Data processing method and electronic device

Patent metadata

Field	Value
Publication number	US-12386841-B2
Application number	US-202318458291-A
Country	US
Kind code	B2
Filing date	Aug 30, 2023
Priority date	Aug 31, 2022
Publication date	Aug 12, 2025
Grant date	Aug 12, 2025

Abstract

Embodiments of the present disclosure provide a data processing method and an electronic device, which relate to the computer field. The method includes: acquiring a time-series dataset, the time-series dataset comprising multiple time-series data items each comprising a time and multiple attribute parameters corresponding thereto; acquiring a target attribute parameter being at least one of the multiple attribute parameters; determining, based on a time-series model, at least one influence factor of the target attribute parameter, the at least one influence factor indicating at least one attribute parameter influencing the target attribute parameter and at least one time corresponding to the at least one attribute parameter; and outputting the at least one influence factor. As such, according to the embodiments of the present disclosure, for a target attribute parameter, at least one influence factor can be determined based on a time-series dataset and a time-series model. Therefore, an accurate reference can be provided for a decision on the target attribute parameter, and the decision made in this way is more accurate.

First claim

The invention claimed is:

1. A data processing method for retail forecasting, the method comprising:
at least one processor configured to implement:
acquiring, by the at least one processor, a time-series dataset from retail sales records, the time-series dataset comprising a plurality of time-series data items each comprising a time and a plurality of corresponding attribute parameters,
wherein the plurality of corresponding attribute parameters comprises at least one of:
a purchase price;
a sales price;
a sales volume;
an inventory;
a sales profit; and
client views;

acquiring, by the at least one processor, a target attribute parameter, which comprises at least the inventory;
determining, by the at least one processor, using a time-series model, at least one influence factor of the target attribute parameter, the at least one influence factor indicating at least one attribute parameter influencing the target attribute parameter and at least one time corresponding to the at least one attribute parameter;
outputting, by the at least one processor, the at least one influence factor;
determining, by the at least one processor, a forecast for the target attribute parameter at a future time using the output at least one influence factor; and
controlling, by the at least one processor, the inventory at the future time in response to the determined forecast for the target attribute parameter,
wherein the at least one influence factor comprises a plurality of influence factors, and the method further comprises:
determining influence of respective influence factors, from among the plurality of influence factors, on the target attribute parameter;
ranking, using the influence of respective influence factors, the plurality of influence factors; and
outputting, using the ranking, part or all of the plurality of influence factors, and

wherein the plurality of influence factors comprise a first influence factor and a second influence factor, the first influence factor has first influence represented as a first interval on the target attribute parameter, the second influence factor has second influence represented as a second interval on the target attribute parameter, and wherein ranking the plurality of influence factors comprises:
in response to determining that an upper limit value of the first interval is less than a lower limit value of the second interval, then determining that the first influence is less than the second influence; or
in response to determining that the first interval and the second interval have an overlapping area, and that a first statistic of the first interval is less than a second statistic of the second interval, then determining that the first influence is less than or equal to the second influence; or
in response to determining that a difference between a lower limit value of the first interval and a lower limit value of the second interval are less than a first threshold, that a difference between an upper limit value of the first interval and an upper limit value of the second interval are less than a second threshold, and that a difference between the first statistic and the second statistic is less than a third threshold, then determining that the first influence is equal to the second influence.

2. The method of claim 1 , wherein each of the at least one influence factor influences the target attribute parameter, and the influence is represented in a form of an interval.

3. The method of claim 1 , the method further comprising:
determining a change of influence of a first attribute parameter, from among the plurality of corresponding attribute parameters, on the target attribute parameter, over time.

4. The method of claim 3 , the method further comprising:
acquiring an indication of the first attribute parameter input by a user.

5. The method of claim 1 , the method further comprising:
acquiring a first adjustment indication for a second attribute parameter, from among-in the plurality of corresponding attribute parameters; and
determining, using the first adjustment indication, a relationship between influence of the second attribute parameter on the target attribute parameter and a time.

6. The method of claim 5 , wherein the relationship between the influence of the second attribute parameter on the target attribute parameter and the time indicates at least one of:
a change of the influence of the second attribute parameter on the target attribute parameter over time; and
a change of accumulative influence of the second attribute parameter on the target attribute parameter over an accumulation of time.

7. The method of claim 6 , further comprising:
determining, using the change of the accumulative influence of the second attribute parameter on the target attribute parameter over the accumulation of time, whether the accumulative influence within a preset time period reaches a preset threshold.

8. The method of claim 5 , further comprising:
acquiring a second adjustment indication of a third attribute parameter, from among the plurality of corresponding attribute parameters; and
determining, using the first adjustment indication and the second adjustment indication, an attribute parameter having greater influence on the target attribute parameter from the second attribute parameter and the third attribute parameter.

9. The method of claim 5 , further comprising:
acquiring the first adjustment indication input by a user.

10. The method of claim 1 , further comprising:
acquiring an initial time-series model; and
removing redundant edges by testing the initial time-series model, to thus obtain the time-series model.

11. The method of claim 1 , further comprising:
selecting, using a relationship between the time-series dataset and a predetermined dataset, the time-series model from a plurality of candidate models.

12. The method of claim 1 , wherein acquiring the time-series dataset comprises:
acquiring an initial time-series dataset;
performing at least one of the following processing on the initial time-series dataset to obtain the time-series dataset;
removing a noise data item; or
generating an augmented data item.

13. The method of claim 12 , wherein generating the augmented data item comprises:
inputting a first data item and a second data item from the initial time-series dataset into a data generative model, to obtain the augmented data item, wherein the first data item has a first time, the second data item has a second time, and the augmented data item has a third time.

14. A data processing method for providing reminder information indicating an abnormal risk of a user, the method comprising:
acquiring, by at least one processor, a time-series dataset collected from social media, the time-series dataset comprising a plurality of time-series data items each comprising a time and a plurality of corresponding attribute parameters,
wherein the plurality of corresponding attribute parameters comprises at least one of:
a user identifier;
a user post;
views of the user post;
comments of the user post; and
an abnormal indication comprising an indication of the abnormal risk of the user committing at least one of suicide and an illegal act;

acquiring, by the at least one processor, a target attribute parameter comprising at least the abnormal indication;
determining, by the at least one processor, using a time-series model, at least one influence factor of the target attribute parameter, the at least one influence factor indicating at least one attribute parameter influencing the target attribute parameter and at least one time c

Assignees

• Nec Corp

Inventors

• Wang Erli
• Feng Lu

Classifications

• G06F16/2462

  Approximate or statistical queries · CPC title

• G06F16/9537

  Spatial or temporal dependent retrieval, e.g. spatiotemporal queries · CPC title

• G06Q10/087

  Inventory or stock management, e.g. order filling, procurement or balancing against orders · CPC title

• G06Q30/0202

  Market predictions or forecasting for commercial activities · CPC title

• G06F16/24578 Primary

  using ranking · CPC title