CN114056343B - Processing method of vehicle-mounted system function, server and storage medium - Google Patents
Processing method of vehicle-mounted system function, server and storage medium Download PDFInfo
- Publication number
- CN114056343B CN114056343B CN202210024105.5A CN202210024105A CN114056343B CN 114056343 B CN114056343 B CN 114056343B CN 202210024105 A CN202210024105 A CN 202210024105A CN 114056343 B CN114056343 B CN 114056343B
- Authority
- CN
- China
- Prior art keywords
- user
- customization
- scheme
- vehicle
- alternative
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W50/08—Interaction between the driver and the control system
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/08—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to drivers or passengers
- B60W40/09—Driving style or behaviour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2540/00—Input parameters relating to occupants
- B60W2540/30—Driving style
Abstract
The application discloses a processing method, which comprises the following steps: receiving a customization scheme which is uploaded by a terminal and used for customizing the functions of the vehicle-mounted system by a vehicle user; obtaining a plurality of user tags of a user according to a customization scheme; obtaining the contribution degree of each customization scheme to each user tag by using all customization schemes uploaded by all terminals; determining the scheme value of each customization scheme to a single user according to the sum of the contribution degrees of each customization scheme to all user tags of the single user; obtaining a plurality of alternative customization schemes according to the scheme value, and processing the alternative customization schemes to obtain a recommended customization scheme which can be executed by the voice server control vehicle; and sending the recommended customization scheme to the terminal corresponding to the request so as to display the recommended customization scheme on the terminal. The recommendation customization scheme can be more pertinently recommended to the user aiming at different users, and a practical personalized customization scheme with strong pertinence is recommended to the user. The application also discloses a server and a storage medium.
Description
Technical Field
The present application relates to the field of transportation, and in particular, to a processing method, a server, and a computer-readable storage medium.
Background
With the development of vehicle intellectualization, the function of customizing the functions of the vehicle-mounted system is realized by combining voice, highly-free customization operation can be provided for users, the users can set a voice trigger condition of 'good morning' by themselves, and execution instructions of a plurality of vehicle-mounted system functions executed by the vehicle when the condition is met, such as 'air conditioner is adjusted to 26 degrees, ventilation is opened in the vehicle, and a seat is adjusted backwards to 3 grades', and the mode can help the users to realize the operation of realizing the functions of the plurality of vehicle-mounted systems by one sentence simply. The whole flow of the customizing function comprises a customizing process and a triggering process, wherein a user is required to set a voice triggering condition and a plurality of execution instructions in the customizing process to generate a customizing scheme; and in the triggering process, the user needs to speak the corresponding triggering condition to the voice assistant in the vehicle cabin, the vehicle can inquire the voice server, and if the voice server inquires the corresponding customized scheme, an instruction is issued to the vehicle for execution.
However, for the user of the vehicle, such a function requires the user to memorize the corresponding voice trigger condition after getting on the vehicle, and the set customized function will not be triggered until the user has no habit or forgets the voice trigger condition. And in the process of using the customization function, the user needs to independently think of the customization scheme according to the own requirements. Without inspiration, learning difficulties and creativity will limit the full use of functionality by users. In another type of method, some customized schemes with high use frequency are provided for the user in a manual screening mode, although the customized schemes can play a certain recommendation role, the method cannot recommend the customized schemes with strong pertinence for the user from the user individuals, so that the use of the function by the user is influenced, and the user experience is poor.
Disclosure of Invention
In view of this, the present application provides a method for processing functions of an in-vehicle system, including:
receiving a customization scheme which is uploaded by a terminal and used for customizing the functions of the vehicle-mounted system by a vehicle user;
acquiring a plurality of user tags of a user according to a customization scheme;
obtaining the contribution degree of each customization scheme to each user label by using all customization schemes uploaded by all terminals;
determining a scheme value of each customization scheme to a single user according to the sum of contribution degrees of each customization scheme to all user tags of the single user;
obtaining a plurality of alternative customization schemes according to the scheme value, and processing the alternative customization schemes to obtain a recommended customization scheme which can be executed by a voice server control vehicle;
and sending the recommended customization scheme to a terminal corresponding to the request so as to display the recommended customization scheme on the terminal.
Therefore, the recommended customization scheme can be more pertinently recommended to the user aiming at different users, and a strong-pertinence and practical personalized customization scheme is recommended to the user, so that the user can obtain more free and personalized vehicle control feeling, the inheritance rate of the user is improved, and the use feeling of the user on the customization function is effectively improved.
The obtaining a plurality of user tags of a user according to a customization scheme includes:
classifying the customization schemes uploaded by the terminal to obtain a plurality of customization scheme labels;
acquiring user information of the user, wherein the user information comprises user basic information, vehicle information, user driving habit information and user driving behavior information;
and inputting the plurality of customized scheme labels and the user information into a user classification model to obtain a plurality of user labels of each user.
Therefore, compared with the traditional recommendation system, the user classification and the user portrait or the user label generation are often performed only by analyzing the personal information of the user, the user classification is performed by utilizing the information related to the vehicle control elements in the aspects of vehicle use habits and the like of the user, the portrait of the user is performed according to the information related to the vehicle control elements of the user, and the user label in the aspect of vehicle use of the user is obtained. The finally formed recommendation customization scheme is matched with the vehicle control behavior of the user better, the user can be recommended more satisfactorily, and the user experience is improved.
The inputting the plurality of customized scheme labels and the user information into a user classification model to obtain the plurality of user labels of each user comprises:
performing feature extraction on the plurality of customized scheme labels and the user information of the user to obtain customized features of the user;
inputting the customized characteristics of each user into the user classification model to obtain label probability values of a plurality of user labels corresponding to each user;
and processing the label probability value according to a preset threshold value to obtain a plurality of user labels of each user.
