Vehicle atomic power recommendation method, device and equipment and storage medium

Abstract

The invention discloses a vehicle atomic power recommendation method, apparatus and device, and a storage medium. The vehicle atomic power recommendation method comprises the steps of obtaining historical data of a scene card edited by a user; inputting the historical data into a preset continuous learning model to obtain an atomic energy recommendation set output by the continuous learning model; and in response to a scene card editing request of a user, extracting matched atomic power from the atomic power recommendation set according to the scene card editing request. According to the invention, the continuous learning method is adopted to analyze the operation behavior of the user on the scene card, and the atomic power with high matching rate is recommended to the user when the user edits the scene card, so that the user experience is effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent vehicles, and in particular, to a vehicle atomic capability recommendation method, device, equipment, and storage medium. Background Art

[0002] Atomic capabilities refer to the automotive functional unit services that users can mobilize, that is, the automotive functions that users can freely deploy. As a highlight of the intelligent cockpit, the scenario card editing software is very powerful, capable of mobilizing more than 500 sensors and more than 300 actuators throughout the vehicle, integrating more than 140 atomic capabilities. Users can develop personalized scenario-based intelligent applications according to their own needs, upgrading the monomer intelligence to "scenario intelligence". With just one key trigger, multiple steps can be achieved directly. Users can also share scenario cards through in-vehicle cloud technology, and the scenario card editing software has thus become a real experience tool serving "scenario intelligence". However, the current actual user utilization rate is not high because when editing scenario cards, users often give up editing due to the inability to find suitable atomic capabilities, resulting in poor user experience. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide a vehicle atomic capability recommendation method, device, equipment, and storage medium, which analyzes the user's operation behavior on the scenario card by using a continuous learning method, and recommends atomic capabilities with a high matching rate for the user when editing the scenario card, thereby effectively improving the user experience.

[0004] To achieve the above object, an embodiment of the present invention provides a vehicle atomic capability recommendation method, including:

[0005] Obtain historical data of the user editing the scenario card;

[0006] Input the historical data into a preset continuous learning model to obtain an atomic capability recommendation set output by the continuous learning model;

[0007] Respond to the user's scenario card editing request, and extract matching atomic capabilities from the atomic capability recommendation set according to the scenario card editing request.

[0008] As an improvement of the above solution, the obtaining of the historical data of the user editing the scenario card specifically includes:

[0009] Obtain historical data of the user editing the scenario card through the vehicle terminal, APP terminal, and WEB terminal, and report the historical data to the cloud so that the cloud can uniformly process the historical data through data logging; wherein, the historical data includes user behavior, operation time, and operation content.

[0010] As an improvement to the above solution, inputting the historical data into a preset continuous learning model to obtain an atomic capability recommendation set output by the continuous learning model specifically includes:

[0011] Parse the historical data to obtain configuration information; wherein, the configuration information includes a trigger atom, a condition atom, a function atom, a scenario card type, a scenario card template ID, and a data source.

[0012] Input the configuration information into the continuous learning model, and learn the configuration information through a preset learning rule to obtain an atomic capability recommendation set.

[0013] As an improvement to the above solution, the method further includes:

[0014] Obtain the historical data of user-edited scenario cards in different vehicle models.

[0015] Perform granularity subdivision on the historical data of different vehicle models, and input the subdivided data into a preset continuous learning model.

[0016] As an improvement to the above solution, the learning of the configuration information through a preset learning rule specifically includes:

[0017] Learn the combined collocations of each atomic capability according to the trigger atom, the condition atom, and the function atom, and calculate the first weight of each atomic capability according to the combination times of each atomic capability.

[0018] As an improvement to the above solution, extracting matching atomic capabilities from the atomic capability recommendation set according to the scenario card editing request specifically includes:

[0019] Extract the atomic capabilities with the first weight greater than a first threshold from the atomic capability recommendation set according to the scenario card editing request, and send the atomic capabilities in descending order of the weight.

