KR-102961459-B1 - METHOD FOR RECOMMENDING PERSONALIZED ROUTINE AND SYSTEM THEREFOR

KR102961459B1KR 102961459 B1KR102961459 B1KR 102961459B1KR-102961459-B1

Abstract

The present disclosure relates to a method for recommending personalized routines and a system thereof. A method according to one embodiment of the present disclosure may include, by a computing system, the steps of receiving data from a plurality of subsystems included in a vehicle; identifying the occurrence of a first event based on the received data; identifying a first action sequence including actions performed by a plurality of subsystems during a predetermined time interval from the time of occurrence of the first event; verifying a preset routine criterion based on the first event and the first action sequence; generating first recommendation routine information by combining the first event and the first action sequence if, as a result of verification, the first event and the first action sequence satisfy the routine criterion; and providing the first recommendation routine information through an output interface.

Inventors

황슬기
이지호
문재철
황일훈

Assignees

(주)카네비모빌리티

Dates

Publication Date: 20260507
Application Date: 20250822

Claims (14)

In a method performed by a computing system, A step of receiving data from a plurality of subsystems included in the vehicle; A step of identifying the occurrence of a first event based on the received data above; A step of identifying a first operation sequence including operations performed by the plurality of subsystems during a predetermined time interval from the time of occurrence of the first event; A step of verifying a preset routine standard based on the first event and the first operation sequence; If, as a result of the above verification, the first event and the first operation sequence satisfy the routine criteria, the step of generating first recommendation routine information by combining the first event and the first operation sequence; and The step of providing the above-mentioned first recommendation routine information through an output interface, The above first operation sequence is, It includes information regarding the type, execution order, and execution time of each of the above operations, and The step of verifying the above routine criteria is, A step of assigning a first weight to each type of the above-mentioned actions and obtaining an action type score; A step of assigning a second weight to the execution order of each of the above operations and obtaining an operation execution order score; A step of assigning a third weight at the time of execution of each of the above operations and obtaining an operation execution time score; A step of integrating the above-mentioned operation type score, the above-mentioned operation execution order score, and the above-mentioned operation execution time score, and calculating a routine score; and If the routine score is greater than or equal to a routine setting threshold included in the routine criteria, the first event and the first operation sequence are determined to satisfy the routine criteria, the method comprising: The first weight is a value greater than the second weight, and the second weight is a value greater than the third weight, and The step of determining that the first event and the first operation sequence satisfy the routine criteria when the routine score is greater than or equal to the routine setting threshold included in the routine criteria is Among a plurality of operation sequences collected during the time interval from the time of occurrence of the first event, the method includes a step of determining that the first operation sequence performed after the occurrence of the first event satisfies the routine criteria only when the occurrence rate of a second operation sequence branching into a subsequent operation different from the first operation sequence is less than or equal to a reference rate. The above routine criteria are, The one that is dynamically adjusted based on user feedback data regarding the above-mentioned first recommendation routine information, Personalized routine recommendation method.
In Article 1, The step of receiving the above data is, For each of the above data, the method includes the step of assigning a timestamp at the time when the data occurred. The step of identifying the first operation sequence above is, A step comprising sorting the above data based on the above timestamp, Personalized routine recommendation method.
In Article 1, The above first event is, An external environment event corresponding to at least one of preset time conditions and weather conditions, and at least one of a first operation performed by at least one of the plurality of subsystems, Personalized routine recommendation method.
delete
In Article 1, The step of verifying the above routine criteria is, A step of obtaining a set of operation sequences by collecting a plurality of operation sequences including operations performed by the plurality of subsystems during the time interval from the time of occurrence of the first event; A step of calculating the similarity between each action sequence included in the set of action sequences and the first action sequence; A step of calculating an integrated similarity by integrating the similarities calculated above; and If the above integrated similarity is greater than or equal to a preset threshold, the method includes the step of determining that the first operation sequence performed after the occurrence of the first event satisfies the routine criteria. Personalized routine recommendation method.
In Article 5, The step of calculating the above similarity is, A method comprising the step of calculating an edit distance between each action sequence included in the set of action sequences and the first action sequence. Personalized routine recommendation method.
