Search

CN-122027380-A - Voice personalized broadcasting method and device, storage medium and electronic device

CN122027380ACN 122027380 ACN122027380 ACN 122027380ACN-122027380-A

Abstract

The application discloses a voice personalized broadcasting method, a device, a storage medium and an electronic device, which relate to the technical field of intelligent home/smart families, wherein the voice personalized broadcasting method comprises the steps of acquiring a broadcasting request and operation parameters sent by intelligent equipment, wherein the broadcasting request is used for indicating broadcasting information to be broadcasted; the method comprises the steps of carrying out information splitting processing on a broadcasting request according to broadcasting information to obtain a conversation mark, determining a target sentence template according to the conversation mark, operation parameters and the sentence template, filling the operation parameters into the target sentence template to obtain voice to be broadcasted, and sending the voice to be broadcasted to the intelligent device so that the intelligent device can broadcast the voice to be broadcasted. The method can efficiently convert the broadcasting request of the intelligent equipment into specific broadcasting contents, and improves the accuracy and instantaneity of information transmission. Meanwhile, through dynamic filling of the operation parameters, individuation and automation of the broadcast content are realized, and user experience is enhanced.

Inventors

  • GUO YANWEN
  • HUANG TAO

Assignees

  • 海尔优家智能科技（北京）有限公司
  • 青岛海尔科技有限公司
  • 海尔智家股份有限公司

Dates

Publication Date
20260512
Application Date
20241111

Claims (10)

  1. 1. A method for personalized speech broadcasting, the method comprising: Acquiring a broadcasting request and operation parameters sent by intelligent equipment, wherein the broadcasting request is used for indicating broadcasting information needing broadcasting, and the broadcasting information comprises execution equipment and corresponding execution actions; Carrying out information splitting processing on the broadcasting request according to the broadcasting information to obtain a speaking operation identifier; determining a target sentence template according to the conversation mark, the operation parameter and the sentence template; And filling the operation parameters into the target statement template to obtain voice to be broadcasted, and sending the voice to be broadcasted to the intelligent equipment so that the intelligent equipment can broadcast the voice to be broadcasted.
  2. 2. The method of claim 1, wherein before the obtaining the broadcast request and the operation parameter sent by the smart device, the method further comprises: acquiring at least one reply sentence and at least one dynamic parameter which are input by a platform configurator or generated based on voice interaction habits of a user; Generating placeholders of each dynamic parameter according to the dynamic parameters; and carrying out replacement processing on the dynamic parameters in the reply sentence according to the placeholders to obtain a plurality of sentence templates, wherein each sentence template at least comprises one placeholder.
  3. 3. The method of claim 1, wherein the speech recognition comprises an execution intent, wherein the operation parameters comprise a time parameter, wherein the determining a target sentence template based on the speech recognition, the operation parameters, and the sentence template comprises: determining a first statement template according to the time parameter, a preset time rule and the statement template, wherein the first statement template is used for indicating a period of time for broadcasting voice by the intelligent equipment; determining a second sentence template according to the execution intention and the sentence template, wherein the second sentence template is used for indicating whether the intelligent equipment completes the execution intention, the target sentence template is formed by adding the first sentence template and the second sentence template, and the first sentence template is in front of the second sentence template.
  4. 4. The method of claim 3, wherein the determining a first sentence template according to the time parameter, the preset time rule, and the sentence template comprises: Determining a preset time period which is met by the time parameter according to the preset time rule, wherein the preset time rule can divide the time of day into different time periods; and determining the first sentence templates according to the preset time periods and the sentence templates, wherein different first sentence templates exist in different preset time periods.
  5. 5. The method of claim 1, wherein the filling the operation parameters into the target sentence template to obtain the voice to be broadcasted comprises: Analyzing and classifying the operation parameters to determine the information name of each category; determining a target information name corresponding to the placeholder according to the placeholder in the target statement template; and filling the operation parameters corresponding to the target information names in the positions of the placeholders to obtain the voice to be broadcasted.
  6. 6. The method of claim 1, wherein the session identification further comprises a device class, the method further comprising: acquiring a prompt statement triggering rule corresponding to the equipment category, wherein different intelligent equipment has different prompt statement triggering rules; judging whether the operation parameters meet the triggering rule of the reminding statement; And under the condition that the operation parameters meet the triggering rules of the reminding sentences, retrieving the reminding sentence templates corresponding to the equipment categories in the configuration platform, and adding the reminding sentence templates into the target sentence templates, wherein the reminding sentence templates are behind the second sentence templates.
  7. 7. The method according to claim 2, wherein the method further comprises: acquiring binding information of a user and the intelligent equipment; And determining a first nickname of the user and a second nickname of the intelligent device according to the binding information, and adding the first nickname and the second nickname into the sentence template.
  8. 8. A voice personalized broadcast device, the device comprising: The system comprises an acquisition module, a control module and a control module, wherein the acquisition module is used for acquiring a broadcasting request and an operation parameter sent by intelligent equipment, the broadcasting request is used for indicating broadcasting information to be broadcasted, and the broadcasting information comprises execution equipment and corresponding execution actions; The processing module is used for carrying out information splitting processing on the broadcasting request according to the broadcasting information to obtain a speaking operation identifier; the determining module is used for determining a target sentence template according to the conversation mark, the operation parameters and the sentence template; and the filling module is used for filling the operation parameters into the target statement template to obtain voice to be broadcasted, and sending the voice to be broadcasted to the intelligent equipment so that the intelligent equipment can play the voice to be broadcasted.
  9. 9. A computer-readable storage medium, characterized in that the computer-readable storage medium comprises a stored program, wherein the program when run performs the method of any one of claims 1 to 7.
  10. 10. An electronic device comprising a memory and a processor, characterized in that the memory has stored therein a computer program, the processor being arranged to execute the method according to any of claims 1 to 7 by means of the computer program.

