Method, apparatus, device and storage medium for information processing

Patent metadata

Field	Value
Publication number	US-2022027770-A1
Application number	US-202117380684-A
Country	US
Kind code	A1
Filing date	Jul 20, 2021
Priority date	Jul 21, 2020
Publication date	Jan 27, 2022
Grant date	—

Abstract

The present disclosure relates to a method, apparatus, device and storage medium for information processing. Specifically, a method is proposed for information processing. In the method, multiple observation samples associated with multiple factors of an application system are received, an observation sample among the multiple observation samples comprising a group of observation values of the multiple factors. At least one attribute of the multiple observation samples is obtained. At least one processing procedure is determined based on the at least one attribute, a processing procedure of the at least one processing procedure being used for processing the multiple observation samples to obtain a causality between the multiple factors. Further, there is provided an apparatus, device and storage medium for information processing. Based on input data to be processed, an algorithm for processing the input data may be automatically determined. In this way, on one hand, the reliance on human labor may be reduced, and on the other hand, the performance and accuracy of the data processing procedure may be increased.

First claim

1 . A method for information processing, comprising:
receiving multiple observation samples associated with multiple factors of an application system, an observation sample among the multiple observation samples comprising a group of observation values of the multiple factors; obtaining at least one attribute of the multiple observation samples; and determining at least one processing procedure based on the at least one attribute, a processing procedure of the at least one processing procedure being used for processing the multiple observation samples to obtain a causality between the multiple factors.

2 . The method of claim 1 , wherein obtaining the at least one attribute of the multiple observation samples comprises obtaining at least any of:
a relationship type of the multiple factors; a dimension of the multiple factors; a data type of the multiple factors; and the number of the multiple observation samples.

3 . The method of claim 2 , wherein
the relationship type comprises at least any of a linear relationship and a non-linear relationship; the dimension comprises at least any of a high dimension and a low dimension; the data type comprises at least any of a continuous data type, a discrete data type and a mixed data type; and the number comprises at least any of a large sample number and a small sample number.

4 . The method of claim 1 , wherein determining the at least one processing procedure comprises: selecting from a processing procedure library the at least one processing procedure that matches the at least one attribute.

5 . The method of claim 4 , wherein selecting the at least one processing procedure comprises:
generating a feature of the multiple observation samples based on the at least one attribute; and looking up the at least one processing procedure in the processing procedure library based on the feature.

6 . The method of claim 1 , wherein determining the at least one processing procedure further comprises:
receiving an instruction on a field to which the application system belongs; and determining the at least one processing procedure for processing the multiple observation samples based on the at least one attribute and the field.

7 . The method of claim 1 , wherein the at least one processing procedure comprises multiple processing procedures, and the method further comprises: using the multiple processing procedures to process the multiple observation samples respectively, so as to provide multiple causalities between the multiple factors, a causality among the multiple causalities being provided by using a processing procedure among the multiple processing procedures to process the multiple observation samples.

8 . The method of claim 7 , wherein providing the multiple causalities comprises: for a processing procedure among the multiple processing procedures,
receiving an instruction on specifying a group of evaluation indicators for evaluating a causality; determining a control parameter for setting the processing procedure based on the group of evaluation indicators; and determining the causality based on the control parameter and the multiple observation samples.

9 . The method of claim 8 , wherein determining the causality comprises:
adjusting the control parameter based on the group of evaluation indicators; and updating the causality based on the adjusted control parameter.

10 . The method of claim 9 , wherein updating the causality comprises:
receiving an instruction on a stop criterion for stopping an iteration; and in response to the updated causality meeting the stop criterion, stopping the iteration to provide the updated causality.

11 . The method of claim 9 , wherein updating the causality further comprises:
updating the updated causality; receiving an instruction on feedback on the updated causality; and adjusting the causality based on the feedback.

12 . The method of claim 11 , wherein outputting the updated causality further comprises: outputting information associated with the group of evaluation indicators, the information being determined based on the updated causality.

13 . The method of claim 11 , wherein outputting the updated causality comprises at least any of:
presenting the causality in a directed acyclic graph, multiple nodes in the directed acyclic graph representing the multiple factors respectively, and an edge in the directed acyclic graph representing a causality between two factors among the multiple factors; and presenting the causality in a matrix, multiple dimensions of the matrix representing the multiple factors respectively, and an element of the matrix representing a weight of a causality between two factors corresponding to the element among the multiple factors.

14 . The method of claim 1 , wherein the multiple factors represent multiple device control parameters of the application system.

15 . The method of claim 8 , wherein the group of observation values included in the observation sample are collected from one or more sensors deployed in the application system; and the method further comprises: providing the causality to the application system.

16 . A device for information processing, comprising a processor, the processor being configured to:
receive multiple observation samples associated with multiple factors of an application system, an observation sample among the multiple observation samples comprising a group of observation values of the multiple factors; obtain at least one attribute of the multiple observation samples; and determine at least one processing procedure based on the at least one attribute, a processing procedure of the at least one processing procedure being used to process the multiple observation samples so as to obtain a causality between the multiple factors.

17 - 32 . (canceled)

33 . A method for information processing, comprising:
receiving multiple observation samples associated with multiple factors of an application system, an observation sample among the multiple observation samples comprising a group of observation values of the multiple factors; using multiple processing procedures to process the multiple observation samples, respectively, so as to determine multiple causalities between the multiple factors, a causality among the multiple causalities being obtained based on a processing procedure among the multiple processing procedures.

34 - 38 . (canceled)

Assignees

• Nec Corp

Inventors

• Pan Zheng

Classifications

• G06F18/2132

  based on discrimination criteria, e.g. discriminant analysis · CPC title

• G06F18/29

  Graphical models, e.g. Bayesian networks · CPC title

• G06N7/01 Primary

  Probabilistic graphical models, e.g. probabilistic networks · CPC title

• G06F18/214

  Generating training patterns; Bootstrap methods, e.g. bagging or boosting · CPC title

• G06F18/2178

  based on feedback of a supervisor · CPC title