Attribute data interval division method and device
A technology of attribute data and data interval, applied in the direction of electrical digital data processing, digital data information retrieval, special data processing application, etc., can solve the problem of low accuracy in dividing attribute data intervals, and achieve the effect of improving accuracy
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0030] Such as figure 2 As shown, it is a schematic flow chart of the attribute data interval division method in Embodiment 1 of the present application, and the specific processing process is as follows:
[0031] Step 21, extract attribute data of user attributes of several classified members.
[0032] When dividing attribute data intervals offline, the attribute data of user attributes of classified members should be extracted as training data, and the training data should be trained and learned to obtain each attribute data interval.
[0033] Among them, the attribute data of the user attributes of the classified members can be pre-stored in the database. Usually, a record is used to save the attribute data of each user attribute of a member. User attributes can include but are not limited to: age, registration date, gender, Location, source of registration, industry, etc.
[0034] The method of extracting attribute data may be, but not limited to, adopting a method of r...
Embodiment 2
[0069] Corresponding to the attribute data interval division method proposed in Embodiment 1 of the present application, the online processing process of determining the member category of the members to be classified is introduced below.
[0070] Such as image 3 As shown, it is a schematic flow chart of the method for classifying members to be classified online in Embodiment 2 of the present application. The specific processing process is as follows:
[0071] Step 31, in the attribute data of each user attribute of the member to be classified, set the missing attribute data as a preset missing value.
[0072] Among them, the preset missing value should be the same as the preset missing value when dividing the attribute data interval.
[0073] Step 32, for each user attribute of the member to be classified, among the plurality of attribute data intervals corresponding to the user attribute, determine the attribute data interval to which the attribute data of the user attribu...
Embodiment 3
[0081] When dividing the attribute data interval according to the method proposed in Embodiment 1 of the present application, if the number of records contained in the divided attribute data interval is too small, the divided attribute data interval will not have statistical significance. When the data range is used to classify members, the accuracy of the classification is lower. In this regard, Embodiment 3 of the present application proposes an implementation manner for better dividing attribute data intervals.
[0082] Such as Figure 4 As shown, it is a schematic flow chart of the attribute data interval division method in Embodiment 3 of the present application, and the specific processing process is as follows:
[0083] Step 41, extract attribute data of user attributes of several classified members.
[0084] Step 42, for each user attribute of the member, determine each initial attribute data interval corresponding to the user attribute according to the attribute dat...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 