Artificial intelligence system and program of artificial intelligence system
The AI system processes user-specified text to generate and output desired information on the terminal, addressing the inefficiencies of conventional chat systems by providing direct access to summaries and replies without search engine queries.
Patent Information
- Application Number
- JP2023077721
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2023-05-10
- Publication Date
- 2024-11-21
AI Technical Summary
Conventional chat systems require users to manually input items with set times and search on search engines for desired information, making it difficult to obtain results without additional effort.
An artificial intelligence system with a user terminal and server that processes user-specified text through pre-trained AI means to generate and output desired information, such as summaries or replies, directly on the user terminal without the need for search engine queries.
Enables users to obtain desired information, such as summaries or replies, directly on their terminal without searching on search engines, improving efficiency and accuracy by leveraging pre-trained AI to process and generate results.
Smart Images

Figure 2024162328000001_ABST
Abstract
Description
[Technical field]
[0001] The present invention relates to an artificial intelligence system that includes a user terminal and a server, in which the user terminal outputs a display or voice based on the server, and a program for the system. [Background technology]
[0002] Conventionally, there is known a program for a chat system having a content inquiring step in which a chatbot inquires on a chat screen of the chat user's terminal about what the chat user wants to be reminded of, a content registering step in which the chatbot registers chat data received from the chat user's terminal after the content inquiring step as reminder content in a database, a date and time inquiring step in which the chatbot inquires on a chat screen of the chat user's terminal about the date and time at which the chat user wants to be notified of the content, a date and time registering step in which the chatbot registers chat data received from the chat user's terminal after the date and time inquiring step as reminder date and time in a database, a reminder date and time determination step in which the chatbot accesses a date and time control unit of a chat server to determine whether the current date and time has reached the registered reminder date and time, and a transmission notification step in which the chatbot sends the reminder content registered in the database to the chat user's terminal when it has determined that the current date and time has reached the registered reminder date and time (for example, Patent Document 1). [Prior art documents] [Patent documents]
[0003] [Patent Document 1] JP 2019-159469 A Summary of the Invention [Problem to be solved by the invention]
[0004] However, the program of the conventional chat system described above was configured to register the entered information together with a set time, and notify the registered information when that time arrived, so there was a problem that when a user wanted to know the desired information, it was difficult to do so without searching on a search engine site.
[0005] Therefore, the present invention is intended to solve the problems of the prior art as described above, that is, the object of the present invention is to provide an artificial intelligence system and a program thereof that allow a user to obtain result information such as a desired reply without searching on a search engine site. [Means for solving the problem]
[0006] The invention of claim 1 is an artificial intelligence system comprising a user terminal and a server, in which the user terminal displays or outputs audio based on the server, and when a specified operation is performed while text is specified in the browser of the user terminal, multiple item menu buttons are displayed, and when one of the multiple item menu buttons is operated, the user terminal transmits instruction command information corresponding to the selected item menu button and the specified text information to the server, and based on the instruction command information received by the server for the received text information, the server executes using a pre-trained artificial intelligence means, and transmits result information obtained from the execution to the user terminal, and the result information received by the user terminal is displayed on the browser or output as audio, thereby solving the above-mentioned problem.
[0007] The invention of claim 2 further solves the above-mentioned problem by, in addition to the configuration of the artificial intelligence system described in claim 1, one of the multiple item menu buttons is for summarizing, and based on instruction command information for summarizing received by the server for the text information, a summary is generated using a pre-trained artificial intelligence means, the result information of the summary generation obtained by the execution is sent to a user terminal, and the result information of the summary generation received by the user terminal is displayed on a browser or output as audio.
[0008] The invention of claim 3 further solves the above-mentioned problem by, in addition to the configuration of the artificial intelligence system described in claim 2, one of the multiple item menu buttons is for generating a reply document, and based on instruction command information for generating a reply document received by the server in response to the text information received, a pre-trained artificial intelligence means is used to generate a reply document, and result information of the reply document generation obtained by the execution is sent to a user terminal, and the result information of the reply document generation received by the user terminal is displayed on a browser or output as audio.
[0009] The invention of claim 4 further solves the above-mentioned problem by having, in addition to the configuration of the artificial intelligence system described in claim 3, one of the multiple item menu buttons is to generate a summary of everyone's daily reports, and based on instruction command information to generate a summary of everyone's daily reports received in response to the text information received by the server, a pre-trained artificial intelligence means is used to generate a summary of everyone's daily reports, and the result information of the summary generation of everyone's daily reports obtained by the execution is sent to a user terminal, and the result information of the summary generation of everyone's daily reports received by the user terminal is displayed on a browser or output as audio.
[0010] The invention of claim 5 further solves the above-mentioned problem by, in addition to the configuration of the artificial intelligence system described in claim 4, one of the multiple item menu buttons is for generating a project progress report, and based on instruction command information for generating a project progress report received in response to the text information received by the server, a pre-trained artificial intelligence means is used to generate a project progress report, result information of the project progress report generation obtained by the execution is sent to a user terminal, and the result information of the project progress report generation received by the user terminal is displayed on a browser or output as audio.
[0011] The invention of claim 6 further solves the above-mentioned problem by, in addition to the configuration of the artificial intelligence system described in claim 5, one of the multiple item menu buttons is for generating a requirements definition template, and based on instruction command information for generating a requirements definition template received in response to the text information received by the server, a pre-trained artificial intelligence means is used to generate the requirements definition template, result information of the requirements definition template generation obtained by the execution is sent to a user terminal, and the result information of the requirements definition template generation received by the user terminal is displayed on a browser or output as audio.
[0012] The invention of claim 7 further solves the above-mentioned problem by being configured in addition to the configuration of the artificial intelligence system described in any one of claims 1 to 6, wherein the pre-trained artificial intelligence means records the received text information and the received instruction command information in a database, and records the generated result information in a database, and when receiving text information that is the same as previously received text information and instruction command information that is the same as previously received text information, generates result information by inserting the pre-trained information between the previous time and the current time, or generates result information by inserting information on the presence or absence of pre-trained information between the previous time and the current time.
[0013] The invention of claim 8 further solves the above-mentioned problem by being configured such that, in addition to the configuration of the artificial intelligence system described in any one of claims 1 to 6, when the pre-trained artificial intelligence means generates result information based on the instruction command information received for the received text information, newer information among the pre-trained information is included in the result information as information indicating that it is newer than older information.
