# US 2019/0378035 A1 · Method, apparatus, device and medium for classifying driving scenario data > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2019/0378035 A1 - Document ID: US20190378035A1 - Status: Published application - Kind: A1 - Application number: 16/353,878 - Filed: 2019-03-14 - Published: 2019-12-12 - Earliest claimed: 2018-06-11 - Assignees: Baidu Online Network Technology (Beijing) Co., Ltd. - Applicants: Baidu Online Network Technology (Beijing) Co., Ltd. - Inventors: Junfei ZHANG; Chen YANG; Qingrui SUN; Jiming MAO; Fangfang DONG - Web page: https://patentgrep.com/patent/US20190378035A1 ## CPC - G06V 20/56: exterior to a vehicle by using sensors mounted on the vehicle - B60W 30/18163: {Lane change; Overtaking manoeuvres} - G06F 16/285: {Clustering or classification} - G06F 18/40: Software arrangements specially adapted for pattern recognition, e.g. user interfaces or toolboxes therefor - G06F 30/20: Design optimisation, verification or simulation (optimisation, verification or simulation of circuit designs G06F30/30) - G06N 5/046: Forward inferencing; Production systems - G06N 20/00: Machine learning - G06V 10/945: {User interactive design; Environments; Toolboxes} - B60W 2554/4049: Relationship among other objects, e.g. converging dynamic objects - B60W 2555/20: Ambient conditions, e.g. wind or rain - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - 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 - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract Embodiments of a method, apparatus, device and computer readable storage medium for classifying driving scenario data includes: acquiring a first driving scenario data set from a crowdsourcing platform, driving scenario data in the first driving scenario data set having been classified; generating a driving scenario classification model at least based on the first driving scenario data set, for classifying driving scenario data collected by a collection entity; acquiring a rule for classifying the driving scenario data, the rule is generated based on a result of classifying the driving scenario data collected by the collection entity using the driving scenario classification model; updating the driving scenario classification model at least based on the rule. ## Claims ### Claim 1 A method for determining a driving scenario classification model, comprising: acquiring a first driving scenario data set from a crowdsourcing platform, driving scenario data in the first driving scenario data set having been classified; generating a driving scenario classification model at least based on the first driving scenario data set, for classifying driving scenario data collected by a collection entity; acquiring a rule for classifying driving scenario data, the rule being generated based on a result of classifying the driving scenario data collected by the collection entity using the driving scenario classification model; and updating the driving scenario classification model at least based on the rule. ### Claim 2 (depends on 1) The method according to claim 1, wherein the driving scenario data in the first driving scenario data set is classified into at least one of: a first category related to a geographic element, a second category related to a traffic signal, or a third category related to a driving behavior. ### Claim 3 (depends on 1) The method according to claim 1, wherein the driving scenario data collected by the collection entity comprises at least one of: information related to a road, information related to a traffic signal, information related to a behavior of the collection entity, or information collected by a sensor installed on the collection entity. ### Claim 4 (depends on 1) The method according to claim 1, wherein the generating a driving scenario classification model comprises: determining a first target function for training the driving scenario classification model; and training the driving scenario classification model using a machine learning method based on the first target function and the first driving scenario data set. ### Claim 5 (depends on 4) The method according to claim 4, wherein the updating the driving scenario classification model comprises: acquiring a second driving scenario data set from the crowdsourcing platform, driving scenario data in the second driving scenario data set having been classified; determining, based on the first target function and the rule, a second target function for training the driving scenario classification model; and updating, based on the second target function and the second driving scenario data set, the driving scenario classification model using the machine learning method, wherein the driving scenario data in the second driving scenario data set is classified at the crowdsourcing platform at least based on the rule. ### Claim 6 A method for classifying driving scenario data, comprising: acquiring first driving scenario data collected by a collection entity; classifying the first driving scenario data using a driving scenario classification model, the driving scenario classification model being generated based on a first driving scenario data set from a crowdsourcing platform; and providing a result of classifying the first driving scenario data for a user, to cause the user to generate a rule for classifying driving scenario data based on the result, the rule being at least used to update the driving scenario classification model. ### Claim 7 (depends on 6) The method according to claim 6, wherein the first driving scenario data comprises at least one of: information related to a road, information related to a traffic signal, information related to a behavior of the collection entity, or information collected by a sensor installed on the collection entity. ### Claim 8 (depends on 6) The method according to claim 6, wherein driving scenario data in the driving scenario data set is classified into at least one of: a