Granted Patent B2

US 12,461,711 · App. 16/760,235 · Granted Nov 4, 2025

Inventors: Tianshi Chen (Pudong New Area, CN); Shaoli Liu (Pudong New Area, CN); Zai Wang (Pudong New Area, CN); Shuai Hu (Pudong New Area, CN)

Assignee: SHANGHAI CAMBRICON INFORMATION TECHNOLOGY CO., LTD.

G06F7/5443G06F9/3001G06F9/445G06F40/263G06F40/58G06N3/02G06N3/04G06N3/08G06T1/20G06T1/60G06T3/4046G06T3/4053G06T5/20G06T5/50G06T7/20G06V10/70G06V10/82G06V10/94G10L15/00G06N3/063G06N3/082G06N3/084G06T2207/10016G06T2207/20084G06V2201/07

Abstract

Claims (27)

1 . An information processing method, wherein the method is applied to a terminal device that includes a computation device, and the computation device stores an instruction set which includes at least one operation instruction stream,

wherein the instruction set includes a matrix-multiply-vector instruction, a vector-multiply-matrix instruction, a matrix-multiply-scalar instruction, a tensor operation instruction, a matrix addition instruction, a matrix subtraction instruction, a matrix retrieving instruction, a matrix loading instruction, a matrix saving instruction, and a matrix moving instruction,

and the method includes:

obtaining first information, wherein the first information is to be processed by the terminal device;

calling the operation instruction stream in the computation device to process the first information to obtain second information, wherein the calling of the operation instruction stream includes;

obtaining a basic operation sequence of a neural network structure,

obtaining a first instruction descriptor stream based on the basic operation sequence,

simplifying the first instruction descriptor stream to obtain a second instruction descriptor stream, and

calling the operation instruction stream based on the second instruction descriptor stream; and

outputting the second information,

wherein the obtaining the first information includes:

pre-processing raw information to obtain the first information, wherein the first information is in a preset format, and the pre-processing includes data deduplication, data encoding, data conversion, and normalization.

2 . The method of claim 1 , wherein when the first information is voice information, the calling of the operation instruction stream in the computation device to process the first information to obtain the second information includes:

calling a voice recognition algorithm in the computation device to recognize the voice information to obtain the second information,

wherein the second information is text information, and the voice recognition algorithm includes at least one operation instruction for voice recognition.

3 . The method of claim 1 , wherein when the first information is image information, the calling of the operation instruction stream in the computation device to process the first information to obtain the second information includes:

calling an image style conversion algorithm in the computation device to convert the style of the image information to obtain the second information,

wherein the style of the second information differs from that of the first information, and the image style conversion algorithm includes at least one operation instruction for converting a painting style or the image style.

4 . The method of claim 1 , wherein when the first information is image information that includes at least one object to be recognized, the calling of the operation instruction stream in the computation device to process the first information to obtain the second information includes:

calling an object detection algorithm in the computation device to perform object detection on the image information to obtain the second information, wherein the second information includes at least a location of an object, and the object detection algorithm includes at least one operation instruction for object detection.

5 . The method of claim 1 , wherein when the first information is voice information to be translated, the calling of the operation instruction stream in the computation device to process the first information to obtain the second information includes:

calling a language translation algorithm in the computation device to translate the voice information to obtain the second information,

wherein the first information differs from the second information, and the language translation algorithm includes at least one operation instruction for language translation.

6 . The method of claim 1 , wherein the simplifying of the first instruction descriptor stream to obtain the second instruction descriptor stream includes:

traversing instruction descriptors in the first instruction descriptor stream to obtain a plurality of instruction descriptors;

searching for a redundant operation in the plurality of instruction descriptors; and

deleting an instruction descriptor corresponding to the redundant operation to obtain the second instruction descriptor stream.

Assignments (1)

Priority Claims (1)

Continuity (1)

References Cited (400)