Search

CN-121973798-A - Roaming intelligent driving method, system and readable storage medium

CN121973798ACN 121973798 ACN121973798 ACN 121973798ACN-121973798-A

Abstract

The invention relates to a roaming intelligent driving method, a roaming intelligent driving system and a readable storage medium, and relates to the field of automatic driving, wherein the method comprises the steps of receiving voice input of a user, and extracting trip intention keywords through natural language understanding and voiceprint feature recognition; the method comprises the steps of calling data interfaces of a plurality of travel platforms based on travel intention keywords, obtaining destination information matched with the travel intention keywords, sorting the destination information according to preset scoring rules, recommending destinations to users in a voice interaction mode, and dynamically adjusting intelligent driving parameters according to the confirmed destinations and the travel intention keywords. The method and the device can realize dynamic destination matching and driving parameter self-adaptive adjustment based on user intention, thereby improving traveling flexibility, comfort and personalized experience.

Inventors

  • LI JIAO
  • HE JINPENG

Assignees

  • 智己汽车科技有限公司

Dates

Publication Date
20260505
Application Date
20251229

Claims (11)

  1. 1. A roaming intelligent driving method, comprising: receiving voice input of a user, and extracting trip intention keywords through natural language understanding and voiceprint feature recognition; Calling data interfaces of a plurality of travel platforms based on the travel intention keywords, and acquiring destination information matched with the travel intention keywords; sorting the destination information according to a preset scoring rule, recommending the destination to the user in a voice interaction mode, and And dynamically adjusting intelligent driving parameters according to the destination confirmed by the user and the trip intention keywords.
  2. 2. The roaming intelligent driving method according to claim 1, wherein the receiving the voice input of the user, extracting the trip intention keywords through natural language understanding and voiceprint feature recognition comprises: Noise filtering and framing processing are carried out on the voice signals; extracting voiceprint characteristics through a voiceprint recognition model and carrying out emotion recognition; Converting the voice signal into characters by using a voice recognition model; Semantic analysis of transcribed text using a large language model, extraction of trip intent keywords, and And carrying out multi-mode data fusion on the emotion recognition result, the intention recognition result, the number of vehicles and the real-time position of the vehicles.
  3. 3. The roaming intelligent driving method according to claim 2, wherein the trip intention keyword includes at least one of office, pick-up child, flower, eat, shopping, hiking, climbing, seeing a doctor, and exercise.
  4. 4. The roaming intelligent driving method of claim 1, wherein the invoking the data interface of the plurality of travel platforms based on the travel intention keyword comprises: combining time information, place information and trip intention keywords as query conditions; calling application program interfaces of a plurality of travel platforms to acquire user-generated content data, and Destination information and corresponding geographic location coordinates are extracted from the user-generated content data.
  5. 5. The roaming intelligent driving method according to claim 4, wherein the preset scoring rule performs comprehensive scoring calculation based on the praise number, the collection number, the travel mode matching degree and the travel duration matching degree.
  6. 6. The roaming intelligent driving method of claim 1, wherein the dynamically adjusting intelligent driving parameters includes: filling road section attribute information according to the interest point attribute in the navigation route; inquiring a preset parameter matching table based on the interest point attribute corresponding to the real-time position of the vehicle and the perceived and identified road type, and At least one parameter of vehicle speed limit, following distance, suspension height, lane selection and lane change aggressiveness is dynamically adjusted.
  7. 7. The method of claim 6, wherein the point of interest attribute comprises at least one of a school, a hospital, a sightseeing spot, a business, an airport, a night city, a mountain road, a tunnel, and a residential area.
  8. 8. The roaming ride-on method of claim 1, further comprising: searching similar network red interest points in a trip heat database according to the point positions of the optimal route; feeding back the network red interest point as a recommended route point to the user, and And updating the navigation path planning according to the user confirmation result.
  9. 9. The method of claim 8, wherein the search range of the near net red points of interest is within a preset distance threshold, and the preset distance threshold is dynamically adjusted according to the road type and the vehicle driving speed.
  10. 10. A roaming intelligent driving system, comprising: the voice interaction module is used for receiving voice input of a user, and extracting trip intention keywords through natural language understanding and voiceprint feature recognition; the data acquisition module is used for calling data interfaces of a plurality of travel platforms based on the travel intention keywords and acquiring destination information matched with the travel intention keywords; a recommending module for ordering the destination information according to a preset scoring rule and recommending the destination to the user by voice interaction mode, and And the parameter adjustment module is used for dynamically adjusting the intelligent driving parameters according to the destination confirmed by the user and the trip intention keywords.
  11. 11. A readable storage medium storing computer instructions which, when executed by a processor, implement the roaming ride-on method of any one of claims 1-9.

