Method and system for interactively changing position-dependent information for vehicles stored in a database
The method and system leverage AI modules to dynamically update vehicle databases with real-time sensor data and user feedback, addressing the challenge of outdated information by ensuring relevance and accuracy.
Patent Information
- Authority / Receiving Office
- DE · DE
- Patent Type
- Applications
- Current Assignee / Owner
- MERCEDES BENZ GROUP AG
- Filing Date
- 2025-03-12
- Publication Date
- 2026-06-03
- Estimated Expiration
- Not applicable · inactive patent
Smart Images
Figure 00000007_0000 
Figure 00000007_0001
Abstract
Description
[0001] The invention relates to a method and a system for the interactive extension or modification of position-dependent information for vehicles stored in a database, as well as a vehicle with such a system.
[0002] The object of the invention is to provide a method and system for the interactive extension or modification of position-dependent information INF(POS) for vehicles stored in a database.
[0003] The invention is defined by the features of the independent claims. Advantageous further developments and embodiments are the subject of the dependent claims.
[0004] A first aspect of the invention relates to a method for interactively extending or modifying position-dependent information INF(POS) stored in a database, comprising the following steps: - Providing a determined current POS position from the database F(t) of the vehicle F dependent information INF(POS F (t)) in vehicle F, with t:= time; - using vehicle sensor(s), capturing current information INF UMG (POS F (t)) to a neighborhood of the vehicle F at its current position POS F (t); - using a first AI module MOD1, determining difference information ΔINF(POS F (t)) between the information provided by the database INF(POS F (t)) and the recorded information INF UMG (POS F (t)); - using a second AI module MOD2, outputting the information INF(POS F (t)) and / or the difference information ΔINF(POS F (t)) in vehicle F; - Capture related comments RESPONSE(INF(POS F (t)), ΔINF(POS F (t))) of occupants of vehicle F; - using a third AI module MOD3, checking the comments RESPONSE(INF(POSF (t)), ΔINF(POS F ))) on their significance and / or their plausibility and / or their relevance for determining verified comment information KINF(RESPONSE(INF(POS F (t)), ΔINF(POS F )))); and - using a fourth AI model MOD4, based on the verified comment information KINF(RESPONSE(INF(POS) F (t)), ΔINF(POS F )))) and the current information INF UMG (POS F (t)) to the environment, modifying or adding to the existing data in the database for the POS position F (t) stored information INF(POS F (t)) in changed information INF*(POS F (t)).
[0005] The database is advantageously a cloud-based database. The database and the vehicle F are advantageously connected via a mobile network for data exchange.
[0006] The position-dependent information INF(POS) stored in the database preferably includes one or more from the following non-exhaustive list: - Weather information, - Traffic information (traffic jams, construction sites, road closures, etc.), - locally relevant news information (from politics, society, development, events, etc.), - Information on structural changes (road construction, changes to buildings, etc.), - In particular, but not exclusively, changes and information regarding vehicle-related infrastructure (charging infrastructure, petrol stations, car washes, car parks and their occupancy, toll roads and payment instructions, etc.) - Information about tourist attractions.
[0007] The current POS position is advantageous F(t) of vehicle F is determined using a satellite-based navigation system (e.g. GPS, Starlink, Galileo, GLONASS, etc.).
[0008] The current information INF acquired locally by means of the vehicle sensor(s) UMG (POS F (t)) to an environment of the vehicle F are initially advantageously located as image data BD(POS F (t)) (2D or 3D) in which the current environment of the vehicle F is depicted. The first AI module MOD1 is advantageously designed and configured to process the image data BD(POS F (t)) with regard to advantageously specified features (which result, for example, from feature categories of the information stored in the database INF(POS)) and to analyze from the current image data BD(POS F (t)) the current information dependent on the given characteristics INF UMG (POS F(t)) in a format such that it can be used with the information provided by the database INF(POS F (t)) compared, and thus the difference information ΔINF(POS F (t)) between INF(POS F (t)) and INF UMG (POS F (t)) can be determined. The first AI module MOD1 advantageously includes a function focused on determining the difference information ΔINF(POS). F (t)) trained machine learning algorithm.
