefore, in order to enhance the interest of the interaction, the robot needs to process the information related to the topic, and generate and output the interactive content conforming to the habit of human conversation (and, as far as possible, conforming to the current habit of the user). This requires the robot to have the capability of processing and analyzing information. However, the processing and analysis modes of different types of information are different, and therefore, the robot cannot have the processing and analysis capability of all types of information. Therefore, in order to ensure that the current topic is the topic that the robot can analyze and process, the robot needs to make certain control guidance for selecting the topic, and guide the user to talk about the topic that the robot is familiar with and the user is also interested in.
Further, in the course of people-to-people conversations, sporting events are often referred to as conversational topics (most users are interested in certain specific sporting events), and topics related to sporting events have a high probability of being of interest to the users. Therefore, in an embodiment of the present invention, the robot is provided with the analysis processing capability of the sports event related topic in advance, and the current topic is guided to the sports event as much as possible in the human-computer interaction process.
Further, in a sports event, the user's attention is often focused on the results of the sports event in a normal state. Thus, there is a significant chance that the user will be focused on (matching the user's points of interest) if the discussion is directed to the results of a sporting event. In particular, there is a great chance that the result prediction will be made for a sporting event that has not yet ended. Therefore, in one embodiment of the invention, the sports events in which the user is interested are taken as topics, and human-computer interaction is performed around the prediction results of the sports events and the user, so that the interest degree of the user in the human-computer interaction is ensured.
The detailed flow of a method according to an embodiment of the invention is described in detail below based on the accompanying drawings, the steps shown in the flow chart of which can be executed in a computer system containing instructions such as a set of computer executable instructions. Although a logical order of steps is illustrated in the flowcharts, in some cases, the steps illustrated or described may be performed in an order different than presented herein.
As shown in fig. 1, in an embodiment, a robot receives and parses multimodal input data during a human-computer interaction process (step S100), and determines whether there is a sporting event (a sporting event in which a user is interested) that can be a topic currently (step S110); but when there is no sports event which can be used as a topic, human-computer interaction is carried out based on other interaction strategies (step S101), and new multi-modal input data of the mobile phone is continued (returning to step S100).
When there is a sports event that can be a topic, it is determined whether the sports event is ended (is not yet started, has started to be in progress but not yet ended, or is already ended) (step S120). If the sporting event has ended, the result of the sporting event is directly acquired (step S141), and multimodal interaction data is generated and output based on the result of the sporting event. That is, with the sporting event as a topic, human-computer interaction is developed around the results of the sporting event with the user.
Acquiring multi-dimensional sample data related to the sporting event when the sporting event is not over (is ongoing or has not started) (step S131); analyzing the sample data, and predicting the prediction result of the sports event by integrating the multi-dimensional analysis result of the sample data (step S132); finally, the user interacts with the sports event as a topic (step S133), wherein the prediction result obtained in step S132 is multi-modal output to the user. That is, with the sporting event as a topic, human-computer interaction is developed with the user around the event result predicted by the robot.
According to the method, the interactive topics are expanded around the sports events in which the user is interested, and the attention of the user is further attracted through the prediction result of the events, so that the interestingness of man-machine interaction is greatly improved, and the man-machine interaction willingness of the user is enhanced.
In the step shown in fig. 1, one of the key points is to determine whether there is currently a sports event that can be a topic (step S110). In order to ensure that the sports event as the topic determined in step S110 can increase the human-computer interaction will of the user certainly, the sports event as the topic needs to satisfy two conditions:
(1) the current user has some interest in the sporting event, and if the user is not interested, the user's willingness to interact with the sporting event cannot be increased by the communication around the sporting event.
(2) The current interaction scenario is suitable for discussing the sporting event, and if the current interaction scenario is not suitable for discussing the sporting event (for example, the user is concentrating on discussing other information), the normal communication process can be broken through when the user communicates around the sporting event, so that the human-computer interaction experience is reduced, and even if the user has a certain interest in the sporting event, the user's interaction will not be improved.
Based on the above analysis, in an embodiment of the present invention, in step S110, it is determined whether there is currently a sporting event that can be a topic by analyzing the current interactive content. Specifically, when the output content of the user contains a certain sporting event during the human-computer interaction, firstly, it may be stated that the user is interested in the sporting event (otherwise, the sporting event is not mentioned in the interactive content), and secondly, the current interactive environment may discuss the sporting event (if the interactive environment is not suitable for discussing the sporting event, the user does not mention the sporting event in the interactive content). Thus, the sporting event may be topical at this time.