Description

Voice personalized broadcasting method and device, storage medium and electronic device Technical Field The application relates to the technical field of intelligent home/intelligent families, in particular to a voice personalized broadcasting method, a device, a storage medium and an electronic device. Background With the rapid development of smart home technology, voice control has become one of the main ways for users to interact with smart home appliances. The user can control various intelligent devices in home through simple voice command, and when the control command is successfully executed or fails, the intelligent household appliance system can timely feed back the execution result to the user through voice broadcasting. At present, many intelligent home appliance systems adopt a technology based on a voice operation platform to realize voice broadcasting. The speaking platform can generate corresponding speaking Identifications (IDs) according to different intentions and categories, and the customizability of speaking contents is realized through a configuration mode. However, in the prior art, the speaking platform broadcasts the same content each time for the same category and intention, and the individuation and innovation are lacking, and the current voice broadcasting usually simply informs the user of the execution result and lacks emotion communication with the user. This may reduce user engagement and interactivity. Disclosure of Invention The application provides a voice personalized broadcasting method, a device, a storage medium and an electronic device, which are used for solving the problems that in the prior art, a speaking configuration platform broadcasts the same content for the same category and intention every time, and the broadcasting content is tedious and monotonous. In a first aspect, the present application provides a voice personalized broadcasting method, including: Acquiring a broadcasting request and operation parameters sent by intelligent equipment, wherein the broadcasting request is used for indicating broadcasting information needing broadcasting, and the broadcasting information comprises execution equipment and corresponding execution actions; Carrying out information splitting processing on the broadcasting request according to the broadcasting information to obtain a speaking operation identifier; determining a target sentence template according to the conversation mark, the operation parameter and the sentence template; And filling the operation parameters into the target statement template to obtain voice to be broadcasted, and sending the voice to be broadcasted to the intelligent equipment so that the intelligent equipment can broadcast the voice to be broadcasted. Optionally, before the obtaining the broadcast request and the operation parameter sent by the intelligent device, the method further includes: acquiring at least one reply sentence and at least one dynamic parameter which are input by a platform configurator or generated based on voice interaction habits of a user; Generating placeholders of each dynamic parameter according to the dynamic parameters; and carrying out replacement processing on the dynamic parameters in the reply sentence according to the placeholders to obtain a plurality of sentence templates, wherein each sentence template at least comprises one placeholder. Optionally, the speaking identifier comprises an execution intention, the operation parameters comprise a time parameter, and the determining a target sentence template according to the speaking identifier, the operation parameters and the sentence template comprises the following steps: determining a first statement template according to the time parameter, a preset time rule and the statement template, wherein the first statement template is used for indicating a period of time for broadcasting voice by the intelligent equipment; determining a second sentence template according to the execution intention and the sentence template, wherein the second sentence template is used for indicating whether the intelligent equipment completes the execution intention, the target sentence template is formed by adding the first sentence template and the second sentence template, and the first sentence template is in front of the second sentence template. Optionally, the determining the first sentence template according to the time parameter, the preset time rule and the sentence template includes: Determining a preset time period which is met by the time parameter according to the preset time rule, wherein the preset time rule can divide the time of day into different time periods; and determining the first sentence templates according to the preset time periods and the sentence templates, wherein different first sentence templates exist in different preset time periods. Optionally, the filling the operation parameter into the target sentence template to obtain the voice to be broad