In this way, the historical user tags of the users can be obtained by outputting the probability values of the user tags and dividing the probability values through the thresholds.
The customizing scheme comprises an execution instruction, and the step of obtaining the contribution degree of each customizing scheme to each user tag by using all the customizing schemes uploaded by all the terminals comprises the following steps:
determining the contribution degree of an execution instruction to the user label according to the model parameters of the user classification model;
and calculating the contribution degree of each customization scheme to each user tag according to the contribution degree of the execution instruction to each user tag.
In this way, the contribution degree of each customization scheme to each user tag is calculated according to the determined contribution degree of the execution instruction to the user tag. Since the user's personalization tends to be closely related to the combined preference of multiple actions to be performed, rather than just a single action. Compared with other scheme value generating modes, for example, a mode of executing actions controlled by a specific vehicle is utilized, the scheme value is determined by utilizing the contribution degree of the execution instruction to the user tag, the recommended customization scheme can be associated with the execution instruction of the user, so that the scheme value of the customization scheme better reflects the personalized customization requirement of the user, the efficiency of generating the recommended customization scheme is improved, the recommended customization scheme is recommended to the user more specifically, the inheritance rate of the user is improved, and the use experience of the user on the customization function is effectively improved.
The method further comprises the following steps:
obtaining the customized information and the vehicle information of each user;
classifying all the customization schemes of each user according to the customization information of each user and/or the multiple customization scheme labels to obtain the customization frequency of each customization scheme;
and determining the customized information, the vehicle information, the customization frequency and all the customization schemes of each user as the private customized data of each user according to the classification result and storing the data.
The obtaining of a plurality of alternative customization solutions according to the solution values and the processing of the plurality of alternative customization solutions to obtain a recommended customization solution which can be executed by the voice server control vehicle comprises:
and performing first sequencing processing on the plurality of alternative customization schemes according to the scheme values to generate the recommended customization scheme.
Therefore, the multiple alternative customization schemes are ranked through the scheme values, and the multiple alternative customization schemes which are most matched with the personalized requirements of the user can be obtained and recommended to the user.
The obtaining a plurality of alternative customization solutions according to the solution value and processing the plurality of alternative customization solutions to obtain a recommended customization solution which can be executed by the voice server control vehicle further comprises:
performing first sequencing processing on the multiple alternative customization schemes according to the scheme values to obtain a first alternative customization scheme;
and preprocessing the first alternative customization scheme according to the current customization state of the user to obtain a second alternative customization scheme which is consistent with the current customization state, wherein the preprocessing comprises deduplication, grouping and/or screening processing.
Therefore, by further carrying out preprocessing such as duplicate removal, grouping and/or screening processing and the like according to the current customization state after the first sequencing processing, the recommendation of the customization scheme can be combined with external conditions such as customization time and the like, and the accuracy of the recommendation is improved.
The obtaining a plurality of alternative customization solutions according to the solution value and processing the plurality of alternative customization solutions to obtain a recommended customization solution which can be executed by the voice server control vehicle further comprises:
and performing second sorting processing on the second alternative customization schemes according to the current customization state, and determining the recommended customization scheme according to the plurality of second alternative customization schemes subjected to the second sorting processing.
Therefore, the multiple alternative customization schemes are sequenced through the current customization state, and the multiple alternative customization schemes which are most matched with the personalized requirements of the user can be obtained and recommended to the user.
The application also provides a server with vehicle-mounted system functions, which comprises a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the method of any one of the above is realized.
The present application also provides a non-transitory computer-readable storage medium, which when executed by one or more processors, implements the method described in any of the above embodiments.
The method comprises the steps that a customization scheme for customizing the functions of the vehicle-mounted system is obtained through a vehicle user uploaded by a receiving terminal; acquiring a plurality of user tags of a user according to a customization scheme; obtaining the contribution degree of each customization scheme to each user label by using all customization schemes uploaded by all terminals; determining a scheme value of each customization scheme to a single user according to the sum of contribution degrees of each customization scheme to all user tags of the single user; obtaining a plurality of alternative customization schemes according to the scheme value, and processing the plurality of alternative customization schemes to obtain a recommended customization scheme which can be executed by a voice server control vehicle; and sending the recommended customization scheme to the terminal corresponding to the request so as to display the recommended customization scheme on the terminal. The method and the system can recommend the recommended customization scheme to the user more pertinently aiming at different users, and recommend a personalized customization scheme with strong pertinence and practicability to the user, so that the user obtains more free and personalized vehicle control feeling, the inheritance rate of the user is improved, and the use feeling of the user on the customization function is effectively improved.
Additional aspects and advantages of the present application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the present application.
Drawings
The above and/or additional aspects and advantages of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
FIG. 1 is a schematic flow diagram of a treatment process of the present application;
fig. 2 is another schematic flow diagram of the processing method of the present application.
Detailed Description
Reference will now be made in detail to embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below by referring to the drawings are exemplary only for the purpose of explaining the embodiments of the present application, and are not to be construed as limiting the embodiments of the present application.
With the development of vehicle intellectualization, the function of customizing the functions of the vehicle-mounted system is realized by combining voice, and highly-free customizing operation can be provided for users. The whole flow of the customizing function comprises a customizing process and a triggering process, wherein a user is required to set a voice triggering condition and a plurality of execution instructions in the customizing process to generate a customizing scheme; and in the triggering process, the user needs to speak the corresponding triggering condition to the voice assistant in the vehicle cabin, the vehicle can inquire the voice server, and if the voice server inquires the corresponding customized scheme, an instruction is issued to the vehicle for execution.