As shown in FIG. 2, in one embodiment, user output is obtained (step S200), and it is determined whether the user output content includes a sporting event (step S210). If not, it is determined that there is no sports event currently available as a topic (step S212). If so, it is determined that there is currently a sports event that can be a topic (step S211) (the user outputs the sports event contained in the content as a topic).
Further, in some practical interactive scenarios, a user may not include a sporting event of interest in his output, but rather may present his attention to the sporting event through user behavior. Thus, in one embodiment, the user's user behavior is detected and analyzed, and when the user behavior indicates that the user is focusing on a sporting event, then first it may be stated that the user is interested in the sporting event (or otherwise does not focus on the sporting event), and second, the current interaction environment may discuss the sporting event (the act of focusing on the sporting event does not interfere with other acts of the user, as the user would not perform the act of focusing on the sporting event if so). Thus, the sporting event may be topical at this time.
As shown in FIG. 3, in one embodiment, user behavior is detected and analyzed (step S300) to determine whether the user is interested in the sporting event (step S310). If there is no attention, it is judged that there is no sports event that can be a topic currently (step S312). If focused on, it is determined that there is currently a sports event that can be a topic (step S211) (the sports event focused on by the user is a topic).
The embodiments shown in fig. 2 and 3 respectively determine whether there is a sporting event that can be a topic from two perspectives. Further, in an embodiment of the present invention, a manner of combining the two angles shown in fig. 2 and fig. 3 is adopted to determine whether there is a sports event that can be regarded as a topic currently. In the human-computer interaction process, whether the sports events are contained in the output content of the user is detected, and whether the user behaviors pay attention to the sports events is detected. If a sporting event is detected from either of the two angles, it is determined that there is a sporting event that can be a topic.
Further, whether the user output content contains the sports event or not is judged under the human-computer interaction scene. In some applications, the user is not currently interacting with the robot (the user is performing other actions). In such an application, the robot mainly analyzes the user behavior to determine whether the user is interested in the sporting event. That is, in a non-human-computer interaction state, the robot collects (spectators) user behaviors and determines whether the user is paying attention to the sporting event.
Furthermore, in a non-human-computer interaction state, if the robot judges that the user pays attention to a certain sports event, human-computer interaction can be actively initiated to the user by taking the sports event as a topic.
In the embodiment shown in fig. 1, to further increase the user's interactive interest, the robot makes a result prediction for the currently incomplete sporting event and develops an interaction with the user based on the predicted result. In this process, one of the key points is that a user must be provided with a relatively reliable (convincing) prediction result, and if the prediction result is too weak, the interaction will be reduced. In an embodiment of the present invention, in order to ensure the reliability of the prediction result, a big data analysis mode is adopted to perform result prediction.
In one embodiment, the robot acquires multi-dimensional sample data related to the sporting event and performs outcome prediction through analysis of the sample data. Specifically, the sample data acquired by the robot includes search data (e.g., google trend, hundredth index, etc.), social data (e.g., microblog, twitter, etc.), historical statistics data of related events (e.g., latest score ranking, historical seizure information, etc.), and user data (man-machine conversation data, etc.).
Further, in one embodiment, the search data, historical statistics, and social data are system background statistics, and the user data includes user feedback data for active questions, user behavior data for online activities, and user historical interaction records.
Specifically, in one embodiment, user data is obtained through three forms of "active questioning, user question gathering and online gaming". Active questioning mainly asks users about their fragrance preference in a form similar to questionnaires. The user problem collection mainly refers to that the intelligent robot obtains certain characteristics through analysis of the user chat logs. And online gaming mainly refers to mining of attention information through the form of a game.
Furthermore, after sample data are collected, the robot extracts features from the data by using a heuristic algorithm, simultaneously divides the data into a training set, a verification set and a test set, obtains a better prediction model through continuous training models and iteration models, and then obtains a prediction result based on various newly collected data.
The information flow diagram shown in fig. 4. The big data prediction system collects user data of users (A, B, C) through a human-computer interaction layer, and collects historical statistics, search data and social data from the background. And then the big data prediction system feeds back the generated prediction result to the user through a man-machine interaction layer.
