CN-121996128-A - Interactive processing method and device and electronic equipment

Abstract

The application discloses an interaction processing method, an interaction processing device and electronic equipment, wherein the method comprises the steps of obtaining a first image on a first interface; the method comprises the steps of analyzing a first image based on a first model to obtain at least one piece of first recommendation information, wherein the first recommendation information is related to at least one image object determined by analyzing the first image, outputting the at least one piece of first recommendation information on a second interface, and outputting a reply result corresponding to target recommendation information based on target recommendation information determined by a user from the at least one piece of first recommendation information.

Inventors

• Guo Huaijie
• Chen Hanliu

Assignees

• 联想(北京)有限公司

Dates

Publication Date

20260508

Application Date

20260125

Claims (10)

1. 1. An interaction processing method, comprising: Obtaining a first image at a first interface; analyzing the first image based on a first model to obtain at least one piece of first recommendation information, wherein the first recommendation information is related to at least one image object determined by analyzing the first image; outputting the at least one piece of first recommendation information on a second interface; and outputting a reply result corresponding to the target recommendation information based on the target recommendation information determined by the user from the at least one piece of first recommendation information.
2. 2. The method of claim 1, further comprising, before outputting a reply result corresponding to the target recommendation information based on the target recommendation information determined by the user from the at least one piece of first recommendation information: responding to the triggering operation of the editing control in the second interface, and acquiring editing data of the first image in a third interface; Analyzing the editing data based on the first model to obtain at least one piece of second recommendation information; outputting the at least one piece of second recommended information on the second interface; And determining target recommendation information in response to a second selection operation of the at least one piece of second recommendation information by the user.
3. 3. The method of claim 1 or 2, further comprising, before outputting a reply result corresponding to target recommendation information based on the target recommendation information determined by the user from the at least one piece of first recommendation information: determining the target recommendation information in response to a first selection operation of the at least one piece of first recommendation information by a user; Wherein the method further comprises: Receiving a first selection operation corresponding to the target recommendation information from the second interface; Or alternatively, the first and second heat exchangers may be, Responding to the triggering operation of the confirmation control output in the second interface, and outputting the at least one piece of second recommendation information in a fourth interface; And receiving a first selection operation corresponding to the target recommendation information on the fourth interface.
4. 4. The method of claim 2, obtaining, at a third interface, edit data for the first image, comprising: Outputting at least one of a circling control, a text editing control and an image cutting control on a third interface; responding to the line input through the circling control, and obtaining a part of the image area which is circled and selected in the first image; Responding to the text input through the text editing control, and obtaining text content added for the first image; and responding to the clipping frame input through the image clipping control, and obtaining a clipped partial image area in the first image.
5. 5. The method of claim 1, analyzing the first image based on a first model to obtain at least one piece of first recommendation information, comprising: based on a first model, analyzing the first image according to an image recognition algorithm corresponding to the target scene identifier to obtain image characteristics; Screening at least one piece of first recommendation information from an information base corresponding to the target scene identification according to the image characteristics; the information base comprises a plurality of pieces of recommended information, and the target scene identifier characterizes the service scene type corresponding to the first image.
6. 6. The method of claim 5, wherein selecting at least one piece of first recommendation information from the information base corresponding to the target scene identifier according to the image feature comprises: determining a target library corresponding to a target recommendation identifier from the information library corresponding to the target scene identifier, wherein the target library comprises at least one piece of recommendation information; According to the image characteristics, at least one piece of first recommendation information is screened from the target library; The target recommendation identification is obtained through the first interface, and the target recommendation identification characterizes the information type.
7. 7. The method of claim 1, wherein the output location of the first recommendation information on the second interface is a display location of the image object associated with the first recommendation information in the first image.
8. 8. The method of claim 2, wherein the output position of the second recommendation information on the second interface is a display position of the image object related to the second recommendation information in the first image.
9. 9. An interaction processing apparatus comprising: An image obtaining unit for obtaining a first image at a first interface; the information processing unit is used for analyzing the first image based on a first model to obtain at least one piece of first recommendation information, wherein the first recommendation information is related to at least one image object determined by analyzing the first image; The information recommending unit is used for outputting the at least one piece of first recommending information on the second interface; and the answer output unit is used for outputting an answer result corresponding to the target recommendation information based on the target recommendation information determined by the user from the at least one piece of first recommendation information.
10. 10. An electronic device, comprising: A display for outputting the first interface and the second interface; The processor is used for obtaining a first image on the first interface, analyzing the first image based on a first model to obtain at least one piece of first recommendation information, wherein the first recommendation information is related to at least one image object determined by analyzing the first image, outputting the at least one piece of first recommendation information on the second interface, and outputting a reply result corresponding to the target recommendation information based on target recommendation information determined by a user from the at least one piece of first recommendation information.