[0014] The invention of claim 9 is a program for an artificial intelligence system in which a user terminal displays or outputs audio based on a server, and solves the above-mentioned problem by having a predetermined operation presence / absence determination step of determining whether a predetermined operation has been performed when text is specified in the browser of the user terminal, a menu display step of displaying multiple item menu buttons in the browser when the predetermined operation has been performed, a button operation presence / absence determination step of determining whether one of the multiple item menu buttons has been operated, an instruction sending step of the user terminal sending instruction command information corresponding to the selected item menu button and the specified text information to the server when one of the multiple item menu buttons is operated, an instruction execution step of executing using a pre-trained artificial intelligence means based on the instruction command information received by the server in response to the received text information, and a result output step of sending result information obtained by the execution by the server to the user terminal, and displaying the result information received by the user terminal on the browser or outputting it as audio. Effect of the Invention
[0015] The artificial intelligence system of the present invention is equipped with a user terminal and a server, which not only enables the user terminal to display or output audio based on the server, but also provides the following unique effects.
[0016] According to the artificial intelligence system of the invention of claim 1, the user simply specifies text and operates the desired menu button, and the specified text information and instruction command information are sent to the server, processed by the artificial intelligence means, and the desired result information is displayed in the browser or output as voice, so that the user can obtain result information such as the desired reply without searching on a search engine site.
[0017] According to the artificial intelligence system of the invention of claim 2, in addition to the effects achieved by the invention of claim 1, the user simply operates the menu button to specify text and summarize it, and the specified text information and instruction command information to summarize are sent to the server and processed by the artificial intelligence means, and the desired result information is displayed in the browser or output as voice, so that the user can obtain the result information of the desired summary generation without searching on a search engine site. In particular, when the specified text is long, a summary of the short sentences is displayed as the result information or output as audio, so that the user does not need to read and understand the entire original text, but can understand the general content by reading or listening to the short sentences.
[0018] According to the artificial intelligence system of the invention of claim 3, in addition to the effect of the invention of claim 2, the user simply operates a menu button to specify text and generate a reply document, and the specified text information and instruction command information to generate a reply document are sent to the server, processed by the artificial intelligence means, and the desired result information is displayed in the browser or output as voice, so that the user can obtain the result information of the desired reply document generation without searching on a search engine site.
[0019] According to the artificial intelligence system of the invention of claim 4, in addition to the effects achieved by the invention of claim 3, the user simply specifies text and operates a menu button to generate a summary of everyone's daily reports, and the specified text information and instruction command information to generate a summary of everyone's daily reports are sent to the server, processed by the artificial intelligence means, and the desired result information is displayed in the browser or output as voice, so that the user can obtain the result information of the desired summary of everyone's daily reports without searching on a search engine site. For example, because it is easy to compare daily reports between employees, administrators can easily understand who is doing similar tasks and who is not working well with others.
[0020] According to the artificial intelligence system of the invention of claim 5, in addition to the effects of the invention of claim 4, a user simply specifies text and operates a menu button for generating a project progress report, and the specified text information and instruction command information for generating a project progress report are sent to the server, processed by the artificial intelligence means, and the desired result information is displayed in the browser or output as voice, so that the user can obtain the result information for generating the desired project progress report without searching on a search engine site. For example, the administrator user can easily grasp what stage has been achieved and what stage has been undertaken, and at what stage a problem is occurring and a problem is occurring.
[0021] According to the artificial intelligence system of the invention of claim 6, in addition to the effects achieved by the invention of claim 5, the user simply specifies text and operates a menu button to generate a requirements definition template, and the specified text information and instruction command information to generate a requirements definition template are sent to the server, processed by the artificial intelligence means, and the desired result information is displayed in the browser or output as voice, so that the user can obtain the result information of the generation of the desired requirements definition template without searching on a search engine site. For example, the administrator user can easily grasp the conditions such as what requirements are needed to do something and what the criteria for making the decision are.
[0022] According to the artificial intelligence system of the invention of claim 7, in addition to the effects achieved by the invention of any one of claims 1 to 6, information pre-learned between the previous time and the current time and information on the presence or absence of that information are included in the result information, and the current result information is at least partially different from the previous result information, so that the user can check the result information by performing multiple operations. In other words, it is possible to obtain more accurate result information than before.
[0023] According to the artificial intelligence system of the invention of claim 8, in addition to the effects achieved by the invention of any one of claims 1 to 6, new information is included in the result information as information indicating that it is new, and changes in the information over time are reflected in the content of the result information, so that the user can understand the changes in the information over time without having to search on a search engine site.
[0024] According to the program of the artificial intelligence system of the invention of claim 9, similar to the effect achieved by the invention of claim 1, the user simply needs to specify text and operate the desired menu button, and the specified text information and instruction command information will be sent to the server, processed by the artificial intelligence means, and the desired result information will be displayed in the browser or output as voice, so that the user can obtain result information such as the desired reply without searching on a search engine site. [Brief description of the drawings]
[0025] [Figure 1] FIG. 1 is a diagram showing the concept of an artificial intelligence system according to an embodiment of the present invention. [Diagram 2] FIG. 2 is a chart showing an example of the operation of the artificial intelligence system according to the embodiment of the present invention. [Diagram 3] FIG. 2 is a diagram showing an example of operation in a browser of the artificial intelligence system according to an embodiment of the present invention. [Figure 4] FIG. 2 is a diagram showing an example of an artificial intelligence function window of the artificial intelligence system according to an embodiment of the present invention. [Diagram 5] 13 is a diagram showing an example of operations on a webmail page displayed by a browser of the artificial intelligence system according to an embodiment of the present invention. [Figure 6] 1A and 1B are diagrams showing an example of an operation on a webmail page displayed by a browser of an artificial intelligence system according to an embodiment of the present invention, and an example of a reply mail window. [Figure 7] 1A and 1B are diagrams showing an example of operation on a daily report management system page displayed by a browser of an artificial intelligence system according to an embodiment of the present invention, and an example of an artificial intelligence function window. [Figure 8] 1A and 1B are diagrams showing an example of an operation on a task management system page displayed by a browser of an artificial intelligence system according to an embodiment of the present invention, and an example of an artificial intelligence function window. [Figure 9] 1A and 1B are diagrams showing an example of an operation on a file management system page displayed by a browser of an artificial intelligence system according to an embodiment of the present invention, and an example of an artificial intelligence function window. [Figure 10] 6A and 6B are diagrams for explaining an example of the difference in result information output in the artificial intelligence function window of the artificial intelligence system according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0026] The artificial intelligence system of the present invention displays multiple item menu buttons when a specified operation is performed with text specified in the browser of the user terminal, and when one of the multiple item menu buttons is operated, the user terminal sends instruction command information corresponding to the selected item menu button and the specified text information to the server, and the server executes the received instruction command information using a pre-trained artificial intelligence means based on the received text information, sends the result information obtained from the execution to the user terminal, and displays the result information received by the user terminal on the browser or outputs it as audio, so that the specific implementation of the system can be any one as long as the user can obtain result information such as the desired response without searching on a search engine site. In addition, the program of the artificial intelligence system of the present invention has a predetermined operation determination step of determining whether or not a predetermined operation has been performed when text is specified in the browser of the user terminal, a menu display step of displaying multiple item menu buttons in the browser when the predetermined operation has been performed, a button operation determination step of determining whether or not one of the multiple item menu buttons has been operated, an instruction sending step of the user terminal sending instruction command information corresponding to the selected item menu button and the specified text information to the server when one of the multiple item menu buttons is operated, an instruction execution step of using a pre-trained artificial intelligence means to execute based on the instruction command information received by the server in response to the received text information, and a result output step of sending the result information obtained by the execution by the server to the user terminal and displaying the result information received by the user terminal on the browser or outputting it as audio, so that the specific implementation of the program can be any as long as the user can obtain result information such as the desired reply without searching on a search engine site.
