Search

CN-122002343-A - Data filtering processing method and device, terminal and network side equipment

CN122002343ACN 122002343 ACN122002343 ACN 122002343ACN-122002343-A

Abstract

The application discloses a data filtering processing method, a device, a terminal and network side equipment, belonging to the technical field of communication; the terminal determines whether second data of a target object is generated based on an artificial intelligence AI model or is generated based on a layer 3 filtering mechanism, performs target operation including at least one of performing layer 3 filtering on the first data and the second data by using a first weight coefficient if the second data is determined to be generated based on the AI model, performing layer 3 filtering on the first data and the second data by using a second weight coefficient if the second data is determined to be generated based on the layer 3 filtering mechanism, wherein the target object is a beam or a cell, the first data is an actual measured value before layer 3 filtering or an actual measured value after layer 1 filtering, and the second data is a signal value after layer 3 filtering which is obtained last time.

Inventors

  • ZHANG HONGPING

Assignees

  • 维沃移动通信有限公司

Dates

Publication Date
20260508
Application Date
20241108

Claims (20)

  1. 1. A data filtering processing method, comprising: the terminal performs measurement to obtain first data of a target object; The terminal determines whether second data of the target object is generated based on an artificial intelligence AI model or whether second data is generated based on a layer 3 filtering mechanism; The terminal performs a target operation, the target operation including at least one of: performing layer 3 filtering on the first data and the second data using a first weight coefficient if it is determined that the second data is generated based on an AI model; performing layer 3 filtering on the first data and the second data using a second weight coefficient if it is determined that the second data is generated based on a layer 3 filtering mechanism; The target object is a beam or a cell, the first data is an actual measurement value before filtering of the layer 3 or an actual measurement value after filtering of the layer 1, and the second data is a signal value after filtering of the layer 3, which is obtained last time.
  2. 2. The method of claim 1, wherein the first weight coefficient is greater than the second weight coefficient.
  3. 3. The method according to claim 1 or 2, wherein the target measurement value F n obtained by layer 3 filtering the first data and the second data using a first weight coefficient satisfies: F n ＝(1–a1)*F n-1 +a1*M n ; Wherein a1 is the first weight coefficient, F n-1 is the second data, the second data is a layer 3 filtered predicted value generated based on an AI model, and M n is the first data.
  4. 4. The method according to claim 1 or 2, wherein the target measurement value F n obtained by layer 3 filtering the first data and the second data using a second weight coefficient satisfies: F n ＝(1–a2)*F n-1 +a2*M n ; Wherein a2 is the second weight coefficient, F n-1 is the second data, the second data is a measurement value generated based on a layer 3 filtering mechanism, and M n is the first data.
  5. 5. The method of any of claims 1-4, wherein prior to layer 3 filtering the first data and the second data using a first weight coefficient, the method further comprises: The terminal determines the first weight coefficient.
  6. 6. The method of claim 5, wherein the determining, by the terminal, the first weight coefficient comprises: The terminal determines the first weight coefficient based on the prediction accuracy corresponding to the second data or the prediction accuracy of the AI model.
  7. 7. The method according to any one of claims 1 to 4, further comprising: the terminal receives at least one of first information and second information from network side equipment; The first information is used for determining the first weight coefficient, and the second information is used for determining the second weight coefficient.
  8. 8. The method of claim 7, wherein the first information comprises any one of: the first weight coefficient; A first filter coefficient associated with the first weight coefficient; Adjusting the coefficient; an offset value; Mapping relation between prediction precision and adjustment coefficient or offset value; Wherein the adjustment coefficient or the offset value is used to determine the first weight coefficient in combination with the second weight coefficient.
  9. 9. The method of claim 8, further comprising any one of: The terminal determines the first weight coefficient based on a1=1/2 (k1/4) , wherein a1 is the first weight coefficient and k1 is the first filter coefficient; The terminal determines the first weight coefficient based on a1=a2×x, wherein a1 is the first weight coefficient, a2 is the second weight coefficient, and x is the adjustment coefficient; The terminal determines the first weight coefficient based on a1=a2+y, wherein a1 is the first weight coefficient, a2 is the second weight coefficient and y is the offset value; The terminal determines an adjustment coefficient based on the obtained prediction precision and the mapping relation, and determines the first weight coefficient based on a1=a2 x, wherein a1 is the first weight coefficient, a2 is the second weight coefficient, and x is the adjustment coefficient; The terminal determines an offset value based on the obtained prediction precision and the mapping relation, and determines the first weight coefficient based on a1=a2+y, wherein a1 is the first weight coefficient, a2 is the second weight coefficient, and y is the offset value.