However, in the process of using the customization function, the user needs to independently think about the customization scheme according to the needs of the user. Without inspiration, learning difficulty and creativity will limit the full use of functionality by the user. In another type of method, some customized schemes with high use frequency are provided for the user in a manual screening mode, although the methods can play a certain recommendation role, the methods cannot recommend the customized schemes with strong pertinence for the user from the user individuals, and therefore user experience is influenced.
Referring to fig. 1, the present application provides a method for processing functions of a vehicle-mounted system, including:
01: receiving a customization scheme which is uploaded by a terminal and used for customizing the functions of the vehicle-mounted system by a vehicle user;
02: acquiring a plurality of user tags of a user according to a customization scheme;
03: obtaining the contribution degree of each customization scheme to each user label by using all customization schemes uploaded by all terminals;
04: generating a scheme value of each customization scheme to a single user according to the sum of the contribution degrees of each customization scheme to all user tags of the single user;
05: obtaining a plurality of alternative customization schemes according to the scheme value, and processing the plurality of alternative customization schemes to obtain a recommended customization scheme which can be executed by a voice server control vehicle;
06: and sending the recommended customization scheme to the terminal corresponding to the request so as to display the recommended customization scheme on the terminal.
The application also provides a server with the vehicle-mounted system function. The server includes a memory and a processor. The processor is used for receiving a request for customizing functions of the vehicle-mounted system by the terminal and obtaining a user label of a user according to the user classification model; calculating a plurality of alternative customization schemes according to the user tags and the model parameters of the user classification model to obtain a scheme value of each alternative customization scheme to the user; processing the multiple alternative customization schemes according to the scheme values to obtain a recommended customization scheme, wherein the recommended customization scheme can be executed by a voice server; and sending the recommended customization scheme to the terminal so as to display the recommended customization scheme on the terminal.
In the process of customizing the vehicle user, the vehicle user receives a customization scheme uploaded by the terminal and used for customizing the functions of the vehicle-mounted system, and a plurality of user tags of the user are obtained according to the customization scheme.
Wherein the terminal comprises a mobile terminal. The mobile terminal equipment comprises mobile phones, tablet computers, notebooks, desktop computers, wearable equipment and the like. For example, an APP which can customize the vehicle-mounted system function of the electric vehicle is installed in the mobile phone, the user operates by opening a corresponding page of the APP, and the APP forms a customization request instruction and sends the customization request instruction according to the operation of the user so as to initiate a request for customizing the vehicle-mounted system function.
A method of obtaining a plurality of user tags for a user according to a customization scheme, comprising:
classifying the customization schemes uploaded by the terminal to obtain a plurality of customization scheme labels;
acquiring user information of a user, wherein the user information comprises user basic information, vehicle information, user driving habit information and user driving behavior information;
and inputting the plurality of customized scheme labels and the user information into the user classification model to obtain a plurality of user labels of each user.
The processor is used for classifying the customization schemes uploaded by the terminal to obtain a plurality of customization scheme labels; acquiring user information of a user, wherein the user information comprises user basic information, vehicle information, user driving habit information and user driving behavior information; and inputting the plurality of customized scheme labels and the user information into the user classification model to obtain a plurality of user labels of each user.
And classifying the customization scheme uploaded by the terminal, classifying the content of the customization scheme by constructing a text classification model, and extracting tags exceeding a threshold value as the tags of the customization scheme.
And acquiring user information of the user, wherein the user information comprises user basic information, vehicle information, user driving habit information and user driving behavior information. The basic information of the user includes personal information of the user, such as age, sex, occupation, hobby and the like, and information of the vehicle purchased by the user, such as time of purchase. The vehicle information includes information of a vehicle type, a vehicle configuration, an on-vehicle system function of the vehicle, a vehicle state, and the like. The driving habit information of the user comprises a high-frequency vehicle control instruction, and if the number of times of playing music in 24 hours reaches a threshold value, the music is played as the high-frequency vehicle control instruction. The user driving behavior information comprises driving behavior data such as vehicle basic setting, common vehicle using time, average vehicle speed and the like.
It should be noted that all user information in the present application is used in an encryption manner, and training and real-time interaction are performed in a dark coding manner. And the method is carried out on the premise of user authorization, and the unauthorized user information cannot be used.
Further, the multiple customized scheme labels and the user information are input into the user classification model, and multiple user labels of each user are obtained. The user classification model comprises a user classification model or a deep learning model. Specifically, a multi-classification model is used based on the server-side capability, and a customized scheme is used as input to predict the confidence of each user label.
The user classification model can classify the user of the user object which initiates the request of customizing the functions of the vehicle-mounted system by the terminal at present so as to output the user label of the current user. The user tags include user tags that are preset in the user classification model to form a user portrait of the current user. For example, each user may obtain one or more user tags, which are "office workers", "driving enjoys", "music arrives", etc. of the current user according to the user classification model.
The user classification model may be trained in advance via training data. In particular, a user classification model may be trained using user training data of a large number of users, each user being an independent user training data. The user training data at least comprises a historical customization scheme, user basic information, vehicle information, user driving habit information and user driving behavior information. Wherein the historical customization scheme comprises the customization scheme determined by the current user in the history of using the customization function. The user basic information is the same as the user information.
Further, the user training data of the historical users are subjected to statistical classification so as to perform feature extraction on the user training data. The historical user has a large amount of historical customization data in the customization process, wherein the customization data comprises information such as a customization scheme and customization time. And constructing a text classification model for the customization scheme, classifying the customization scheme, extracting tags exceeding a threshold value as customization scheme tags, and then summarizing the customization scheme tags. And inputting the extracted features into a user classification model pair for processing so as to output historical user labels corresponding to the users, optimizing model parameters of the user classification model according to user training data of a plurality of historical users, optimizing the model parameters of the user classification model through the user training data of a large number of users, stopping training when a preset training end condition is met, and determining the optimized user classification model as the user classification model.