Further, typically, for a sporting event, the user is not simply interested in that sporting event. The user also has some detailed preference features for sporting events. For example, for a competitive sports event, the user may prefer a certain party/a certain team/a certain player (e.g., a football game, the user may pay a significant attention to a certain team). Therefore, to further enhance the user's interactive willingness, in one embodiment, the bot also references user preferences when interactively outputting around the sporting event in which the user is interested. For example, if the user is interested in a football game and the user is biased toward team a, then the robot will focus around team a when the football game is being themed.
To obtain user preferences, in one embodiment, a robot collects multi-modal behaviors of a user for a sporting event; analyzing the multi-modal behavior to obtain and save user preferences corresponding to the sporting event. Here, the user preferences are obtained and saved in advance (further, the robot may obtain and save user preferences of a plurality of users for a plurality of different sporting events). When human-computer interaction around a sporting event is required, the robot extracts corresponding user preferences from the sporting event (and the current user) as topics. Furthermore, the prediction result of the sports event is predicted by combining the preference of the user; and interacting with the user on the topic of the sporting event in conjunction with the user preferences.
Further, the so-called prediction result, which is an estimate of what may happen in the future, is not necessarily a completely determined result. In order to avoid understanding of the deviation by the user and reflect the speciality and reliability of the prediction result, in one embodiment of the invention, a plurality of different prediction results of the sports event are obtained in the process of obtaining the prediction results, and each prediction result corresponds to a corresponding occurrence probability; correspondingly, when the prediction result is output to the user, a plurality of different prediction results of the sports event, the occurrence probability corresponding to each prediction result, the prediction basis and the information source are output to the user in a multi-mode. Therefore, the user can know the prediction source of the prediction result, and the specialty and the reliability of the result prediction are embodied, so that the interaction willingness of the user is improved. In addition, the output of a large amount of related data can also increase auxiliary topics surrounding the sports event, and the further interaction willingness of the user is greatly improved.
In summary, the method of the present invention selects a sporting event as a topic entry point to interact with the user by predicting the outcome of the sporting event. Compared with the prior art, the method can greatly improve the interaction willingness of the user and improve the user experience of man-machine interaction.
Based on the method, the invention also provides an intelligent robot. As shown in fig. 5, in one embodiment, the robot includes:
a current topic parsing module 510 configured to receive and parse the multi-modal input data, and determine whether there is a sports event that can be a topic currently;
a sporting event progress analysis module 520 configured to determine whether a sporting event that may be topical is not ongoing or ongoing but not yet finished when there is a sporting event;
a sporting event data collection module 530 configured to obtain multi-dimensional sample data related to a sporting event when the sporting event is not yet in progress or is in progress but is not yet over;
an event result prediction module 540 configured to analyze the sample data and predict a prediction result of the sports event by integrating a multi-dimensional analysis result of the sample data;
an event result acquisition module 560 configured to acquire an actual result of the sporting event when the sporting event has ended;
an interaction output module 550 configured to interact with the user on the topic of the sporting event, wherein the predicted or actual result is multimodal output to the user.
Further, in an embodiment, the current topic parsing module includes an interactive content parsing unit, and the interactive content parsing unit is configured to determine that a sports event can be a topic when the output content of the user includes the sports event in the human-computer interaction process.
Further, in an embodiment, the current topic analysis module includes a user behavior analysis unit, and the user behavior analysis unit is configured to detect and analyze a user behavior of the user, and determine that the sports event can be a topic when the user behavior indicates that the user is paying attention to the sports event.
Further, in an embodiment, the robot further includes a user preference collecting module, and the user preference collecting unit is configured to collect multi-modal behaviors of the user for the sporting event, analyze the multi-modal behaviors, and obtain and store user preferences corresponding to the sporting event; when human-computer interaction around a sporting event is required, corresponding user preferences are extracted according to the sporting event as a topic.
As shown in fig. 6, the current topic parsing module 610 is configured to receive and parse multimodal input data, and determine whether there is currently a sporting event that can be a topic;
the sporting event progress analysis module 620 is configured to determine whether a sporting event that may be topical is not ongoing or ongoing but not yet finished when there is a sporting event;
the sporting event data collection module 630 is configured to obtain multi-dimensional sample data related to a sporting event when the sporting event is not ongoing or ongoing but not yet finished;
the user preference collection module 670 is configured to obtain and store user preferences for the corresponding sporting events, extract the corresponding user preferences from the sporting events as topics
The event result prediction module 640 is configured to analyze the sample data and predict a prediction result of the sports event by combining a multi-dimensional analysis result of the user preference comprehensive sample data;
the event result acquisition module 660 is configured to acquire the actual results of the sporting event when the sporting event has ended;
the interaction output module 650 is configured to interact with the user on the topic of a sporting event in conjunction with the user preferences, wherein predicted results or actual results are multimodal output to the user.
