An information processing method and device, electronic equipment and storage medium

Abstract

Embodiments of the present application provide an information processing method and device, electronic equipment and storage medium. The method comprises: obtaining reference information of a plurality of users, wherein the reference information comprises behavior information, driving information and feedback information of the same user, the behavior information comprises behavior information of a user in a terminal device associated with a vehicle, the driving information comprises driving information when the vehicle logs in a user account, and the feedback information comprises user feedback information on the use of the vehicle; and according to the reference information, a software update package of an automatic driving system of the vehicle is pushed to the plurality of users. Therefore, one embodiment of the present application can generate a software update package of an automatic driving system of a vehicle from multiple data dimensions and push it to the user, so that the driving control strategy of the automatic driving system is more in line with the actual needs of the user, thereby improving the user's automatic driving experience and shortening the user's adaptation period to the automatic driving function.

Description

Technical Field

[0001] This invention relates to the field of communication technology, and in particular to an information processing method, apparatus, electronic device, and storage medium. Background Technology

[0002] With the development of autonomous driving technology, users are becoming increasingly free from driving tasks. However, the level of user awareness and trust in autonomous driving lags far behind the development speed of autonomous driving products, resulting in a general situation where the actual user experience is poor and does not meet user expectations.

[0003] To increase users' willingness to purchase and usage rates of autonomous driving features, OEMs and supply chain technology solution providers have made numerous attempts to personalize autonomous driving functions and adapt to user styles, striving to shorten the adaptation and trust-building period for these functions. For example, one current approach involves designing and delivering an information alert mechanism centered on 'audio-visual information', based on the visual interfaces of the in-vehicle instrument panel and central control screen, as well as the in-vehicle audio-visual system, and according to the hazard levels and vehicle intentions required for different autonomous driving scenarios.

[0004] However, in the process of realizing this invention, the inventors discovered that although the above-mentioned simple reminder mechanism can improve the clarity and timeliness of information transmission when users use the autonomous driving function, different users may have different driving needs, and this simple reminder mechanism often cannot meet the needs of different users for autonomous driving control strategies. Summary of the Invention

[0005] The purpose of this invention is to provide an information processing method, apparatus, electronic device, and storage medium to solve the problem that the existing technology cannot meet the needs of different users for different autonomous driving control strategies.

[0006] On the one hand, an information processing method is provided, the method comprising:

[0007] The system obtains reference information from multiple users, including behavioral information, driving information, and feedback information belonging to the same user. The behavioral information includes user behavior information in terminal devices associated with the vehicle, the driving information includes driving information when the vehicle is logged into the user's account, and the feedback information includes user feedback information on vehicle usage.

[0008] Based on the reference information, software update packages for the vehicle's autonomous driving system are pushed to the multiple users.

[0009] In one possible implementation, pushing the software update package for the vehicle's autonomous driving system to the plurality of users based on the reference information includes:

[0010] For each user's reference information, obtain a first tag for the behavior information, a second tag for the driving information, and a third tag for the feedback information;

[0011] The first tag, second tag, and third tag of the same user are classified to obtain the target identification information of the tag category for each user.

[0012] Based on the target identification information of the multiple users, push the software update package of the vehicle's autonomous driving system to the multiple users.

[0013] In one possible implementation, the behavior information, the driving information, and the feedback information each include multiple data entries; obtaining the first tag of the behavior information, the second tag of the driving information, and the third tag of the feedback information includes:

[0014] Obtain the first matching rule that each piece of data in the behavior information conforms to, and determine the first tag corresponding to the first matching rule according to the first correspondence relationship, wherein the first correspondence relationship is the correspondence relationship between the tag and the matching rule;

[0015] Obtain the second matching rule that each piece of data in the driving information conforms to, and determine the second tag corresponding to the second matching rule based on the first correspondence relationship;

[0016] Obtain the third matching rule that each piece of data in the feedback information conforms to, and determine the third tag corresponding to the third matching rule based on the first correspondence.

[0017] In one possible implementation, the classification process for the first tag, second tag, and third tag of the same user to obtain target identification information for each user's tag category includes:

[0018] Using semantic analysis and machine learning algorithms, the first tag, second tag, and third tag of the same user are classified to obtain the target identifier information of the tag category for each user.

[0019] In one possible implementation, the step of pushing the software update package of the vehicle's autonomous driving system to the multiple users based on the target identification information of the multiple users includes:

[0020] From the target identification information of the multiple users, target identification information with a first parameter greater than a preset threshold is selected, wherein the first parameter is the ratio of the number of the same target identification information to the total number of target identification information of the multiple users;

[0021] Based on the second correspondence, a first target driving control strategy is determined for each target identification information whose first parameter is greater than a preset threshold. The second correspondence is the correspondence between the identification information of the label category and the driving control strategy.

[0022] Based on each of the first target driving control strategies, a first software update package for the vehicle's autonomous driving system is generated.

[0023] The first software update package is pushed to the multiple users.

[0024] In one possible implementation, the step of pushing the software update package of the vehicle's autonomous driving system to the multiple users based on the target identification information of the multiple users includes:

[0025] Based on the second correspondence, a second target driving control strategy corresponding to each of the target identification information is determined, wherein the second correspondence is the correspondence between the identification information of the tag category and the driving control strategy;

[0026] Based on each of the second target driving control strategies, a second software update package for the vehicle's autonomous driving system is generated as the second software update package for the user corresponding to the target identification information.

[0027] The second software update package is pushed to the user corresponding to the second software update package.

[0028] In one possible implementation, the behavior information, the driving information, and the feedback information each include multiple data entries, with each data entry corresponding to a tag; the method further includes:

[0029] For the data content corresponding to the tags under the same category represented by the target identification information, perform artificial intelligence (AI) semantic understanding to obtain AI description information of the target identification information;

[0030] Obtain search keywords;

[0031] Obtain the target identifier information that matches the search keywords;

[0032] The AI ​​description information displays the target identifier information that matches the search keywords.

[0033] In one possible implementation, the behavior information, the driving information, and the feedback information each include multiple data entries, with each data entry corresponding to a tag; the method further includes:

[0034] Based on the target data end of the data content corresponding to the tag under the same category represented by the target identification information, determine the data end information of the target identification information;

[0035] Obtain search keywords;

[0036] Obtain the target identifier information that matches the search keywords;

[0037] The data terminal information displays the target identifier information that matches the search keywords.

[0038] In one possible implementation, determining the data endpoint information of the target identifier information based on the data endpoint of the data content corresponding to the tag under the same category represented by the target identifier information includes:

[0039] Based on the predetermined weights of different data terminals, the information of the data terminal with the largest weight value among the target data terminals is determined as the data terminal information of the target identification information;

[0040] or,

[0041] The information of the data terminal with the largest second parameter among the target data terminals is determined as the data terminal information of the target identification information, wherein the second parameter is the ratio of the number of the same target data terminal to the total number of all target data terminals.

[0042] On the other hand, an information processing apparatus is provided, the apparatus comprising:

[0043] The information acquisition module is used to acquire reference information from multiple users. The reference information includes behavioral information, driving information, and feedback information belonging to the same user. The behavioral information includes the user's behavioral information in the terminal device associated with the vehicle. The driving information includes the driving information when the vehicle is logged into the user's account. The feedback information includes the user's feedback information on the use of the vehicle.

[0044] The push module is used to push software update packages for the vehicle's autonomous driving system to the multiple users based on the reference information.

[0045] In one possible implementation, the push module includes:

[0046] The tag determination submodule is used to obtain, for each user's reference information, a first tag for the behavior information, a second tag for the driving information, and a third tag for the feedback information;

[0047] The classification processing submodule is used to classify the first tag, the second tag, and the third tag of the same user to obtain the target identification information of the tag category for each user.

[0048] The push module is used to push the software update package of the vehicle's autonomous driving system to the multiple users based on the target identification information of the multiple users.