Therefore, compared with the traditional recommendation system, the user classification and the user portrait or the user label generation are often performed only by analyzing the personal information of the user, the user classification is performed by utilizing the information related to the vehicle control elements in the aspects of vehicle use habits and the like of the user, the portrait of the user is performed according to the information related to the vehicle control elements of the user, and the user label in the aspect of vehicle use of the user is obtained. The finally formed recommendation customization scheme is matched with the vehicle control behavior of the user better, the user can be recommended more satisfactorily, and the user experience is improved.
The method for inputting a plurality of customized scheme labels and user information into a user classification model to obtain a plurality of user labels of each user comprises the following steps:
performing feature extraction on the plurality of customized scheme labels and user information of the user to obtain customized features of the user;
inputting the customized characteristics of each user into a user classification model to obtain label probability values of a plurality of user labels corresponding to each user;
and processing the label probability value according to a preset threshold value to obtain a plurality of user labels of each user.
The processor is used for extracting the characteristics of the plurality of customized scheme labels and the user information of the user to obtain the customized characteristics of the user; inputting the customized characteristics of each user into a user classification model to obtain label probability values of a plurality of user labels corresponding to each user; and processing the label probability value according to a preset threshold value to obtain a plurality of user labels of each user.
Statistical aggregation may be performed for multiple customization scheme tags. Performing statistical classification on information such as user basic information, vehicle information, user driving habit information, user driving behavior information and the like in the user information, for example, grouping the users according to the age of the users; determining the state of the user according to the time of the vehicle union user using the vehicle; and counting the design combination preference of the execution instruction in the existing customization scheme of the user, carrying out statistical analysis on the preference, and classifying the user according to the preference of the user on the vehicle control instruction.
After the characteristics of a plurality of customized scheme labels and user information of a user are extracted to obtain customized characteristics of the user, the customized characteristics can be taken as customized characteristics according to each classified category, and the customized characteristics are expressed by Token character strings to complete the characteristic extraction and taken as the input of a user classification model.
For example, historical customization scheme A: the triggering conditions are as follows: monday through friday, 8: 30, of a nitrogen-containing gas; the execution instruction is as follows: navigating to the company, opening the vehicle window and playing music. The scenario tag for customized scenario a may be determined to be "on time to work".
Meanwhile, the user training data such as the execution action, the user basic information, the vehicle information, the user driving habit information, the user driving behavior information and the like are subjected to statistical classification, and the feature extraction can be specifically carried out in the form of a character string Token.
For example, users are grouped according to their ages, and the ages are Token-coded, for example, the ages may be segmented: 18-30 years old: 1, 30-40 years old: 2. the occupation can adopt one-hot coding or word vector coding, etc.
For another example, the state of the user is determined to be in Token form according to the time when the user uses the vehicle. Or classifying the users according to the vehicle control command preference of the users in the vehicle.
Further, each classified category is represented as a separate Token, and then all tokens can be concatenated into a string as input. The stitching may include random stitching, or sequential stitching.
For example, the feature Token "1356874" represents "user information: age: 30, a working city: shanghai; the vehicle state: v1; customizing the scheme label: working; and executing the action: navigating to a company; "
Inputting the customized characteristics of each user into a user classification model to obtain label probability values of a plurality of user labels corresponding to each user;
and processing the label probability value according to a preset threshold value to obtain a plurality of user labels of each user.
And inputting the features after the features are extracted into the user classification model. Wherein the user classification model comprises a logistic regression model. Inputting the character string Token into the model, extracting the characteristics, and outputting the probability of each user label corresponding to the historical user. Meanwhile, a specific threshold value is set for the probability, and when the probability is higher than the specific threshold value, the user label is marked for the historical user, so that all historical user labels corresponding to the user are obtained. For example, the output user tags include: young vitality, sense of sinking and steadiness, returning early and late, freedom in self, enjoyment of driving, creative youth and the like. Each user tag may characterize the user's personal needs for vehicle handling.
In this way, the historical user tags of the users can be obtained by outputting the probability values of the user tags and dividing the probability values through the thresholds.
The customization scheme comprises an execution instruction, and is characterized in that the step of obtaining the contribution degree of each customization scheme to each user tag by using all the customization schemes uploaded by all the terminals comprises the following steps:
determining the contribution degree of an execution instruction to a user label according to the model parameters of the user classification model;
and calculating the contribution degree of each customization scheme to each user tag according to the contribution degree of the execution instruction to each user tag.
The processor is used for determining the contribution degree of the execution instruction to the user label according to the model parameters of the user classification model; and calculating the contribution degree of each customization scheme to each user tag according to the contribution degree of the execution instruction to each user tag.
Wherein the model parameter is the weight of each feature Token in the user classification model to each output user label. And deriving the contribution value of the execution instruction in each historical customization scheme to the user tag according to the weight of each characteristic Token to each output user tag, wherein the contribution value is taken as the contribution value of the customization scheme to the user tag. For example, in the model, each vehicle control command can be used as a feature, 0 and 1 codes are used for recording whether the feature exists, and then the contribution value of each feature is reversely analyzed by using the weight of the feature.
The content of each customization scheme may include customization information that customizes the execution of one or more functions in the in-vehicle system, and may include a plurality of information elements. Including, for example, trigger conditions, execution instructions, customized basic information, and the like. The execution instruction is used for controlling the vehicle to execute relevant vehicle-mounted system functions according to the execution instruction in the customization scheme when the trigger condition in the customization scheme is met. The execution instructions may include combinations and sequences of one or more specific vehicle control actions, such as "open windows" and then "play music".