[0027] For example, the user terminal may be a desktop personal computer terminal, a notebook personal computer terminal, a smartphone terminal, a tablet terminal, or the like that sends and receives information, and may be any terminal that can be freely connected to a server via a communication network including a wide area network, such as the Internet, a local network, or a telephone line. Also, the server may be a single server or multiple servers on a cloud. The artificial intelligence means may be configured as an interactive system, such as ChatGPT (Generative Pre-trained Transformer), and may be configured to be installed on one server or multiple servers on a cloud. EXAMPLES
[0028] An artificial intelligence system 100 according to an embodiment of the present invention will be described below with reference to FIGS. 1 to 10(B). Here, FIG. 1 is a diagram showing the concept of an artificial intelligence system 100 which is an embodiment of the present invention, FIG. 2 is a chart diagram showing an example of the operation of the artificial intelligence system 100 which is an embodiment of the present invention, FIG. 3 is a diagram showing an example of an operation in the browser 112 of the artificial intelligence system 100 which is an embodiment of the present invention, FIG. 4 is a diagram showing an example of an artificial intelligence function window 114 of the artificial intelligence system 100 which is an embodiment of the present invention, FIG. 5 is a diagram showing an example of an operation in a webmail page 115 displayed by the browser 112 of the artificial intelligence system 100 which is an embodiment of the present invention, FIG. 6(A) is a diagram showing an example of an operation in a webmail page 115 displayed by the browser 112 of the artificial intelligence system 100 which is an embodiment of the present invention, FIG. 6(B) is a diagram showing an example of a reply mail window 116, and FIG. 7(A) is a diagram showing an example of a daily report displayed by the browser 112 of the artificial intelligence system 100 which is an embodiment of the present invention. FIG. 7(B) is a diagram showing an example of operation on the management system page 117, FIG. 7(B) is a diagram showing an example of the artificial intelligence function window 114, FIG. 8(A) is a diagram showing an example of operation on the task management system page 118 displayed by the browser 112 of the artificial intelligence system 100 which is an embodiment of the present invention, FIG. 8(B) is a diagram showing an example of the artificial intelligence function window 114, FIG. 9(A) is a diagram showing an example of operation on the file management system page 119 displayed by the browser 112 of the artificial intelligence system 100 which is an embodiment of the present invention, FIG. 9(B) is a diagram showing an example of the artificial intelligence function window 114, FIG. 10(A) is a diagram for explaining an example of the difference in result information GR output in the artificial intelligence function window 114 of the artificial intelligence system 100 which is an embodiment of the present invention, and shows the state when operated last time, and FIG. 10(B) is a diagram showing the state when operated this time.
[0029] An artificial intelligence system 100 according to an embodiment of the present invention includes a user terminal 110 and a server 120, as shown in FIG. The user terminal 110 is configured to display the information using a browser 112 on a display unit 111 of the user terminal 110 based on the information from the server 120, or to output the information as sound using a speaker of the user terminal 110. In this embodiment, when a predetermined operation is performed while text is specified on the browser 112 of the user terminal 110, a plurality of item menu buttons 113a (114b) are displayed. When one of the multiple item menu buttons 113a (114b) is operated, the user terminal 110 transmits to the server 120 the instruction command information and the specified text information TX corresponding to the selected item menu button 113a (114b).
[0030] The server 120 then executes the received text information TX using the pre-trained artificial intelligence means based on the received instruction command information. Here, the pre-trained artificial intelligence means is configured to collect and store information from an accessible range on the Internet or from a range specified by a URL, etc., either constantly or at predetermined time intervals, and process the text information TX received from the user terminal 110 based on the received instruction command information to generate result information GR. Specifically, the system divides the text information TX into subjects, predicates, modifiers, and objects, grasps the intent of the instruction and command information, and generates result information GR by referring to the accumulated information so as to reply in accordance with the intent.
[0031] When generating result information GR, in order to make it easier for the user to understand, if there is a character limit, the explanation is basically generated by combining a subject, predicate, modifier, and object in multiple sentences within the character limit. In addition, if it is determined that one sentence is better than multiple sentences due to character limit, the explanation will be generated in one sentence. Then, the server 120 transmits result information GR obtained through the execution to the user terminal 110. The user terminal 110 is configured to then display the received result information GR on the browser 112, or output it as audio.
[0032] As a result, the user simply specifies text and operates the desired menu button, and the specified text information TX and instruction command information are transmitted to the server 120, where they are processed by the artificial intelligence means, and the desired result information GR is displayed on the browser 112 or output as voice. As a result, the user can obtain result information GR such as a desired reply without performing a search on a search engine site.
[0033] Next, an example of the operation of the artificial intelligence system 100 will be described in more detail. As shown in FIG. 2, in step S1, as a predetermined operation presence / absence determination step, the user terminal 110 determines whether or not text has been specified in the browser 112 of the user terminal 110. If it is determined that the text has been specified, the process proceeds to step S2, whereas if it is determined that the text has not yet been specified, step S1 is repeated. For example, as shown in FIG. 3, assume that an arbitrary website page is displayed on the browser 112 of the user terminal 110, and text is selected and specified by the user.
[0034] In FIG. 3, the text color is inverted to indicate the selected and specified portion. Although the method of selecting and specifying the text has been described as a method of specifying the range by dragging the mouse, the method is not limited to this. Regardless of whether or not the text itself is displayed in the browser 112, the text may be specified by selecting and specifying a file.
[0035] In step S2, as a predetermined operation presence / absence determination step, user terminal 110 determines whether or not a right click operation of a mouse has been performed as an example of a predetermined operation while text has been specified. If it is determined that the predetermined operation has been performed, the process proceeds to step S3. On the other hand, if it is determined that the predetermined operation has not been performed, step S2 is repeated. Although the right-click operation of the mouse is given as an example of the predetermined operation, the present invention is not limited to this. For example, it may be a predetermined key operation on the keyboard of the user terminal 110, or it may be a tap operation, a flick operation, or the like.