[0009] The second AI module MOD2 is advantageously designed and configured to process the information INF(POS F (t)) and / or the difference information ΔINF(POS F (t)) in vehicle F to be verbally output by means of a synthetically generated voice. Advantageously, the second AI module MOD2 is further designed and configured to process the information INF(POS F (t)) and / or the difference information ΔINF(POS F(t)) to output visually, e.g. in the form of images that contain the information INF(POS F (t)) and / or the difference information ΔINF(POS F (t)) clarify or illustrate.
[0010] Advantageously, the second AI module MOD2 is designed and configured to provide individualized information (INF(POS)) to the vehicle's occupant(s). F (t)) and / or the difference information ΔINF(POS F (t)) to output, i.e., only information that has passed an individual preference filter of the respective occupant(s) is output in the vehicle. This generates an addition or modification of the information INF(POS) stored in the database based on individualized interactions with the respective occupant(s) of the vehicle F.
[0011] Advantageously, the second AI module MOD2 is executed and configured to access the information INF(POS) F (t)) and the difference information ΔINF(POSF (t)) based questions QUEST(INF(POS F (t)), ΔINF(POS F (t)))) to generate and output in vehicle F, where responses RESPONSE(QUEST(INF(POS F (t)), ΔINF(POS F (t))))) are recorded by the inmates in response to the questions; whereby the answers are captured using the third AI module MOD3 RESPONSE(QUEST(INF(POS F (t)), ΔINF(POS F (t))))) on their significance and / or their plausibility and / or their relevance for determining verified comment information KINF(RESPONSE(QUEST(INF(POS F (t)), ΔINF(POS F (t))))) are checked; and where, using the fourth AI model MOD4, based on the checked comment information KINF(RESPONSE(QUEST(INF(POS) F (t)), ΔINF(POS F (t))))), previously in the database for the position POS F (t) stored information INF(POS F (t)) in changed information INF*(POS F (t)) will be changed.
[0012] Advantageously, the second AI module MOD2 includes an INF(POS) module for outputting spoken information. F (t)) and / or spoken difference information ΔINF(POS F (t)) trained machine learning algorithm, in particular a language model. Advantageously, the language model is either a large language model or a small language model. For further information on language models, reference is made to the relevant state of the art. The recording of comments is advantageously done
[0013] RESPONSE(INF(POS F (t)), ΔINF(POS F (t)))) and / or the answers RESPONSE(QUEST(INF(POS F (t)), ΔINF(POS F (t))))) of the occupants by means of microphones arranged in vehicle F.
[0014] Checking the comments RESPONSE(INF(POS F (t)), ΔINF(POS F))) on their significance and / or their plausibility and / or their relevance for determining verified comment information KINF(RESPONSE(INF(POS F (t)), ΔINF(POS F )))) is carried out by the third AI module MOD3, advantageously based on predefined significance criteria, plausibility criteria and relevance criteria.
[0015] Advantageously, the third AI module MOD3 includes a function for checking comments: RESPONSE(INF(POS) F (t)), ΔINF(POS F (t)))) on their significance and / or their plausibility and / or their relevance for determining verified comment information KINF(RESPONSE(INF(POS F (t)), ΔINF(POS F )))) trained machine learning algorithm, in particular a language model. Advantageously, the language model is either a "Large Language Model" or a "Small Language Model".
[0016] Advantageously, the third AI module MOD3 is executed and configured based on the comments RESPONSE(INF(POS) F (t)), ΔINF(POS F (t)))) and / or the answers RESPONSE(QUEST(INF(POS F (t)), ΔINF(POS F (t))))) to generate and output new questions, and to capture and evaluate the answers accordingly, so that interactive communication with one or more occupants of the vehicle takes place. Ultimately, this training also includes tested comment information KINF(RESPONSE(INF(POS) F (t)), ΔINF(POS F )))) generated.
[0017] Advantageously, the fourth AI model, MOD4, includes a feature that allows for the modification or addition of information previously stored in the database for the POS position. F (t) stored information INF(POS F (t)) in changed information INF*(POS F (t)), based on the verified comment information KINF(RESPONSEINF(POS F (t)), ΔINF(POSF (t))))) and the current information INF UMG (POS F (t)) to the environment, trained machine learning algorithm, in particular a language model.
[0018] The task is further solved by a computer system with a data processing device, wherein the data processing device is designed such that a method as described above is performed on the data processing device.
[0019] Furthermore, the object of the invention is solved by a digital storage medium with electronically readable control signals, wherein the control signals can interact with a programmable computer system in such a way that a method as described above is carried out.
