JP7267643B2 - Automated reporting system - Google Patents

Description

The present invention relates to an automatic report generation system.

Japanese Patent Laying-Open No. 2015-75792 describes a report creation system using a mobile terminal possessed by a worker who performs maintenance and inspection work on a property. This report creation system describes a report creation system that collects maintenance and inspection results for each work item of a property using information based on voice input by a worker.
Since this report creation system automatically collects voice-input information for each work item on a property, its application is limited to maintenance and inspection work on a property. Also, the system cannot report arbitrary content.

JP 2015-75792 A

An object of one invention described in this specification is to provide an automatic report creation system capable of automatically creating reports for various purposes.

The above problem is based on the knowledge that a report can be created automatically by extracting the necessary terms from the speech information included in the conversation, for example, using a terminology dictionary. In a preferred embodiment, a position information confirmation unit such as GPS is provided, and by confirming the position information and specifying the place and time of the meeting, etc., the place and start time of the meeting can be automatically determined. Based on the knowledge that it can be grasped.

One of the inventions described in this specification relates to an automatic report generation system.
This system 1 has a voice recognition section 3 , a position information confirmation section 5 , a timer section 7 and a terminology dictionary 9 . A position information confirmation unit confirms the position of the automatic report generation system and confirms that the automatic report generation system remains within a predetermined geographical range for a predetermined period of time or more. A location information confirmation unit then determines the location of the meeting in relation to the location of the automatic reporting system. The obtained meeting place may be appropriately stored in the storage unit of the system.

In this case, the timing unit obtains the start time based on the time at which the speech recognition unit recognized that the pre-stored start term was input.

The timekeeping unit also determines that the time the automated reporting system leaves the predetermined geographic area or the time that the automatic reporting system leaves the predetermined geographic area is the last time the voice was heard by the speech recognition unit. Find the end time based on the input time.

The speech recognition unit stores the speech from the start time to the end time as recorded speech, analyzes the recorded speech, and extracts utterance keywords, which are terms included in the term dictionary, from the recorded speech. Remember.
The automated reporting system also creates a file that contains information about meeting location, start time, end time, and keywords to be spoken and that is associated with the recorded speech. In this way, the system automatically generates reports.

A preferred example of the above system is as follows.
That is, the position information confirming unit displays candidates for the meeting place based on the position information of the automatic report creation system, and stores the input meeting place as the meeting place.

A preferred example of the above system is as follows.
In conjunction with a scheduler or conference room reservation system,
receive meeting information stored by a scheduler or room reservation system;
If the position information confirmed by the position information confirmation unit is related to the information included in the meeting information, either or both of the meeting place information and the attendee information included in the meeting information are read.

Another example of the automatic report generation system 1 is:
has a speech recognition unit 3, a timer unit 7, and a terminology dictionary 9;
The speech recognition unit 3 recognizes that a pre-stored start word has been input,
The timing unit 7 obtains the start time based on the time when the speech recognition unit 3 recognized that the start term was input,
The speech recognition unit 3 recognizes that a pre-stored end term has been input,
The timing unit 7 obtains the end time based on the time when the speech recognition unit 3 recognized that the end term was input,
The speech recognition unit 3 stores the speech from the start time to the end time as recorded speech, analyzes the recorded speech, and extracts utterance keywords, which are terms included in the term dictionary 9, from among the terms included in the recorded speech. and store
create a file containing information about the start time, end time and utterance keywords associated with the recorded speech;
An automatic report generation system 1 .

This automatic report generation system can automatically generate reports for various purposes.

FIG. 1 is a block diagram for explaining the automatic report creation system. FIG. 2 is a block diagram showing the basic configuration of the computer. FIG. 3 is a conceptual diagram showing an example of a report format. FIG. 4 is a conceptual diagram showing how a plurality of company names are read from the storage unit and the read company names are displayed as location candidates. FIG. 5 is a conceptual diagram showing an example of a scheduler display screen.

DESCRIPTION OF THE PREFERRED EMBODIMENTS Embodiments for carrying out the present invention will be described below with reference to the drawings. The present invention is not limited to the embodiments described below, and includes appropriate modifications within the scope obvious to those skilled in the art from the following embodiments.

