Search

CN-114020995-B - Recall method, device, electronic equipment and storage medium based on artificial intelligence

CN114020995BCN 114020995 BCN114020995 BCN 114020995BCN-114020995-B

Abstract

The disclosure provides a recall method, a recall device, electronic equipment and a storage medium based on artificial intelligence, and relates to the technical field of data processing, in particular to the field of artificial intelligence. The method comprises the steps of determining a first embedded value corresponding to a first user based on user characteristics of the first user and resource characteristics of information input by the first user, wherein the first embedded value is used for representing the user characteristics, the resource characteristics and the association degree between the user characteristics and the resource characteristics, determining a second user meeting similar conditions with the first user based on the first embedded value, and carrying out resource recall for the first user based on resource information corresponding to the second user.

Inventors

  • YAN PENGFEI

Assignees

  • 北京百度网讯科技有限公司

Dates

Publication Date
20260508
Application Date
20210918

Claims (9)

  1. 1. A recall method based on artificial intelligence, comprising: based on historical behavior information of a first user, determining that the first user is a cold start user; the cold-start user comprises users with the historical behavior information quantity smaller than or equal to a second threshold value; Determining a first embedded value corresponding to a first user based on user characteristics of the first user and resource characteristics of information input by the first user, wherein the first embedded value is used for representing the user characteristics, the resource characteristics and the association degree between the user characteristics and the resource characteristics; The method comprises the steps of acquiring a positive resource feature sample set and a negative resource feature sample set which are acquired based on a historical point spread log set of a historical user, and training an embedded value model by using a user feature sample set and an embedded value, wherein the positive resource feature sample set comprises a displayed resource, clicks the log set of the resource, and the negative resource feature sample set comprises a displayed resource, and does not click the log set of the resource; Determining, based on the first embedded value, a second user that satisfies a similar condition to the first user; And carrying out resource recall for the first user based on the resource information corresponding to the second users, wherein the resource recall comprises at least one piece of resource information corresponding to each second user, at least one piece of resource information is clicked resource information, at least one piece of resources corresponding to all the second users are combined, the total clicking number of each resource is recorded, and the resource with the largest total clicking number is confirmed to be the first user recall resource.
  2. 2. The method of claim 1, wherein prior to the determining the first embedded value corresponding to the first user based on the user characteristic of the first user and the resource characteristic corresponding to the information input by the first user, the method further comprises: acquiring user information of the first user; User characteristics of the first user are determined based on the user information.
  3. 3. The method of claim 1, wherein prior to the determining the first embedded value corresponding to the first user based on the user characteristic of the first user and the resource characteristic of the information input by the first user, the method further comprises: receiving information input by the first user; And processing the information input by the first user to obtain the resource characteristics.
  4. 4. The method of claim 1, wherein the method further comprises: Screening the history point spread log set, wherein the history point spread log set comprises history point spread logs of clicking operations and user information corresponding to the clicking operations; determining an embedded value set based on the history click log comprising click operations and user information corresponding to the click operations; the set of embedded values is used to determine a second user that satisfies a similar condition as the first user.
  5. 5. The method of claim 1 or 4, wherein the determining, based on the first embedded value, a second user that satisfies a similar condition to the first user comprises: Determining a second embedded value satisfying the similar condition in the embedded value set based on the first embedded value; And determining the user corresponding to the second embedded value as the second user.
  6. 6. A recall device based on artificial intelligence, comprising: the user attribute confirmation unit is used for determining that the first user is a cold start user based on the historical behavior information of the first user, wherein the cold start user comprises users with the number of the historical behavior information being smaller than or equal to a second threshold value; A determining unit, configured to determine a first embedded value corresponding to a first user based on a user feature of the first user and a resource feature of information input by the first user, where the first embedded value is used to characterize the user feature, the resource feature, and a degree of association between the user feature and the resource feature; the method comprises the steps of determining a second user meeting similar conditions with the first user based on a first embedded value, determining the first embedded value based on an embedded value model, training the embedded value model based on a positive resource feature sample set and a negative resource feature sample set which are obtained by historical point spread log sets of historical users, and user feature sample sets and embedded values, wherein the positive resource feature sample set comprises a log set for displaying resources and clicking the resources, the negative resource feature sample set comprises a log set for displaying the resources and not clicking the resources, evaluating the embedded value model to obtain a model evaluation index of the embedded value model, and if the model evaluation index is smaller than a preset threshold, adjusting parameters of the embedded value model, retraining the embedded value model until the model evaluation index is larger than or equal to the preset threshold, and confirming that training of the embedded value model is completed; The recall unit is used for recalling the resources for the first user based on the resource information corresponding to the second users, and comprises the steps of recalling at least one piece of resource information corresponding to each second user, wherein the at least one piece of resource information is clicked resource information, merging at least one piece of resources corresponding to all the second users, recording the total clicking number of each resource, and confirming the resource with the largest total clicking number as the first user recalled resource.
  7. 7. An electronic device, comprising: At least one processor, and A memory communicatively coupled to the at least one processor, wherein, The memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-5.
  8. 8. A non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method of any one of claims 1-5.
  9. 9. A computer program product comprising computer programs/instructions which, when executed by a processor, implement the method of any of claims 1-5.