[0020] Furthermore, the object of the invention is solved by a computer program product with program code stored on a machine-readable medium for carrying out the method as described above, when the program code is executed on a data processing device.
[0021] Furthermore, the invention relates to a computer program with program code for carrying out the method as described above when the program runs on a data processing device. For this purpose, the data processing device can be configured as any computer system known from the prior art.
[0022] Another aspect of the invention relates to a system for the interactive extension or modification of position-dependent information (INF(POS)) stored in a database. The proposed system comprises: the database, which provides information based on a determined current position (POS). F(t) of the vehicle F dependent information INF(POS F (t)) in vehicle F, with t:= time, is executed and set up; vehicle sensor(s) used to capture current information INF UMG (POS F (t)) to a neighborhood of the vehicle F at its current position POS F (t) is executed and set up; a first AI module MOD1, which is used to determine difference information ΔINF(POS F (t)) between the information provided by the database INF(POS F (t)) and the recorded information INF UMG (POS F (t)) is executed and set up; a second AI module MOD2, which is used to output the information INF(POS F (t)) and / or the difference information ΔINF(POS F (t)) is installed and set up in vehicle F; a recording device for recording associated comments RESPONSE(INF(POS F (t)), ΔINF(POS F(t))) is executed and set up by occupants of vehicle F; a third AI module MOD3, which is used to check the comments RESPONSE(INF(POS F (t)), ΔINF(POS F )) on their significance and / or their plausibility and / or their relevance for determining verified comment information KINF(RESPONSE(INF(POS F (t)), ΔINF(POS F )))) is executed and configured; and a fourth AI model MOD4, which is executed and configured based on the verified comment information KINF(RESPONSE(INF(POS F (t)), ΔINF(POS F )))) and the current information INF UMG (POS F (t)) to the environment, previously in the database for the position POS F (t) stored information INF(POS F (t)) in changed information INF*(POS F (t)) to add or change.
[0023] The AI modules MOD1, MOD2, MOD3, MOD4 are advantageously implemented on individual dedicated processors P1, P2, P3, P4 or on a single processor PX or on multiple processors PY distributed in a network or cloud.
[0024] The vehicle sensor(s) should ideally include one or more from the following non-exhaustive list: - Radar sensor, - Ultrasonic sensor, - LiDAR sensor, - Infrared sensor, - Video sensor, - Camera sensor.
[0025] Advantageous further developments of the proposed system result from a meaningful and analogous transfer of the explanations of the proposed procedure to the system.
[0026] Another aspect of the invention relates to a vehicle with a system as described above.
[0027] Further advantages, features, and details will become apparent from the following description, in which – possibly with reference to the drawings – at least one embodiment is described in detail. Identical, similar, and / or functionally equivalent parts are identified by the same reference numerals.
[0028] They show: Fig. 1. a schematic outline of a proposed procedure, and Fig. 2 a schematic structure of a proposed system.
[0029] Fig. Figure 1 shows a schematic sequence of a proposed procedure for the interactive extension or modification of position-dependent information INF(POS) stored in a database, with the following steps.
[0030] In step 101, the database provides data from a determined current POS position. F (t) of the vehicle F dependent information INF(POS F(t)) in vehicle F, with t:= time
[0031] In step 102, current information (INF) is acquired using vehicle sensor(s). UMG (POS F (t)) to a neighborhood of the vehicle F at its current position POS F (t).
[0032] In step 103, a first AI module MOD1 is used to determine difference information ΔINF(POS). F (t)) between the information provided by the database INF(POS F (t)) and the recorded information INF UMG (POS F (t)).
[0033] In step 104, a second AI module MOD2 is used to output the information INF(POS). F (t)) and / or the difference information ΔINF(POS F (t)) in vehicle F.
[0034] In step 105, associated comments are captured using RESPONSE(INF(POS). F (t)), ΔINF(POS F(t))) of occupants of vehicle F.
[0035] In step 106, a third AI module MOD3 is used to check the comments RESPONSE(INF(POS) F (t)), ΔINF(POS F ))) on their significance and / or their plausibility and / or their relevance for determining verified comment information KINF(RESPONSE(INF(POS F (t)), ΔINF(POS F )))).