[0036] In step S3, as a menu display step, the user terminal 110 displays a plurality of item menu buttons 113a (114b) on the browser 112. For example, as shown in FIG. 3, by right-clicking the mouse, the user terminal 110 displays a pop-up menu window 113, in which a plurality of item menu buttons 113a are displayed. The pop-up menu window 113 provides, as examples of multiple item menu buttons 113a, an "Artificial Intelligence Function" button, a "Summarize!" button, a "Tell me!" button, a "Create a reply document" button, a "Please create a summary of everyone's daily reports!" button, a "Tell me the progress of the project!" button, and a "Please create a requirements definition template!" button.
[0037] When the "artificial intelligence function" button is selected, the user terminal 110 opens an artificial intelligence function window 114 as shown in FIG. The artificial intelligence function window 114 includes, for example, a text input field 114a, a plurality of item menu buttons 114b, and a generation result output field 114c. More specifically, as an example of multiple item menu button 114b, similar to the pop-up menu window 113, a "Summarize!" button, a "Tell me!" button, a "Create a reply document" button, a "Please create a summary of everyone's daily reports!" button, a "Tell me about the progress of the project!" button, and a "Please create a requirements definition template!" button are provided. When the "artificial intelligence function" button is selected, the user terminal 110 opens an artificial intelligence function window 114 and inputs the specified text into a text input field 114a of the artificial intelligence function window 114. It should be noted that the pop-up menu window 113 may be configured so that only the "artificial intelligence function" button is displayed, and the artificial intelligence function window 114 is opened when the "artificial intelligence function" button is operated.
[0038] In step S4, as a button operation determination step, user terminal 110 determines whether or not one of a plurality of item menu buttons 113a (114b) has been operated. If it is determined that an operation has been performed, the process proceeds to step S5. On the other hand, if it is determined that an operation has not been performed yet, step S4 is repeated. For example, in FIG. 3, when the “Summarize!” button in the pop-up menu window 113 is selected, the user terminal 110 is configured to open the artificial intelligence function window 114 and input the specified text into the text input field 114a of the artificial intelligence function window 114, as shown in FIG. 4.
[0039] In step S5, as an instruction transmission step, the user terminal 110 transmits to the server 120 instruction command information corresponding to the selected item menu button 113a (114b) and the specified text information TX. Specifically, the text information TX designated in the browser 112 shown in FIG. 3 and instruction command information for summarizing corresponding to the “Summarize!” button in the pop-up menu window 113 are transmitted to the server 120. In other words, the text information TX entered in the text input field 114a of the artificial intelligence function window 114 shown in FIG. 4 and the instruction command information to summarize corresponding to the “Summarize!” button are transmitted to the server 120. The same operation is performed when the "Artificial Intelligence Function" button in the pop-up menu window 113 is selected in Fig. 3, and when the "Summarize!" button in the artificial intelligence function window 114 is selected in Fig. 4. A detailed explanation of this will be omitted.
[0040] In step S6, as an instruction execution step, the server 120 generates a summary as an example using a pre-trained artificial intelligence means based on instruction command information to summarize the received text information TX as an example of the instruction command information received.
[0041] In step S7, as a result output step, the server 120 transmits to the user terminal 110 result information GR of the summary generation, which is an example of the result obtained by the execution. The user terminal 110 then displays the received example of summary generation result information GR in the generation result display field 114c of the artificial intelligence function window 114 as an example in the browser 112. Although the configuration has been described in which the summary generation result information GR is displayed in the generation result display field 114c of the artificial intelligence function window 114, the user terminal 110 may be configured to output the summary generation result information GR by voice using a speaker. That is, at least one of the following is executed: the summary generation result information GR is displayed on the browser 112 and / or output as audio from the speaker.
[0042] As a result, as described above, the user simply specifies text and operates the desired menu button, and the specified text information TX and instruction command information are transmitted to the server 120, where they are processed by the artificial intelligence means, and the desired result information GR is displayed on the browser 112 or output as voice. As a result, the user can obtain result information GR such as a desired reply without performing a search on a search engine site.
[0043] Furthermore, in this embodiment, one of the multiple item menu buttons 113a (114b) is a "Summarize!" button, which indicates that a summary should be made. When the “Summarize!” button is selected, the user terminal 110 transmits to the server 120 instruction command information (also called a prompt) to summarize corresponding to the selected “Summarize!” button and the specified text information TX. Then, based on the instruction command information to summarize received for the text information TX received by the server 120, a summary is generated using a pre-trained artificial intelligence means, and the summary generation result information GR obtained by the execution is transmitted to the user terminal 110. The user terminal 110 is then configured to display the received summary generation result information GR in the generation result display field 114c of the artificial intelligence function window 114 as an example of the browser 112, or to output it as voice.
[0044] Thus, the user simply operates a menu button to specify text and summarize it, and the specified text information TX and instruction command information to summarize are transmitted to the server 120 and processed by the artificial intelligence means, and the desired result information GR is displayed on the browser 112 or output as voice. As a result, the user can obtain the desired summary generation result information GR without performing a search on a search engine site. In particular, when the specified text is a long sentence, a summary of the short sentence is displayed as the result information GR or is output as voice. As a result, users can understand the general content by reading or listening to short sentences without having to read and understand the entire original text.
[0045] In this embodiment, one of the multiple item menu buttons 113a (114b) is a "Tell me!" button that provides a detailed explanation. When the “Tell me!” button is selected, the user terminal 110 transmits to the server 120 instruction command information for a detailed explanation corresponding to the selected “Tell me!” button and the specified text information TX. Then, based on the instruction command information received from the server 120 to provide a detailed explanation in response to the received text information TX, the server 120 generates an explanatory text using a pre-trained artificial intelligence means, and transmits the result information GR of the explanatory text generation obtained by the execution to the user terminal 110. The user terminal 110 is then configured to display the received result information GR of the explanation generation in the generation result display field 114c of the artificial intelligence function window 114 as an example of the browser 112, or to output it as voice.
[0046] Thus, the user simply operates a menu button for specifying text and providing a detailed explanation, and the specified text information TX and instruction command information for providing a detailed explanation are transmitted to the server 120, where they are processed by the artificial intelligence means, and the desired result information GR is displayed on the browser 112 or output as voice. As a result, the user can obtain the desired result information GR of the description generation without searching on a search engine site. In particular, when the specified text is a sentence or name containing a recently coined word or multiple difficult terms, an explanatory sentence that is easy to understand or a sentence that is longer than the length of the specified text is displayed as result information GR or output as audio. As a result, users can get a rough idea of the content by reading or listening to the description, rather than having to read the entire original text and search for and understand every word.