[0049] In one possible implementation, the behavior information, the driving information, and the feedback information each include multiple data entries; the tag determination submodule is specifically used for:

[0050] Obtain the first matching rule that each piece of data in the behavior information conforms to, and determine the first tag corresponding to the first matching rule according to the first correspondence relationship, wherein the first correspondence relationship is the correspondence relationship between the tag and the matching rule;

[0051] Obtain the second matching rule that each piece of data in the driving information conforms to, and determine the second tag corresponding to the second matching rule based on the first correspondence relationship;

[0052] Obtain the third matching rule that each piece of data in the feedback information conforms to, and determine the third tag corresponding to the third matching rule based on the first correspondence.

[0053] In one possible implementation, the classification processing submodule is specifically used for:

[0054] Using semantic analysis and machine learning algorithms, the first tag, second tag, and third tag of the same user are classified to obtain the target identifier information of the tag category for each user.

[0055] In one possible implementation, the push submodule is specifically used for:

[0056] From the target identification information of the plurality of users, target identification information with a first parameter greater than a preset threshold is selected, wherein the first parameter is the ratio of the number of the same target identification information to the total number of target identification information of the plurality of users;

[0057] Based on the second correspondence, a first target driving control strategy is determined for each target identification information whose first parameter is greater than a preset threshold. The second correspondence is the correspondence between the identification information of the label category and the driving control strategy.

[0058] Based on each of the first target driving control strategies, a first software update package for the vehicle's autonomous driving system is generated.

[0059] The first software update package is pushed to the multiple users.

[0060] In one possible implementation, the push submodule is specifically used for:

[0061] Based on the second correspondence, a second target driving control strategy corresponding to each of the target identification information is determined, wherein the second correspondence is the correspondence between the identification information of the tag category and the driving control strategy;

[0062] Based on each of the second target driving control strategies, a second software update package for the vehicle's autonomous driving system is generated as the second software update package for the user corresponding to the target identification information.

[0063] The second software update package is pushed to the user corresponding to the second software update package.

[0064] In one possible implementation, the behavior information, the driving information, and the feedback information each include multiple data entries, with each data entry corresponding to a tag; the device further includes:

[0065] The AI ​​understanding module is used to perform artificial intelligence (AI) semantic understanding on the data content corresponding to the tags under the same category represented by the target identification information, and obtain the AI ​​description information of the target identification information;

[0066] The search term acquisition module is used to acquire search keywords;

[0067] A matching module is used to obtain the target identification information that matches the search keyword;

[0068] The first display module is used to display the AI ​​description information of the target identification information that matches the search keyword.

[0069] In one possible implementation, the behavior information, the driving information, and the feedback information each include multiple data entries, with each data entry corresponding to a tag; the device further includes:

[0070] The data end determination module is used to determine the data end information of the target identification information based on the target data end of the data content corresponding to the tag under the same category represented by the target identification information;

[0071] The search term acquisition module is used to acquire search keywords;

[0072] A matching module is used to obtain the target identification information that matches the search keyword;

[0073] The second display module is used to display the data terminal information of the target identification information that matches the search keyword.

[0074] In one possible implementation, the data terminal determination module is specifically used for:

[0075] Based on the predetermined weights of different data terminals, the information of the data terminal with the largest weight value among the target data terminals is determined as the data terminal information of the target identification information;

[0076] or,

[0077] The information of the data terminal with the largest second parameter among the target data terminals is determined as the data terminal information of the target identification information, wherein the second parameter is the ratio of the number of the same target data terminal to the total number of all target data terminals.

[0078] On the other hand, an electronic device is provided, comprising:

[0079] processor;

[0080] Memory used to store the processor's executable instructions;

[0081] The processor is configured to perform operations to implement the information processing method described above.

[0082] In another aspect, a processor-readable storage medium is provided, the processor-readable storage medium storing a computer program for causing the processor to perform the information processing method described above.

[0083] One of the above technical solutions has the following advantages or beneficial effects:

[0084] In one embodiment of the present invention, reference information of multiple users can be obtained, and software update packages for the vehicle's autonomous driving system can be pushed to multiple users based on the reference information. The reference information includes behavior information, driving information, and feedback information belonging to the same user. The behavior information includes user behavior information in a terminal device associated with the vehicle. The driving information includes driving information when the vehicle logs into a user account. The feedback information includes user feedback information on vehicle usage.

[0085] Therefore, in one embodiment of the present invention, software update packages for the vehicle's autonomous driving system can be pushed to multiple users based on user behavior information in the terminal devices associated with the vehicle, driving information when the vehicle logs into the user's account, and user feedback information on vehicle usage. That is, in one embodiment of the present invention, software update packages for the vehicle's autonomous driving system can be generated from the aforementioned multiple data dimensions and pushed to users, thereby making the driving control strategy of the autonomous driving system more in line with the actual needs of users, thus improving the user's autonomous driving experience and shortening the user's adaptation period for the autonomous driving function.

[0086] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit the invention. Attached Figure Description

[0087] The accompanying drawings, which are incorporated in and form part of this specification, illustrate one embodiment of the invention and, together with the description, serve to explain the principles of the invention.

[0088] Figure 1 This is a flowchart illustrating an information processing method according to an exemplary embodiment;

[0089] Figure 2 This is a block diagram illustrating an information processing apparatus according to an exemplary embodiment;

[0090] Figure 3 This is a block diagram illustrating an electronic device according to an exemplary embodiment. Detailed Implementation

[0091] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of apparatuses and methods consistent with some aspects of the invention as detailed in the appended claims.

[0092] Figure 1 This is a flowchart illustrating an information processing method according to an exemplary embodiment, which can be applied to a server, such as... Figure 1 As shown, the method may include the following steps 101 to 102:

[0093] Step 101: Obtain reference information from multiple users.

[0094] The reference information includes behavioral information, driving information, and feedback information belonging to the same user. The behavioral information includes the user's behavioral information in the terminal device associated with the vehicle. The driving information includes the driving information when the vehicle is logged into the user's account. The feedback information includes the user's feedback information on the use of the vehicle.

[0095] In addition, the user behavior information in the aforementioned vehicle-related terminal devices may include behavior information from multiple applications (APPs) installed on the vehicle-related terminal devices (such as system-level APPs, travel APPs, social APPs, and vehicle control APPs). For example, the frequency of remote vehicle control via APP (including sending destination addresses, remotely starting the vehicle, turning on the air conditioning, etc. via APP), search records in the navigation APP's search box, trip start and end point information, trip distance / duration information, route selection preference information, call records in each trip (including the number of calls, the duration of each call, and whether Bluetooth devices are connected), the frequency of mobile devices being actively activated by the user during driving, the usage frequency of instant messaging APPs during vehicle driving, and the usage frequency of other non-vehicle-owned APPs.

[0096] In one embodiment of the present invention, data authorization from the terminal device can be obtained, and a script can be pre-embedded in the APP installed on the terminal device, so that the script is run at certain time intervals to obtain the aforementioned behavioral information in these APPs.

[0097] The aforementioned driving information may include trip information (including origin and destination location information, trip duration / distance), non-autonomous driving style information (including acceleration and deceleration information (i.e., acceleration and brake pedal input), sharp steering information (i.e., steering wheel angle and attitude angle), average speed, and starting acceleration), user's active intervention in driving tasks after the assisted driving / autonomous driving function is activated (including steering and pedal operation), and real-time vehicle information records (including vehicle speed, orientation angle, location, and actuator task status), as well as the current assisted driving / autonomous driving task status and environmental perception information records. In one embodiment of the invention, a script can be pre-embedded in the vehicle's controller, which runs at regular intervals to acquire the aforementioned driving information. For example, in autonomous driving mode, when the user is hands-free and feet-free (i.e., hands not touching the steering wheel, feet not touching the brake and accelerator pedals), glances at an adjacent target vehicle to the side, and the current distance to the target vehicle is approximately xx m, the vehicle speed is xx km / h, and the attitude angle is xx°, the user actively turns the steering wheel to the right and applies the brakes urgently. If the vehicle is currently in a Bluetooth call, the aforementioned driving information can be collected for this scenario.

[0098] The aforementioned feedback information may include after-sales maintenance details of the vehicle and user evaluations of the vehicle's functions. Specifically, in one embodiment of the invention, this feedback information can be obtained at regular intervals through the vehicle operation system (e.g., a vehicle after-sales system).