[0036] In step 107, a fourth AI model, MOD4, is used based on the verified comment information KINF(RESPONSE(INF(POS)). F (t)), ΔINF(POS F )))) and the current information INF UMG (POS F (t)) to the environment, a change or addition to the information previously stored in the database for the POS position F (t) stored information INF(POS F (t)) in changed information INF*(POS F (t)).
[0037] Fig.Figure 2 shows a schematic structure of a proposed system for the interactive extension or modification of position-dependent information INF(POS) stored in a database, comprising: the database 201, which is used to provide information from a determined current position POS F (t) of the vehicle F dependent information INF(POS F (t)) in vehicle F, with t:= time, is executed and set up; vehicle sensor(s) 202, which are used to capture current information INF UMG (POS F (t)) to a neighborhood of the vehicle F at its current position POS F (t) is / are executed and set up; a first AI module MOD1 203, which is used to determine difference information ΔINF(POS F (t)) between the information provided by the database INF(POS F (t)) and the recorded information INF UMG (POS F(t)) is executed and set up; a second AI module MOD2 204, which is used to output the information INF(POS F (t)) and / or the difference information ΔINF(POS F (t)) is installed and set up in vehicle F; a recording device 205, which is used to record associated comments RESPONSE(INF(POS F (t)), ΔINF(POS F (t))) is executed and set up by occupants of vehicle F; a third AI module MOD3 206, which is used to check the comments RESPONSE(INF(POS F (t)), ΔINF(POS F )) on their significance and / or their plausibility and / or their relevance for determining verified comment information KINF(RESPONSE(INF(POS F (t)), ΔINF(POS F )))) is executed and configured; and a fourth AI module MOD4 207, which is executed and configured based on the verified comment information KINF(RESPONSE(INF(POS F (t)), ΔINF(POS F)))) and the current information INF UMG (POS F (t)) to the environment, previously in the database for the position POS = POS F (t) stored information INF(POS F (t)) in changed information INF*(POS F (t)) to add or change.
[0038] Although the invention has been further illustrated and explained in detail by means of preferred embodiments, the invention is not limited by the disclosed examples, and other variations can be derived from them by a person skilled in the art without departing from the scope of protection of the invention. It is therefore clear that a multitude of possible variations exist. It is also clear that the embodiments mentioned as examples are truly only examples and are not to be understood in any way as limiting, for example, the scope of protection, the possible applications, or the configuration of the invention.Rather, the preceding description and the description of the figures enable the person skilled in the art to implement the exemplary embodiments in concrete terms, whereby the person skilled in the art, with knowledge of the disclosed inventive concept, can make various changes, for example with regard to the function or the arrangement of individual elements mentioned in an exemplary embodiment, without leaving the scope of protection defined by the claims and their legal equivalents, such as further explanations in the description. Reference symbol list 101 - 107 Procedural steps 201 database 202 vehicle sensor(s) 203 first AI module 204 second AI module 205 Recording device 206 third AI module 207 fourth AI module
Claims
[1] Method for interactively extending or modifying position-dependent information INF(POS) stored in a database, comprising the following steps: - Provide from the database (101) from a determined current position POS F (t) of the vehicle F dependent information INF(POS F (t)) in vehicle F, with t:= time; - using vehicle sensor(s), recording (102) current information INF UMG (POS F (t)) to a neighborhood of the vehicle F at its current position POS F (t); - using a first AI module MOD1, determining (103) difference information ΔINF(POS F (t)) between the information provided by the database INF(POS F (t)) and the recorded information INF UMG (POS F (t)); - using a second AI module MOD2, output (104) the information INF(POS F(t)) and / or the difference information ΔINF(POS F (t)) in vehicle F; - Capture (105) related comments RESPONSE(INF(POS F (t)), ΔINF(POS F (t))) of occupants of vehicle F; - using a third AI module MOD3, checking the comments RESPONSE(INF(POS F (t)), ΔINF(POS F ))) on their significance and / or their plausibility and / or their relevance for determining (106) verified comment information KINF(RESPONSE(INF(POS F (t)), ΔINF(POS F )))); and - using a fourth AI model MOD4, based on the verified comment information KINF(RESPONSE(INF(POS) F (t)), ΔINF(POS F )))) and the current