[0047] It should be noted that a "Tell me about the problem" button may be provided as one of the multiple item menu buttons 113a (114b). When the "Tell me the problem" button is selected, the presence or absence of a problem corresponding to the "Tell me the problem" button is checked, and if there is a problem, instruction command information explaining the content of the problem and the specified text information TX are transmitted to the server 120. Then, the server 120 checks whether there are any problems with the received text information TX, and if there are any problems, generates an explanatory text using the pre-trained artificial intelligence means based on instruction command information to explain the contents of the problems, and transmits the result information GR of the explanatory text generation obtained by the execution to the user terminal 110. The user terminal 110 is then configured to display the received result information GR of the explanation generation in the generation result display field 114c of the artificial intelligence function window 114 as an example of the browser 112, or to output it as voice. Thus, the user simply operates a menu button to specify text, check whether there are any problems, and if there are any problems, explain the details thereof, and the specified text information TX and instruction command information to check whether there are any problems and explain the details thereof, if there are any problems, are transmitted to the server 120 and processed by the artificial intelligence means, and the desired result information GR is displayed on the browser 112 or output as voice. As a result, the user can obtain the desired information GR on the result of the generation of an explanation regarding the problem with the content of the specified text without reading the specified text.
[0048] Also, as shown in FIG. 5, when browser 112 is displaying webmail page 115, as an example of a specified operation, user terminal 110 can determine that the user has specified text by selecting one received email from the inbox and displaying the contents of that received email in received email display area 115a. Furthermore, when text is specified, the browser 112 of the user terminal 110 displays a "Summary" button 115c and a "Create reply document" button 115e in the item menu column 115b as examples of a plurality of item menu buttons (113a, 114b).
[0049] Then, when the “Summary” button 115c is selected, the user terminal 110 transmits the text information TX of the specified received email and instruction command information to summarize to the server 120, and similar to the example shown in FIG. 4, the server 120 generates a summary using the pre-trained artificial intelligence means based on the instruction command information to summarize received for the received text information TX, and transmits the summary generation result information GR obtained by the execution to the user terminal 110. The user terminal 110 is configured to then display the received summary generation result information GR in the summary generation result field 115d of the item menu field 115b of the browser 112.
[0050] Next, as shown in FIG. 6(A), it is assumed that, as an example of a predetermined operation, the user operates a "Create reply document" button 115e which indicates that a reply document is to be generated. In this case, the text specified may be, for example, the summary generation result information GR displayed in the generation result display field 114c of the item menu field 115b of the browser 112, or the text of the specified original received email, but the summary generation result information GR displayed in the summary generation result field 115d is preferable. This is because the content has been recognized and generated by an artificial intelligence means. Also, this is because it is the content that the user understands as the content of the received email.
[0051] When the user terminal 110 determines that the "Create reply document" button 115e has been operated, the user terminal 110 transmits to the server 120 instruction command information to generate a reply document corresponding to the selected item menu button, and the text of the summary generation result information GR as the specified text information TX, or the text of the original received email. Then, the server 120 executes reply document generation using the pre-trained artificial intelligence means based on the instruction command information to generate a reply document in response to the received text information TX, and transmits the result information GR of the executed reply document generation to the user terminal 110. Then, as shown in FIG. 6(B), the user terminal 110 is configured to open a reply mail window 116 and display the received reply document generation result information GR in the reply mail window 116 as an example of the browser 112. Of course, audio output may also be used.
[0052] Also, on the webmail page 115 displayed on the browser 112, the text of the received email may be selected with the mouse as shown in FIG. 3, inverted in color, and the pop-up menu window 113 may be displayed by right-clicking, and the "Create reply document" button among the multiple item menu buttons 113a may be operated. In this case, as shown in FIG. 4, the user terminal 110 opens the artificial intelligence function window 114 and displays the reply document generation result information GR received from the server 120 in a generation result display field 114c.
[0053] As a result, the user simply operates a menu button to specify text and generate a reply document, and the specified text information TX and instruction command information to generate a reply document are sent to the server 120, where they are processed by the artificial intelligence means, and the desired result information GR is displayed on the browser 112 or output as voice. As a result, the user can obtain the desired reply document generation result information GR without performing a search on a search engine site.
[0054] Although not shown, one of the multiple item menu buttons 113a (114b) may be a "Please correct my email!" button for correcting an email document before sending it. The user specifies the text entered in the new mail window or reply mail window, and displays the multiple item menu button 113a (114b) by right-clicking or the like, and selects the "Please correct my email!" button. Then, instruction command information for correcting the mail document before sending corresponding to the selected item menu button and the text input in the new mail window or reply mail window as the specified text information TX are transmitted to the server 120.
[0055] Then, the server 120 executes generation of a corrected email document using a pre-trained artificial intelligence means based on instruction command information for correcting the email document before sending, received in response to the received text information TX, and transmits result information GR of the corrected email document generation obtained by the execution to the user terminal 110. Then, the user terminal 110 may be configured to, for example, open a new email window and display the received edited email document generation result information GR in the generation result display section 114c of the artificial intelligence function window 114 or in the new email window as an example of the browser 112.
[0056] As a result, the user simply specifies text and operates a menu button for correcting the e-mail document before sending, and the specified text information TX and instruction command information for correcting the e-mail document before sending are sent to the server 120, where they are processed by the artificial intelligence means, and the desired result information GR is displayed on the browser 112 or output as voice. As a result, the user can obtain the desired corrected email document generation result information GR without searching on a search engine site. More specifically, the relationship between the subject and predicate of a sentence, the position of modifiers, and typos are corrected. As a result, emails can be sent in text that is easier to understand.
[0057] Furthermore, in this embodiment, as shown in Figures 3, 4, and 7(A), one of the multiple item menu buttons 113a (114b) is a ``Please create a summary of everyone's daily reports!'' button, which generates a summary of everyone's daily reports. For example, as shown in FIG. 7(A), it is assumed that the browser 112 of the user terminal 110 displays a daily report management system page 117 as an example. When the user selects the first development group in the organization tree structure display field on the left side of the daily report management system page 117, icons 117a of the daily report files submitted by the group members are displayed in the daily report file display field on the right side. Furthermore, it is assumed that the user selects and specifies icons 117a of a plurality of daily report files as an example displayed in the daily report file display field. Then, when a right click operation is performed as the predetermined operation, the user terminal 110 displays a pop-up menu window 113.
[0058] When the "Please create a summary of everyone's daily reports!" button is selected, the user terminal 110 transmits to the server 120 instruction command information to generate a summary of everyone's daily reports corresponding to the selected "Please create a summary of everyone's daily reports!" button, and multiple daily report files specified as the specified text information TX. Then, based on the instruction command information for generating a summary of the daily reports of all the employees received in response to the text information TX received by the server 120, the server 120 uses the pre-trained artificial intelligence means to generate a summary of the daily reports of all the employees. For example, the artificial intelligence means reads daily report files of multiple members and determines which members have done what. Then, the names of the members are matched with their actions, and a summary is generated based on the actions.