  10. 10. The method of claim 9, wherein the adjustment factor is greater than 1 or the offset value is greater than 0.
  11. 11. The method according to any one of claims 7 to 10, wherein the second information comprises any one of: a second weight coefficient; and a second filter coefficient associated with the second weight coefficient.
  12. 12. The method of claim 11, wherein in the case where the second information includes the second filter coefficient, the method further comprises: the terminal determines the second weight coefficient based on a2=1/2 (k2/4) , wherein a2 is the second weight coefficient and k2 is the second filter coefficient.
  13. 13. A data filtering processing method, comprising: The network side equipment sends first information and second information to the terminal; The first information is used for determining a first weight coefficient, the second information is used for determining a second weight coefficient, and the first weight coefficient is used for carrying out layer 3 filtering on the first data and the second data of the target object by using the first weight coefficient when the terminal determines that the second data of the target object is generated based on an AI model; the second weight coefficient is used for carrying out layer 3 filtering on the first data and the second data of the target object by using the second weight coefficient when the terminal determines that the second data of the target object is generated based on a layer 3 filtering mechanism; The target object is a beam or a cell, the first data is an actual measurement value before layer 3 filtering or an actual measurement value after layer 1 filtering, which is obtained by the terminal executing measurement, and the second data is a signal value after layer 3 filtering, which is obtained last time.
  14. 14. The method of claim 13, wherein the first information comprises any one of: the first weight coefficient; A first filter coefficient associated with the first weight coefficient; Adjusting the coefficient; an offset value; Mapping relation between prediction precision and adjustment coefficient or offset value; Wherein the adjustment coefficient or the offset value is used to determine the first weight coefficient in combination with the second weight coefficient.
  15. 15. The method of claim 14, wherein the determining of the first weight coefficient includes any one of: In the case that the first information includes the first filter coefficient, the determining manner of the first weight coefficient is: determining the first weight coefficient according to a1=1/2 (k1/4) , wherein a1 is the first weight coefficient, and k1 is the first filter coefficient; in the case that the first information includes the adjustment coefficient or includes a mapping relationship between prediction accuracy and the adjustment coefficient, the determining manner of the first weight coefficient is: determining the first weight coefficient according to a1=a2×x, wherein a1 is the first weight coefficient, a2 is the second weight coefficient, and x is the adjustment coefficient; And when the first information comprises the offset value or comprises a mapping relation between prediction precision and the offset value, determining the first weight coefficient according to a1=a2+y, wherein a1 is the first weight coefficient, a2 is the second weight coefficient and y is the offset value.
  16. 16. The method of claim 15, wherein the adjustment factor is greater than 1 or the offset value is greater than 0.
  17. 17. The method of any of claims 13 to 16, wherein the second information comprises any of: a second weight coefficient; and a second filter coefficient associated with the second weight coefficient.
  18. 18. The method of claim 17, wherein, in the case where the second information includes the second filter coefficient, the second weight coefficient is determined by: And determining the second weight coefficient according to a2=1/2 (k2/4) , wherein a2 is the second weight coefficient, and k2 is the second filter coefficient.
  19. 19. A data filtering processing apparatus, comprising: The processing module is used for executing measurement and obtaining first data of a target object; the processing module is further configured to determine whether second data of the target object is generated based on an artificial intelligence AI model or whether second data is generated based on a layer 3 filtering mechanism; the processing module is further configured to perform a target operation, where the target operation includes at least one of: performing layer 3 filtering on the first data and the second data using a first weight coefficient if it is determined that the second data is generated based on an AI model; performing layer 3 filtering on the first data and the second data using a second weight coefficient if it is determined that the second data is generated based on a layer 3 filtering mechanism; The target object is a beam or a cell, the first data is an actual measurement value before filtering of the layer 3 or an actual measurement value after filtering of the layer 1, and the second data is a signal value after filtering of the layer 3, which is obtained last time.
  20. 20. The apparatus of claim 19, wherein the target measurement value F n obtained by layer 3 filtering the first data and the second data using a first weight coefficient satisfies: F n ＝(1–a1)*F n-1 +a1*M n ; Wherein a1 is the first weight coefficient, F n-1 is the second data, the second data is a layer 3 filtered predicted value generated based on an AI model, and M n is the first data.