first category related to a geographic element, a second category related to a traffic signal, or a third category related to a driving behavior. ### Claim 9 (depends on 6) The method according to claim 6, further comprising: acquiring second driving scenario data collected by the collection entity; and classifying the second driving scenario data using the driving scenario classification model updated at least based on the rule. ### Claim 10 (depends on 9) The method according to claim 9, wherein the driving scenario classification model is updated based on a second driving scenario data set from the crowdsourcing platform and the rule, wherein driving scenario data in the second driving scenario data set is classified at the crowdsourcing platform at least based on the rule. ### Claim 11 (depends on 9) The method according to claim 9, wherein at least one of the classified first driving scenario data or the second classified driving scenario data is used to train a conveyance. ### Claim 12 An apparatus for determining a driving scenario classification model, comprising: at least one processor; and a memory storing instructions, the instructions when executed by the at least one processor, cause the at least one processor to perform operations, the operations comprising: acquiring a first driving scenario data set from a crowdsourcing platform, driving scenario data in the first driving scenario data set having been classified; generating a driving scenario classification model at least based on the first driving scenario data set, for classifying driving scenario data collected by a collection entity; acquiring a rule for classifying driving scenario data, the rule being generated based on a result of classifying the driving scenario data collected by the collection entity using the driving scenario classification model; and updating the driving scenario classification model at least based on the rule. ### Claim 13 (depends on 12) The apparatus according to claim 12, wherein the driving scenario data in the first driving scenario data set is classified into at least one of: a first category related to a geographic element, a second category related to a traffic signal, or a third category related to a driving behavior. ### Claim 14 (depends on 12) The apparatus according to claim 12, wherein the driving scenario data collected by the collection entity comprises at least one of: information related to a road, information related to a traffic signal, information related to a behavior of the collection entity, or information collected by a sensor installed on the collection entity. ### Claim 15 (depends on 12) The apparatus according to claim 12, wherein the generating a driving scenario classification model comprises: determining a first target function for training the driving scenario classification model; and training the driving scenario classification model using a machine learning method based on the first target function and the first driving scenario data set. ### Claim 16 (depends on 15) The apparatus according to claim 15, wherein the updating the driving scenario classification model comprises: acquiring a second driving scenario data set from the crowdsourcing platform, driving scenario data in the second driving scenario data set having been classified; determining, based on the first target function and the rule, a second target function for training the driving scenario classification model; and updating, based on the second target function and the second driving scenario data set, the driving scenario classification model using the machine learning method, wherein the driving scenario data in the second driving scenario data set is classified at the crowdsourcing platform at least based on the rule. ### Claim 17 (depends on 6) An apparatus for classifying driving scenario data, comprising: at least one processor; and a memory storing instructions, the instructions when executed by the at least one processor, cause the at least one processor to perform the method of claim 6. ### Claim 18 (depends on 17) The apparatus according to claim 17, wherein the first driving scenario data comprises at least one of: information related to a road, information related to a traffic signal, information related to a behavior of the collection entity, or information collected by a sensor installed on the collection entity. ### Claim 19 (depends on 17) The apparatus according to claim 17, wherein driving scenario data in the driving scenario data set is classified into at least one of: a first category related to a geographic element, a second category related to a traffic signal, or a third category related to a driving behavior. ### Claim 20 (depends on 17) The apparatus according to claim 17, further comprising: acquiring second driving scenario data collected by the collection entity; and classifying the second driving scenario data using the driving scenario classification model updated at least based on the rule. ### Claim 21 (depends on 20) The apparatus according to claim 20, wherein the driving scenario classification model is updated based on a second driving scenario data set from the crowdsourcing platform and the rule, wherein driving scenario data in the second driving scenario data set is classified at the crowdsourcing platform at least based on the rule. ### Claim 22 (depends on 20) The apparatus according to claim 20, wherein at least one of the classified first driving scenario data or the classified second driving scenario data is used to train a conveyance. ### Claim 23 (depends on 1) A computer readable storage medium, storing a computer program, wherein the computer program, when executed by a processor, implements the method according to claim 1. ### Claim 24 (depends on 6) A computer readable storage medium, storing a computer program, wherein the computer program, when executed by a processor, implements the method according to claim 6.