TWI688873B - Enviromental information question and answer system and method - Google Patents

Abstract

This disclosure provides an environmental information question and answer system and method including the following steps. A message interface generates and sends a language input command to a processor according to a received language message, wherein the language input command includes at least one of a target environment data and an auxiliary environmental data. The processor selectively generates the target environment data or the auxiliary environmental data not included in the language input command, and the semantic analysis component analyzes the target environment data and the auxiliary environmental data. The processor analyzes the strongest association between the target environment data and the auxiliary environmental data according to a plurality of data points of the environmental knowledge base. The processor generates the query command according to the strongest association, and generates a response command according to the query command and the environmental knowledge base. The processor sends the response command to the message interface, and the message interface received the response command shows the response message.

Description

Environmental information question answering system and method

The invention relates to an environmental information question answering system and method, in particular to an environmental intelligence question answering system and method based on artificial intelligence.

With the development of artificial intelligence and communication software, the use of artificial intelligence robots on communication software to perform simple responses or query data has gradually become a trend. Users can send messages to the robot through communication software or other interfaces. The robot analyzes the keywords contained in the message content and searches the database based on the keywords to provide the information the user needs.

However, when the above-mentioned device is used in disaster prevention, because the meteorological data is too large, the robot needs to spend more time or hardware resources when searching for the data; in this case, when the message sent by the user is not complete ( For example, the lack of time, location or clear weather information in the message), the robot may spend more time searching, and the result found is most likely not the information that the user actually wants. This situation not only causes inconvenience to the user in the use process (the user may fail to provide complete information in the first place due to insufficient understanding of the operation of the robot), but may also cause the user to fail to provide complete information Users cannot obtain the correct meteorological information they need, so they cannot predict and evaluate natural disasters in real time, affecting the effectiveness of disaster prevention.

Therefore, there is still a need for an environmental information question answering system and method to improve the above problems.

The present invention is to provide an environmental information question answering system and method. When the information sent by the user is not complete, the system and method can respond to the user's questions according to different weather conditions, so as to reduce the time and time spent by the robot in searching data Hardware resources.

The invention provides a question and answer method for environmental information, including: generating and transmitting a language input command to a processor according to the received language message using the message sending and receiving interface, wherein the language input command includes a target environment data and an auxiliary environment data At least one of; receiving the at least one of the target environment data and the auxiliary environment data included in the language input command by a semantic analysis component of the processor, and selectively generating the language input command by the processor The target environmental data or the auxiliary environmental data that are not included, and analyze the target environmental data and the auxiliary environmental data with the semantic analysis element; the processor analyzes the target environmental data based on multiple data points of an environmental knowledge base An optimal relationship with the auxiliary environment data; the processor generates a query command based on the optimal relationship, and generates a response command based on the query command and the environmental knowledge base; the processor transmits the Responding to the message sending and receiving interface; and presenting the reply message with the message receiving and sending interface receiving the responding command.

The invention provides a question and answer method for environmental information, including: a message sending and receiving interface for generating a language input command and receiving and presenting a response message according to the received language message, wherein the language input command includes a target environment data and a At least one of the auxiliary environmental data; a processor electrically connected to the message transceiving interface and including a semantic analysis component, the processor is used to receive the language input command and selectively generate the language input command not included The target environmental data or the auxiliary environmental data, and analyzing the target environmental data and the auxiliary environmental data with the semantic analysis element; and an environmental knowledge base, interconnected with the processor, and including multiple data points; wherein the processing The device analyzes an optimal correlation between the target environmental data and the auxiliary environmental data according to the data points of the environmental knowledge base, and generates a query command according to the optimal correlation, and according to the query command and the The environmental knowledge base generates and sends the response message to the message receiving and sending interface.

The present invention is to provide an environmental information question answering system and method. When the information transmitted by the user is not complete, the system and method can respond to the user's questions according to different weather conditions, effectively reducing the time spent by the robot searching for data And hardware resources, so that users can more accurately predict and evaluate natural disasters according to different weather conditions.