[0020] As an improvement to the above solution, if the atomic capability recommendation set further includes a scenario card template, then extracting matching atomic capabilities from the atomic capability recommendation set according to the scenario card editing request specifically includes:

[0021] Extract matching atomic capabilities from the atomic capability recommendation set according to the scenario card editing request; or,

[0022] Extract matching scenario card templates from the atomic capability recommendation set according to the scenario card editing request; or,

[0023] Extract matching atomic capabilities and scenario card templates from the atomic capability recommendation set according to the scenario card editing request.

[0024] Among them, the scenario card template includes multiple atomic capabilities.

[0025] As an improvement to the above solution, the learning of the configuration information through a preset learning rule specifically includes:

[0026] According to the scenario card type and the scenario card template ID, obtain the first number of times each scenario card template is used as a parent template and the second number of times it is used as a sub - template;

[0027] According to the first number of times and the second number of times, calculate the second weight of each scenario card template used as a parent template.

[0028] As an improvement to the above solution, the extraction of a matching scenario card template from the atomic - ability recommendation set according to the scenario card editing request specifically includes:

[0029] Extract the scenario card templates with a second weight greater than a second threshold from the atomic - ability recommendation set according to the scenario card editing request as candidate scenario card templates;

[0030] Calculate the similarity between the scenario card editing request and the candidate scenario card templates, and select the candidate scenario card template with the highest similarity as the target scenario card template.

[0031] An embodiment of the present invention also provides a vehicle atomic - ability recommendation device, including:

[0032] An acquisition module, configured to acquire historical data of a user editing a scenario card;

[0033] A learning module, configured to input the historical data into a preset continuous - learning model to obtain an atomic - ability recommendation set output by the continuous - learning model;

[0034] A recommendation module, configured to respond to a user's scenario card editing request and extract matching atomic capabilities from the atomic - ability recommendation set according to the scenario card editing request.

[0035] An embodiment of the present invention also provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, the vehicle atomic - ability recommendation method described in any one of the above is implemented.

[0036] An embodiment of the present invention also provides a computer - readable storage medium. The computer - readable storage medium includes a stored computer program. Wherein, when the computer program runs, it controls the device where the computer - readable storage medium is located to execute the vehicle atomic - ability recommendation method described in any one of the above.

[0037] Compared with the prior art, the beneficial effects of a vehicle atomic capability recommendation method, device, equipment, and storage medium provided by an embodiment of the present invention are as follows: By obtaining historical data of a user editing a scenario card; inputting the historical data into a preset continuous learning model to obtain an atomic capability recommendation set output by the continuous learning model; and in response to a user's scenario card editing request, extracting a matching atomic capability or scenario card template from the atomic capability recommendation set according to the scenario card editing request. The embodiment of the present invention analyzes the user's operation behavior on the scenario card by using a continuous learning method, and recommends atomic capabilities with a high matching rate or appropriate scenario card templates for the user when editing the scenario card, thereby effectively improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 is a schematic flowchart of a preferred embodiment of a vehicle atomic capability recommendation method provided by the present invention;

[0039] Figure 2 is a schematic architecture diagram of a vehicle atomic capability recommendation method provided by the present invention;

[0040] Figure 3 is a schematic diagram of a recommendation interface of a vehicle atomic capability recommendation method provided by the present invention;

[0041] Figure 4 is a schematic structural diagram of a preferred embodiment of a vehicle atomic capability recommendation device provided by the present invention;

[0042] Figure 5 is a schematic structural diagram of a preferred embodiment of a terminal device provided by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0043] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0044] Please refer to Figure 1 , Figure 1 is a schematic flowchart of a preferred embodiment of a vehicle atomic capability recommendation method provided by the present invention. The vehicle atomic capability recommendation method includes:

[0045] S1. Obtain historical data of a user editing a scenario card;

[0046] S2. Input the historical data into a preset continuous learning model to obtain an atomic capability recommendation set output by the continuous learning model;

[0047] S3. Respond to the user's scenario card editing request, and extract matching atomic capabilities from the atomic capability recommendation set according to the scenario card editing request.

