Voice assistant for records

1. A method comprising:

receiving a first voice data via a video including image frames originating at a camera, the first voice data being indicative of speech provided to an assistant device, the speech requesting first information stored in a database record;

determining a first request type based on the first information, the first request type indicative of a type of data that the speech is requesting;

generating, by a processor, a first query data for requesting the first information stored in the database record based on the first request type, the first query data referencing the database record storing the first information;

determining at an access server a request type and a variable, the request type being configured to identify the variable, the variable being used to form the first query data and also configured to be included in translated text determined from the speech;

providing the first query data to a database server storing the database record;

receiving a first record data from the database server providing the first information;

providing the first information to the assistant device for voice playback in response to the request for the first information; and

determining characteristics of the speech, wherein the first query data is also based on the characteristics of the speech, at least one characteristic of the speech being used to identify a person providing a portion of the speech to identify different users having a history of interacting with the assistant device.

2. The method of claim 1 , wherein the characteristics of the speech include one or more of a volume of the speech, a speed of the speech, a language of the speech, or an accent of the speech.

3. The method of claim 1 , further comprising:

identifying a person providing the speech, wherein the first query data is also based on the identification of the person providing the speech.

4. The method of claim 1 , further comprising:

determining content of the first record data;

generating a second query data based on the first query data and the first record data; and

providing the second query data to the database server storing the database record.

5. The method of claim 4 , wherein determining the content of the first record data includes identifying a first time period associated for data included in the content, and the second query data is associated with a second time period different than the first time period for the data.

6. The method of claim 5 , wherein the second time period is subsequent to the first time period.

7. An electronic device, comprising:

one or more processors; and

memory storing instructions, wherein the processor is configured to execute the instructions such that the processor and memory are configured to:

receive a first voice data via a video including image frames originating at a camera, the first voice data being indicative of speech provided to an assistant device, the speech requesting first information stored in a database record;

determine a first request type based on the first information, the first request type indicative of a type of data that the speech is requesting;

generate a first query data for requesting the first information stored in the database record based on the first request type, the first query data referencing the database record storing the first information;

determine at an access server a request type and a variable, the request type being configured to identify the variable, the variable being used to form the first query data and also configured to be included in translated text determined from the speech;

provide the first query data to a database server storing the database record;

receive a first record data from the database server providing the first information;

provide the first information to the assistant device for voice playback in response to the request for the first information; and

determine characteristics of the speech, wherein the first query data is also based on the characteristics of the speech, at least one characteristic of the speech being used to identify a person providing a portion of the speech to identify different users having a history of interacting with the assistant device.

8. The electronic device of claim 7 , wherein the characteristics of the speech include one or more of a volume of the speech, a speed of the speech, a language of the speech, or an accent of the speech.

9. The electronic device of claim 7 , wherein the processor is configured to execute the instructions such that the processor and memory are configured to:

identify a person providing the speech, wherein the first query data is also based on the identification of the person providing the speech.

10. The electronic device of claim 7 , wherein the processor is configured to execute the instructions such that the processor and memory are configured to:

determine content of the first record data;

generate a second query data based on the first query data and the first record data; and

provide the second query data to the database server storing the database record.

11. The electronic device of claim 10 , wherein determining the content of the first record data includes identifying a first time period associated for data included in the content, and the second query data is associated with a second time period different than the first time period for the data.

12. The electronic device of claim 11 , wherein the second time period is subsequent to the first time period.

13. A computer program product including one or more non-transitory computer-readable media storing computer program instructions, execution of which by a processing system causes the processing system to perform operations comprising:

receive a first voice data via a video including image frames originating at a camera, the first voice data being indicative of speech provided to an assistant device, the speech requesting first information stored in a database record;

determine a first request type based on the first information, the first request type indicative of a type of data that the speech is requesting;

generate a first query data for requesting the first information stored in the database record based on the first request type, the first query data referencing the database record storing the first information;

determine at an access server a request type and a variable, the request type being configured to identify the variable, the variable being used to form the first query data and also configured to be included in translated text determined from the speech;

provide the first query data to a database server storing the database record;

receive a first record data from the database server providing the first information;

provide the first information to the assistant device for voice playback in response to the request for the first information; and

determine characteristics of the speech, wherein the first query data is also based on the characteristics of the speech, at least one characteristic of the speech being used to identify a person providing a portion of the speech to identify different users having a history of interacting with the assistant device.

14. The computer program product of claim 13 , wherein the characteristics of the speech include one or more of a volume of the speech, a speed of the speech, a language of the speech, or an accent of the speech.

15. The computer program product of claim 13 , wherein the processor is configured to execute the instructions such that the processor and memory are configured to:

identify a person providing the speech, wherein the first query data is also based on the identification of the person providing the speech.

16. The computer program product of claim 13 , wherein the processor is configured to execute the instructions such that the processor and memory are configured to:

determine content of the first record data;

generate a second query data based on the first query data and the first record data; and

provide the second query data to the database server storing the database record.

17. The computer program product of claim 13 , wherein determining the content of the first record data includes identifying a first time period associated for data included in the content, and the second query data is associated with a second time period different than the first time period for the data.