The above description of the disclosure and the following description of the embodiments are used to demonstrate and explain the spirit and principle of the present invention, and provide a further explanation of the scope of the patent application of the present invention.

The following describes in detail the detailed features and advantages of the present invention in the embodiments. The content is sufficient for any person skilled in the relevant art to understand and implement the technical content of the present invention, and according to the contents disclosed in this specification, the scope of patent application and the drawings Anyone skilled in the relevant art can easily understand the purpose and advantages of the present invention. The following examples further illustrate the views of the present invention in detail, but do not limit the scope of the present invention in any way.

Please refer to FIG. 1, which is a structural diagram of an environmental information question answering system 1 according to an embodiment of the present invention. As shown in FIG. 1, the environmental information question and answer system 1 includes a message sending and receiving interface 11, a processor 13 and an environmental knowledge base 15. The message transceiving interface 11 may be an interface having a function of receiving language messages. The message transceiving interface may generate language input commands according to the received language messages, and receive response messages during the operation of the environmental information question answering system 1, and send the response messages to Present to the user in the form of text or speech. For example, the message sending and receiving interface 11 may be a communication software or a web page that can receive or generate text messages, or an acoustic-electric conversion component (such as a microphone and a speaker) that can send and receive voice messages. It should be noted that since the environmental information question answering system 1 of the present invention is applied to environmental inquiries and subsequent disaster assessment and disaster prevention decisions, language input commands may include target environmental data and auxiliary environmental data. Specifically, the above target environmental data may be data related to water conservancy, meteorology, and geology, or other laws and regulations related to natural disasters, such as the distribution of pumps nationwide, rainfall, temperature, earthquake scale, or other related disaster prevention. The provisions of laws and regulations, and the above-mentioned auxiliary environmental data may be information such as the time and place required to query the target environmental data. In other words, if the information provided by the user is complete, the language input command includes the target environment data and auxiliary environment data; however, when the information provided by the user is not complete, the language input command only includes the target environment data and auxiliary One of the environmental information.

The processor 13 may be a central processing unit (central processing unit, CPU) or any element with a computing function, and the processor 13 includes a semantic analysis element 131 and is electrically connected to the message transceiving interface 11. During the operation of the environmental information question answering system 1, the processor 13 can receive language input commands from the messaging interface 11 and selectively generate language input commands when the language input commands do not include both target environment data and auxiliary environment data The target environmental data or auxiliary environmental data not included, and the semantic analysis component 131 analyzes the target environmental data and auxiliary environmental data.

The environmental knowledge base 15 can be any physical hard drive with storage function and electrically connected to the processor 13 or a cloud hard drive in communication with the processor 13 and contains multiple data points and multiple data paths. The aforementioned target environment data and auxiliary environment data are associated with the data points, and the data points are connected to each other through the data paths. During the operation of the environmental information question answering system 1, the environmental knowledge base 15 is used to provide the above-mentioned data points to the processor 13, so that the processor 13 can analyze the most between the target environmental data and the auxiliary environmental data based on the data points Optimal relevance, and generate a query command according to the best relevance, then search the data stored in the environmental knowledge base 15 according to the query command to generate a response message, and send the response message to the message sending and receiving interface 11.

As mentioned above, in order to efficiently find the data required by the user from the environmental knowledge base 15, the processor 13 first calculates the best between the target environmental data and the auxiliary environmental data using the "shortest path algorithm" Relevance, and then convert the best relevance into a series of codes as the aforementioned query command. Therefore, the processor 13 can directly obtain the information required by the user from the environmental knowledge base 15 according to the query instruction. In detail, the environmental knowledge base 15 includes multiple data points and multiple data paths connecting the data points, and forms a "knowledge model"; the processor 13 stores the data points and data paths stored in the environmental knowledge base 15 Treated as different nodes and connections, and take the auxiliary environment data provided by the user as the starting point, and the target environment data queried by the user as the end point, find the two most relevant data points from the above data points (generally available It is defined as a search path where the total number or sum of data paths is the minimum value), and this path is defined as the above-mentioned "best relevance". After finding the best relevance, the processor 13 may convert the search path associated with the best relevance into a specific program instruction (that is, the aforementioned "query instruction"), and obtain Program instructions, enter the environmental knowledge base 15 to find out the environmental data associated with the path.