[0099] Currently, data points can be deployed through vehicle data networks. In manual driving mode, this continuously collects information such as steering wheel angle, acceleration and brake pedal inputs, and vehicle posture to record and model the user's driving style and behavior. In autonomous driving mode, the focus is on collecting user behavior when actively intervening in autonomous driving functions, such as when the user takes over steering wheel control leading to function disengagement, or when the user actively applies the brakes to disengage the function. Simultaneously, sensor data from a certain period before the intervention is recorded for user scenario analysis. After identifying the reasons for the user's intervention, targeted optimizations are made to the vehicle control in that scenario. In other words, this current approach can perform 'data modeling' of the driver, creating a replica of the driver's driving behavior and style, which can then be applied to corresponding autonomous driving functional scenarios, providing a 'driving yourself' experience.

[0100] While the current solutions described above can provide autonomous vehicle control that more closely resembles the user's own driving behavior and style, building upon the existing audio-visual alerts, this approach relies on data collection based on a single user's behavior / interventions in vehicle control. This limited data scope can easily lead to uncontrollable biases in the learning outcomes.

[0101] In one embodiment of the present invention, the aforementioned reference information from multiple users can be collected, thereby expanding the data dimensions and further enriching the data details. In addition to deploying data points in advance at the vehicle architecture level, it is also necessary to incorporate data sources other than vehicle control, including the operation of in-vehicle hardware and software touchpoints, vehicle system operation, user travel itinerary information and terminal device APP data behavior, social-related behavior data, and user feedback information on vehicle use. This enables autonomous driving to provide timely, appropriate, and adaptive human-machine interaction strategies and related functions based on a deep understanding of the user's real-time status.

[0102] In addition, it should be noted that after obtaining the above-mentioned behavioral information, driving information and feedback information, information unrelated to autonomous driving can be deleted. In this way, by deleting redundant information unrelated to autonomous driving, the software update package of the autonomous driving system can be pushed to the user more accurately based on the remaining information.

[0103] Step 102: Based on the reference information, push the software update package of the vehicle's autonomous driving system to the multiple users.

[0104] The method of pushing the software update package of the vehicle's autonomous driving system to multiple users can be achieved by pushing the software update package of the autonomous driving system to the vehicle terminal where one user's account is logged in after the user's account has been logged in; or, the software update package of the autonomous driving system can be pushed to the terminal device's APP (such as a vehicle control APP).

[0105] In addition, after the vehicle terminal receives the push notification to install the aforementioned software update package, it can install the software update package onto the vehicle terminal. In this way, the autonomous driving system on the vehicle where the vehicle terminal is located can use the driving control strategy carried by the software update package.

[0106] It should be noted that the driving control strategy described in this application embodiment includes a strategy for controlling the driving of the vehicle, as well as a strategy for information interaction between the user and the vehicle.

[0107] After the terminal device receives a preset operation (such as a click) on the pushed software update package, the terminal device can send the software update package to the vehicle terminal with which it has established a connection (such as a Bluetooth connection), thereby installing the software update package on the vehicle terminal. In this way, the autonomous driving system on the vehicle where the vehicle terminal is located can use the driving control strategy carried by the software update package.

[0108] Optionally, the aforementioned reference information can be collected in real time, and at preset time intervals, software update packages for the vehicle's autonomous driving system can be pushed to the multiple users based on the reference information collected within that time interval.

[0109] Alternatively, if a user's driving behavior is relatively stable over a period of time, the vehicle's onboard terminal can continue to collect the aforementioned reference information after the software update package is installed. If the subsequently collected reference information indicates a deviation in behavior, a new software update package can be pushed to the user again based on the collected reference information once a certain amount of deviation data reaches a set threshold.

[0110] Furthermore, it should be noted that the aforementioned multiple users may include users of different vehicles or different users of the same vehicle. Moreover, the software update package is derived from the aforementioned reference information; therefore, the driving control strategy carried by the software update package aligns with the user's driving style and preference decision-making strategy.

[0111] For example, users E and F, assuming they use the same vehicle but have their own user ID accounts, can have their respective software update packages proactively pushed to users E and F via the in-vehicle terminal / app. Users can then choose whether to install the update, thus changing the autonomous driving interaction strategy under their logged-in user ID to the updated strategy. In this way, when user E uses the vehicle, their ID is automatically recognized, triggering the driving control strategy adapted to their style; similarly, when user F uses the vehicle, their ID is automatically recognized, triggering the driving control strategy adapted to their style.

[0112] As can be seen from steps 101 to 102 above, in one embodiment of the present invention, reference information of multiple users can be obtained, and software update packages of the vehicle's autonomous driving system can be pushed to multiple users based on the reference information. The reference information includes behavior information, driving information and feedback information belonging to the same user. The behavior information includes the behavior information of the user in the terminal device associated with the vehicle. The driving information includes the driving information when the vehicle logs into the user's account. The feedback information includes the user's feedback information on the use of the vehicle.

[0113] Therefore, in one embodiment of the present invention, software update packages for the vehicle's autonomous driving system can be pushed to multiple users based on user behavior information in the terminal devices associated with the vehicle, driving information when the vehicle logs into the user's account, and user feedback information on vehicle usage. That is, in one embodiment of the present invention, software update packages for the vehicle's autonomous driving system can be generated from the aforementioned multiple data dimensions and pushed to users, thereby making the driving control strategy of the autonomous driving system more in line with the actual needs of users, thus improving the user's autonomous driving experience and shortening the user's adaptation period for the autonomous driving function.

[0114] In another embodiment of the information processing method of the present invention, step 102, "pushing the software update package of the vehicle's autonomous driving system to the plurality of users according to the reference information," includes the following sub-steps A1 to A2:

[0115] Sub-step A1: For each user's reference information, obtain the first tag of the behavior information, the second tag of the driving information, and the third tag of the feedback information;

[0116] Sub-step A2: Classify the first tag, second tag, and third tag of the same user to obtain the target identifier information of the tag category for each user;

[0117] Sub-step A3: Based on the target identification information of the multiple users, push the software update package of the vehicle's autonomous driving system to the multiple users.

[0118] In sub-step A1, if the information processing method of this embodiment is executed by the server, the server can obtain the above-mentioned behavior information, driving information and feedback information, and then determine the first tag of the behavior information, the second tag of the driving information and the third tag of the feedback information.

[0119] Alternatively, the terminal device that collects the above-mentioned behavioral information may determine the first tag of the behavioral information and then send the behavioral information and the first tag to the server; the vehicle terminal that collects the above-mentioned driving information may determine the second tag of the driving information and then send the driving information and the second tag to the server; the vehicle operation system (e.g., the vehicle after-sales system) that collects the above-mentioned feedback information may determine the third tag of the feedback information and then send the feedback information and the third tag to the server.

[0120] In addition, the first label is used to represent the user behavior characteristics expressed by the data content corresponding to the first label, the second label is used to represent the vehicle driving characteristics expressed by the data content corresponding to the second label, and the third label is used to represent the user feedback characteristics expressed by the data content corresponding to the third label.

[0121] As can be seen from sub-step A1, it is necessary to determine the respective tags for each user based on their behavior information, driving information, and feedback information.

[0122] After obtaining the first, second, and third tags for each user through sub-step A1, it is necessary to classify the first, second, and third tags belonging to the same user to obtain the target identification information of each user's tag category. Then, based on the target identification information of each user's tag category, the software update package of the vehicle's autonomous driving system is pushed to each user.

[0123] As can be seen from the above sub-steps A1 to A3, in one embodiment of the present invention, after obtaining the above-mentioned behavior information, driving information and feedback information, the features of each piece of information, i.e., tags, can be extracted, and then the extracted tags can be classified. Then, the software update package can be pushed according to the tag category, instead of directly pushing the software update package according to the above-mentioned behavior information, driving information and feedback information, thereby saving system overhead.