For example, user 1 and user 2, historical customization schemes A and B:
historical customization scenario a: whenever the time "monday to friday" is satisfied, 8: 30 ", the execution instruction is: navigating to the company, opening the vehicle window and playing music. The scheme label for the custom scheme A is "on time to work";
history customization scheme B: whenever the user says: "xiao peng sprint", the execution order is: a vehicle: and in a rapid mode, closing the vehicle window and listening to the broadcast. The scenario label for customized scenario B is "drive with.
The model has a history customization scheme A and basic information of the user 1 according to the user 1: age 30, output user 1 user tags as: the office worker actively works and enjoys double-break;
the model has a history customization scheme B and user 2 basic information according to the user 2: age 25, output user 1 user tags as: the people are loved in life and driving and creative in young.
Obtaining the weight of each feature Token to each output user label according to the model parameters, namely the contribution degree is as follows:
on-time work: navigation to the company: 90%, opening the vehicle window: 15%, music playing: 45 percent;
enjoying driving: a rapid mode: 85%, closing the window: 45%, listening to the broadcast: 5 percent.
Further, the contribution degree of each customization scheme to each user tag is calculated according to the contribution degree of the execution instruction to each user tag.
The weights of all the execution instructions to each user tag can be linearly superposed to obtain the contribution degree of each customization scheme to each user tag. In some embodiments, the weight of each user tag may also be non-linearly superimposed by all the execution instructions, for example, the feature weight is further enhanced according to different feature types, so that the contribution degree of the execution instructions in the feature is highlighted, and a better recommended scheme can be obtained by customizing a personalized scheme for the user.
For example, in the above example, the contribution of the customization scheme A to "on-time work" can be calculated as: 90% +15% +45% =1.5, and the degree of contribution of the customized solution B to "driving enjoyment" is: 85% +45% +5% = 1.35.
In this way, the contribution degree of each customization scheme to each user tag is calculated according to the determined contribution degree of the execution instruction to the user tag. Since the user's personalization tends to be closely related to the combined preference of multiple actions to be performed, rather than just a single action. Compared with other scheme value generation modes, for example, a mode of executing actions controlled by a specific vehicle is utilized, the scheme value is determined by utilizing the contribution degree of the execution instruction to the user tag, the recommended customization scheme can be associated with the execution instruction of the user, so that the scheme value of the customization scheme reflects the personalized customization requirement of the user, the efficiency of generating the recommended customization scheme is improved, the recommended customization scheme is recommended to the user in a more targeted manner, the inheritance rate of the user is improved, and the use experience of the user on the customization function is effectively improved.
Further, determining the scheme value of each customization scheme to the single user according to the sum of the contribution degree of each customization scheme to all user tags of the single user.
And after the user tags of the users are obtained, each user has one or more user tags, the contribution degree of each customization scheme to all the user tags of the users is calculated, and the calculation result is the scheme value of each customization scheme to the user. Wherein the scheme value may characterize a degree of value that the customization scheme recommends to the user. The scheme value can comprise a score value or a character string and the like, and is determined according to the preset strategy of the scheme value.
For example, user 1, through the user classification model, obtains that the user label is not: enjoys driving and goes to work on time.
Customization protocol A: whenever the time "monday to friday" is satisfied, 8: 30 ", the execution instructions are: navigating to the company, opening the vehicle window and playing music. (ii) a
Customizing scheme B: whenever the user says: "xiao peng sprint", the execution order is: vehicle: and in a rapid mode, closing the vehicle window and listening to the broadcast.
The scenario label for the customized scenario A is then "on time to work". The scenario label for customized scenario B is "drive with.
The weight of the execution instruction to each user tag in all customization scenarios is obtained:
on time to work: navigation to the company: 90%, opening the vehicle window: 10%, playing music: 10 percent.
The value of the custom scheme a for the "on-time" user tag is 90% +10% +10% = 1.1.
Enjoying driving: navigation to the company: 10%, opening the window: 10%, playing music: 50 percent. The value of the customized solution a to the "driving enjoyed" user label is then: 10% +10% +50% = 0.7.
Further, the solution value of the customized solution a to the user 1 is: 1.1+0.7 = 1.8.
And after the scheme value of the customization scheme for the user is obtained through calculation, a plurality of alternative customization schemes are obtained according to the scheme value, and the alternative customization schemes are processed to obtain a recommended customization scheme which can be executed by the voice server control vehicle.
Specifically, the ordering may be performed according to the scheme values, all the customization schemes in the database are ordered from high score to low score, the ordered customization schemes are preprocessed by deduplication and the like, and finally, a predetermined number of alternative customization schemes are obtained, for example, the first 100 customization schemes from high score to low score according to the scheme values.
Further, the plurality of alternative customization solutions are processed to obtain a recommended customization solution that can be executed by the voice server control vehicle.
A method for processing a plurality of alternative customization alternatives to a recommended customization alternative executable by a voice server controlled vehicle, comprising:
and carrying out first sequencing processing on the multiple alternative customization schemes according to the scheme values to generate a recommended customization scheme.
The processor is used for carrying out first sequencing processing on the plurality of alternative customization schemes according to the scheme values to generate a recommended customization scheme.
Specifically, after the scheme values of the multiple alternative customization schemes are obtained, a first ordering process is performed on the multiple alternative customization schemes to generate a recommended customization scheme. The first sequencing processing comprises sequencing from high to low according to the value of the scheme value, determining all or a predetermined number of alternative customization schemes as recommended customization schemes according to the sequencing sequence, sending the recommended customization schemes to a user, and displaying the recommended customization schemes on a terminal.
Therefore, the multiple alternative customization schemes are ranked through the scheme values, and the multiple alternative customization schemes which are most matched with the personalized requirements of the user can be obtained and recommended to the user.
