Method and device for recognizing time information from voice information

1. A method for recognizing time information from speech data, comprising the following steps:

at a device having one or more processors and memory:

obtaining text information corresponding to speech data;

identifying at least a first time feature contained in the speech data based on the text information;

searching within a respective configuration file corresponding to the first time feature to obtain a corresponding time identifier for the first time feature;

assigning the corresponding time identifier to a field that is in intermediate time data and that corresponds to the respective configuration file in which the first time feature is located, the intermediate time data comprising multiple fields, and each field corresponding to a respective configuration file of a plurality of configuration files, each of the plurality of configuration files corresponding to a respective category related to time;

obtaining a current time in accordance with a determination that a day-of-week field in the intermediate time data has an assigned value, and that a this-week/next-week field does not have an assigned value;

determining whether a time identifier of the day-of-week field in the intermediate time data is later than a day-of-week value of the current time;

in accordance with a determination that the time identifier of the day-of-week field in the intermediate time data is later than the day-of-week value of the current time, setting the value of the this-week/next-week field in the intermediate time data as this week;

in accordance with a determination that the time identifier of the day-of-week field in the intermediate time data is earlier than the day-of-week value of the current time, setting the value of the this-week/next-week field in the intermediate time data as next week;

obtaining, according to content of one or more fields in the intermediate time data, system time data corresponding to the time information contained in the speech data; and

generating a calendar reminder at the device according to the system time data corresponding to the time information contained in the speech data.

2. The method for recognizing time information from speech data according to claim 1 , further comprising:

receiving a new time feature that does not exist in the plurality of configuration files, and a category corresponding to the new time feature;

adding the new time feature into a respective configuration file of the category corresponding to the new time feature;

determining whether the respective configuration file of the corresponding category has a time feature having to the same meaning as that of the new time feature;

in accordance with a determination that the respective configuration file of the corresponding category has a time feature having the same meaning as that of the new time feature, setting, according to a time identifier of the time feature that has the same meaning, a time identifier corresponding to the new time feature; and

in accordance with a determination that the respective configuration file of the corresponding category does not have a time feature having the same meaning as that of the new time feature, providing a new time identifier for the new time feature in the respective configuration file of the corresponding category.

3. The method for recognizing time information from speech data according to claim 1 , wherein identifying at least the first time feature contained in the speech data based on the text information includes:

searching, in a time feature table in each configuration file of the plurality of configuration files, for a time feature that matches at least a portion of the text information.

4. The method for recognizing time information from speech data according to claim 3 , wherein searching within a respective configuration file corresponding to the first time feature to obtain a corresponding time identifier for the first time feature includes:

searching, in a time identifier table in the respective configuration file in which the first time feature is located, the time identifier corresponding to the first time feature.

5. The method for recognizing time information from speech data according to claim 1 , wherein obtaining, according to content of one or more fields in the intermediate time data, system time data corresponding to the time information contained in the speech data, includes:

a determination that a morning/afternoon field in the intermediate time data does not have an assigned value, and that a date field does not have an assigned value or is assigned the same date as a current date; and

determining whether a time identifier of a time point field in the intermediate time data is later than a time point of the current time;

in accordance with a determination that the time identifier of the time point field in the intermediate time data is later than the time point of the current time, setting the morning/afternoon field in the intermediate time data to be a morning/afternoon value that is consistent with the current time; and

in accordance with a determination that the time identifier of the time point field in the intermediate time data is earlier than the time point of the current time, setting the morning/afternoon field in the intermediate time data to be a morning/afternoon value that is different from a morning/afternoon value consistent with the current time.

6. The method for recognizing time information from speech data according to claim 1 , wherein:

the first time feature corresponds to tomorrow; and

the method further comprises assigning, to a date field in the intermediate time data, a date of the current time when the current time is within a range from 0 a.m. to x a.m., wherein x is a preset time point.

7. An electronic device for recognizing time information from speech data, comprising:

one or more processors; and

memory storing instructions, the instructions, when executed by the one or more processors, cause the processors to perform operations comprising:

obtaining text information corresponding to speech data;

identifying at least a first time feature contained in the speech data based on the text information;

searching within a respective configuration file corresponding to the first time feature to obtain a corresponding time identifier for the first time feature;

assigning the corresponding time identifier to a field that is in intermediate time data and that corresponds to the respective configuration file in which the first time feature is located, the intermediate time data comprising multiple fields, and each field corresponding to a respective configuration file of a plurality of configuration files, each of the plurality of configuration files corresponding to a respective category related to time;

obtaining a current time in accordance with a determination that a day-of-week field in the intermediate time data has an assigned value, and that a this-week/next-week field does not have an assigned value;

determining whether a time identifier of the day-of-week field in the intermediate time data is later than a day-of-week value of the current time;

in accordance with a determination that the time identifier of the day-of-week field in the intermediate time data is later than the day-of-week value of the current time, setting the value of the this-week/next-week field in the intermediate time data as this week;

in accordance with a determination that the time identifier of the day-of-week field in the intermediate time data is earlier than the day-of-week value of the current time, setting the value of the this-week/next-week field in the intermediate time data as next week;

obtaining, according to content of one or more fields in the intermediate time data, system time data corresponding to the time information contained in the speech data; and

generating a calendar reminder at the device according to the system time data corresponding to the time information contained in the speech data.