[0124] In another embodiment of the information processing method of the present invention, the behavior information, the driving information, and the feedback information each include multiple data contents; sub-step A1 "obtaining the first tag of the behavior information, the second tag of the driving information, and the third tag of the feedback information" includes the following sub-steps B1 to B3:

[0125] Sub-step B1: Obtain the first matching rule that each piece of data in the behavior information conforms to, and determine the first tag corresponding to the first matching rule according to the first correspondence relationship, wherein the first correspondence relationship is the correspondence relationship between the tag and the matching rule;

[0126] Sub-step B2: Obtain the second matching rule that each piece of data in the driving information conforms to, and determine the second tag corresponding to the second matching rule according to the first correspondence relationship;

[0127] Sub-step B3: Obtain the third matching rule that each data content in the feedback information conforms to, and determine the third tag corresponding to the third matching rule based on the first correspondence.

[0128] Firstly, the aforementioned behavioral information includes multiple data items, matching rules, and corresponding first tags, as shown in Table 1:

[0129] Table 1. Behavioral Information, Matching Rules, and Examples of First Tags

[0130]

[0131]

[0132]

[0133] As shown in Table 1, if the data content with serial number 1 in Table 1 meets the rule of "remotely controlling the vehicle via APP every day > first preset value", then the first label of the data content is "remote control expert"; if it meets the rule of "number of times navigation is sent in advance / total number of trips per week > second preset value", then the first label of the data content is "planning expert".

[0134] If the data content with serial number 2 in Table 1 meets the rule "the proportion of trips with a destination distance exceeding the first preset distance / the proportion of weekly trips > the third preset value", then the first label of this data content is "long-distance traveler". If it meets the rule "the proportion of trips with a destination distance less than the second preset distance / the proportion of weekly trips > the fourth preset value", then the first label of this data content is "short-distance commuter".

[0135] If the data content with serial number 3 in Table 1 meets the rule "Number of non-Bluetooth calls in a single trip ≤ fifth preset value", then the first label of this data content is "weak interference call"; if it meets the rule "Number of Bluetooth calls in a single trip > sixth preset value", then the first label of this data content is "strong interference call".

[0136] If the data content with serial number 4 in Table 1 meets the rule "the number of times the mobile device is actively turned on by the user in two consecutive trips is ≥ the seventh preset value", then the first label of this data content is "heavy device dependence"; if it meets the rule "the number of times the mobile device is actively turned on by the user in two consecutive trips is ≤ the eighth preset value", then the first label of this data content is "mild device dependence".

[0137] If the data content with serial number 5 in Table 1 meets the rule "Total time spent using instant messaging apps during a single trip > Ninth preset value", then the first label of this data content is "High risk of distraction". If it meets the rule "Total time spent using instant messaging apps during a single trip < Tenth preset value", then the first label of this data content is "Low risk of distraction".

[0138] If the data entry with serial number 6 in Table 1 meets the rule "Total number of times other non-vehicle-owned apps are used during a single trip > eleventh preset value", then the first label for this data entry is "high risk of distraction". If it meets the rule "Total number of times other non-vehicle-owned apps are used during a single trip < twelfth preset value", then the first label for this data entry is "low risk of distraction".

[0139] Secondly, the aforementioned driving information includes multiple data items, matching rules, and corresponding second tags, as shown in Table 2:

[0140] Table 2. Driving Information, Matching Rules, and Examples of Second Tags

[0141]

[0142]

[0143] As shown in Table 2, if the data entry with serial number 1 in Table 2 meets the rule of "the proportion of trips to destinations exceeding the first preset distance / the proportion of weekly trips > the third preset value", then the second label of this data entry is "long-distance traveler". If it meets the rule of "the proportion of trips to destinations less than the second preset distance / the proportion of weekly trips > the fourth preset value", then the second label of this data entry is "short-distance commuter". If it meets the rule of "the number of trips to other places exceeding the third preset distance in a single month > the thirteenth preset value", then the second label of this data entry is "travel expert".

[0144] If the data entry with serial number 2 in Table 2 meets the rule "no emergency operations in a single month, and the average speed is within the predetermined speed range", then the second label for this data entry is "calm style". If it meets the rule "number of emergency operations in a single month > the fourteenth preset value, and the average speed is greater than the upper limit of the predetermined speed range", then the second label for this data entry is "aggressive and irritable style". If it meets the rule "number of emergency operations in a single month < the fifteenth preset value, and the average speed is lower than the lower limit of the predetermined speed range", then the second label for this data entry is "overly conservative style".

[0145] If the data content with serial number 3 in Table 2 meets the rule of "Number of normal triggers in a single month > the sixteenth preset value", then the second label of this data content is "dangerous driving"; if it meets the rule of "Number of normal triggers in a single month ≤ the seventeenth preset value", then the second label of this data content is "safe driving".

[0146] If the data entry with serial number 4 in Table 2 meets the rule that "the user's behavior is completely opposite to the behavior of the current assisted driving / autonomous driving function", then the second label for this data entry is "contradictory to expected decision". If it meets the rule that "the user's behavior is the same as the assisted driving / autonomous driving function, but the user applies assistance", then the second label for this data entry is "the expected decision does not meet expectations". If it meets the rule that "the user's intervention does not interfere with the autonomous driving function", then the second label for this data entry is "consistent with expected decision".

[0147] Thirdly, the feedback information mentioned above includes multiple data items, matching rules, and corresponding third tags, as shown in Table 3:

[0148] Table 3 Feedback Information, Matching Rules, and Examples of Third Tags

[0149]

[0150] As shown in Table 3, if the data item with serial number 1 in Table 3 belongs to "feedback on driving style related to acceleration and deceleration comfort, lane change success rate / timing, etc. of autonomous driving functions", then the third label of this data item is "driving style does not meet expectations". If it belongs to "feedback on emergency-triggered safety warnings / braking / avoidance functions, resulting in accident feedback", then the third label of this data item is "safety / accident risk in some scenarios". If it belongs to "questions about the specific use and operation steps of the function", then the third label of this data item is "function not understood". If it belongs to "suggestions on other new functions not currently provided", then the third label of this data item is "suggestions on new function experience".

[0151] If the data entry with serial number 2 in Table 3 belongs to "Front and rear bumper accidents and repairs", then the third label for this data entry is "Rear-end collision accidents / repairs". If it belongs to "Scratches around the body", then the third label for this data entry is "Low-to-medium speed scrapes accidents / repairs". If it belongs to "Autonomous driving related hardware replacement / warranty", then the third label for this data entry is "Related hardware failure repairs / replacements".

[0152] As can be seen from the above, in one embodiment of the present invention, a first correspondence between tags and matching rules can be predetermined, thereby determining the matching rules that each data content conforms to for the above-mentioned behavioral information, driving information, and feedback information, and thus determining the tags of each data.

[0153] In another embodiment of the information processing method of the present invention, sub-step A2, "classifying the first tag, the second tag, and the third tag of the same user to obtain target identification information of the tag category for each user", includes the following sub-step C1:

[0154] Sub-step C1: Using semantic analysis algorithms and machine learning algorithms, classify the first tag, second tag, and third tag of the same user to obtain the target identifier information of the tag category for each user.

[0155] In natural language processing, it is often necessary to find similar sentences or approximate expressions of sentences. In such cases, it is necessary to group similar sentences together, and semantic analysis algorithms can be used for this purpose. Similarly, in one embodiment of this invention, a semantic analysis algorithm can be used to process the aforementioned first, second, and third tags to find tags in similar scenarios or tags expressing similar features, thereby achieving clustering of these tags.

[0156] Furthermore, machine learning is a multidisciplinary field involving probability theory, statistics, approximation theory, convex analysis, and algorithm complexity theory, among others. It specifically studies how computers can simulate or implement human learning behavior to acquire new knowledge or skills and reorganize existing knowledge structures to continuously improve their performance. Therefore, in one embodiment of this invention, by combining the aforementioned semantic analysis algorithm and machine learning algorithm to classify the first, second, and third labels, more accurate label categories can be obtained.