Although the embodiments of the present invention have been described above, the above description is only for the convenience of understanding the present invention, and is not intended to limit the present invention. There are various other embodiments of the method of the present invention. Various corresponding changes or modifications may be made by those skilled in the art without departing from the spirit of the invention, and these corresponding changes or modifications are intended to fall within the scope of the appended claims.
Claims (9)
1. An interactive output method for a robot, the method comprising:
receiving and analyzing multi-modal input data, and judging whether a sports event which can be used as a topic exists at present according to user input content, user behaviors and an interactive scene obtained by analysis;
determining whether a sporting event has not been conducted or is being conducted but has not ended when there is a sporting event that can be a topic;
obtaining multi-dimensional sample data related to the sporting event when the sporting event is not ongoing or ongoing but not yet finished; acquiring multi-dimensional sample data related to the sports event, wherein the acquiring of the multi-dimensional sample data comprises acquiring search data, social data, historical statistical data of related events and user data, and the user data comprises user feedback data for active questioning, user behavior data for online activities and historical user interaction records;
analyzing the sample data, and predicting the prediction result of the sports event by integrating the multi-dimensional analysis result of the sample data; in the process of predicting the prediction result of the sports event, acquiring a plurality of different prediction results of the sports event, wherein each prediction result corresponds to a corresponding occurrence probability;
and interacting with a user by taking the sports event as a topic, wherein the prediction result is output to the user in a multi-mode manner.
2. The method of claim 1, wherein determining whether there is a sporting event that can be a topic currently exists, wherein determining that a first sporting event can be a topic when the output content of the user includes the first sporting event during human-computer interaction.
3. The method of claim 1, wherein determining whether there is a sporting event that can be a topic currently exists, wherein detecting and analyzing the user behavior of the user determines that a second sporting event can be a topic when the user behavior indicates that the user is focusing on the second sporting event.
4. The method of claim 1, wherein multi-dimensional sample data related to the sporting event is obtained, wherein the sample data contains user preferences, the method further comprising:
capturing multi-modal behavior of the user for the sporting event;
analyzing the multi-modal behavior to obtain and save user preferences corresponding to the sporting event;
extracting the corresponding user preferences from the sporting event as a topic;
predicting a predicted outcome of the sporting event in conjunction with the user preference;
interacting with a user on the topic of the sporting event in conjunction with the user preferences.
5. The method of claim 1, wherein:
and outputting the prediction result to the user, wherein the plurality of different prediction results of the sports event, the occurrence probability corresponding to each prediction result, the prediction basis and the information source are output to the user in a multi-mode manner.
6. An intelligent robot, characterized in that the robot comprises:
the current topic analyzing module is configured to receive and analyze the multi-modal input data, and judge whether a sports event which can be used as a topic exists at present according to the user input content, the user behavior and the interactive scene obtained by analysis;
a sporting event progress analysis module configured to determine whether a sporting event that can be a topic is not ongoing or ongoing but not yet ended when there is the sporting event;
a sporting event data collection module configured to obtain multi-dimensional sample data relating to the sporting event when the sporting event is not yet in progress or is in progress but is not yet over; acquiring multi-dimensional sample data related to the sports event, wherein the acquiring of the multi-dimensional sample data comprises acquiring search data, social data, historical statistical data of related events and user data, and the user data comprises user feedback data for active questioning, user behavior data for online activities and historical user interaction records;
an event result prediction module configured to analyze the sample data and predict a prediction result of the sporting event by integrating a multi-dimensional analysis result of the sample data; in the process of predicting the prediction result of the sports event, acquiring a plurality of different prediction results of the sports event, wherein each prediction result corresponds to a corresponding occurrence probability;
an interaction output module configured to interact with a user on the topic of the sporting event, wherein the prediction result is multimodal output to the user.
7. The robot of claim 6, wherein the current topic parsing module comprises an interactive content parsing unit configured to determine that a first sporting event is possible as a topic when the output content of the user comprises the first sporting event during the human-computer interaction.
8. The robot of claim 6, wherein the current topic analysis module comprises a user behavior analysis unit configured to detect and analyze a user behavior of the user, and determine that a second athletic event is possible as a topic when the user behavior indicates that the user is focusing on the second athletic event.