The method for processing a plurality of alternative customization solutions to obtain a recommended customization solution executable by a voice server control vehicle further comprises the following steps:
carrying out first sequencing processing on a plurality of alternative customization schemes according to the scheme values to obtain a first alternative customization scheme;
and preprocessing the first alternative customization scheme according to the current customization state of the user to obtain a second alternative customization scheme which is consistent with the current customization state, wherein the preprocessing comprises deduplication, grouping and/or screening processing.
The processor is used for carrying out first sequencing processing on the multiple alternative customization schemes according to the scheme values to obtain a first alternative customization scheme; and preprocessing the first alternative customization scheme according to the current customization state of the user to obtain a second alternative customization scheme which is consistent with the current customization state, wherein the preprocessing comprises deduplication, grouping and/or screening processing.
Specifically, a first ordering process is performed on the multiple alternative customization schemes according to the scheme values to obtain a first alternative customization scheme. The first sequencing processing comprises sequencing from high to low according to the score of the scheme value, determining all or a preset number of the alternative customization schemes as recommended customization schemes according to the sequencing sequence, sending the recommended customization schemes to the user, and displaying the recommended customization schemes on the terminal.
And after the first alternative customization scheme is obtained, preprocessing the first alternative customization scheme according to the current customization state of the user to obtain a second alternative customization scheme which is consistent with the current customization state, wherein the preprocessing comprises duplicate removal, grouping and/or screening.
The current customization state of the user comprises the current customization time, the customized current environment information and other states. For example, the first 100 alternative customization solutions obtained after the first ordering process are subjected to deduplication processing, meanwhile, grouping and screening are performed according to customization time, and 50 customization solutions that match the current customization state of the user are prioritized and determined as the second alternative customization solutions.
A method for processing a plurality of alternative customization solutions to obtain a recommended customization solution executable by a voice server controlled vehicle, further comprising:
and performing second sorting processing on the second alternative customization schemes according to the current customization state, and determining a recommended customization scheme according to the plurality of second alternative customization schemes subjected to the second sorting processing.
The processor is used for carrying out second sorting processing on the second alternative customization scheme according to the current customization state, and determining the recommended customization scheme according to the plurality of alternative customization schemes after the second sorting processing.
Specifically, after a plurality of second alternative customization solutions are obtained, further, second ordering processing is performed on the second alternative customization solutions according to the current customization state, and a recommended customization solution is determined according to the plurality of alternative customization solutions after the second ordering processing. For example, the most recent customization scheme is ranked ahead to rank the second alternative customization scheme by the most recent time of the customization time.
Therefore, by further carrying out preprocessing such as duplicate removal, grouping and/or screening processing and the like according to the current customization state after the first sequencing processing, the recommendation of the customization scheme can be combined with external conditions such as customization time and the like, and the accuracy of the recommendation is improved.
Referring to fig. 2, the processing method further includes:
07: obtaining the customized information and the vehicle information of each user;
08: classifying all the customization schemes of each user according to the customization information of each user and/or a plurality of customization scheme labels to obtain the customization frequency of each customization scheme;
09: and according to the classification result, determining the customization information, the vehicle information, the customization frequency and all customization schemes of each user as the private customization data of each user and storing the data.
The processor is used for acquiring the customized information and the vehicle information of each user; classifying all the customization schemes of each user according to the customization information of each user and/or a plurality of customization scheme labels to obtain the customization frequency of each customization scheme; and according to the classification result, determining the customization information, the vehicle information, the customization frequency and all customization schemes of each user as the private customization data of each user and storing the data.
And obtaining the customized information and the vehicle information of each user. The customized information of the user may include the time of customization, the information of the external environment such as the weather temperature during customization, the city or location during customization, and the personal basic information of the user. The vehicle information includes a vehicle state.
All customization solutions for each user are categorized according to the customization information for each user, and/or a plurality of customization solution tags. Wherein the classification process comprises a multi-stage classification process. For example, the first-level classification is performed according to the customized scheme label, then the second-level classification is performed according to the customized time, and then the historical customized scheme is subjected to grouping statistics to count the number of customizations in each group as the frequency of the occurrence of the historical customized scheme, so as to obtain the historical customized frequency.
And determining the customization information, the vehicle information, the customization frequency and all customization schemes of each user as the private customization data of the user according to the classification result, and storing the data to form the recommendation data of the private customization of the user. And then, the applicable recommendation customization scheme can be dynamically recommended to the user in real time according to the recommendation data.
Therefore, the training data, the output data and the model parameters can be stored, the historical customization frequency can be obtained through processing, and meanwhile, the historical customization frequency and the user information are stored, so that the method can be used for subsequently generating the recommended customization scheme in real time and returning the recommended customization scheme to the user without any operation of the user in the real-time recommendation of the personalized customization scheme of the user.
And after the recommended customization scheme is determined, sending the recommended customization scheme to the terminal corresponding to the request so as to display the recommended customization scheme on the terminal.
The request comprises a request for customizing the functions of the vehicle-mounted system, which is initiated by a user through a terminal. For example, a user can open a customized APP through a customized APP installed on a mobile phone and enter a customized page. The request can be initiated when the user enters the customized page, or can be initiated when the user clicks the 'recommend' operation button through the 'recommend' operation button displayed on the customized page. After receiving the request, obtaining a recommended customization scheme according to any one of the processing methods, sending the recommended customization scheme to a terminal corresponding to the request, and displaying the recommended customization scheme on the terminal, wherein the user can select or edit the displayed recommended customization scheme so as to determine the required customization scheme.