Description

Recall method, device, electronic equipment and storage medium based on artificial intelligence Technical Field The present disclosure relates to the field of data processing technologies, and in particular, to an artificial intelligence based method, apparatus, electronic device, and storage medium in the field of artificial intelligence. Background Artificial intelligence (ARTIFICIAL INTELLIGENCE, AI) is a comprehensive technology of computer science, and by researching the design principle and implementation method of various intelligent machines, the machines have the functions of sensing, reasoning and decision. Recall systems are one of the important applications in the field of artificial intelligence, and can help users find information that may be of interest to them in an information overload environment, and recall information to push to users interested in the information. Disclosure of Invention The present disclosure provides a method, apparatus, electronic device, and storage medium for recall based on artificial intelligence. According to a first aspect of the present disclosure, an artificial intelligence based recall method is provided, including determining a first embedded value corresponding to a first user based on a user characteristic of the first user and a resource characteristic of information input by the first user, the first embedded value being used to characterize the user characteristic, the resource characteristic, and a degree of association between the user characteristic and the resource characteristic; Determining, based on the first embedded value, a second user that satisfies a similar condition to the first user; and carrying out resource recall for the first user based on the resource information corresponding to the second user. According to a second aspect of the present disclosure, there is provided an artificial intelligence based recall device comprising: The device comprises a determining unit, a determining unit and a processing unit, wherein the determining unit is used for determining a first embedded value corresponding to a first user based on the user characteristic of the first user and the resource characteristic of the information input by the first user, and the first embedded value is used for representing the user characteristic, the resource characteristic and the association degree between the user characteristic and the resource characteristic; And the recall unit is used for carrying out resource recall for the first user based on the resource information corresponding to the second user. A third aspect of the present disclosure provides an electronic device comprising at least one processor and a memory communicatively coupled to the at least one processor, wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the artificial intelligence based recall method described above. A fourth aspect of the present disclosure provides a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the artificial intelligence based recall method described above. A fifth aspect of the present disclosure provides a computer program product comprising computer programs/instructions which, when executed by a processor, implement the artificial intelligence based recall method described above. It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the disclosure, nor is it intended to be used to limit the scope of the disclosure. Other features of the present disclosure will become apparent from the following specification. Drawings The drawings are for a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein: FIG. 1 is a schematic diagram of one architecture of an artificial intelligence based recall system provided by embodiments of the present disclosure; FIG. 2 is another architectural schematic diagram of an artificial intelligence based recall system provided by embodiments of the present disclosure; FIG. 3 is a schematic flow diagram of an alternative artificial intelligence based recall method provided by embodiments of the present disclosure; FIG. 4 is a schematic flow diagram of another alternative artificial intelligence based recall method provided by embodiments of the present disclosure; FIG. 5 is a schematic diagram of yet another architecture of an artificial intelligence based recall system provided by embodiments of the present disclosure; FIG. 6 is a schematic diagram of an alternative architecture of an artificial intelligence based recall device provided by an embodiment of the present application; FIG. 7 is a block diagram of an electronic device used to implement an artificial intelligence based recall method of an embodiment of the present disclosure. Detailed Description Ex