8. The device for recognizing time information from speech data according to claim 7 , wherein the operations further comprise:

receiving a new time feature that does not exist in the plurality of configuration files, and a category corresponding to the new time feature;

adding the new time feature into a respective configuration file of the category corresponding to the new time feature;

determining whether the respective configuration file of the corresponding category has a time feature having to the same meaning as that of the new time feature;

in accordance with a determination that the respective configuration file of the corresponding category has a time feature having the same meaning as that of the new time feature, setting, according to a time identifier of the time feature that has the same meaning, a time identifier corresponding to the new time feature; and

in accordance with a determination that the respective configuration file of the corresponding category does not have a time feature having the same meaning as that of the new time feature, providing a new time identifier for the new time feature in the respective configuration file of the corresponding category.

9. The device for recognizing time information from speech data according to claim 7 , wherein identifying at least the first time feature contained in the speech data based on the text information includes:

searching, in a time feature table in each configuration file of the plurality of configuration files, for a time feature that matches at least a portion of the text information.

10. The device for recognizing time information from speech data according to claim 9 , wherein searching within a respective configuration file corresponding to the first time feature to obtain a corresponding time identifier for the first time feature includes:

searching, in a time identifier table in the respective configuration file in which the first time feature is located, the time identifier corresponding to the first time feature.

11. The device for recognizing time information from speech data according to claim 7 , wherein obtaining, according to content of one or more fields in the intermediate time data, system time data corresponding to the time information contained in the speech data, includes:

a determination that a morning/afternoon field in the intermediate time data does not have an assigned value, and that a date field does not have an assigned value or is assigned the same date as a current date; and

determining whether a time identifier of a time point field in the intermediate time data is later than a time point of the current time;

in accordance with a determination that the time identifier of the time point field in the intermediate time data is later than the time point of the current time, setting the morning/afternoon field in the intermediate time data to be a morning/afternoon value that is consistent with the current time; and

in accordance with a determination that the time identifier of the time point field in the intermediate time data is earlier than the time point of the current time, setting the morning/afternoon field in the intermediate time data to be a morning/afternoon value that is different from a morning/afternoon value consistent with the current time.

12. The device for recognizing time information from speech data according to claim 7 , wherein:

the first time feature corresponds to tomorrow; and

the operations further include assigning, to a date field in the intermediate time data, a date of the current time when the current time is within a range from 0 a.m. to x a.m., wherein x is a preset time point.

13. A non-transitory computer-readable storage medium storing instructions, the instructions, when executed by one or more processors, cause the processors to perform operations comprising:

obtaining text information corresponding to speech data;

identifying at least a first time feature contained in the speech data based on the text information;

searching within a respective configuration file corresponding to the first time feature to obtain a corresponding time identifier for the first time feature;

assigning the corresponding time identifier to a field that is in intermediate time data and that corresponds to the respective configuration file in which the first time feature is located, the intermediate time data comprising multiple fields, and each field corresponding to a respective configuration file of a plurality of configuration files, each of the plurality of configuration files corresponding to a respective category related to time;

obtaining a current time in accordance with a determination that a day-of-week field in the intermediate time data has an assigned value, and that a this-week/next-week field does not have an assigned value;

determining whether a time identifier of the day-of-week field in the intermediate time data is later than a day-of-week value of the current time;

in accordance with a determination that the time identifier of the day-of-week field in the intermediate time data is later than the day-of-week value of the current time, setting the value of the this-week/next-week field in the intermediate time data as this week;

in accordance with a determination that the time identifier of the day-of-week field in the intermediate time data is earlier than the day-of-week value of the current time, setting the value of the this-week/next-week field in the intermediate time data as next week;

obtaining, according to content of one or more fields in the intermediate time data, system time data corresponding to the time information contained in the speech data; and

generating a calendar reminder at the device according to the system time data corresponding to the time information contained in the speech data.

14. The non-transitory computer-readable storage medium according to claim 13 , wherein the operations further comprise:

receiving a new time feature that does not exist in the plurality of configuration files, and a category corresponding to the new time feature;

adding the new time feature into a respective configuration file of the category corresponding to the new time feature;

determining whether the respective configuration file of the corresponding category has a time feature having to the same meaning as that of the new time feature;

in accordance with a determination that the respective configuration file of the corresponding category has a time feature having the same meaning as that of the new time feature, setting, according to a time identifier of the time feature that has the same meaning, a time identifier corresponding to the new time feature; and

in accordance with a determination that the respective configuration file of the corresponding category does not have a time feature having the same meaning as that of the new time feature, providing a new time identifier for the new time feature in the respective configuration file of the corresponding category.

15. The non-transitory computer-readable storage medium for recognizing time information from speech data according to claim 13 , wherein identifying at least the first time feature contained in the speech data based on the text information includes:

searching, in a time feature table in each configuration file of the plurality of configuration files, for a time feature that matches at least a portion of the text information.

16. The non-transitory computer-readable storage medium for recognizing time information from speech data according to claim 15 , wherein searching within a respective configuration file corresponding to the first time feature to obtain a corresponding time identifier for the first time feature includes:

searching, in a time identifier table in the respective configuration file in which the first time feature is located, the time identifier corresponding to the first time feature.

17. The non-transitory computer-readable storage medium for recognizing time information from speech data according to claim 13 , wherein obtaining, according to content of one or more fields in the intermediate time data, system time data corresponding to the time information contained in the speech data, includes:

a determination that a morning/afternoon field in the intermediate time data does not have an assigned value, and that a date field does not have an assigned value or is assigned the same date as a current date; and

determining whether a time identifier of a time point field in the intermediate time data is later than a time point of the current time;

in accordance with a determination that the time identifier of the time point field in the intermediate time data is later than the time point of the current time, setting the morning/afternoon field in the intermediate time data to be a morning/afternoon value that is consistent with the current time; and

in accordance with a determination that the time identifier of the time point field in the intermediate time data is earlier than the time point of the current time, setting the morning/afternoon field in the intermediate time data to be a morning/afternoon value that is different from a morning/afternoon value consistent with the current time.