Returning estimated value of search keywords of entire account

Patent metadata

Field	Value
Publication number	US-9449049-B2
Application number	US-201113318335-A
Country	US
Kind code	B2
Filing date	Aug 4, 2011
Priority date	Aug 4, 2010
Publication date	Sep 20, 2016
Grant date	Sep 20, 2016

Abstract

Techniques for returning estimated value of search keywords of an entire account include, for the entire account, obtaining one or more selected search keywords and their respective forecast periods and parameter settings. An estimated value of a respective search keyword in the respective forecast period is forecasted. Based on stored historical data and parameter settings of the respective search keyword, the estimated value of the respective search keyword is modified to obtain a modified estimated value. The modified estimated value of each search keyword is added up to generate an estimated value of the entire account. The estimated value of the entire account is returned to a client terminal from which the entire account is logged in. The present disclosure modifies the respective search keyword's estimated value so that the estimated value of the entire account satisfies the expected value of the client.

First claim

What is claimed is:

1. A method of returning an estimated account value of search keywords, performed by one or more processors configured with computer-executable instructions, the method comprising:
obtaining one or more search keywords associated with an account, a respective forecast period and a respective bid price corresponding to each individual search keyword of the one or more search keywords;
providing an estimated value corresponding to each individual search keyword, the respective forecast period, and the respective bid price;
calculating the estimated account value based on a sum of the estimated values corresponding to each individual search keyword of the one or more search keywords;
defining a plurality of value intervals associated with the estimated account value;
assigning a respective allowable error to each of the value intervals; and
generating an interval estimated value between a first value equaling the estimated account value multiplied by (1−ε i (ε i +1)) and a second value equaling the estimated account value multiplied by (1+ε i (ε i +1)) when the estimated account value falls between a third value equaling an upper bound of the value interval that corresponds to the estimated account value divided by (1+ε i ) and a fourth value equaling a lower bound of a next higher value interval divided by (1−ε i+1 ), wherein ε i is a first respective allowable error assigned to the value interval that corresponds to the estimated account value and ε i+1 is a second respective allowable relative error assigned to the next higher value interval.

2. A method as recited in claim 1 , further comprising:
selecting a plurality of historical presentation time periods, each of which is similar in length to the respective forecast period, a historical period comprising the plurality of historical presentation time periods;
generating a series of ratios, each of which corresponds to a proportion of a historical value corresponding to a respective historical presentation time period of the plurality of historical presentation time periods with respect to the historical period; and
multiplying the estimated value corresponding to each individual search keyword by a sum of the series of ratios to generate a modified estimated value corresponding to each individual search keyword.

3. A method as recited in claim 2 , wherein the providing the estimated value of each individual search keyword, the respective forecast period and the respective bid price comprises:
obtaining a historical presentation volume of each individual search keyword and a presentation ratio of each individual search keyword at different presentation locations;
determining a number of presentations of each individual search keyword at the different presentation locations based on the historical presentation volume and the presentation ratio of each individual search keyword;
obtaining an estimated earning and an estimated cost of each individual search keyword at an individual location of the different presentation locations; and
calculating the estimated value of each individual search keyword in the respective forecast period at the different presentation locations based on a sum of estimated earnings and estimated costs of each individual search keyword at the different presentation locations.

4. A method as recited in claim 1 , further comprising returning the interval estimated value.

5. A method as recited in claim 1 , further comprising:
obtaining multiple entire accounts;
sorting estimated values of the multiple entire accounts;
selecting a preset number of entire accounts to a sorting order from low to high from the sorted estimated values; and
returning a notification message to one or more client terminals from which the selected entire accounts are logged in.

6. A search engine server comprising:
a memory to maintain executable program instructions; and
a processor that retrieves one or more search keywords associated with an account, a respective forecast period, and a respective bid price corresponding to each individual search keyword of the one or more search keywords; provides an estimated value corresponding to each individual search keyword, the respective forecast period, and the respective bid price; determines an estimation error based on the estimated value and an actual value corresponding to a historical presentation time period that is similar in length to the respective forecast period; substitutes the actual value plus a compensation threshold for the estimated value when the estimation error is greater than a predetermined threshold; calculates an estimated account value based on a sum of the estimated values corresponding to each individual search keyword of the multiple search keywords; defines a plurality of value intervals associated with the estimated account value, assigns a respective allowable error to each of the value intervals, and generates an interval estimated value between a first value equaling the estimated account value multiplied by (1−ε i (ε i +1)) and a second value equaling the estimated account value multiplied by (1+ε i (ε i +1)) when the estimated account value falls between a third value equaling an upper bound of the value interval that corresponds to the estimated account value divided by (1+ε i ) and a fourth value equaling a lower bound of a next higher value interval divided by (1−ε i+1 ), wherein ε i is a first respective allowable error assigned to the value interval that corresponds to the estimated account value and ε i+1 is a second respective allowable relative error assigned to the next higher value interval.

7. A search engine server as recited in claim 6 , wherein the processor further selects a plurality of historical presentation time periods, each of which is similar in length to the respective forecast period, a historical period comprising the plurality of historical presentation time periods, wherein the processor generates a series of ratios, each of which corresponds to a proportion of a historical value corresponding to a respective historical presentation time period of the plurality of historical presentation time periods with respect to the historical period, and wherein the processor multiplies the estimated value corresponding to each individual search keyword by a sum of the series of ratios to generate a modified estimated value corresponding to each individual search keyword.

8. A search engine server as recited in claim 7 , wherein the processor further retrieves a historical presentation volume of each individual search keyword and a presentation ratio of each individual search keyword at different presentation locations, calculates a number of presentation times of each individual search keyword at the different presentation locations based on the historical presentation volume and the presentation ratio of each individual search keyword, obtains an estimated earning and an estimated cost of each individual search keyword at an individual location of the different presentation locations, and calculates the estimated value of each individual search keyword in the individual forecast period at the different presentation locations based on a sum of estimated earnings and estimated costs of each individual search keyword at the different presentation locations.

9. A search engine server as recited in claim 6 , wherein the processor further returns the estimated account value.

10. A search engine server as recited in claim 6 , wherein the processor sorts estimated values corresponding to a plurality of accounts and, from the sorted estimated values, retrieves a number of accounts to a sorting order that meet a preset number,
wherein the returning

Assignees

• Zhang Tao
• Guo Jiaqing
• Guo Ning
• Alibaba Group Holding Ltd

Inventors

• Zhang Tao
• Guo Jiaqing
• Guo Ning

Classifications

• G06Q30/0275

  Auctions · CPC title

• G06F16/24578 Primary

  using ranking · CPC title

• G06Q30/0254

  based on statistics · CPC title

• G06Q30/0247

  Calculate past, present or future revenues · CPC title

• G06Q30/02 Primary

  Marketing; Price estimation or determination; Fundraising · CPC title