information INF UMG (POS F (t)) to the environment, modifying or adding (107) to the existing database for the POS position F (t) stored information INF(POS F(t)) in changed information INF*(POS F (t)). [2] Method according to claim 1, wherein the second AI module MOD2 is applied to the information INF(POS F (t)) and the difference information ΔINF(POS F (t)) based questions QUEST(INF(POS F (t)), ΔINF(POS F (t)))) are generated and output in vehicle F, with responses RESPONSE(QUEST(INF(POS F (t)), ΔINF(POS F (t))))) are recorded by the inmates in response to the questions; whereby the answers are captured using the third AI module MOD3 RESPONSE(QUEST(INF(POS F (t)), ΔINF(POS F (t))))) on their significance and / or their plausibility and / or their relevance for determining verified comment information KINF(RESPONSE(QUEST(INF(POS F (t)), ΔINF(POS F (t))))) are checked; and where, using the fourth AI model MOD4, based on the checked comment information KINF(RESPONSE(QUEST(INF(POS) F (t)), ΔINF(POSF (t))))), previously in the database for the position POS F (t) stored information INF(POS F (t)) in changed information INF*(POS F (t)) will be changed. [3] Method according to one of claims 1 to 2, wherein the position-dependent information INF(POS) stored in the database comprises one or more of the following: - Weather information - Traffic information (traffic jams, construction sites, road closures, etc.) - locally relevant news information - Information on structural changes - Information about tourist attractions. [4] Method according to any one of claims 1 to 3, wherein the first AI module MOD1 is designed to determine the difference information ΔINF(POS F (t)) trained machine learning algorithm. [5] Method according to any one of claims 1 to 4, wherein the second AI module MOD2 is configured to output (104) spoken information INF(POS F (t)) and / or spoken difference information ΔINF(POS F (t)) trained machine learning algorithm, in particular a language model. [6] Method according to any one of claims 1 to 5, wherein the third AI module MOD3 is configured to check the comments RESPONSE(INF(POS) F (t)), ΔINF(POS F (t)))) on their significance and / or their plausibility and / or their relevance for determining verified comment information KINF CHECKED (COM(INF(POS F (t)), ΔINF(POS F )))) trained machine learning algorithm, in particular a language model. [7] Method according to any one of claims 1 to 6, wherein the fourth AI model MOD4 is designed to modify or supplement (107) the previously stored in the database for the POS position F (t) stored information INF(POS F (t)) in changed information INF*(POS F (t)), based on the verified comment information KINF(RESPONSE(INF(POS F (t)), ΔINF(POS F (t))))) and the current information INF UMG (POS F (t)) to the environment, trained machine learning algorithm, in particular a language model. [8] Computer system comprising a data processing device, wherein the data processing device is configured such that a method according to one of the preceding claims is carried out on the data processing device. [9] System for interactive extension or modification of position-dependent information stored in a database INF(POS), comprising: - the database (201), which is used to provide data from a determined current position POS F (t) of the vehicle F dependent information INF(POS F (t)) in vehicle F, with t:= time is executed and set up; - Vehicle sensor(s) (202) used to capture current information INF UMG (POS F (t)) to a neighborhood of the vehicle F at its current position POS F (t) is / are executed and set up; - a first AI module MOD1 (203) for determining difference information ΔINF(POS F (t)) between the information provided by the database INF(POS F (t)) and the recorded information INF UMG (POS F (t)) is executed and set up; - a second AI module MOD2 (204) for outputting the information INF(POS F (t)) and / or the difference information ΔINF(POS F (t)) is carried out and equipped in vehicle F; - a capture device (205) for capturing associated comments RESPONSE(INF(POS F (t)), ΔINF(POS F (t))) is carried out and set up by occupants of vehicle F; - a third AI module MOD3 (206), which is used to check the comments RESPONSE(INF(POS F (t)), ΔINF(POS F )) on their significance and / or their plausibility and / or their relevance for determining verified comment information KINF(RESPONSE(INF(POS F (t)), ΔINF(POS F )))) is executed and set up; and - a fourth AI module MOD4 (207) that is executed and configured based on the verified comment information KINF(RESPONSE(INF(POS) F (t)), ΔINF(POS F)))) and the current information INF UMG (POS F (t)) to the environment, previously in the database for the position POS = POS F (t) stored information INF(POS F (t)) in changed information INF*(POS F (t)) to add or change. [10] Vehicle with a system according to claim 9.