FIG. 1 is a block diagram for explaining the automatic report creation system. As shown in FIG. 1, this system 1 has a speech recognition section 3, a position information confirmation section 5, a timer section 7, and a terminology dictionary 9. FIG. It is desirable that this system be a system in which processing is automatically performed by a computer. Also, this system may be capable of processing the input as one of the information when there is an input from the user.

FIG. 2 is a block diagram showing the basic configuration of the computer. As shown in this figure, the computer has an input section 11, an output section 13, a control section 15, a calculation section 17 and a storage section 19, and each element is connected by a bus 21 or the like to exchange information. is made possible. For example, the storage unit may store a control program or various types of information. When predetermined information is input from the input unit, the control unit reads out the control program stored in the storage unit. Then, the control unit appropriately reads the information stored in the storage unit and notifies it to the calculation unit. In addition, the control unit conveys appropriately input information to the calculation unit. The calculation unit performs calculation processing using the received various information, and stores the information in the storage unit. The control unit reads the calculation result stored in the storage unit and outputs it from the output unit. Various processes are executed in this manner. Each means executes these various processes.

When the automatic report preparation system 1 (the user who carries it) moves, the position information confirmation unit 5 such as GPS stores the position of the automatic report preparation system 1 in the storage unit at any time. The clock unit 7 is means for obtaining and storing the time, and also for measuring the time. For example, if the automatic report creation system 1 stays within a certain range (for example, within 10 m) for a predetermined time or more (for example, 1 minute or more), it stores the place where the person stopped as the meeting place. For this reason, information about a certain period of time and a certain range is stored in the storage unit. Then, the system 1 receives the positional information of the system 1 from the positional information confirming unit 5, and the system 1 reads out the information regarding the fixed time and the fixed range from the storage unit. Then, using the time information from the timer unit 7, the position information of the system 1 of the position information confirmation unit 5, and the information on the read fixed time and fixed range, it is determined whether the system 1 exists within a fixed time and within a fixed range. judge whether or not Then, when the system 1 judges that the system 1 exists within a certain range for a certain period of time or more, the location of the system 1 is stored in the storage unit as a meeting place. In this way, the position information confirming unit 5 confirms the position of the automatic report preparation system 1 and confirms that the automatic report preparation system 1 has stayed within a predetermined geographical range for a certain period of time or longer. Then, the position information confirming unit 5 stores the meeting place in relation to the position of the automatic report creation system 1 .

In that case, the timer unit 7
(1) the time when the automatic report creation system 1 began to stay in a predetermined geographical area;
(2) the time at which speech was input to the speech recognition unit 3 after the automatic report generation system 1 began to stay within a predetermined geographical area; Determine the start time based on the time you recognized that the term was entered. Either of these may be set in advance in the system.

The above (1) will be explained. As described above, in the system 1, the clock section 7 stores the time. Also, the position information confirmation unit 5 stores the position of the system 1 . For this reason, when the system 1 determines that the system 1 exists within a certain range for a certain period of time or more, the system 1 reads the time when the system 1 started to exist within the certain range from the storage unit in the timer unit 7, and detects the start time. Just do it.

The above (2) will be described. The speech recognition unit 3 has, for example, a sound collection function. Then, the speech recognition unit 3 appropriately records the speech input to the system 1 and stores it in the storage unit. At this time, the speech recognition unit 3 may analyze each term included in the speech. The system 1 may obtain information about time from the clock unit 7 and store each term in the storage unit together with the time when each term was input to the system 1 . As described above, when the system 1 determines that the automatic report creation system 1 has stayed in a predetermined geographical range for a certain period of time or more, the voice recognition unit 3 (automatically) starts recording, or The voice recognition section 3 may be turned on. The system 1 may determine that a meeting or the like has started when the volume of the sound (particularly in a specific frequency range) stored in the storage unit is above a certain level, and store that time as the start time. In this case, for example, the information on the specific frequency range and the information on the constant volume are stored in the storage unit, read out as appropriate, and the audio information stored in the storage unit and the voice information read out from the storage unit are specified. It is sufficient to compare the information related to the frequency domain and the information related to a certain volume, and determine that the volume of the audio information in a specific frequency domain among the audio information stored in the storage unit is above a certain level. In this way, the system 1 causes the storage unit to store the time when the voice is input to the voice recognition unit 3 as the start time after the automatic report creation system 1 begins to stay within a predetermined geographical range. be able to.

Finally, the above (3) will be explained. In this case as well, the description of the same parts as in (2) above is omitted. A term dictionary 9 stores one or more start terms, for example associated with the start of a meeting. An example of a starting term is "Thank you for waiting." "Thank you," "Please," "Thank you," "I'll start," and "I'll start." The speech recognition section 3 stores the speech in the storage section. At this time, for example, information about the time when each term was input to the system 1 is received from the clock unit 7, and information about the time is stored together with the recognized term in the storage unit. The system 1 reads from the term dictionary 9 the term stored as the starting term. Then, the system 1 determines whether or not the term (conversation term) stored in the storage unit matches the read start term. Then, when the term (conversational term) stored in the storage unit matches any of the start terms, the time at which the conversational term was input to the system 1 is read out from the storage unit. At this time, the clock unit 7 of the system 1 may obtain the time. Then, the read time is stored in the storage unit as the start time. In this manner, the system 1 can obtain the start time based on the time at which the speech recognition unit 3 recognizes that the pre-stored start term has been input.

Another example of (3) is, for example, when the user arrives at the meeting place and just before the meeting starts, the user turns on the power of the system 1 and speaks a start word (for example, "start"), so that the system 1 , the time at which the start of the meeting is recognized and the start term is input to the system 1 may be received from the timer unit and stored in the storage unit as the start time. At this time, the position information confirming unit 5 may store the place where the system 1 exists in the storage unit as the meeting place.

In the example of (3) above, when a term used for a meeting is generated, it can be set as the start time. This prevents the system from erroneously judging that the meeting has started because it has stopped. In addition, for example, it is possible to prevent the system from erroneously determining that a meeting has started when the user has been sitting in the waiting room for a certain period of time to transfer trains or buses.

In addition, the timing unit 7 measures (1) the time when the automatic report preparation system 1 leaves the predetermined geographical range, (2) before the time when the automatic report preparation system 1 leaves the predetermined geographical range, The end time is obtained based on the time when the voice was last input to the voice recognition unit 3 and (3) the time when the voice recognition unit recognized that the pre-stored end term was input. Either of these may be set in advance in the system.

The above (1) will be explained. As described above, in the system 1, the clock section 7 stores the time. Also, the position information confirmation unit 5 stores the position of the system 1 . Therefore, when the system 1 determines that the system 1 has left the certain geographical range, the system 1 judges that the meeting has ended, reads out the time when the system 1 left the certain geographical range from the storage unit in the clock unit 7, and terminates the meeting. It should be time.

The above (2) will be described. The system 1, for example, obtains information about the time from the clock unit 7, and stores in the storage unit the time when the speech was input to the system 1 (therefore, the speech recognition unit 3) and each term analyzed by the speech recognition unit. . That is, the system 1 stores each term and the time at which the term was spoken in the memory. A position information confirmation unit 5 stores the position of the system 1, and the system 1 analyzes the position information and recognizes that the system 1 has left a predetermined geographical range. Since system 1 remembers each term and the time at which it was spoken, the time at which the last term was spoken is the time prior to the time system 1 left the given geographic area. be the end time. In this way, the system 1 stores the time when the voice was last input to the speech recognition unit 3 before the time when the automatic report preparation system 1 left the predetermined geographical range as the end time. can be stored in

Finally, the above (3) will be explained. In this case as well, the description of the same parts as in (2) above is omitted. A term dictionary 9 stores, for example, one or more end terms associated with the start of a meeting. Examples of ending terms are "thank you", "end", "good job", "thank you for your hard work". The speech recognition section 3 stores the speech in the storage section. The system 1 reads out the terms stored as end terms from the term dictionary 9 . Then, the system 1 determines whether or not the term (conversation term) stored in the storage unit matches the read end term. Then, if the term (conversational term) stored in the storage unit matches any of the end terms, the time at which the conversational term was input to the system 1 is read from the storage unit. Then, the read time is stored in the storage unit as the end time. In this manner, the system 1 can determine and store the end time based on the time at which the speech recognition unit recognizes that the pre-stored end term has been entered.

Another example of (3) is, for example, when the user leaves the meeting place, the user turns on the power of the system 1 and speaks an end word (for example, "end of recording"). The time at which the end term is input to the system 1 may be received from the clock unit and stored as the end time in the storage unit. At this time, the system 1 may automatically turn off the power.

The speech recognition unit 3 stores the speech from the start time to the end time as recorded speech, analyzes the recorded speech, and extracts utterance keywords, which are terms included in the term dictionary 9, from among the terms included in the recorded speech. and memorize it.

A term dictionary 9 stores a plurality of utterance keywords. The system 1 reads the utterance keyword from the term dictionary 9, reads out the conversation terms stored in the storage unit, and determines whether the conversation term matches any of the utterance keywords. Then, if the conversational term matches any of the utterance keywords, the utterance keyword may be stored in the storage unit.

The system then creates the data for the report.
The automatic report creation system 1 reads out the information on the meeting location, start time, end time and utterance keywords stored in the storage unit. In addition, the system reads data relating to the recorded speech of the conversation stored in the storage unit. Then, the system 1 uses the read meeting place, start time, end time and speech keyword information and recorded speech data to generate a file containing the meeting place, start time, end time and speech keywords, and to extract the recorded speech. create a file associated with In this way, the system automatically generates reports.

FIG. 3 is a conceptual diagram showing an example of a report format. Display data is created so that the information about the meeting place stored in the storage unit and read out is displayed at the position 31 about the place. This can be done, for example, by placing the read meeting place data following the location tag. When such data is prepared, the information on the place of the meeting is displayed at the position 31 on the screen where the user displays the report. The date and time may also be displayed at the position 33 related to the date and time using the information about the start time and the end time stored in the storage unit. The date and time may be displayed by displaying the start time and the end time, or by displaying only the start time, or by calculating the difference between the end time and the start time and displaying the meeting time. can be At the content position 37, one or more utterance keywords stored in the storage unit are displayed. Examples of spoken keywords are terms that need to be explained with respect to a particular drug. Then, like informed consent, one can easily check whether all the terms that need to be explained have been spoken. If all the spoken keywords are not displayed at the content position 37, the content of the conversation may be checked using the voice file reading icon 39, which will be described later.

Also, the utterance keyword that needs to be explained may be stored in advance in the storage unit. Then, the system 1 may determine whether the utterance keywords included in the conversation match all the required keywords. In addition, the system 1 may display information calling attention to the report when the utterance keywords included in the conversation do not cover all the necessary keywords. In this method, terms and marks for calling attention are stored in the storage unit, and if the utterance keywords included in the conversation do not cover all the necessary keywords, the words and marks for calling attention are stored in the storage unit. Terms and marks should be processed as they appear in the report.

If the participants have the same application installed, the location information confirmation unit 5 can be used to ascertain who attended the same meeting. In this case, the storage unit stores information about the user of the terminal that installed each system, reads out the stored information about the user, and controls it so that it is displayed at the position 35 where the participants are displayed. good too.

The position information confirming unit 5 may display candidates for the meeting place based on the position information of the automatic report creation system 1, and may store the input meeting place as the meeting place.

For example, there is a case where a building is occupied by multiple companies. In this case, the storage unit stores information about companies such as a plurality of company names in relation to the location of the building. A location information confirmation unit 5 confirms the location of the system 1 and reads out information on a plurality of companies located in the building. Then, the system 1 reads the information about the plurality of companies from the storage unit, for example, and displays the names of the plurality of companies in the position 31 related to the location of the report. A plurality of company names may be displayed in a pull-down format. FIG. 4 is a conceptual diagram showing how a plurality of company names are read from the storage unit and the read company names (AAAAAA, BBBBBB, and CCCCCC) are displayed as candidates for locations (meeting locations). . Then, if the user selects the company name, the system 1 receives input regarding the company name. Then, the system 1 may store the entered company name in the storage unit as the meeting place. In this way, candidates for the meeting place can be displayed, and the meeting place can be easily specified without manual input.

In conjunction with a scheduler or conference room reservation system,
receive meeting information stored by a scheduler or room reservation system;
If the position information confirmed by the position information confirmation unit 5 is related to the information included in the meeting information, either or both of the meeting place information and the attendee information included in the meeting information may be read.

FIG. 5 is a conceptual diagram showing an example of a scheduler display screen. In this example, when a date on the calendar is specified with an arrow icon 41, the schedule scheduled for that day is displayed on the schedule display screen 43. FIG. This system is associated with each date and stores the schedule for that day in the storage unit. The schedule includes meeting information such as meeting titles, scheduled meeting times, meeting locations, scheduled attendees, and meeting outlines. Then, the system 1 linked with the scheduler reads information about the meeting place from the storage unit. Then, the system 1 may determine that the meeting place is correct when the position information confirmed by the position information confirmation unit 5 matches the meeting place. In addition, the system 1 may read the information of prospective attendees stored regarding the meeting from the storage unit. Then, the read information about the expected attendees may be written in the attendee column of the report described above.

Another aspect of the automatic report preparation system has a speech recognition section 3, a timer section 7, and a terminology dictionary 9. FIG. It is desirable that this system be a system in which processing is automatically performed by a computer. Also, this system may be capable of processing the input as one of the information when there is an input from the user. This system basically performs the same processing as the system described above.

For example, a user speaks a starting term to the system. The voice is then input into the system. Then, the speech recognition unit 3 recognizes that the pre-stored start word has been input. For example, the term dictionary 9 stores one or more starting terms. The speech recognition section 3 stores the speech in the storage section. The system 1 reads from the term dictionary 9 the term stored as the starting term. Then, the system 1 determines whether or not the term (conversation term) stored in the storage unit matches the read start term. Then, when the term (conversational term) stored in the storage unit matches any of the start terms, the time at which the conversational term was input to the system 1 is read out from the storage unit. At this time, the clock unit 7 obtains the start time based on the time when the speech recognition unit 3 recognized that the start term was input.

For example, a user speaks a termination term to the system. The voice is then input into the system. The speech recognition unit 3 recognizes that the pre-stored ending term has been input. For example, the term dictionary 9 stores one or more end terms. The speech recognition section 3 stores the speech in the storage section. The system 1 reads out the terms stored as end terms from the term dictionary 9 . Then, the system 1 determines whether or not the term (conversation term) stored in the storage unit matches the read end term. Then, if the term (conversational term) stored in the storage unit matches any of the end terms, the time at which the conversational term was input to the system 1 is read from the storage unit. The timing unit 7 may obtain the end time based on the time when the speech recognition unit 3 recognized that the end term was input.

The speech recognition unit 3 stores speech from the start time to the end time as recorded speech. The system 1 then creates a recorded voice file. The recorded voice is analyzed, and utterance keywords, which are included in the term dictionary 9, are extracted and stored from among the terms included in the recorded voice. Then, a file containing information on the start time, end time and utterance keywords and associated with the recorded voice is created.

The automatic report creation system 1 described above can be said to have a configuration in which the position information confirmation unit 5 is further included in the above-described automatic report creation system.

INDUSTRIAL APPLICABILITY The present invention can be used in fields related to information communication.

1 Automatic Report Preparation System 3 Voice Recognition Unit 5 Location Information Confirmation Unit 7 Clock Unit 9 Terminology Dictionary

Claims (6)

An automated reporting system comprising:
having a voice recognition unit, a location information confirmation unit, a timer unit, and a terminology dictionary;
When the position information confirmation unit confirms the position of the automatic report creation system and the automatic report creation system stays in a predetermined geographical range for a certain period of time or more,
The location information confirmation unit obtains a meeting location associated with the location of the automatic reporting system;
The timing unit
determining the start time based on the time at which the speech recognition unit recognized that the pre-stored start term was input;
The timing unit is configured so that the time when the automatic report generation system leaves the predetermined geographical range, or the time before the time when the automatic report generation system leaves the predetermined geographical range, and the speech recognition unit receives a voice. Find the end time based on the last input time,
The speech recognition unit stores the speech from the start time to the end time as recorded speech, analyzes the recorded speech, and recognizes terms included in the term dictionary among the terms included in the recorded speech. Extract and store utterance keywords,
creating a file containing information about the meeting location, the start time, the end time and the utterance keywords, the file associated with the recorded speech;
Automated reporting system. The automatic report generation system of claim 1,
The position information confirming unit displays candidates for the meeting place based on the position information of the automatic report creation system, and stores the input meeting place as the meeting place. The automatic report generation system of claim 1,
In conjunction with a scheduler or conference room reservation system,
receiving meeting information stored by the scheduler or conference room reservation system;
reading either or both of the meeting place information and the attendee information included in the meeting information when the location information confirmed by the location information checking unit matches the meeting location information included in the meeting information;
The file contains either or both of meeting location information and attendee information contained in the read meeting information,
system. the computer,
An automated reporting system comprising:
having a voice recognition unit, a location information confirmation unit, a timer unit, and a terminology dictionary;
When the position information confirmation unit confirms the position of the automatic report creation system and the automatic report creation system stays in a predetermined geographical range for a certain period of time or more,
The location information confirmation unit obtains a meeting location associated with the location of the automatic reporting system;
The timing unit
determining the start time based on the time at which the speech recognition unit recognized that the pre-stored start term was input;
The timekeeping unit controls the time at which the automatic report generation system leaves the predetermined geographical range, or before the time at which the automatic report generation system leaves the predetermined geographical range, and the speech recognition unit receives a voice. Find the end time based on the last input time,
The speech recognition unit stores the speech from the start time to the end time as recorded speech, analyzes the recorded speech, and identifies terms included in the term dictionary among the terms included in the recorded speech. Extract and store utterance keywords,
creating a file containing information about the meeting location, the start time, the end time and the utterance keywords, the file associated with the recorded speech;
A program to act as an automated reporting system. A program for causing a computer to function as an automated reporting system, comprising:
The automatic report creation system has a voice recognition unit, a location information confirmation unit, a timer unit, and a terminology dictionary,
When the position information confirmation unit confirms the position of the automatic report creation system and the automatic report creation system stays in a predetermined geographical range for a certain period of time or more,
The location information confirmation unit obtains a meeting location associated with the location of the automatic reporting system;
The timing unit
determining the start time based on the time at which the speech recognition unit recognized that the pre-stored start term was input;
The timing unit is configured so that the time when the automatic report generation system leaves the predetermined geographical range, or the time before the time when the automatic report generation system leaves the predetermined geographical range, and the speech recognition unit receives a voice. Find the end time based on the last input time,
The speech recognition unit stores the speech from the start time to the end time as recorded speech, analyzes the recorded speech, and identifies terms included in the term dictionary among the terms included in the recorded speech. Extract and store utterance keywords,
Based on the information on the meeting location, the start time, the end time, and the utterance keyword, which are data for the report, and the format of the report that is displayed based on the data for the report, the recorded voice and produce display data that is output as a report with relevant content;
program. An automatic report preparation method using an automatic report preparation system,
The automatic report creation system has a voice recognition unit, a location information confirmation unit, a timer unit, and a terminology dictionary,
When the position information confirmation unit confirms the position of the automatic report creation system and the automatic report creation system stays in a predetermined geographical range for a certain period of time or more,
The location information confirmation unit obtains a meeting location associated with the location of the automatic reporting system;
The timing unit
determining the start time based on the time at which the speech recognition unit recognized that the pre-stored start term was input;
The timing unit is configured so that the time when the automatic report generation system leaves the predetermined geographical range, or the time before the time when the automatic report generation system leaves the predetermined geographical range, and the speech recognition unit receives a voice. Find the end time based on the last input time,
The speech recognition unit stores the speech from the start time to the end time as recorded speech, analyzes the recorded speech, and recognizes terms included in the term dictionary among the terms included in the recorded speech. Extract and store utterance keywords,
Based on the information on the meeting location, the start time, the end time, and the utterance keyword, which are data for the report, and the format of the report that is displayed based on the data for the report, the recorded voice and produce display data that is output as a report with relevant content;
Automated reporting method.

Images