To specifically describe the operation flow of the environmental information question answering system 1, please refer to FIG. 2, which is a flowchart of an environmental information question answering method according to an embodiment of the present invention. When a user enters a text command or a voice command including a language message through the messaging interface 11, please refer to step S11: the messaging interface 11 generates and sends a language input command to the processor 13 according to the received language message. When the processor 13 receives the language input command sent by the message transceiving interface 11, please refer to step S13: the semantic analysis component 131 of the processor 13 receives at least one of the target environment data and the auxiliary environment data included in the language input command; wherein the target Environmental data is meteorological data that the user wants to query, such as rainfall or temperature, and auxiliary environmental data is the time or place where the user wants to query the weather data. In addition, the semantic analysis component 131 can analyze the target environment data and the auxiliary environment data included in the input command, so that the processor 13 can determine whether the language input command includes both the target environment data and the auxiliary environment data. When the language input command does not include the target environment data and the auxiliary environment data, please refer to step S15: the processor 13 selectively generates target environment data or auxiliary environment data not included in the language input command, and analyzes the target with the semantic analysis component 131 Environmental data and auxiliary environmental data. For example, when the user asks "How much rainfall is Taipei?", the environmental information question answering system 1 first analyzes the above-mentioned language input command with the semantic analysis component 131: the target environmental data is "rainfall" and the auxiliary environmental data is "Taipei", The processor 13 further determines that the language input command is still missing another auxiliary environment data "time", and generates a time data (for example, within one hour) to supplement the information missing from the language input command.

As mentioned in the previous paragraph, when the language input command includes both the target environment data and the auxiliary environment data, please continue to S17: the processor 13 analyzes the best between the target environment data and the auxiliary environment data based on multiple data points of the environmental knowledge base 15 Relevance. To put it simply, when the user asks "How much rainfall is Taipei?", the environmental knowledge base 15 may contain multiple data points related to "Taipei" and multiple data points related to "Rainfall", and the processor 13 The two data points with the shortest search time can be regarded as the best relevance. To continue, please refer to step S19: the processor 13 generates a query command based on the best relevance, and generates a response command based on the query command and the environmental knowledge base 15; wherein the query command can be composed of program code so that the processor 13 can retrieve the environment from the query command The knowledge base 15 searches for the data required by the user, and generates a response command according to the search result. After the processor 13 generates a response command, please refer to step S21: the processor 13 transmits the response command to the message transceiving interface 11, and step S23: the message transceiving interface 11 receives and presents the response message for the user to read or listen to environmental information Q&A Weather information provided by System 1.

To explain step S15 and step S17 of FIG. 2 in more detail, please refer to FIG. 3. FIG. 3 is a detailed flowchart of an environmental information question answering method according to an embodiment of the invention. As mentioned above, language input commands may lack target environment data or auxiliary environment data due to incomplete information provided by users. Please refer to step S151: when the processor 13 determines that the language input command does not include auxiliary environment data, the processor 13 generates auxiliary environment data using preset auxiliary conditions or real-time environmental conditions; wherein the preset auxiliary conditions are stored in the processor 13 in advance, real-time The environmental conditions are selectively stored in the environmental knowledge base 15. When the processor 13 determines that the environmental knowledge base 15 does not have real-time environmental conditions, it generates auxiliary environmental data with preset auxiliary conditions. Specifically, the preset auxiliary condition may be a preset time (for example: within the last hour) or a preset location (for example: all of Taiwan). When the user only asks "how much rainfall?", the processor 13 It can be interpreted as "how much rainfall has the entire Taiwan had in the last hour?". On the other hand, the immediate environmental conditions may be special weather warnings issued by government agencies, such as heavy rain warnings. During the special weather warning period, there will be a large number of users with disaster prevention decision needs to query the weather conditions; therefore, when the user asks "How much rainfall in Taipei?" during the heavy rain warning period, the processor 13 can automatically provide Taipei within three hours Rainfall, so that users can make disaster assessments based on valid data. In addition, please refer to step S153: when the processor 13 determines that the language input command does not include the target environmental data, the processor 13 generates the target environmental data based on the preset weather data. To put it simply, the target environment data can be the most inquired meteorological data; for example, when the user asks "How is the weather in Taipei today?" and the language input command lacks the target environment data, the processor 13 can interpret it as "Today's Taipei What is the temperature?", and search for relevant information from the Environmental Knowledge Base 15.

