Method and device for pushing information

1. A method of pushing information, comprising:

receiving a search word entered in a client;

obtaining a natural search list by invoking a natural search service to perform a search operation on the search word, wherein the natural search list comprises a first threshold number of natural search materials and a first evaluation score of each of the natural search materials, the natural search service being configured to perform a natural search on the search word;

obtaining a push information list by invoking a push information search service to perform a search operation on the search word, wherein the push information list comprises a second threshold number of push materials and a second evaluation score of each of the push materials, the push information search service being configured to perform a non-natural search on the search word;

obtaining an integrated evaluation score of each of the natural search materials in the natural search list by integrating the first evaluation score and the second evaluation score of a material existing in the natural search list and the push information list at the same time;

re-ranking the natural search materials in the natural search list according to the integrated evaluation scores; and

pushing re-ranked natural search materials to the client;

wherein obtaining the push information list by invoking the push information search service to perform the search operation on the search word further comprises:

invoking the push information search service;

acquiring push materials;

selecting the second threshold number of push materials according to text relevance; and

respectively calculating second evaluation scores of the second threshold number of push materials according to a preset push evaluation parameter and a score weight of the push evaluation parameter; and

wherein respectively calculating the second evaluation scores of the second threshold number of push materials according to the preset push evaluation parameter and the score weight of the push evaluation parameter comprises:

obtaining the score weight of the push evaluation parameter of the push material corresponding to the search word; and

taking a product obtained by multiplying the push evaluation parameter of the push material with the score weight as the second evaluation score of the push material.

2. The method according to claim 1 , wherein obtaining the natural search list by invoking the natural search service to perform the search operation on the search word further comprises:

invoking the natural search service;

acquiring natural search materials;

selecting the first threshold number of natural search materials according to text relevance;

ranking the first threshold number of natural search materials according to ranking scores by a preset ranking method; and

taking the ranking score of each of the natural search materials as the first evaluation score.

3. The method according to claim 2 , wherein the preset ranking method is obtained by training collected data associated with a user experience index in a search log.

4. The method according to claim 1 , further comprising:

optimizing and updating the score weight of the push evaluation parameter of the push material corresponding to the search word according to a search log under a constraint of a preset user experience index.

5. A device for pushing information, the device comprising:

a processor which invokes machine readable instructions corresponding to a control logic for pushing information stored on a storage medium and executes the machine readable instructions to:

receive a search word entered in a client;

obtain a natural search list by invoking a natural search service to perform a search operation on the search word, wherein the natural search list comprises a first threshold number of natural search materials and a first evaluation score of each of the natural search materials, the natural search service being configured to perform a natural search on the search word;

obtain a push information list by invoking a push information search service to perform a search operation on the search word, wherein the push information list comprises a second threshold number of push materials and a second evaluation score of each of the push materials, the push information search service being configured to perform a non-natural search on the search word;

obtain an integrated evaluation score of each of the natural search materials in the natural search list by integrating the first evaluation score and the second evaluation score of a material existing in the natural search list and the push information list at the same time;

re-rank the natural search materials in the natural search list according to the integrated evaluation scores; and

push re-ranked natural search materials to the client;

wherein when obtaining the push information list by invoking the push information search service to perform the search operation on the search word, the machine readable instructions cause the processor to:

invoke the push information search service;

acquire push materials;

select the second threshold number of push materials according to text relevance; and

respectively calculate second evaluation scores of the second threshold number of push materials according to a preset push evaluation parameter and a score weight of the push evaluation parameter, and

wherein when respectively calculating the second evaluation scores of the second threshold number of push materials according to the preset push evaluation parameter and the score weight of the push evaluation parameter, the machine readable instructions cause the processor to:

obtain the score weight of the push evaluation parameter of the push material corresponding to the search word; and

take a product obtained by multiplying the push evaluation parameter of the push material with the score weight as the second evaluation score of the push material.

6. The device according to claim 5 , wherein when obtaining the natural search list by invoking the natural search service to perform the search operation on the search word, the machine readable instructions cause the processor to:

invoke the natural search service;

acquire natural search materials;

select the first threshold number of natural search materials according to text relevance;

rank the first threshold number of natural search materials according to ranking scores by a preset ranking method; and

take the ranking score of each of the natural search materials as the first evaluation score.

7. The device according to claim 6 , wherein the preset ranking method is obtained by training collected data associated with a user experience index in a search log.

8. The device according to claim 5 , wherein the machine readable instructions cause the processor to:

optimize and update the score weight of the push evaluation parameter of the push material corresponding to the search word according to a search log under a constraint of a preset user experience index.

9. A non-transitory machine readable storage medium storing machine readable instructions executed by one or more processors, the machine readable instructions cause the processors to:

receive a search word entered in a client;

obtain a natural search list by invoking a natural search service to perform a search operation on the search word, wherein the natural search list comprises a first threshold number of natural search materials and a first evaluation score of each of the natural search materials, the natural search service being configured to perform a natural search on the search word;

obtain a push information list by invoking a push information search service to perform a search operation on the search word, wherein the push information list comprises a second threshold number of push materials and a second evaluation score of each of the push materials, the push information search service being configured to perform a non-natural search on the search word;

obtain an integrated evaluation score of each of the natural search materials in the natural search list by integrating the first evaluation score and the second evaluation score of a material existing in the natural search list and the push information list at the same time;

re-rank the natural search materials in the natural search list according to the integrated evaluation scores; and

push re-ranked natural search materials to the client,

wherein obtaining the push information list by invoking the push information search service to perform the search operation on the search word further comprises:

invoking the push information search service;

acquiring push materials;

selecting the second threshold number of push materials according to text relevance; and

respectively calculating second evaluation scores of the second threshold number of push materials according to a preset push evaluation parameter and a score weight of the push evaluation parameter, and

wherein respectively calculating the second evaluation scores of the second threshold number of push materials according to the preset push evaluation parameter and the score weight of the push evaluation parameter comprises:

obtaining the score weight of the push evaluation parameter of the push material corresponding to the search word; and

taking a product obtained by multiplying the push evaluation parameter of the push material with the score weight as the second evaluation score of the push material.

10. The storage medium according to claim 9 , wherein obtaining the natural search list by invoking the natural search service to perform the search operation on the search word further comprises:

invoking the natural search service;

acquiring natural search materials;

selecting the first threshold number of natural search materials according to text relevance;

ranking the first threshold number of natural search materials according to ranking scores by a preset ranking method; and

taking the ranking score of each of the natural search materials as the first evaluation score.

11. The storage medium according to claim 10 , wherein the preset ranking method is obtained by training collected data associated with a user experience index in a search log.

12. The storage medium according to claim 9 , further comprising:

optimizing and updating the score weight of the push evaluation parameter of the push material corresponding to the search word according to a search log under a constraint of a preset user experience index.