[0059] Next, the server 120 transmits to the user terminal 110 result information GR of the summary generation of the daily reports of all the members obtained by the execution. Then, as shown in Figure 7 (B), the user terminal 110 is configured to display the result information GR of the summary generation of the received daily reports of all users in the generation result display section 114c of the artificial intelligence function window 114 as an example of the browser 112. Of course, audio output may also be used.
[0060] As a result, the user simply operates a menu button to specify text and generate a summary of everyone's daily reports, and the specified text information TX and instruction command information to generate a summary of everyone's daily reports are sent to the server 120, where they are processed by the artificial intelligence means, and the desired result information GR is displayed on the browser 112 or output as audio. As a result, the user can obtain the result information GR of the summary generation of the daily reports of all the desired people without searching on a search engine site. For example, since it is easy to compare daily reports between employees, managers (supervisors) can easily understand who is doing similar things or who is not working well with others.
[0061] Also in this embodiment, as shown in Figures 3, 4, and 8(A), one of the multiple item menu buttons 113a (114b) is a "Tell me about the progress of the project!" button, which generates a report on the progress of the project. For example, assume that the browser 112 of the user terminal 110 is displaying a task management system page 118 as an example, as shown in FIG. 8(A). When the user selects a project in the project member tree structure display field on the left side of the task management system page 118, an icon 118a of the task file of that project is displayed in the task display field on the right side. Furthermore, it is assumed that the user selects and specifies icons 118a of multiple task files as an example displayed in the task display field. Then, when a right click operation is performed as the predetermined operation, the user terminal 110 displays a pop-up menu window 113.
[0062] When the "Tell us how the project is progressing!" button is selected, the user terminal 110 transmits to the server 120 instruction command information for generating a report on the progress of the project corresponding to the selected "Tell us how the project is progressing!" button, and a plurality of task files specified as the specified text information TX. Then, based on the instruction command information for generating a project progress report received in response to the text information TX received by the server 120, the server 120 uses the pre-trained artificial intelligence means to generate a project progress report. For example, the artificial intelligence means reads multiple task files to grasp the progress pace and problems of the tasks.
[0063] It also predicts when the current task step will be completed and when you can move on to the next step, and generates a project progress report by analyzing what percentage of the total task has been completed. Then, the server 120 transmits to the user terminal 110 the result information GR of the project progress report generation obtained by the execution. Then, as shown in Figure 8 (B), the user terminal 110 is configured to display the received project progress report generation result information GR in the generation result display section 114c of the artificial intelligence function window 114 as an example of the browser 112. Of course, audio output may also be used.
[0064] As a result, the user simply specifies text and operates a menu button to generate a project progress report, and the specified text information TX and instruction command information to generate a project progress report are sent to the server 120, where they are processed by the artificial intelligence means, and the desired result information GR is displayed on the browser 112 or output as audio. As a result, the user can obtain the result information GR of the progress report generation of the desired project without searching on a search engine site. For example, an administrator (supervisor) user can easily grasp what stage has been achieved and what stage has been undertaken, and at what stage problems are occurring and difficulties are being encountered.
[0065] Furthermore, in this embodiment, as shown in Figures 3, 4, and 9(A), one of the multiple item menu buttons 113a (114b) is a ``Please create a requirements definition template!'' button, which generates a requirements definition template. For example, assume that the browser 112 of the user terminal 110 is displaying a file management system page 119 as shown in FIG. 9(A). When the user selects a desired project in the project-specific tree structure display field on the left side of the file management system page 119, an icon 119a for the proposal file of that project is displayed in the file display field on the right side. Furthermore, it is assumed that the user selects and specifies icon 119a of a proposal file as an example displayed in the file display field. Then, when a right click operation is performed as the predetermined operation, the user terminal 110 displays a pop-up menu window 113.
[0066] When the "Please create a requirements definition template!" button is selected, the user terminal 110 transmits to the server 120 instruction command information for generating a requirements definition template corresponding to the selected "Please create a requirements definition template!" button and the proposal file specified as the specified text information TX. Then, based on the instruction command information for generating a template for the requirements definition received in response to the text information TX received by the server 120, the server 120 uses the pre-trained artificial intelligence means to generate a template for the requirements definition. For example, the artificial intelligence means reads a proposal file, understands what the purpose and outline are, grasps the necessary requirements for the system configuration, takes into account possible problems and scenarios, grasps the flow after the system is constructed, and generates a requirements definition template that includes this information.
[0067] Then, the server 120 transmits to the user terminal 110 result information GR of the requirements definition template generation obtained by execution. Then, as shown in Figure 9 (B), the user terminal 110 is configured to display the result information GR of the template generation of the received requirements definition in the generation result display section 114c of the artificial intelligence function window 114 as an example of the browser 112. Of course, audio output may also be used.
[0068] As a result, the user simply operates a menu button to specify text and generate a requirements definition template, and the specified text information TX and instruction command information to generate a requirements definition template are sent to the server 120, where they are processed by the artificial intelligence means, and the desired result information GR is displayed on the browser 112 or output as audio. As a result, the user can obtain the result information GR of the template generation of the desired requirements definition without searching on a search engine site. For example, the user who is the administrator (supervisor) can easily grasp the conditions such as what requirements are needed to do something and what the criteria for making the decision are.
[0069] In this embodiment, the pre-trained artificial intelligence means records the received text information TX and the received instruction command information in a database. At the same time, the pre-trained artificial intelligence means records the generated result information GR in the database. When text information TX that is the same as previously received text information TX and instruction command information that is the same as previously received instruction command information are received, the result information GR is generated by inserting the pre-learned information BT between the previous time and the current time, or the result information GR is generated by inserting the presence / absence information of the pre-learned information BT between the previous time and the current time. For example, FIG. 10(A) shows the previous generation result displayed in the generation result display field 114c. On the other hand, FIG. 10(B) shows the current generation result displayed in the generation result display field 114c.
[0070] The underlined portions of the generated result information GR displayed in the generation result display field 114c shown in FIG. 10(B) are the portions that were generated taking into consideration the information BT that was pre-learned between the previous time and the current time. In this way, the information BT pre-learned between the previous time and this time and information on the presence or absence of that information are entered into the result information GR, and the current result information GR is at least partially different from the previous result information GR. As a result, the user can confirm the result information GR by performing the operation multiple times. In other words, it is possible to obtain result information GR with higher accuracy than the previous time.
[0071] Furthermore, in this embodiment, the pre-trained artificial intelligence means records the collected information in the database with the date information of collection and the date information of publication on the Internet added thereto. When the pre-trained artificial intelligence means generates result information GR based on the instruction command information received for the received text information TX, it is configured to enter information NW that is newer than the older information among the pre-trained information into the result information GR as information indicating that it is newer. The underlined portion of the generated result information GR displayed in the generated result display field 114c shown in FIG. 10(B) is the portion where newer information NW than older information is entered in the result information GR as newer information. In this way, new information is entered into the result information GR as information indicating that the information is new, and changes in the information over time are reflected in the contents of the result information GR. As a result, users can understand the information including changes over time without having to search on a search engine site.