Therefore, the method and the system have the advantages that the customization scheme for customizing the functions of the vehicle-mounted system is achieved through the vehicle user uploaded by the receiving terminal; acquiring a plurality of user tags of a user according to a customization scheme; obtaining the contribution degree of each customization scheme to each user label by using all customization schemes uploaded by all terminals; determining a scheme value of each customization scheme to a single user according to the sum of contribution degrees of each customization scheme to all user tags of the single user; obtaining a plurality of alternative customization schemes according to the scheme value, and processing the plurality of alternative customization schemes to obtain a recommended customization scheme which can be executed by a voice server control vehicle; and sending the recommended customization scheme to the terminal corresponding to the request so as to display the recommended customization scheme on the terminal. The method and the system can recommend the recommended customization scheme to the user more pertinently aiming at different users, and recommend a personalized customization scheme with strong pertinence and practicability to the user, so that the user obtains more free and personalized vehicle control feeling, the inheritance rate of the user is improved, and the use feeling of the user on the customization function is effectively improved.
The present application also provides a computer-readable storage medium. One or more non-transitory computer-readable storage media storing a computer program that, when executed by one or more processors, performs the method of any of the embodiments described above. It will be understood by those skilled in the art that all or part of the processes in the method for implementing the above embodiments may be implemented by a computer program instructing relevant software. The program may be stored in a non-volatile computer readable storage medium, which when executed, may include the flows of embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), or the like.
In the description of the present specification, reference to the description of "one embodiment", "some embodiments", "illustrative embodiments", "examples", "specific examples" or "some examples" or the like means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present application. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction. Meanwhile, the description referring to the terms "first", "second", and the like is intended to distinguish the same kind or similar operations, and "first" and "second" have a logical context in some embodiments, and do not necessarily have a logical context in some embodiments, and need to be determined according to actual embodiments, and should not be determined only by a literal meaning.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and the scope of the preferred embodiments of the present application includes other implementations in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present application.
Although embodiments of the present application have been shown and described above, it is to be understood that the above embodiments are exemplary and not to be construed as limiting the present application, and that changes, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present application.
Claims (10)
1. A processing method for functions of a vehicle-mounted system is characterized by comprising the following steps:
receiving a customization scheme which is uploaded by a terminal and used for customizing the functions of the vehicle-mounted system by a vehicle user;
acquiring a plurality of user tags of a user according to a customization scheme;
obtaining the contribution degree of each customization scheme to each user label by using all customization schemes uploaded by all terminals;
determining a scheme value of each customization scheme to a single user according to the sum of contribution degrees of each customization scheme to all user tags of the single user;
obtaining a plurality of alternative customization schemes according to the scheme value, and processing the alternative customization schemes to obtain a recommended customization scheme which can be executed by a voice server control vehicle;
and sending the recommended customization scheme to a terminal corresponding to the request so as to display the recommended customization scheme on the terminal.
2. The process of claim 1, wherein said obtaining a plurality of user tags for a user according to a customization scheme comprises:
classifying the customization schemes uploaded by the terminal to obtain a plurality of customization scheme labels;
acquiring user information of the user, wherein the user information comprises user basic information, vehicle information, user driving habit information and user driving behavior information;
and inputting the plurality of customized scheme labels and the user information into a user classification model to obtain a plurality of user labels of each user.
3. The process of claim 2, wherein said entering said plurality of customization scheme labels and said user information into a user classification model, resulting in a plurality of user labels for each user comprises:
performing feature extraction on the plurality of customized scheme labels and the user information of the user to obtain customized features of the user;
inputting the customized characteristics of each user into the user classification model to obtain label probability values of a plurality of user labels corresponding to each user;
and processing the label probability value according to a preset threshold value to obtain a plurality of user labels of each user.
4. The processing method according to claim 3, wherein the customization schemes include execution instructions, and wherein the obtaining the contribution degree of each customization scheme to each user tag by using all customization schemes uploaded by all terminals comprises:
determining the contribution degree of an execution instruction to the user label according to the model parameters of the user classification model;
and calculating the contribution degree of each customization scheme to each user tag according to the contribution degree of the execution instruction to each user tag.
5. The processing method of claim 4, further comprising:
obtaining the customized information and the vehicle information of each user;
classifying all the customization schemes of each user according to the customization information of each user and/or the multiple customization scheme labels to obtain the customization frequency of each customization scheme;
and determining the customization information, the vehicle information, the customization frequency and all customization schemes of each user as the private customization data of each user according to the classification processing result and storing the private customization data.
6. The processing method of claim 1, wherein obtaining a plurality of alternative customization solutions according to the solution value and processing the plurality of alternative customization solutions to obtain a recommended customization solution executable by a voice server controlled vehicle comprises:
and performing first sequencing processing on the plurality of alternative customization schemes according to the scheme values to generate the recommended customization scheme.
7. The processing method of claim 6, wherein obtaining a plurality of alternative customization solutions according to the solution value and processing the plurality of alternative customization solutions to obtain a recommended customization solution executable by a voice server controlled vehicle further comprises:
performing first sequencing processing on the multiple alternative customization schemes according to the scheme values to obtain a first alternative customization scheme;
and preprocessing the first alternative customization scheme according to the current customization state of the user to obtain a second alternative customization scheme which is consistent with the current customization state, wherein the preprocessing comprises deduplication, grouping and/or screening processing.
8. The processing method of claim 7, wherein obtaining a plurality of alternative customization solutions according to the solution value and processing the plurality of alternative customization solutions to obtain a recommended customization solution executable by a voice server controlled vehicle further comprises:
and performing second sorting processing on the second alternative customization schemes according to the current customization state, and determining the recommended customization scheme according to the plurality of second alternative customization schemes subjected to the second sorting processing.
9. An on-board system-enabled server, characterized in that the server comprises a memory and a processor, the memory having stored therein a computer program, which, when executed by the processor, carries out the method according to any one of claims 1-8.