Description

Interactive processing method and device and electronic equipment Technical Field The present application relates to the field of artificial intelligence technologies, and in particular, to an interaction processing method, an interaction processing device, and an electronic device. Background At present, when a user is confused, a word description or a shot image is usually provided for an intelligent customer service, and a solution is provided for the user by the intelligent customer service according to the word or the image, such as how to solve a system fault, how to treat after trauma, and the like. The intelligent solution is based on accurate positioning of the problems, so that the requirements of aligning and confirming the problems, focusing the problems and updating the problems in time are high. Disclosure of Invention In view of the above, the present application provides an interaction processing method, device and electronic equipment, as follows: an interaction processing method, comprising: Obtaining a first image at a first interface; analyzing the first image based on a first model to obtain at least one piece of first recommendation information, wherein the first recommendation information is related to at least one image object determined by analyzing the first image; outputting the at least one piece of first recommendation information on a second interface; and outputting a reply result corresponding to the target recommendation information based on the target recommendation information determined by the user from the at least one piece of first recommendation information. In the above method, optionally, before outputting a reply result corresponding to the target recommendation information based on the target recommendation information determined by the user from the at least one piece of first recommendation information, the method further includes: responding to the triggering operation of the editing control in the second interface, and acquiring editing data of the first image in a third interface; Analyzing the editing data based on the first model to obtain at least one piece of second recommendation information; outputting the at least one piece of second recommended information on the second interface; And determining target recommendation information in response to a second selection operation of the at least one piece of second recommendation information by the user. In the above method, optionally, before outputting a reply result corresponding to the target recommendation information based on the target recommendation information determined by the user from the at least one piece of first recommendation information, the method further includes: determining the target recommendation information in response to a first selection operation of the at least one piece of first recommendation information by a user; Wherein the method further comprises: Receiving a first selection operation corresponding to the target recommendation information from the second interface; Or alternatively, the first and second heat exchangers may be, Responding to the triggering operation of the confirmation control output in the second interface, and outputting the at least one piece of second recommendation information in a fourth interface; And receiving a first selection operation corresponding to the target recommendation information on the fourth interface. In the above method, optionally, in a third interface, obtaining editing data of the first image includes: Outputting at least one of a circling control, a text editing control and an image cutting control on a third interface; responding to the line input through the circling control, and obtaining a part of the image area which is circled and selected in the first image; Responding to the text input through the text editing control, and obtaining text content added for the first image; and responding to the clipping frame input through the image clipping control, and obtaining a clipped partial image area in the first image. The method, optionally, based on a first model, analyzes the first image to obtain at least one piece of first recommendation information, including: based on a first model, analyzing the first image according to an image recognition algorithm corresponding to the target scene identifier to obtain image characteristics; Screening at least one piece of first recommendation information from an information base corresponding to the target scene identification according to the image characteristics; the information base comprises a plurality of pieces of recommended information, and the target scene identifier characterizes the service scene type corresponding to the first image. The method, optionally, according to the image feature, screens at least one piece of first recommendation information from the information base corresponding to the target scene identifier, including: determining a target library correspondi