[0072] As shown in FIG. 10(B), the display of the generated result information GR may be configured so that the part of the result information GR in which newer information NW is entered as newer information rather than older information is displayed more emphasized than other parts. Examples of the emphasis include underlining, making the text bold, using a color that stands out from the rest, highlighting, and the like. As a result, in the generated result information GR, new information NW stands out more than old information. As a result, the user can pay particular attention to the new information network. The information BT that has been pre-learned between the previous time and the current time may also be configured to be highlighted and displayed in the same manner as the new information NW. As a result, the information BT pre-learned between the previous time and the current time stands out in the generated result information GR. As a result, the user can pay particular attention to the parts of the information BT that have been pre-learned between the previous time and the current time.
[0073] Furthermore, for each button of the multiple item menu buttons 113a (114b), multiple levels of character limit may be set, such as a "Summarize! (300 characters)" button, "Summarize! (500 characters)" button, "Tell me! (300 characters)" button, "Tell me! (500 characters)" button, "Create a reply document (100 characters)" button, "Create a reply document (300 characters)" button, "Please create a summary of everyone's daily reports! (300 characters)" button, "Please create a summary of everyone's daily reports! (500 characters)" button, "Tell me the progress of the project! (300 characters)" button, "Tell me the progress of the project! (500 characters)" button, "Please create a requirements definition template! (300 characters)" button, and "Please create a requirements definition template! (500 characters)" button, so that character number condition information for the result information GR to be generated is included in the instruction command information corresponding to the item menu button.
[0074] As a result, the result information GR with the number of characters desired by the user is displayed on the browser 112 or output as voice. As a result, we can instantly respond to requests, whether they are for detailed information or general information. In particular, when there is no character limit, the pre-trained artificial intelligence means tends to provide a detailed explanation using multiple sentences, so if you want to know the main points or want to reply by capturing the main points, it is recommended that you generate the message with a character limit. By providing buttons with different character limits, the user can obtain the result information GR with the number of characters desired in just one go. In other words, in the case of a configuration in which instruction command information is transmitted without a character limit, it is possible to eliminate the trouble of first obtaining result information GR with a relatively large number of characters, and then changing it to result information GR with a relatively small number of characters due to a character limit.
[0075] The artificial intelligence system 100, an embodiment of the present invention obtained in this manner, comprises a user terminal 110 and a server 120, and when a specified operation is performed while text is specified in the browser 112 of the user terminal 110, displays multiple item menu buttons 113a (114b), and when one of the multiple item menu buttons 113a (114b) is operated, the user terminal 110 transmits instruction command information corresponding to the selected item menu button 113a (114b) and the specified text information TX to the server 120, and based on the instruction command information received by the server 120 for the received text information TX, executes it using a pre-trained artificial intelligence means, and transmits the result information GR obtained by the execution to the user terminal 110, and displays the result information GR received by the user terminal 110 on the browser 112 or outputs it as voice, thereby allowing the user to obtain the result information GR such as a desired reply without searching on a search engine site.
[0076] Furthermore, one of the multiple item menu buttons 113a (114b) indicates that the user wants to summarize, and based on the instruction and command information indicating that the server 120 wants to summarize the text information TX received by the server 120, the server 120 executes summary generation using a pre-trained artificial intelligence means, and transmits the result information GR of the summary generation obtained by the execution to the user terminal 110, and the result information GR of the summary generation received by the user terminal 110 is displayed on the browser 112 or output as audio. This allows the user to obtain the desired result information GR of the summary generation without searching on a search engine site, and the user does not need to read and understand the entire original text, but can understand the general content by reading or listening to short sentences.
[0077] In addition, one of the multiple item menu buttons 113a (114b) is for generating a reply document, and based on the instruction command information for generating a reply document received in response to the text information TX received by the server 120, the server 120 executes reply document generation using a pre-trained artificial intelligence means, and transmits the result information GR of the reply document generation obtained by the execution to the user terminal 110, and the result information GR of the reply document generation received by the user terminal 110 is displayed on the browser 112 or output as audio, so that the user can obtain the result information GR of the desired reply document generation without searching on a search engine site.
[0078] Furthermore, one of the multiple item menu buttons 113a (114b) indicates that a summary of the daily reports of all employees will be generated, and based on the instruction command information to generate a summary of the daily reports of all employees received in response to the text information TX received by the server 120, the server 120 uses a pre-trained artificial intelligence means to generate a summary of the daily reports of all employees, and sends the result information GR of the summary of the daily reports of all employees obtained by the execution to the user terminal 110, and the result information GR of the summary of the daily reports of all employees received by the user terminal 110 is displayed on the browser 112 or output as audio. This allows the user to obtain the desired result information GR of the summary of the daily reports of all employees without searching on a search engine site, and since, for example, daily reports between employees can be easily compared, the administrator user can easily understand who is doing similar things with whom or who is not working well together with whom.
[0079] In addition, one of the multiple item menu buttons 113a (114b) is for generating a project progress report, and based on the instruction command information for generating a project progress report received in response to the text information TX received by the server 120, the server 120 executes the generation of the project progress report using a pre-trained artificial intelligence means, and transmits the result information GR of the project progress report generation obtained by the execution to the user terminal 110, and the result information GR of the project progress report generation received by the user terminal 110 is displayed on the browser 112 or output as audio.As a result, the user can obtain the result information GR of the desired project progress report generation without searching on a search engine site, and the administrator user can easily grasp, for example, what stage has been achieved and what stage has been started, and at which stage there are problems and difficulties.
[0080] Furthermore, one of the multiple item menu buttons 113a (114b) indicates the generation of a requirements definition template, and based on the instruction command information to generate a requirements definition template received in response to the text information TX received by the server 120, the generation of the requirements definition template is executed using a pre-trained artificial intelligence means, and the result information GR of the requirements definition template generation obtained by the execution is sent to the user terminal 110, and the result information GR of the requirements definition template generation received by the user terminal 110 is displayed on the browser 112 or output as audio.As a result, the user can obtain the result information GR of the desired requirements definition template generation without searching on a search engine site, and the administrator user can easily grasp conditions such as what and what requirements are needed to do what, and what the judgment is based on.
[0081] In addition, the pre-trained artificial intelligence means records the received text information TX and the received instruction command information in a database, and also records the generated result information GR in the database. When the means receives text information TX that is identical to the previously received text information TX and instruction command information that is identical to the previously received instruction command information, it generates result information GR by inputting the pre-trained information BT between the previous time and the current time, or generates result information GR by inputting information on the presence or absence of pre-trained information BT between the previous time and the current time. This allows the user to check the result information GR by operating multiple times and obtain result information GR that is more accurate than the previous time.