[0157] For example, the first tag includes: remote control expert, long-distance traveler, highly disruptive calls, heavy device dependence, high risk of distraction; the second tag includes: long-distance traveler, aggressive and irritable driving style, dangerous driving; the third tag includes: lack of understanding of functions, low-to-medium speed minor accidents / repairs; then the aforementioned semantic analysis algorithm and machine learning algorithm can be used to classify these tags according to different degrees of "driving experience," "familiarity with functions," and "driving style," that is:

[0158] The labels "Remote control expert" and "Functional incomprehension" indicate that users are familiar with the simple vehicle control functions of the terminal device, but have a low level of familiarity with the complex autonomous driving functions in the car. Therefore, these two labels can be classified under the category of "moderate functional familiarity".

[0159] "Highly disruptive calls", "Excessive device dependence", "High risk of distraction", "Aggressive and irritable driving style", "Dangerous driving", "Low-to-medium speed minor collisions / repairs" - these labels will be classified under the "Dangerous driving style" category.

[0160] The label "long-distance traveler" indicates that the user has relatively rich driving experience; therefore, this label will be classified under the category of "relatively experienced drivers".

[0161] In another embodiment of the information processing method of the present invention, sub-step A3, "pushing the software update package of the vehicle's autonomous driving system to the multiple users based on the target identification information of the multiple users," includes the following sub-steps D1 to D4:

[0162] Sub-step D1: Select target identifier information from the target identifier information of the multiple users whose first parameter is greater than a preset threshold, wherein the first parameter is the ratio of the number of the same target identifier information to the total number of target identifier information of the multiple users;

[0163] Sub-step D2: Based on the second correspondence, determine the first target driving control strategy corresponding to each target identification information whose first parameter is greater than a preset threshold. The second correspondence is the correspondence between the identification information of the tag category and the driving control strategy.

[0164] Sub-step D3: Based on each of the first target driving control strategies, generate a first software update package for the vehicle's autonomous driving system;

[0165] Sub-step D4: Push the first software update package to the multiple users.

[0166] For example, if the target identification information of the aforementioned multiple users includes 10 items, where the number of target identification information A is X1 and the number of target identification information B is X2, and X1 / 10 > preset threshold and X2 / 10 > preset threshold, then the first target driving control strategy corresponding to target identification information A and the first target driving control strategy corresponding to target identification information B can be obtained from the second correspondence between the identification information of the predetermined tag category and the driving control strategy. Then, two first software update packages can be generated according to these two first target driving control strategies, and then these two first software update packages can be pushed to each of the aforementioned multiple users.

[0167] It can be understood that if there is no driving control strategy corresponding to a target identifier information whose first parameter is greater than a preset threshold in the above second correspondence, the target identifier information whose first parameter is greater than the preset threshold will be deleted, that is, the target identifier information whose first parameter is greater than the preset threshold will not generate a corresponding software update package.

[0168] In addition, if the first parameter of a target identifier is greater than a preset threshold, it indicates that the number of users corresponding to the tag category represented by the target identifier is large. In this case, the driving control strategy corresponding to the target identifier in the second correspondence is applicable to most users. Therefore, the software update package generated according to the driving control strategy corresponding to the target identifier can be pushed to each of the above multiple users.

[0169] In another embodiment of the information processing method of the present invention, sub-step A3, "pushing the software update package of the vehicle's autonomous driving system to the multiple users based on the target identification information of the multiple users," includes the following sub-steps E1 to E3:

[0170] Sub-step E1: Based on the second correspondence, determine the second target driving control strategy corresponding to each of the target identification information, where the second correspondence is the correspondence between the identification information of the tag category and the driving control strategy;

[0171] Sub-step E2: Based on each of the second target driving control strategies, generate a second software update package for the vehicle's autonomous driving system, as the second software update package for the user corresponding to the target identification information;

[0172] Sub-step E3: Push the second software update package to the user corresponding to the second software update package.

[0173] For example, if the target identification information of the above multiple users includes 10, then the second target driving control strategy corresponding to each target identification information can be obtained from the second correspondence between the identification information of the pre-determined tag category and the driving control strategy. Then, a second software update package can be generated according to each second target driving control strategy, resulting in 10 second software update packages. These 10 second software update packages are then pushed to the corresponding users (for example, the second software update package generated by the second target driving control strategy corresponding to target identification information C is pushed to the user corresponding to target identification information C).

[0174] It can be understood that if there is no driving control strategy corresponding to a certain target identification information in the above second correspondence, then the target identification information will be deleted, that is, the target identification information will not generate a corresponding software update package.

[0175] As can be seen from the above, in one embodiment of the present invention, a corresponding software update package can also be generated based on the target identification information of each user's tag category, that is, to realize personalized adjustment of the driving control strategy for each user, so as to make the driving control strategy of the autonomous driving system more in line with the actual needs of the user.

[0176] In addition, the driving control strategy corresponding to the above-mentioned "moderate familiarity with functions" may include: using standard-style human machine interface (HMI) information reminder configuration, and providing driving users with operation prompts throughout the process, including but not limited to instrument text, in-vehicle AI voice broadcast, etc. At the same time, the vehicle control style will become more conservative and reliable to make up for the time difference in operation understanding caused by the user's lack of familiarity with the functions.

[0177] Driving control strategies corresponding to "dangerous driving style" may include: when the autonomous driving function is activated, the user's intervention in the opposite direction will trigger the vehicle's HMI system to provide more sensitive audio and visual prompts to ensure that the user is aware of the risks of dangerous driving style intervention, while providing aggressive performance in following and lane changing scenarios to meet the expectations of users with this style.

[0178] Driving control strategies corresponding to "relatively rich driving experience" may include: using a light-style HMI information alert configuration, providing system-level information and prompts only in dangerous situations, giving drivers and passengers a non-disturbing usage scenario, and the vehicle control style can also learn and train based on the user's driving input information, thereby replicating the user's driving behavior.

[0179] In another embodiment of the information processing method of the present invention, the behavior information, the driving information, and the feedback information each include multiple data contents, and each data content corresponds to a tag; the method further includes the following steps F1 to F4:

[0180] Step F1: Perform AI semantic understanding on the data content corresponding to the tags under the same category represented by the target identification information to obtain the AI ​​description information of the target identification information;

[0181] Step F2: Obtain search keywords;

[0182] Step F3: Obtain the target identifier information that matches the search keyword;

[0183] Step F4: Display the AI ​​description information of the target identifier information that matches the search keyword.

[0184] The AI ​​description information mentioned above is obtained by performing AI semantic understanding on the data content corresponding to the label under the category represented by the target identification information. Therefore, the AI ​​description information is used to describe the feature information of the data content corresponding to the label under the category represented by the target identification information. For example, if a target identification information is "dangerous driving style", then the AI ​​description information is used to describe the dangerous driving behavior in the data content corresponding to the "dangerous driving style".

[0185] In addition, by searching for keywords, AI description information of target identifiers that match the search keywords can be found and displayed, making it easier for relevant personnel to view.

[0186] In another embodiment of the information processing method of the present invention, the behavior information, the driving information, and the feedback information each include multiple data contents, and each data content corresponds to a tag; the method further includes the following steps G1 to G4:

[0187] Step G1: Determine the data endpoint information of the target identifier information based on the target data endpoint of the data content corresponding to the tag under the same category represented by the target identifier information;

[0188] Step G2: Obtain search keywords;

[0189] Step G3: Obtain the target identifier information that matches the search keyword;

[0190] Step G4: Display the data terminal information of the target identifier information that matches the search keyword.

[0191] Among them, the data end information of the aforementioned target identification information is used to indicate the source information of the data content under the category represented by the target identification information.

[0192] In addition, by searching for keywords, one can find the data source information of the target identification information that matches the search keywords, thereby displaying the found data source information, which makes it easier for relevant personnel to view the data source of the target data identification information they are looking for.

[0193] In another embodiment of the information processing method of the present invention, step G1, "determining the data end information of the target identification information based on the data end of the data content corresponding to the tag under the same category represented by the target identification information", includes the following sub-step H1:

[0194] Sub-step H1: Based on the predetermined weights of different data terminals, determine the information of the data terminal with the largest weight value among the target data terminals as the data terminal information of the target identification information;

[0195] or,

[0196] The information of the data terminal with the largest second parameter among the target data terminals is determined as the data terminal information of the target identification information, wherein the second parameter is the ratio of the number of the same target data terminal to the total number of all target data terminals.