In Article 5, The step of calculating the above similarity is, The method comprises the step of embedding each operation sequence included in the above operation sequence set and the first operation sequence into a vector space, and calculating the vector similarity between the embedded vectors. Personalized routine recommendation method.
In Article 1, The step of verifying the above routine criteria is, Among the plurality of operation sequences above, a step of calculating the number of occurrences of operation sequences having a similarity to the first operation sequence greater than or equal to a reference value; and If the above occurrence count is greater than or equal to a preset reference count, the method includes a step of determining that the first operation sequence performed after the occurrence of the first event satisfies the routine reference. Personalized routine recommendation method.
delete
In Article 1, The steps provided above are, A step of receiving a user response regarding whether to approve the first recommendation routine information; and If the above user response is an approval input that approves the above first recommendation routine information, the method includes the step of storing the above first recommendation routine information in a routine database. Personalized routine recommendation method.
delete
In Article 1, The steps provided above are, A step of receiving a user response regarding whether to approve the first recommendation routine information; and If the above user response is an approval input that approves the above first recommendation routine information, the method includes the step of storing the above first recommendation routine information in a routine database. A step of monitoring routine trigger data received from the plurality of subsystems; and If the routine trigger data is data corresponding to the first event, the method further includes the step of executing the first operation sequence. Personalized routine recommendation method.
In Article 12, The step of monitoring the above routine trigger data is, A step of searching for routine trigger data with respect to the routine database; A step of identifying a matching routine corresponding to the routine trigger data using the results of the above search; A step of identifying second situation information that is different from first situation information in which a second operation sequence corresponding to the above matching routine is performed; The step of providing exception situation checking content including the above second situation information through the output interface; and A method comprising the step of executing the second operation sequence when a response approving the execution of the second operation sequence is received with respect to the above exception situation checking content. Personalized routine recommendation method.
Communication interface; Memory where a computer program is loaded; and The computer program described above includes one or more processors on which it is executed, The above computer program is, The operation of receiving data from multiple subsystems included in the vehicle; An operation to identify the occurrence of a first event based on the received data above; An operation to identify a first operation sequence including operations performed by the plurality of subsystems during a predetermined time interval from the time of occurrence of the first event; An operation to verify a preset routine standard based on the first event and the first operation sequence; If, as a result of the above verification, the first event and the first operation sequence satisfy the routine criteria, the operation of generating first recommendation routine information by combining the first event and the first operation sequence; and Includes instructions that perform the operation of providing the above-mentioned first recommendation routine information through an output interface, The above first operation sequence is, It includes information regarding the type, execution order, and execution time of each of the above operations, and The operation of verifying the above routine criteria is, An action of assigning a first weight to each of the above types of actions and obtaining an action type score; An action of assigning a second weight to the execution order of each of the above actions and obtaining an action execution order score; An action of assigning a third weight at the time of execution of each of the above actions and obtaining a score at the time of action execution; An operation to integrate the above-mentioned operation type score, the above-mentioned operation execution order score, and the above-mentioned operation execution time score, and to calculate a routine score; and If the routine score is greater than or equal to the routine setting threshold included in the routine criteria, the first event and the first operation sequence include an operation of determining that they satisfy the routine criteria. The first weight is a value greater than the second weight, and the second weight is a value greater than the third weight, and If the routine score is greater than or equal to the routine setting threshold included in the routine criteria, the operation of determining that the first event and the first operation sequence satisfy the routine criteria is, Among a plurality of operation sequences collected during the time interval from the time of occurrence of the first event, the operation includes determining that the first operation sequence performed after the occurrence of the first event satisfies the routine criteria only when the occurrence rate of a second operation sequence branching into a subsequent operation different from the first operation sequence is less than or equal to a reference rate. The above routine criteria are, The one that is dynamically adjusted based on user feedback data regarding the above-mentioned first recommendation routine information, Personalized routine recommendation system.