9. The robot of claim 6, further comprising user data further comprising a user preference collection module configured to:
acquiring multi-modal behaviors of the user for the sports event, analyzing the multi-modal behaviors, and acquiring and storing user preferences corresponding to the sports event;
extracting the corresponding user preferences from the sporting event as a topic.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611146822.6A CN106843461B (en) | 2016-12-13 | 2016-12-13 | Interactive output method for robot and robot |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611146822.6A CN106843461B (en) | 2016-12-13 | 2016-12-13 | Interactive output method for robot and robot |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106843461A CN106843461A (en) | 2017-06-13 |
| CN106843461B true CN106843461B (en) | 2020-06-26 |
Family
ID=59139817
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611146822.6A Active CN106843461B (en) | 2016-12-13 | 2016-12-13 | Interactive output method for robot and robot |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106843461B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107562863A (en) * | 2017-08-30 | 2018-01-09 | 深圳狗尾草智能科技有限公司 | Chat robots reply automatic generation method and system |
| US11577145B2 (en) * | 2018-01-21 | 2023-02-14 | Stats Llc | Method and system for interactive, interpretable, and improved match and player performance predictions in team sports |
| CN108595420A (en) * | 2018-04-13 | 2018-09-28 | 畅敬佩 | A kind of method and system of optimization human-computer interaction |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001188782A (en) * | 1999-12-28 | 2001-07-10 | Sony Corp | Device and method for processing information and recording medium |
| CN104200090B (en) * | 2014-08-27 | 2017-07-14 | 百度在线网络技术（北京）有限公司 | Forecasting Methodology and device based on multi-source heterogeneous data |
| CN105138671A (en) * | 2015-09-07 | 2015-12-09 | 百度在线网络技术（北京）有限公司 | Human-computer interaction guiding method and device based on artificial intelligence |
| CN105798918B (en) * | 2016-04-29 | 2018-08-21 | 北京光年无限科技有限公司 | A kind of exchange method and device towards intelligent robot |
| CN106200962A (en) * | 2016-07-08 | 2016-12-07 | 北京光年无限科技有限公司 | Exchange method and system towards intelligent robot |
-
2016
- 2016-12-13 CN CN201611146822.6A patent/CN106843461B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN106843461A (en) | 2017-06-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11810576B2 (en) | Personalization of experiences with digital assistants in communal settings through voice and query processing | |
| CN109977208B (en) | Dialogue system integrating FAQ (failure-based query language) and task and active guidance | |
| CN106951468B (en) | Talk with generation method and device | |
| CN112365894B (en) | AI-based composite voice interaction method and device and computer equipment | |
| CN107797984B (en) | Intelligent interaction method, equipment and storage medium | |
| CN110557659B (en) | Video recommendation method and device, server and storage medium | |
| CN110830812B (en) | Similar anchor classification model training method, anchor recommendation method and related device | |
| US20080281444A1 (en) | Predictive modeling system and method for fantasy sports | |
| CN106843461B (en) | Interactive output method for robot and robot | |
| CN110503954B (en) | Voice skill starting method, device, equipment and storage medium | |
| CN109873752B (en) | Robot interaction method, device, storage medium and equipment in communication group | |
| US20230119860A1 (en) | Matching system, matching method, and matching program | |
| CN112927692B (en) | Automatic language interaction method, device, equipment and medium | |
| CN111581521A (en) | Group member recommendation method, device, server, storage medium and system | |
| CN110347797A (en) | Method for detecting, system, equipment and the storage medium of text information | |
| CN111611369B (en) | Interaction method and related device based on artificial intelligence | |
| CN113413590B (en) | Information verification method, device, computer equipment and storage medium | |
| CN115994266A (en) | Resource recommendation method, device, electronic equipment and storage medium | |
| CN109313638B (en) | Application recommendation | |
| CN106462253A (en) | Scoring method and scoring system based on interaction information | |
| CN111522722A (en) | Data analysis method, electronic equipment and storage medium | |
| CN116610790B (en) | Method, device, equipment and medium for acquiring response data | |
| CN117593774A (en) | Vehicle-mounted VPA image generation method, system, electronic equipment and storage medium | |
| CN114422812A (en) | Live broadcast method and device, electronic equipment, storage medium and product | |
| Ghosh et al. | A Proposed Cognitive Framework Model for a Student Support Voice based Chatbot using XAI |
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 |