[0197] For example, the labels under the category represented by the target identification information Y1 include Z1, Z2, and Z3. Among them, Z1 comes from the terminal device dimension, Z2 comes from the vehicle dimension, and Z3 comes from the user feedback dimension. Among them, the vehicle dimension is pre-determined to have the largest weight, so the "data terminal information" of the target identification information Y1 is "vehicle terminal".

[0198] Alternatively, if the labels under the category represented by the target identification information Y2 include Z4, Z5, and Z6, where Z4 comes from the terminal device dimension, Z5 comes from the user dimension, and Z6 comes from the user dimension, then the "user dimension" has the largest proportion, and the "data terminal information" of the target identification information Y2 is the "user dimension".

[0199] Therefore, in one embodiment of the present invention, the data end information of the target identifier information can be determined based on the weight or proportion of the data end of the data content under the category represented by the target identifier information.

[0200] In another embodiment of the information processing method of the present invention, the above embodiments can be combined with each other.

[0201] Optionally, an implementation method obtained by a combination of methods may be described in the following steps H1 to H13:

[0202] Step H1: Obtain reference information from multiple users, including behavioral information, driving information, and feedback information belonging to the same user. Behavioral information includes user behavior information in terminal devices associated with the vehicle, driving information includes driving information when the vehicle is logged into the user's account, and feedback information includes user feedback on vehicle usage.

[0203] For each user's reference information, perform the following steps H3 to H5;

[0204] Step H3: Obtain the first matching rule that each piece of data in the behavior information conforms to, and determine the first tag corresponding to the first matching rule according to the first correspondence relationship. The first correspondence relationship is the correspondence between the tag and the matching rule.

[0205] Step H4: Obtain the second matching rule that each piece of data in the driving information conforms to, and determine the second tag corresponding to the second matching rule according to the first correspondence relationship;

[0206] Step H5: Obtain the third matching rule that each piece of data in the feedback information conforms to, and determine the third tag corresponding to the third matching rule based on the first correspondence relationship;

[0207] Step H6: Using semantic analysis and machine learning algorithms, classify the first, second, and third tags of the same user to obtain the target identifier information of each user's tag category;

[0208] After step H6, steps H7 to H10 can be executed, or steps H11 to H13 can be executed:

[0209] Step H7: Select target identifier information from multiple users whose first parameter is greater than a preset threshold, where the first parameter is the ratio of the number of the same target identifier information to the total number of target identifier information from multiple users;

[0210] Step H8: Based on the second correspondence, determine the first target driving control strategy corresponding to each target identification information whose first parameter is greater than a preset threshold. The second correspondence is the correspondence between the identification information of the label category and the driving control strategy.

[0211] Step H9: Based on each first target driving control strategy, generate a first software update package for the vehicle's autonomous driving system;

[0212] Step H10: Push the first software update package to multiple users;

[0213] Step H11: Based on the second correspondence mentioned above, determine the second target driving control strategy corresponding to each target identification information;

[0214] Step H12: Based on each second target driving control strategy, generate a second software update package for the vehicle's autonomous driving system as the second software update package for the user corresponding to the target identification information;

[0215] Step H13: Push the second software update package to the user corresponding to the second software update package.

[0216] In summary, compared to traditional solutions, one embodiment of the present invention not only enables multi-dimensional information tagging and tag clustering of the main vehicle user, but also allows for learning and configuration for multiple users / vehicle users within a single vehicle. In addition to traditionally collecting user data at the vehicle control level, it further collects data on user interactions during vehicle use, including large-screen interaction, in-vehicle voice interaction, and APP vehicle control interaction. Furthermore, with user authorization, it acquires user data at the mobile system / application level related to car-related social media and related social software. This allows for a comprehensive analysis and understanding of the user's familiarity with all vehicle-related functions, driving experience, and driving style from multiple dimensions. Consequently, autonomous driving can provide timely, appropriate, and adaptive human-machine interaction strategies and related functions based on a deep understanding of the user's real-time state.

[0217] Figure 2 This is a block diagram illustrating an information processing apparatus according to an exemplary embodiment, the information processing apparatus may include the following modules:

[0218] The information acquisition module 201 is used to acquire reference information from multiple users. The reference information includes behavioral information, driving information, and feedback information belonging to the same user. The behavioral information includes the user's behavioral information in the terminal device associated with the vehicle. The driving information includes the driving information when the vehicle logs into the user's account. The feedback information includes the user's feedback information on the use of the vehicle.

[0219] The push module 202 is used to push the software update package of the vehicle's autonomous driving system to the multiple users based on the reference information.

[0220] In one possible implementation, the push module 202 includes:

[0221] The tag determination submodule is used to obtain, for each user's reference information, a first tag for the behavior information, a second tag for the driving information, and a third tag for the feedback information;

[0222] The classification processing submodule is used to classify the first tag, the second tag, and the third tag of the same user to obtain the target identification information of the tag category for each user.

[0223] The push module is used to push the software update package of the vehicle's autonomous driving system to the multiple users based on the target identification information of the multiple users.

[0224] In one possible implementation, the behavior information, the driving information, and the feedback information each include multiple data entries; the tag determination submodule is specifically used for:

[0225] Obtain the first matching rule that each piece of data in the behavior information conforms to, and determine the first tag corresponding to the first matching rule according to the first correspondence relationship, wherein the first correspondence relationship is the correspondence relationship between the tag and the matching rule;

[0226] Obtain the second matching rule that each piece of data in the driving information conforms to, and determine the second tag corresponding to the second matching rule based on the first correspondence relationship;

[0227] Obtain the third matching rule that each piece of data in the feedback information conforms to, and determine the third tag corresponding to the third matching rule based on the first correspondence.

[0228] In one possible implementation, the classification processing submodule is specifically used for:

[0229] Using semantic analysis and machine learning algorithms, the first tag, second tag, and third tag of the same user are classified to obtain the target identifier information of the tag category for each user.

[0230] In one possible implementation, the push submodule is specifically used for:

[0231] From the target identification information of the multiple users, target identification information with a first parameter greater than a preset threshold is selected, wherein the first parameter is the ratio of the number of the same target identification information to the total number of target identification information of the multiple users;

[0232] Based on the second correspondence, a first target driving control strategy is determined for each target identification information whose first parameter is greater than a preset threshold. The second correspondence is the correspondence between the identification information of the label category and the driving control strategy.

[0233] Based on each of the first target driving control strategies, a first software update package for the vehicle's autonomous driving system is generated.

[0234] The first software update package is pushed to the multiple users.

[0235] In one possible implementation, the push submodule is specifically used for:

[0236] Based on the second correspondence, a second target driving control strategy corresponding to each of the target identification information is determined, wherein the second correspondence is the correspondence between the identification information of the tag category and the driving control strategy;

[0237] Based on each of the second target driving control strategies, a second software update package for the vehicle's autonomous driving system is generated as the second software update package for the user corresponding to the target identification information.

[0238] The second software update package is pushed to the user corresponding to the second software update package.

[0239] In one possible implementation, the behavior information, the driving information, and the feedback information each include multiple data entries, with each data entry corresponding to a tag; the device further includes:

[0240] The AI ​​understanding module is used to perform artificial intelligence (AI) semantic understanding on the data content corresponding to the tags under the same category represented by the target identification information, and obtain the AI ​​description information of the target identification information;

[0241] The search term acquisition module is used to acquire search keywords;

[0242] A matching module is used to obtain the target identification information that matches the search keyword;

[0243] The first display module is used to display the AI ​​description information of the target identification information that matches the search keyword.

[0244] In one possible implementation, the behavior information, the driving information, and the feedback information each include multiple data entries, with each data entry corresponding to a tag; the device further includes:

[0245] The data end determination module is used to determine the data end information of the target identification information based on the target data end of the data content corresponding to the tag under the same category represented by the target identification information;

[0246] The search term acquisition module is used to acquire search keywords;

[0247] A matching module is used to obtain the target identification information that matches the search keyword;

[0248] The second display module is used to display the data terminal information of the target identification information that matches the search keyword.