Description

Method for recommending personalized routines and system therefrom The present disclosure relates to a method and system for recommending personalized routines within a vehicle. Vehicles are equipped with various subsystems, such as navigation, climate control, audio systems, and seat control systems, which play a crucial role in enhancing driver convenience and safety. In particular, drivers tend to perform the same or similar series of actions repeatedly in specific situations, and technologies that identify and recommend personalized routines based on this are gaining attention for improving the vehicle user experience. Recently, active research has been conducted to collect and analyze in-vehicle user data to provide personalized services, and this is considered an important technology that can contribute to reducing unnecessary operations while driving and increasing safety. However, conventional technology has primarily used a method of identifying routines based solely on whether a specific action has been repeated a certain number of times or more after an event occurs. Because this approach relies only on simple repeatability, it has limitations in that it fails to distinguish between various branching patterns that may actually exist after the same starting action. Consequently, problems have arisen where different branching actions are mistakenly identified as the same routine, or conversely, actions that are sufficiently consistent are not accurately determined to be routines. Furthermore, conventional technology has been limited by the lack of methods to quantitatively evaluate the similarity between action sequences, resulting in reduced precision in user-customized routine recommendations. This acts as a significant obstacle to optimizing the user experience and has made it difficult to provide more sophisticated and personalized routines in various in-vehicle situations. These issues not only hinder the qualitative improvement of the vehicle user experience but also remain a critical challenge in ensuring safety during driving. FIG. 1 is a system configuration diagram for explaining the configuration and operation of a vehicle system according to some embodiments of the present disclosure. FIG. 2 is a system configuration diagram for explaining in detail the configuration and operation of a vehicle system according to some embodiments of the present disclosure, described with reference to FIG. 1. FIG. 3 is a flowchart illustrating the operation of a personalized routine recommendation method according to some embodiments of the present disclosure. FIG. 4 is a detailed flowchart for explaining the detailed operation of a personalized routine recommendation method according to some embodiments of the present disclosure, described with reference to FIG. 3. FIG. 5 is a drawing for illustrating an event according to some embodiments of the present disclosure. FIG. 6 is a detailed flowchart for explaining the detailed operation of a personalized routine recommendation method according to some embodiments of the present disclosure, described with reference to FIG. 3. FIG. 7 is a detailed flowchart for explaining the detailed operation of a personalized routine recommendation method according to some embodiments of the present disclosure, described with reference to FIG. 3. FIG. 8 is a detailed flowchart for explaining the detailed operation of a personalized routine recommendation method according to some embodiments of the present disclosure, described with reference to FIG. 3. FIG. 9 is a diagram illustrating the operation of a personalized routine recommendation method according to some embodiments of the present disclosure, described with reference to FIG. 8. FIG. 10 is a detailed flowchart for explaining the detailed operation of a personalized routine recommendation method according to some embodiments of the present disclosure, described with reference to FIG. 8. FIG. 11 is a drawing for explaining the operation of a personalized routine recommendation method according to some embodiments of the present disclosure, described with reference to FIG. 10. FIG. 12 is a detailed flowchart for explaining the detailed operation of a personalized routine recommendation method according to some embodiments of the present disclosure, described with reference to FIG. 3. FIG. 13 is a detailed flowchart for explaining the detailed operation of a personalized routine recommendation method according to some embodiments of the present disclosure, described with reference to FIG. 12. FIG. 14 is a detailed flowchart for explaining the detailed operation of a personalized routine recommendation method according to some embodiments of the present disclosure, described with reference to FIG. 3. FIG. 15 is a detailed flowchart for explaining the detailed operation of a personalized routine recommendation method according to some embodiments of the present disclosure, described with reference to FIG. 14. FIG. 16 is