Search

CN-114550243-B - Service mode recommendation method and device, electronic equipment and storage medium

CN114550243BCN 114550243 BCN114550243 BCN 114550243BCN-114550243-B

Abstract

The invention provides a service mode recommendation method, a device, electronic equipment and a storage medium, wherein the method comprises the steps of obtaining first voice and/or a first image of a user, determining a current target service mode based on the obtained first voice and/or first image, and adjusting the current target service mode based on historical use conditions, wherein the historical use conditions comprise evaluation information of a last target service mode in a set time period, the evaluation information is determined based on second voice and/or a second image of the user, and the evaluation information of the last target service mode is used in current service mode recommendation, so that the current target service mode of the current recommendation can be more suitable for actual demands of the user, and optimization of user use experience is achieved while a function of the service mode recommendation is refined.

Inventors

  • WANG JINHONG

Assignees

  • 青岛海尔科技有限公司
  • 海尔智家股份有限公司

Dates

Publication Date
20260505
Application Date
20220210

Claims (9)

  1. 1. A service mode recommendation method, comprising: Acquiring a first voice and a first image of a user; Determining identity information of the user based on the acquired first voice and first image; determining a voice service mode use requirement based on the first voice; based on limb actions and/or behavior gestures in the first image, carrying out demand analysis on the user to obtain an image service mode use demand; fusing the voice service mode use requirement and the image service mode use requirement to obtain a target service mode use requirement; Determining a current target service mode based on the identity information and the target service mode use requirement; based on the historical use condition, adjusting the current target service mode; Wherein the historical use condition comprises evaluation information of a last target service mode in a set time period, and the evaluation information is determined based on second voice and/or second images of the user.
  2. 2. The service mode recommendation method according to claim 1, wherein the determining the identity information of the user based on the acquired first voice and first image comprises: Voiceprint extraction is carried out on the first voice to obtain voiceprint characteristics of the user; determining voice identity information of the user based on the voiceprint features; user identity identification is carried out on the first image, and image identity information of the user is obtained; And determining the identity information of the user based on the voice identity information and the image identity information.
  3. 3. The service mode recommendation method according to claim 1 or 2, wherein the evaluation information is determined based on the steps of: Determining a second voice and/or a second image of the user; Carrying out user emotion analysis on the second voice and/or the second image to obtain voice emotion and/or image emotion of the user; based on the speech emotion and/or image emotion, evaluation information for the last target service mode is determined.
  4. 4. The service mode recommendation method of claim 3, wherein the performing user emotion analysis on the second voice to obtain the voice emotion of the user comprises: performing voice emotion recognition on the second voice to obtain a voice emotion recognition result of the user; and/or, performing voice transcription on the second voice to obtain a transcription text of the second voice; carrying out semantic emotion recognition on the transfer text to obtain a semantic emotion recognition result of the user; And determining the voice emotion of the user based on the voice emotion recognition result and/or the semantic emotion recognition result.
  5. 5. The service mode recommendation method according to claim 3, wherein said performing a user emotion analysis on said second image to obtain an image emotion of said user comprises: determining a face area and/or a limb action area in the second image; carrying out facial expression recognition on the facial area to obtain the expression emotion of the user; and/or performing action recognition on the limb action area to obtain the action emotion of the user; And determining the image emotion of the user based on the expression emotion and/or the action emotion.
  6. 6. The service mode recommendation method according to claim 1 or 2, wherein said adjusting said current target service mode based on historical usage conditions further comprises: Transmitting a control instruction indicated by the current target service mode to a terminal corresponding to the user, so as to request the terminal to recommend the current target service mode to the user after receiving the control instruction.
  7. 7. A service mode recommendation device, comprising: a voice image acquisition unit for acquiring a first voice and a first image of a user; The target service mode determining unit is used for determining identity information of the user based on the acquired first voice and first image, determining voice service mode using requirements based on the first voice, analyzing requirements of the user based on limb actions and/or behavior gestures in the first image to obtain image service mode using requirements, fusing the voice service mode using requirements and the image service mode using requirements to obtain target service mode using requirements, and determining a current target service mode based on the identity information and the target service mode using requirements; The system comprises an adjustment unit, a user unit and a control unit, wherein the adjustment unit is used for adjusting the current target service mode based on historical use conditions, the historical use conditions comprise evaluation information of the last target service mode in a set time period, and the evaluation information is determined based on second voice and/or second images of the user.
  8. 8. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the service mode recommendation method according to any one of claims 1 to 6 when the computer program is executed by the processor.
  9. 9. A non-transitory computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the service mode recommendation method according to any one of claims 1 to 6.