Please continue to refer to Figure 3. When the language input command already includes the target environment data and the auxiliary environment data, please refer to step S171: the processor 13 generates multiple associations between the target environment data and the auxiliary environment data based on multiple data points of the environmental knowledge base 15; The data points are connected to each other by multiple data paths, and the target environmental data and the auxiliary environmental data are associated with the data points. After the processor 13 generates multiple correlations between the target environmental data and the auxiliary environmental data, please proceed to step S173: the processor 13 calculates the sum of the multiple data paths of the correlations, and takes the sum as the minimum value of the Relevance as the best relevance. Simply put, when the sum of the data paths between the two data points is the minimum, it means that the two data points have the strongest correlation, and the time required for the processor 13 to search for the data is also the shortest; therefore, By step S173, the environmental information question answering system 1 can efficiently provide the meteorological data required by the user.

In addition, it is worth mentioning that the information provided by this environmental information question and answer system 1 is not limited to meteorological data. Any information related to "natural environment", such as: water conservancy and disaster related regulations, national distribution of pumps, etc. The information can be interrogated through the environmental information question and answer system 1. Therefore, the aforementioned target environmental data and auxiliary environmental data are not limited to the meteorological data exemplified in this disclosure, and the data points stored in the environmental knowledge base 15 are in addition to energy and weather. The data is related, and it can also be related to the provisions of laws and regulations related to water conservancy and disasters, the distribution status of the national pumping machines or other information, and the invention is not limited to this.

In summary, the present invention is to provide an environmental information question answering system 1 and method. When the information transmitted by the user is not complete, the system and method can respond to the user's questions according to different weather conditions, effectively reducing the robot The time and hardware resources spent searching for data allow users to more accurately predict and assess natural disasters based on different weather conditions.

Although the present invention is disclosed as the foregoing embodiments, it is not intended to limit the present invention. Without departing from the spirit and scope of the present invention, all modifications and retouching are within the scope of patent protection of the present invention. For the protection scope defined by the present invention, please refer to the attached patent application scope.

1: Environmental information question and answer system 11: messaging interface 13: processor 15: Environmental Knowledge Base 131: Semantic analysis components

FIG. 1 is a structural diagram of an environmental information question answering system according to an embodiment of the present invention. 2 is a flowchart of an environmental information question answering method according to an embodiment of the invention. FIG. 3 is a detailed flowchart of an environmental information question answering method according to an embodiment of the invention.

Claims (9)