[0249] In one possible implementation, the data terminal determination module is specifically used for:

[0250] Based on the predetermined weights of different data terminals, the information of the data terminal with the largest weight value among the target data terminals is determined as the data terminal information of the target identification information;

[0251] or,

[0252] The information of the data terminal with the largest second parameter among the target data terminals is determined as the data terminal information of the target identification information, wherein the second parameter is the ratio of the number of the same target data terminal to the total number of all target data terminals.

[0253] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0254] Those skilled in the art will understand that all or part of the steps in the methods of the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it includes the following steps:

[0255] The system obtains reference information from multiple users, including behavioral information, driving information, and feedback information belonging to the same user. The behavioral information includes user behavior information in terminal devices associated with the vehicle, the driving information includes driving information when the vehicle is logged into the user's account, and the feedback information includes user feedback information on vehicle usage.

[0256] Based on the reference information, software update packages for the vehicle's autonomous driving system are pushed to the multiple users.

[0257] In one possible implementation, pushing the software update package for the vehicle's autonomous driving system to the plurality of users based on the reference information includes:

[0258] For each of the aforementioned users, the reference information,

[0259] Obtain a first tag for the behavior information, a second tag for the driving information, and a third tag for the feedback information;

[0260] The first tag, second tag, and third tag of the same user are classified to obtain the target identification information of the tag category for each user.

[0261] Based on the target identification information of the multiple users, push the software update package of the vehicle's autonomous driving system to the multiple users.

[0262] In one possible implementation, the behavior information, the driving information, and the feedback information each include multiple data entries; obtaining the first tag of the behavior information, the second tag of the driving information, and the third tag of the feedback information includes:

[0263] Obtain the first matching rule that each piece of data in the behavior information conforms to, and determine the first tag corresponding to the first matching rule according to the first correspondence relationship, wherein the first correspondence relationship is the correspondence relationship between the tag and the matching rule;

[0264] Obtain the second matching rule that each piece of data in the driving information conforms to, and determine the second tag corresponding to the second matching rule based on the first correspondence relationship;

[0265] Obtain the third matching rule that each piece of data in the feedback information conforms to, and determine the third tag corresponding to the third matching rule based on the first correspondence.

[0266] In one possible implementation, the classification process for the first tag, second tag, and third tag of the same user to obtain target identification information for each user's tag category includes:

[0267] Using semantic analysis and machine learning algorithms, the first tag, second tag, and third tag of the same user are classified to obtain the target identifier information of the tag category for each user.

[0268] In one possible implementation, the step of pushing the software update package of the vehicle's autonomous driving system to the multiple users based on the target identification information of the multiple users includes:

[0269] From the target identification information of the multiple users, target identification information with a first parameter greater than a preset threshold is selected, wherein the first parameter is the ratio of the number of the same target identification information to the total number of target identification information of the multiple users;

[0270] Based on the second correspondence, a first target driving control strategy is determined for each target identification information whose first parameter is greater than a preset threshold. The second correspondence is the correspondence between the identification information of the label category and the driving control strategy.

[0271] Based on each of the first target driving control strategies, a first software update package for the vehicle's autonomous driving system is generated.

[0272] The first software update package is pushed to the multiple users.

[0273] In one possible implementation, the step of pushing the software update package of the vehicle's autonomous driving system to the multiple users based on the target identification information of the multiple users includes:

[0274] Based on the second correspondence, a second target driving control strategy corresponding to each of the target identification information is determined, wherein the second correspondence is the correspondence between the identification information of the tag category and the driving control strategy;

[0275] Based on each of the second target driving control strategies, a second software update package for the vehicle's autonomous driving system is generated as the second software update package for the user corresponding to the target identification information.

[0276] The second software update package is pushed to the user corresponding to the second software update package.

[0277] In one possible implementation, the behavior information, the driving information, and the feedback information each include multiple data entries, with each data entry corresponding to a tag; the method further includes:

[0278] For the data content corresponding to the tags under the same category represented by the target identification information, perform artificial intelligence (AI) semantic understanding to obtain AI description information of the target identification information;

[0279] Obtain search keywords;

[0280] Obtain the target identifier information that matches the search keywords;

[0281] The AI ​​description information displays the target identifier information that matches the search keywords.

[0282] In one possible implementation, the behavior information, the driving information, and the feedback information each include multiple data entries, with each data entry corresponding to a tag; the method further includes:

[0283] Based on the target data end of the data content corresponding to the tag under the same category represented by the target identification information, determine the data end information of the target identification information;

[0284] Obtain search keywords;

[0285] Obtain the target identifier information that matches the search keywords;

[0286] The data terminal information displays the target identifier information that matches the search keywords.

[0287] In one possible implementation, determining the data endpoint information of the target identifier information based on the data endpoint of the data content corresponding to the tag under the same category represented by the target identifier information includes:

[0288] Based on the predetermined weights of different data terminals, the information of the data terminal with the largest weight value among the target data terminals is determined as the data terminal information of the target identification information;

[0289] or,

[0290] The information of the data terminal with the largest second parameter among the target data terminals is determined as the data terminal information of the target identification information, wherein the second parameter is the ratio of the number of the same target data terminal to the total number of all target data terminals.

[0291] The storage medium mentioned above includes, for example, read-only memory (ROM) / random access memory (RAM), magnetic disk, optical disk, etc.

[0292] Embodiments of the present invention also provide an electronic device, which may be, for example, an in-vehicle terminal.

[0293] like Figure 3 As shown, the electronic device includes a memory 320, a transceiver 310, and a processor 300;

[0294] Memory 320 is used to store computer programs;

[0295] Transceiver 310 is used to receive and send data under the control of processor 300;

[0296] The processor 300 is used to read the computer program in the memory 320 and execute the information processing method described above.

[0297] Among them, Figure 3In this context, the bus architecture can include any number of interconnected buses and bridges, specifically connecting various circuits of one or more processors 300 (represented by processor 300) and memory 320 (represented by memory 320). The bus architecture can also link various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. The bus interface is used to provide an interface. The transceiver 310 can be multiple elements, including transmitters and receivers, providing a unit for communicating with various other devices over a transmission medium, including wireless channels, wired channels, optical fibers, etc. For different user equipment, the user interface 330 can also be an interface capable of connecting external or internal devices, including but not limited to keypads, displays, speakers, microphones, joysticks, etc.

[0298] The processor 300 is responsible for managing the bus architecture and general processing, while the memory 320 can store the data used by the processor 300 when performing operations.

[0299] Optionally, the processor 300 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or a complex programmable logic device (CPLD). The processor 300 may also adopt a multi-core architecture.

[0300] The processor 300 executes any of the methods provided in the embodiments of the present invention according to the obtained executable instructions by calling a computer program stored in the memory 320. The processor 300 and the memory 320 may also be physically separated.

[0301] It should be noted that the electronic device provided in this embodiment of the invention can implement all the method steps implemented in the above method embodiment and achieve the same technical effect. Therefore, the parts and beneficial effects that are the same as those in the method embodiment will not be described in detail here.

[0302] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage and optical storage) containing computer-usable program code.

[0303] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-executable instructions. These computer-executable instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0304] These processor-executable instructions may also be stored in a processor-readable memory that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the processor-readable memory produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0305] These processors can execute instructions that can also be loaded onto a computer or other programmable data processing device, causing a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable device for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0306] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. An information processing method, characterized in that, The method includes: The system obtains reference information from multiple users, including behavioral information, driving information, and feedback information belonging to the same user. The behavioral information includes user behavior information in terminal devices associated with the vehicle, the driving information includes driving information when the vehicle is logged into the user's account, and the feedback information includes user feedback information on vehicle usage. Based on the reference information, push the software update package of the vehicle's autonomous driving system to the multiple users; The step of pushing the software update package of the vehicle's autonomous driving system to the multiple users based on the reference information includes: For each user's reference information, obtain a first tag for the behavior information, a second tag for the driving information, and a third tag for the feedback information; The first tag, second tag, and third tag of the same user are classified to obtain the target identification information of the tag category for each user. Based on the target identification information of the multiple users, push the software update package of the vehicle's autonomous driving system to the multiple users; The step of pushing the software update package of the vehicle's autonomous driving system to the multiple users based on the target identification information of the multiple users includes: From the target identification information of the plurality of users, target identification information with a first parameter greater than a preset threshold is selected, wherein the first parameter is the ratio of the number of the same target identification information to the total number of target identification information of the plurality of users; Based on the second correspondence, a first target driving control strategy is determined for each target identification information whose first parameter is greater than a preset threshold. The second correspondence is the correspondence between the identification information of the label category and the driving control strategy. Based on each of the first target driving control strategies, a first software update package for the vehicle's autonomous driving system is generated. The first software update package is pushed to the multiple users.