Description

Roaming intelligent driving method, system and readable storage medium Technical Field The invention relates to the field of automatic driving, in particular to a roaming intelligent driving method, a roaming intelligent driving system and a readable storage medium. Background Along with the rapid development of technology, the fusion application of intelligent driving and large models has become a research hotspot and development trend of the automobile industry. Conventional intelligent driving systems typically rely on the user having an explicit destination and generating an explicit route for automatic driving based on navigation. Although this approach improves the convenience of driving, it still requires the user to have a clear trip intention and destination before going out. The existing intelligent driving system mainly performs path planning by manually inputting a destination, and performs vehicle control by adopting fixed or manually-adjustable driving parameters. Some systems may display hot points of interest on the navigation map, guide the user to select to set as a destination, or employ a default driving strategy when there is no navigation route. However, the prior art has a problem of insufficient adaptability in processing travel scenes without an explicit destination or requiring dynamic adjustment of a destination. The user interaction mode is relatively complicated, trip intention cannot be understood through natural language, and proper destinations can not be matched according to the intention, and particularly, flexibility is lacking in complex traveling, business and other scenes. Meanwhile, intelligent driving parameters are usually fixedly arranged, dynamic adaptation cannot be carried out according to travel intentions and real-time road conditions, and driving comfort and personalized experience are affected. These limitations make it difficult for existing systems to meet the wider and diversified travel needs of users. Disclosure of Invention In view of the above-mentioned drawbacks of the prior art, an object of the present invention is to provide a roaming intelligent driving method, system and readable storage medium, which can implement dynamic destination matching and driving parameter adaptive adjustment based on user intention, so as to improve traveling flexibility, comfort and personalized experience. In order to achieve the above purpose, the present invention adopts the following technical scheme. In a first aspect, the invention provides a roaming intelligent driving method, which adopts the following technical scheme: receiving voice input of a user, and extracting trip intention keywords through natural language understanding and voiceprint feature recognition; Calling data interfaces of a plurality of travel platforms based on the travel intention keywords, and acquiring destination information matched with the travel intention keywords; sorting the destination information according to a preset scoring rule, recommending the destination to the user in a voice interaction mode, and And dynamically adjusting intelligent driving parameters according to the destination confirmed by the user and the trip intention keywords. Further, in the roaming intelligent driving method, the receiving the voice input of the user, and extracting the trip intention keywords through natural language understanding and voiceprint feature recognition includes: Noise filtering and framing processing are carried out on the voice signals; extracting voiceprint characteristics through a voiceprint recognition model and carrying out emotion recognition; Converting the voice signal into characters by using a voice recognition model; Semantic analysis of transcribed text using a large language model, extraction of trip intent keywords, and And carrying out multi-mode data fusion on the emotion recognition result, the intention recognition result, the number of vehicles and the real-time position of the vehicles. Further, in the roaming intelligent driving method, the trip intention keywords include at least one of office work, child pick-up, flower appreciation, dining, shopping, hiking, climbing, doctor seeing and body building. Further, in the roaming intelligent driving method, the calling the data interfaces of the plurality of travel platforms based on the travel intention keywords includes: combining time information, place information and trip intention keywords as query conditions; calling application program interfaces of a plurality of travel platforms to acquire user-generated content data, and Destination information and corresponding geographic location coordinates are extracted from the user-generated content data. Further, in the roaming intelligent driving method, the preset scoring rule performs comprehensive scoring calculation based on the praise number, the collection number, the travel mode matching degree and the travel duration matching degree. Further, in the roam