An environmental information question and answer method, comprising: generating and transmitting a language input command to a processor according to a received language message with a message sending and receiving interface, wherein the language input command includes at least one of target environmental data and auxiliary environmental data A semantic analysis component of the processor to receive the at least one of the target environment data and the auxiliary environment data included in the language input command, and selectively generate the language input command not included in the processor by the processor The target environmental data or the auxiliary environmental data, and analyzing the target environmental data and the auxiliary environmental data with the semantic analysis element; using the processor to analyze the target environmental data and the auxiliary according to multiple data points of an environmental knowledge base An optimal relationship between environmental data; the processor generates a search path based on the optimal relationship, and converts the search path into a query command, and generates a response based on the query command and the environmental knowledge base Command; the processor sends the response command to the message transceiving interface; and the message transceiving interface receiving the response command presents a response message. The environmental information question and answer method according to claim 1, wherein when the processor determines that the language input command does not include the auxiliary environment data, the processor selectively generates the target environment data not included in the language input command or The auxiliary environmental data further includes: the processor generates the auxiliary environmental data with a preset auxiliary condition or a real-time environmental condition; The preset auxiliary condition is stored in the processor in advance, and the preset auxiliary condition includes at least one of a preset time condition or a preset location condition, and the real-time environmental condition is selectively stored in The environmental knowledge base, and the real-time environmental conditions include a special meteorological condition issued by a government agency, and when the processor determines that the environmental knowledge base does not have the real-time environmental conditions, the auxiliary environmental data is generated with the preset auxiliary conditions . The environmental information question and answer method according to claim 1, wherein when the processor determines that the language input command does not include the target environment data, the processor selectively generates the target environment data not included in the language input command or The auxiliary environmental data further includes: the processor generates the target environmental data with a preset meteorological data. The environmental information question and answer method according to claim 1, wherein the data points are connected to each other by a plurality of data paths, and the data points represent storage locations of the target environmental data and the auxiliary environmental data in the environmental knowledge base , When the processor analyzes the best correlation between the target environment data and the auxiliary environment data according to the data points of the environmental knowledge base, further includes: the processor generates the data according to the data points Multiple correlations between the target environmental data and the auxiliary environmental data, wherein the correlations are the data paths between the target environmental data and the auxiliary environmental data; and the processor calculates the correlations A sum of the data paths, and the correlation with the sum as the minimum value is used as the best correlation. An environmental information question and answer system, including: A message transceiving interface for generating a language input command and receiving a response command according to a received language message, and presenting a response message, wherein the language input command includes at least one of a target environment data and an auxiliary environment data A processor, electrically connected to the message sending and receiving interface, and including a semantic analysis component, the processor is used to receive the language input command and selectively generate the target environment data or the auxiliary not included in the language input command Environmental data, and analyzes the target environmental data and the auxiliary environmental data with the semantic analysis component; and an environmental knowledge base, which is interconnected with the processor and contains multiple data points; wherein the processor is based on the environmental knowledge base The data points, analyze an optimal correlation between the target environmental data and the auxiliary environmental data, and generate a search path according to the optimal correlation, convert the search path into a query command, and based on the query The command and the environmental knowledge base generate and send the response command to the messaging interface. The environmental information question answering system according to claim 5, further includes a preset auxiliary condition, wherein the preset auxiliary condition includes at least one of a preset time condition or a preset location condition, the preset auxiliary condition is It is stored in the processor in advance, and is used by the processor to generate the auxiliary environment data under the preset auxiliary conditions when the processor determines that the language input command does not include the auxiliary environment data. The environmental information question answering system as described in claim 5 further includes an instant environmental condition, wherein the instant environmental condition includes a special meteorological condition issued by a government agency, and the instant environmental condition is selectively stored in the environmental knowledge Library and used when the processor judges that When the language input command does not include the auxiliary environmental data, and the processor determines that the environmental knowledge base does not have the real-time environmental conditions, the processor generates the auxiliary environmental data with the predetermined auxiliary conditions. The environmental information question and answer system as described in claim 5 further includes a preset meteorological data. The preset meteorological data is used when the processor determines that the language input command does not include the target environmental data. Let meteorological data generate the target environmental data. According to the environmental information question and answer system of claim 5, the environmental knowledge base further includes a plurality of data paths, wherein the data paths are used to connect the data points to each other, so that the processor generates the data points based on the data points Multiple correlations between the target environmental data and the auxiliary environmental data, and used by the processor when the processor generates the correlations between the target environmental data and the auxiliary environmental data according to the data points Calculate a sum of the data paths of the correlations, and use the correlation whose sum is the minimum as the best correlation, where the data points indicate that the target environment and the auxiliary environment data are in the The storage location of the environmental knowledge base, the correlations are the data paths between the target environmental data and the auxiliary environmental data.

Images