2. The method according to claim 1, characterized in that, The behavioral information, the driving information, and the feedback information each include multiple data items; The acquisition of the first tag of the behavior information, the second tag of the driving information, and the third tag of the feedback information includes: Obtain the first matching rule that each piece of data in the behavior information conforms to, and determine the first tag corresponding to the first matching rule according to the first correspondence relationship, wherein the first correspondence relationship is the correspondence relationship between the tag and the matching rule; Obtain the second matching rule that each piece of data in the driving information conforms to, and determine the second tag corresponding to the second matching rule based on the first correspondence relationship; Obtain the third matching rule that each piece of data in the feedback information conforms to, and determine the third tag corresponding to the third matching rule based on the first correspondence.

3. The method according to claim 1, characterized in that, The classification process for the first tag, second tag, and third tag of the same user to obtain target identifier information for each user's tag category includes: Using semantic analysis and machine learning algorithms, the first tag, second tag, and third tag of the same user are classified to obtain the target identifier information of the tag category for each user.

4. The method according to claim 1, characterized in that, The step of pushing the software update package of the vehicle's autonomous driving system to the multiple users based on the target identification information of the multiple users includes: Based on the second correspondence, a second target driving control strategy corresponding to each of the target identification information is determined, wherein the second correspondence is the correspondence between the identification information of the tag category and the driving control strategy; Based on each of the second target driving control strategies, a second software update package for the vehicle's autonomous driving system is generated as the second software update package for the user corresponding to the target identification information. The second software update package is pushed to the user corresponding to the second software update package.

5. The method according to claim 1, characterized in that, The behavioral information, the driving information, and the feedback information each include multiple data entries, with each data entry corresponding to a tag; the method further includes: For the data content corresponding to the tags under the same category represented by the target identification information, perform artificial intelligence (AI) semantic understanding to obtain AI description information of the target identification information; Obtain search keywords; Obtain the target identifier information that matches the search keywords; The AI ​​description information displays the target identifier information that matches the search keywords.

6. The method according to claim 1, characterized in that, The behavioral information, the driving information, and the feedback information each include multiple data entries, with each data entry corresponding to a tag. The method further includes: Based on the target data end of the data content corresponding to the tag under the same category represented by the target identification information, determine the data end information of the target identification information; Obtain search keywords; Obtain the target identifier information that matches the search keywords; The data terminal information displays the target identifier information that matches the search keywords.

7. The method according to claim 6, characterized in that, The process of determining the data endpoint information of the target identifier information based on the data endpoint of the data content corresponding to the tag under the same category represented by the target identifier information includes: Based on the predetermined weights of different data terminals, the information of the data terminal with the largest weight value among the target data terminals is determined as the data terminal information of the target identification information; or, The information of the data terminal with the largest second parameter among the target data terminals is determined as the data terminal information of the target identification information, wherein the second parameter is the ratio of the number of the same target data terminal to the total number of all target data terminals.

8. An information processing device, characterized in that, The device includes: The information acquisition module is used to acquire reference information from multiple users. The reference information includes behavioral information, driving information, and feedback information belonging to the same user. The behavioral information includes the user's behavioral information in the terminal device associated with the vehicle. The driving information includes the driving information when the vehicle is logged into the user's account. The feedback information includes the user's feedback information on the use of the vehicle. The push module is used to push the software update package of the vehicle's autonomous driving system to the multiple users based on the reference information; The push module includes: The tag determination submodule is used to obtain, for each user's reference information, a first tag for the behavior information, a second tag for the driving information, and a third tag for the feedback information; The classification processing submodule is used to classify the first tag, the second tag, and the third tag of the same user to obtain the target identification information of the tag category for each user. The push submodule is used to push the software update package of the vehicle's autonomous driving system to the multiple users based on the target identification information of the multiple users; The push submodule is specifically used for: From the target identification information of the plurality of users, target identification information with a first parameter greater than a preset threshold is selected, wherein the first parameter is the ratio of the number of the same target identification information to the total number of target identification information of the plurality of users; Based on the second correspondence, a first target driving control strategy is determined for each target identification information whose first parameter is greater than a preset threshold. The second correspondence is the correspondence between the identification information of the label category and the driving control strategy. Based on each of the first target driving control strategies, a first software update package for the vehicle's autonomous driving system is generated. The first software update package is pushed to the multiple users.

9. The apparatus according to claim 8, characterized in that, The behavioral information, the driving information, and the feedback information each include multiple data items; The label determination submodule is specifically used for: Obtain the first matching rule that each piece of data in the behavior information conforms to, and determine the first tag corresponding to the first matching rule according to the first correspondence relationship, wherein the first correspondence relationship is the correspondence relationship between the tag and the matching rule; Obtain the second matching rule that each piece of data in the driving information conforms to, and determine the second tag corresponding to the second matching rule based on the first correspondence relationship; Obtain the third matching rule that each piece of data in the feedback information conforms to, and determine the third tag corresponding to the third matching rule based on the first correspondence.

10. The apparatus according to claim 8, characterized in that, The classification processing submodule is specifically used for: Using semantic analysis and machine learning algorithms, the first tag, second tag, and third tag of the same user are classified to obtain the target identifier information of the tag category for each user.

11. The apparatus according to claim 8, characterized in that, The push submodule is specifically used for: Based on the second correspondence, a second target driving control strategy corresponding to each of the target identification information is determined, wherein the second correspondence is the correspondence between the identification information of the tag category and the driving control strategy; Based on each of the second target driving control strategies, a second software update package for the vehicle's autonomous driving system is generated as the second software update package for the user corresponding to the target identification information. The second software update package is pushed to the user corresponding to the second software update package.

12. The apparatus according to claim 8, characterized in that, The behavior information, the driving information, and the feedback information each include multiple data entries, with each data entry corresponding to a tag; the device also includes: The AI ​​understanding module is used to perform artificial intelligence (AI) semantic understanding on the data content corresponding to the tags under the same category represented by the target identification information, and obtain the AI ​​description information of the target identification information; The search term acquisition module is used to acquire search keywords; A matching module is used to obtain the target identification information that matches the search keyword; The first display module is used to display the AI ​​description information of the target identification information that matches the search keyword.

13. The apparatus according to claim 8, characterized in that, The behavior information, the driving information, and the feedback information each include multiple data entries, with each data entry corresponding to a tag; the device also includes: The data end determination module is used to determine the data end information of the target identification information based on the target data end of the data content corresponding to the tag under the same category represented by the target identification information; The search term acquisition module is used to acquire search keywords; A matching module is used to obtain the target identification information that matches the search keyword; The second display module is used to display the data terminal information of the target identification information that matches the search keyword.

14. The apparatus according to claim 13, characterized in that, The data terminal determination module is specifically used for: Based on the predetermined weights of different data terminals, the information of the data terminal with the largest weight value among the target data terminals is determined as the data terminal information of the target identification information; or, The information of the data terminal with the largest second parameter among the target data terminals is determined as the data terminal information of the target identification information, wherein the second parameter is the ratio of the number of the same target data terminal to the total number of all target data terminals.

15. An electronic device, characterized in that, include: processor; Memory used to store the processor's executable instructions; The processor is configured to perform operations performed by the information processing method as described in any one of claims 1 to 7.

16. A processor-readable storage medium, characterized in that, The processor-readable storage medium stores a computer program for causing the processor to perform the information processing method according to any one of claims 1 to 7.

Images