Description

Service mode recommendation method and device, electronic equipment and storage medium Technical Field The invention relates to the technical field of intelligent home, in particular to a service mode recommendation method, a device, electronic equipment and a storage medium. Background With the rapid development of science and technology, intelligent home appliances are gradually popularized, and the popularization of intelligent home appliances can bring great convenience to the daily life of people and can provide diversified selection and services. Most of the current intelligent home appliances carry voice control or image control functions, namely, can provide intelligent services for users through voice control or image control, but after that, whether the provided intelligent services meet the actual demands of the users or not cannot be considered, namely, whether the users can be satisfied or not, and once the services provided by the intelligent home appliances deviate, namely, the deviations from the demands of the users are far, the use experience of the users is poor easily. Disclosure of Invention The invention provides a service mode recommending method, a device, electronic equipment and a storage medium, which are used for solving the defect that the recommended service mode in the prior art cannot meet the actual requirements of users, so that the use experience of the users is poor. The invention provides a service mode recommending method, which comprises the following steps: Acquiring a first voice and/or a first image of a user; Determining a current target service mode based on the acquired first voice and/or first image; based on the historical use condition, adjusting the current target service mode; Wherein the historical use condition comprises evaluation information of a last target service mode in a set time period, and the evaluation information is determined based on second voice and/or second images of the user. According to the mode recommendation method provided by the invention, the current target service mode is determined based on the acquired first voice and/or first image, and the mode recommendation method comprises the following steps: Determining identity information and/or target service mode use requirements of the user based on the acquired first voice and/or first image; And determining the current target service mode based on the identity information and/or the target service mode use requirement. According to the mode recommendation method provided by the invention, the method for determining the identity information of the user based on the acquired first voice and/or first image comprises the following steps: Voiceprint extraction is carried out on the first voice to obtain voiceprint characteristics of the user; determining voice identity information of the user based on the voiceprint features; and/or carrying out user identity recognition on the first image to obtain image identity information of the user; and determining the identity information of the user based on the voice identity information and/or the image identity information. According to the mode recommendation method provided by the invention, the evaluation information is determined based on the following steps: Determining a second voice and/or a second image of the user; Carrying out user emotion analysis on the second voice and/or the second image to obtain voice emotion and/or image emotion of the user; based on the speech emotion and/or image emotion, evaluation information for the last target service mode is determined. According to the mode recommendation method provided by the invention, the user emotion analysis is performed on the second voice to obtain the voice emotion of the user, and the mode recommendation method comprises the following steps: performing voice emotion recognition on the second voice to obtain a voice emotion recognition result of the user; and/or, performing voice transcription on the second voice to obtain a transcription text of the second voice; carrying out semantic emotion recognition on the transfer text to obtain a semantic emotion recognition result of the user; And determining the voice emotion of the user based on the voice emotion recognition result and/or the semantic emotion recognition result. According to the mode recommendation method provided by the invention, the user emotion analysis is carried out on the second image to obtain the image emotion of the user, and the mode recommendation method comprises the following steps: determining a face area and/or a limb action area in the second image; carrying out facial expression recognition on the facial area to obtain the expression emotion of the user; and/or performing action recognition on the limb action area to obtain the action emotion of the user; And determining the image emotion of the user based on the expression emotion and/or the action emotion. According to the mode recommendation me