10. A non-transitory computer-readable storage medium of a computer program, wherein the computer program, when executed by one or more processors, implements the method of any one of claims 1-8.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210024105.5A CN114056343B (en) | 2022-01-11 | 2022-01-11 | Processing method of vehicle-mounted system function, server and storage medium |
| PCT/CN2022/138934 WO2023134380A1 (en) | 2022-01-11 | 2022-12-14 | Interaction method, server, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210024105.5A CN114056343B (en) | 2022-01-11 | 2022-01-11 | Processing method of vehicle-mounted system function, server and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114056343A CN114056343A (en) | 2022-02-18 |
| CN114056343B true CN114056343B (en) | 2022-05-10 |
Family
ID=80230714
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210024105.5A Active CN114056343B (en) | 2022-01-11 | 2022-01-11 | Processing method of vehicle-mounted system function, server and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN114056343B (en) |
| WO (1) | WO2023134380A1 (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114056343B (en) * | 2022-01-11 | 2022-05-10 | 广州小鹏汽车科技有限公司 | Processing method of vehicle-mounted system function, server and storage medium |
| CN117575548B (en) * | 2024-01-17 | 2024-03-22 | 华安证券股份有限公司 | Service scheme intelligent generation method and system based on business requirements |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106790938A (en) * | 2016-11-16 | 2017-05-31 | 上海趣讯网络科技有限公司 | A kind of man-machine interaction onboard system based on artificial intelligence |
| CN109710055A (en) * | 2017-12-15 | 2019-05-03 | 蔚来汽车有限公司 | The interaction control method of vehicle intelligent interactive system and vehicle-mounted interactive terminal |
| CN109910816A (en) * | 2019-03-11 | 2019-06-21 | 广州小鹏汽车科技有限公司 | A kind of automobile individual cultivation method, system and automobile |
| CN110103865A (en) * | 2019-04-17 | 2019-08-09 | 浙江合众新能源汽车有限公司 | The vehicle-mounted individual cultivation application system of driver based on recognition of face |
| CN111591236A (en) * | 2019-02-21 | 2020-08-28 | 广州汽车集团股份有限公司 | Personalized configuration system for vehicle |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11010261B2 (en) * | 2017-03-31 | 2021-05-18 | Commvault Systems, Inc. | Dynamically allocating streams during restoration of data |
| CN112559852A (en) * | 2019-09-10 | 2021-03-26 | 北京搜狗科技发展有限公司 | Information recommendation method and device |
| CN114056343B (en) * | 2022-01-11 | 2022-05-10 | 广州小鹏汽车科技有限公司 | Processing method of vehicle-mounted system function, server and storage medium |
-
2022
- 2022-01-11 CN CN202210024105.5A patent/CN114056343B/en active Active
- 2022-12-14 WO PCT/CN2022/138934 patent/WO2023134380A1/en unknown
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106790938A (en) * | 2016-11-16 | 2017-05-31 | 上海趣讯网络科技有限公司 | A kind of man-machine interaction onboard system based on artificial intelligence |
| CN109710055A (en) * | 2017-12-15 | 2019-05-03 | 蔚来汽车有限公司 | The interaction control method of vehicle intelligent interactive system and vehicle-mounted interactive terminal |
| CN111591236A (en) * | 2019-02-21 | 2020-08-28 | 广州汽车集团股份有限公司 | Personalized configuration system for vehicle |
| CN109910816A (en) * | 2019-03-11 | 2019-06-21 | 广州小鹏汽车科技有限公司 | A kind of automobile individual cultivation method, system and automobile |
| CN110103865A (en) * | 2019-04-17 | 2019-08-09 | 浙江合众新能源汽车有限公司 | The vehicle-mounted individual cultivation application system of driver based on recognition of face |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2023134380A1 (en) | 2023-07-20 |
| CN114056343A (en) | 2022-02-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114056343B (en) | Processing method of vehicle-mounted system function, server and storage medium | |
| CN107797984B (en) | Intelligent interaction method, equipment and storage medium | |
| CN110364146B (en) | Speech recognition method, speech recognition device, speech recognition apparatus, and storage medium | |
| CN109885713A (en) | Facial expression image recommended method and device based on voice mood identification | |
| EP3705990A1 (en) | Method and system for providing interactive interface | |
| CN107463701B (en) | Method and device for pushing information stream based on artificial intelligence | |
| CN106649780A (en) | Information providing method and device based on artificial intelligence | |
| CN107256428B (en) | Data processing method, data processing device, storage equipment and network equipment | |
| US20090193344A1 (en) | Community mood representation | |
| CN106407178A (en) | Session abstract generation method and device | |
| CN110956956A (en) | Voice recognition method and device based on policy rules | |
| CN109275047A (en) | Video information processing method and device, electronic equipment, storage medium | |
| CN108922540B (en) | Method and system for carrying out continuous AI (Artificial Intelligence) conversation with old people user | |
| KR102572701B1 (en) | Electronic device for providing response message to user based on user's status information and method for operating the same | |
| US20220148576A1 (en) | Electronic device and control method | |
| CN111145721A (en) | Personalized prompt language generation method, device and equipment | |
| KR20180097117A (en) | Electronic apparatus, document displaying method of thereof and non-transitory computer readable recording medium | |
| KR102628042B1 (en) | Device and method for recommeding contact information | |
| CN109325223A (en) | Article recommended method, device and electronic equipment | |
| CN112541120B (en) | Recommendation comment generation method, device, equipment and medium | |
| KR20160029895A (en) | Apparatus and method for recommending emotion-based character | |
| CN112910754A (en) | Message processing method, device, equipment and storage medium based on group session | |
| CN113746875A (en) | Voice packet recommendation method, device, equipment and storage medium | |
| CN108320208A (en) | Vehicle recommends method and device | |
| CN107894882A (en) | A kind of pronunciation inputting method of mobile terminal |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |