Information processing apparatus and method for conversion of video picture into text

1. A document production system, comprising:

a terminal apparatus; and

a server, which, in operation:

receives retrieval information from the terminal apparatus;

retrieves file information based on the retrieval information, the file information including a selection of files for a user to select from, the selection of files including first video picture data of a video picture shot by a wearable camera attached to or used by a police officer and second video picture data of a video picture shot by an on-vehicle camera mounted on a police vehicle;

transmits the file information to the terminal apparatus, the terminal apparatus receives the file information from the server and transmits selection information to the server, the selection information selecting a file from the selection of files;

receives the selection information from the terminal apparatus;

obtains, based on the selection information, video picture data from a storage apparatus storing the first video picture data and the second video picture data;

extracts voice data included in the obtained video picture data and converts the extracted voice data into text data;

generates a file including a plurality of data sets,

each of the plurality of data sets including a time stamp of a voice included in the voice data, text included in the text data that corresponds to the voice, and information associated with the obtained video picture data that includes information about events that occurred within a predetermined amount of time of the time stamp; and

transmits the generated file to the terminal apparatus.

2. The document production system according to claim 1 , wherein the storage apparatus stores the time stamp of the voice included in the voice data.

3. The document production system according to claim 1 , wherein each of the plurality of data sets includes image data included in the obtained video picture data that is shot at a time indicated by the time stamp.

4. The document production system according to claim 1 , wherein the storage apparatus stores the information associated with the obtained video picture data together with a time when the information has been generated.

5. The document production system according to claim 1 , wherein the information associated with the obtained video picture data includes information for at least one of a light ON state of the police vehicle, a sudden starting detection of the police vehicle, a collision detection of the police vehicle, a speed excess detection of the police vehicle, or a back door opening detection of the police vehicle.

6. The document production system according to claim 1 , wherein the information associated with the obtained video picture data includes information for at least one of a takeout of a gun state indicating that the gun is taken out from a gun folder, a manual record on/off state indicating that the wearable camera or the on-vehicle camera is turned on or off by a user, a dash detection, a falling detection, or a fight detection of the user.

7. The document production system according to claim 1 , wherein the storage apparatus stores global positioning system (GPS) information of the police officer or the police vehicle in association with a time when a voice occurs.

8. The document production system according to claim 1 , wherein the server converts the voice data into the text data in a video picture range designated by the terminal apparatus.

9. The document production system according to claim 1 , wherein each of the plurality of data sets includes identification information of a speaker in the voice data.

10. The document production system according to claim 1 , wherein the server, in operation, links the generated file to the obtained video picture data as a generation source of the generated file, and stores the generated file with the obtained video picture data in the storage apparatus.

11. A method comprising:

receiving, by a server, retrieval information from a terminal apparatus;

retrieves, by the server, file information based on the retrieval information, the file information including a selection of files for a user to select from, the selection of files including first video picture data of a video picture shot b a wearable camera attached to or used by a police officer and second video picture data of a video picture shot by an on-vehicle camera mounted on a police vehicle;

transmits, by the server, the file information to the terminal apparatus, the terminal apparatus receives the file information from the server and transmits selection information to the server, the selection information selecting a file from the selection of files;

receiving, by the server, the selection information from the terminal apparatus;

obtaining, by the server and based on the selection information, video picture data from a storage apparatus storing the first video picture data and the second video picture data;

extracting, by the server, voice data included in the obtained video picture data;

converting, by the server, the voice data into text data;

generating a file including a plurality of data sets,

each of the plurality of data sets including a time stamp of a voice included in the voice data, text included in the text data that corresponds to the voice, and information associated with the video picture data that includes information about events that occurred within a predetermined amount of time of the time stamp;

transmitting the generated file to the terminal apparatus.

12. The document production system according to claim 1 , wherein the time stamp is linked to the obtained video picture data, the generated file is displayed on the terminal apparatus, and a video picture is displayed on the terminal apparatus in response to the time stamp being selected by a user of the terminal apparatus.

13. The document production system according to claim 1 , wherein, in a case where the selection information selects the first video picture data, the information associated with the obtained video picture data includes information for at least one of a takeout of a gun state indicating that the gun is taken out from a gun folder, a manual record on/off state indicating that the wearable camera is turned on or off by the police officer, a dash detection, a falling detection, or a fight detection of the police officer.

14. The document production system according to claim 1 , wherein, in a case where the selection information selects the second video picture data, the information associated with the obtained video picture data includes information for at least one of a light ON state of the police vehicle, a sudden starting detection of the police vehicle, a collision detection of the police vehicle, a speed excess detection of the police vehicle, or a back door opening detection of the police vehicle.