[0082] Furthermore, when the pre-trained artificial intelligence means generates result information GR based on the instruction and command information received in response to the received text information TX, the pre-trained information NW that is newer than the older information is entered into the result information GR as information indicating that it is new, allowing the user to understand the information including changes over time without having to search on a search engine site.
[0083] The program of the artificial intelligence system 100 according to the embodiment of the present invention includes predetermined operation determination steps S1 and S2 for determining whether or not a predetermined operation has been performed while text is specified in the browser 112 of the user terminal 110, a menu display step S3 for displaying a plurality of item menu buttons 113a (114b) in the browser 112 when the predetermined operation has been performed, a button operation determination step S4 for determining whether or not one of the plurality of item menu buttons 113a (114b) has been operated, and a button operation determination step S5 for determining whether or not the user terminal 110 has operated the selected item menu button 113a (114b) when one of the plurality of item menu buttons 113a (114b) has been operated. The system has an instruction sending step S5 of sending instruction command information corresponding to (114b) and the specified text information TX to the server 120, an instruction execution step S6 of executing an instruction using a pre-trained artificial intelligence means based on the instruction command information received in response to the text information TX received by the server 120, and a result output step S7 of sending the result information GR obtained by the execution by the server 120 to the user terminal 110 and displaying the result information GR received by the user terminal 110 on the browser 112 or outputting it as voice, thereby providing significant benefits, such as allowing the user to obtain result information GR such as a desired reply without searching on a search engine site. [Explanation of symbols]
[0084] 100 ··· Artificial Intelligence Systems 110 User terminal 111... Display section 112 ··· Browser 113 Pop-up menu window (multiple item menu button) 113a Multiple Item Menu Button 114 ··· Artificial Intelligence Function Window (Multiple Item Menu Button) 114a··· Text input field 114b Multiple Item Menu Button 114c... Generation result display field 115 ··· Webmail page (email browser) 115a··· Received email display field 115b... Item menu column 115c... "Summary" button 115d... Summary generation result column 115e "Create reply document" button 116 Reply Mail Window 117 ··· Daily Report Management System Page 117a Daily report file icon 118 ··· Task Management System Page 118a Task file icon 119 ··· File Management System Page 119a··· (Project) proposal file icon 120 Server TX: (specified) text information GR (generated) result information BT: Information learned in advance between the previous time and this time NW: Newer information than old information learned in advance
Claims
1. An artificial intelligence system comprising a user terminal and a server, the user terminal displaying or outputting audio based on the server, displaying a plurality of item menu buttons when a predetermined operation is performed while text is specified in the browser of the user terminal; When one of the plurality of item menu buttons is operated, the user terminal transmits instruction command information and specified text information corresponding to the selected item menu button to the server; The server executes the instruction command information received from the received text information using a pre-trained artificial intelligence means, and transmits the result information obtained by the execution to the user terminal; An artificial intelligence system characterized in that the result information received by the user terminal is displayed on a browser or output as audio.
2. one of the plurality of item menu buttons is for summarizing; The server executes a summary generation process using a pre-trained artificial intelligence means based on instruction and command information to summarize the received text information, and transmits the summary generation result information to a user terminal.
2. The artificial intelligence system according to claim 1, characterized in that the result information of the summary generation received by the user terminal is displayed on a browser or output as voice.
3. one of the plurality of item menu buttons is for generating a reply document; The server executes a reply document generation process using a pre-trained artificial intelligence means based on instruction command information for generating a reply document received in response to the received text information, and transmits result information of the reply document generation process to a user terminal; 3. The artificial intelligence system according to claim 2, wherein the result information of the reply document generation received by the user terminal is displayed on a browser or output as voice.
4. one of the plurality of item menu buttons is to generate a summary of daily reports for all members; The server uses a pre-trained artificial intelligence means to generate a summary of the daily reports of all employees based on instruction and command information for generating a summary of the daily reports of all employees received in response to the text information received by the server, and transmits the result information of the summary generation of the daily reports of all employees obtained by the execution to the user terminal; The artificial intelligence system according to claim 3, characterized in that the result information of the summary generation of the daily reports of all the members received by the user terminal is displayed on a browser or output as voice.
5. one of the plurality of item menu buttons is for generating a project status report; The server executes project progress report generation using a pre-trained artificial intelligence means based on instruction command information for generating a project progress report received in response to the text information received by the server, and transmits the result information of the project progress report generation obtained by the execution to a user terminal; 5. The artificial intelligence system according to claim 4, characterized in that the user terminal is configured to display the result information of the project progress report generation received on a browser or output it as voice.
6. One of the plurality of item menu buttons is for generating a template of a requirements definition; The server generates a requirements definition template using a pre-trained artificial intelligence means based on instruction command information for generating a requirements definition template received for the text information received by the server, and transmits result information of the requirements definition template generated by the execution to a user terminal; 6. The artificial intelligence system according to claim 5, characterized in that the result information of the template generation of the requirements definition received by the user terminal is displayed on a browser or output as voice.
7. The artificial intelligence system described in any one of claims 1 to 6, characterized in that the pre-trained artificial intelligence means records the received text information and the received instruction command information in a database, and records the generated result information in the database, and when it receives text information that is identical to previously received text information and instruction command information that is identical to previously received text information, it generates result information by inserting the pre-trained information between the previous time and the current time, or generates result information by inserting information on the presence or absence of pre-trained information between the previous time and the current time.
8. An artificial intelligence system as described in any one of claims 1 to 6, characterized in that when the pre-trained artificial intelligence means generates result information based on the instruction and command information received for the received text information, newer information among the pre-trained information is included in the result information as information indicating that it is newer than older information.
9. A program of an artificial intelligence system that a user terminal displays or outputs voice based on a server, a predetermined operation presence / absence determination step of determining whether or not a predetermined operation has been performed in a state in which text is specified in the browser of the user terminal; a menu display step of displaying a plurality of item menu buttons on a browser when the predetermined operation is performed; a button operation determination step of determining whether or not one of the plurality of item menu buttons has been operated; an instruction transmission step of transmitting, when one of the plurality of item menu buttons is operated, instruction command information and designated text information corresponding to the selected item menu button from the user terminal to a server; An instruction execution step in which the server executes the instruction and command information received from the server using a pre-trained artificial intelligence means based on the received instruction and command information; A program for an artificial intelligence system, comprising a result output step of transmitting result information obtained by execution by the server to a user terminal, and displaying the result information received by the user terminal on a browser or outputting it as audio.
Citation Information
Patent Citations
Program for chat system
JP2019159469A
Cited By
Electronic device and control method therefor
WO2026147089A1