Description

Data filtering processing method and device, terminal and network side equipment Technical Field The application belongs to the technical field of communication, and particularly relates to a data filtering processing method, a device, a terminal and network side equipment. Background With the development of communication technology, in order to reduce measurement in a communication system, an artificial intelligence (ARTIFICIAL INTELLIGENCE, AI) model is introduced to generate predicted values after layer 3 filtering as data after layer 3 filtering. Since a certain error exists in the prediction of the AI model, when the subsequent layer 3 is filtered based on the predicted value after the layer 3 is filtered, an error transmission is caused, and the filtering effect of the layer 3 is poor. Therefore, the related art has a problem in that the filtering effect of the layer 3 is poor. Disclosure of Invention The embodiment of the application provides a data filtering processing method, a device, a terminal and network side equipment, which can solve the problem of poor filtering effect of a layer 3. In a first aspect, a data filtering processing method is provided, including: the terminal performs measurement to obtain first data of a target object; The terminal determines whether second data of the target object is generated based on an artificial intelligence AI model or whether second data is generated based on a layer 3 filtering mechanism; The terminal performs a target operation, the target operation including at least one of: performing layer 3 filtering on the first data and the second data using a first weight coefficient if it is determined that the second data is generated based on an AI model; performing layer 3 filtering on the first data and the second data using a second weight coefficient if it is determined that the second data is generated based on a layer 3 filtering mechanism; The target object is a beam or a cell, the first data is an actual measurement value before filtering of the layer 3 or an actual measurement value after filtering of the layer 1, and the second data is a signal value after filtering of the layer 3, which is obtained last time. In a second aspect, a data filtering processing method is provided, including: The network side equipment sends first information and second information to the terminal; The first information is used for determining a first weight coefficient, the second information is used for determining a second weight coefficient, and the first weight coefficient is used for carrying out layer 3 filtering on the first data and the second data of the target object by using the first weight coefficient when the terminal determines that the second data of the target object is generated based on an AI model; the second weight coefficient is used for carrying out layer 3 filtering on the first data and the second data of the target object by using the second weight coefficient when the terminal determines that the second data of the target object is generated based on a layer 3 filtering mechanism; The target object is a beam or a cell, the first data is an actual measurement value before layer 3 filtering or an actual measurement value after layer 1 filtering, which is obtained by the terminal executing measurement, and the second data is a signal value after layer 3 filtering, which is obtained last time. In a third aspect, there is provided a data filtering processing apparatus comprising: The measuring module is used for executing measurement and obtaining first data of a target object; A determining module for determining whether second data of the target object is generated based on an artificial intelligence AI model or whether it is generated based on a layer 3 filtering mechanism; an execution module for executing a target operation, the target operation comprising at least one of: performing layer 3 filtering on the first data and the second data using a first weight coefficient if it is determined that the second data is generated based on an AI model; performing layer 3 filtering on the first data and the second data using a second weight coefficient if it is determined that the second data is generated based on a layer 3 filtering mechanism; The target object is a beam or a cell, the first data is an actual measurement value before filtering of the layer 3 or an actual measurement value after filtering of the layer 1, and the second data is a signal value after filtering of the layer 3, which is obtained last time. In a fourth aspect, there is provided a data filtering processing apparatus including: The sending module is used for sending the first information and the second information to the terminal; The first information is used for determining a first weight coefficient, the second information is used for determining a second weight coefficient, and the first weight coefficient is used for carrying out layer 3 filtering on the first data and