[0048] Specifically, in the embodiment of the present invention, first, historical data of the user editing the scenario card is obtained, and then the historical data is used as input data and input into a preset continuous learning model. The continuous learning model continuously learns the combination of atomic capabilities in the historical data, and then obtains an atomic capability recommendation set output by the continuous learning model. When receiving a scenario card editing request sent by the user, respond to the scenario card editing request and directly extract matching atomic capabilities from the atomic capability recommendation set.

[0049] The embodiment of the present invention adopts a continuous learning method to analyze the user's operation behavior on the scenario card, recommends atomic capabilities with a high matching rate for the user when editing the scenario card, and effectively improves the user experience.

[0050] In another preferred embodiment, the obtaining of the historical data of the user editing the scenario card specifically includes:

[0051] Obtain the historical data of the user editing the scenario card through the vehicle end, the APP end, and the WEB end, and report the historical data to the cloud so that the cloud can uniformly process the historical data through data logging; wherein, the historical data includes user behavior, operation time, and operation content.

[0052] Specifically, please refer to Figure 2 , Figure 2It is a schematic architecture diagram in a vehicle atomic ability recommendation method provided by the present invention. In an embodiment of the present invention, historical data of a user-edited scenario card is obtained through the vehicle end, the APP end, and the WEB end, and the historical data is reported to the cloud. The historical data includes user behavior, operation time, and operation content. Among them, user behavior refers to behaviors such as execution, creation, and modification of the user on the scenario editing card; operation time refers to the time when the user edits the scenario card and the time of each atomic ability in the scenario editing card; operation content refers to relevant instructions of the atomic ability set by the user. After receiving the reported historical data, the cloud performs unified processing on the historical data through data logging and stores the historical data in the database. The continuous learning model continuously learns and analyzes by retrieving corresponding historical data from the cloud database to form various atomic ability recommendation combination schemes and scenario card template schemes, which are recorded as the atomic ability recommendation set. When the user edits the scenario card, the HiPhi Play service (i.e., the scenario card editing software service) of the cloud is called through their respective gateways, and HiPhi Play then calls the atomic ability recommendation set output by the continuous learning model through feign. According to the atomic ability selected by the user when editing the scenario card, the atomic ability with a high matching rate or the appropriate scenario card template in the atomic ability recommendation set is pushed to each end again through HiPhi Play. The user can choose to use or not use it until the scenario card creation is completed.

[0053] The embodiment of the present invention can recommend atomic abilities with a high matching rate or appropriate scenario card templates to users when editing scenario cards, making the vehicle no longer just a means of transportation; at the same time, it also publicizes the vehicle highlights invisibly, improves the user's familiarity with the vehicle functions, and increases the usage rate of HiPhi Play.

[0054] In another preferred embodiment, in step S2, inputting the historical data into a preset continuous learning model to obtain the atomic ability recommendation set output by the continuous learning model specifically includes:

[0055] S201, parsing the historical data to obtain configuration information; wherein, the configuration information includes trigger atoms, conditional atoms, functional atoms, scenario card types, scenario card template IDs, and data sources;

[0056] S202, inputting the configuration information into the continuous learning model, and learning the configuration information through a preset learning rule to obtain the atomic ability recommendation set.

[0057] Specifically, the embodiments of the present invention parse the historical data obtained from each end to obtain configuration information. The configuration information includes trigger atoms, condition atoms, function atoms, scenario card types, scenario card template IDs, and data sources. Trigger atoms, condition atoms, and function atoms are three main types of atomic capabilities. After parsing the configuration information, the configuration information is input into a continuous learning model, and according to preset learning rules, the combination and matching of each atomic capability are continuously learned and analyzed based on the configuration information, and then an atomic capability recommendation set output by the continuous learning model is obtained.

[0058] In yet another preferred embodiment, the method further includes:

[0059] Obtain historical data of user-edited scenario cards in different vehicle models;

[0060] Perform granular subdivision on the historical data of different vehicle models, and input the subdivided data into a preset continuous learning model.

[0061] Specifically, the embodiments of the present invention can also obtain historical data of user-edited scenario cards in different vehicle models. Because for different vehicle models, the owner audiences are different, and for different vehicle models, the atomic capability libraries will also vary, and accurate push can be performed according to the vehicle model. Therefore, the embodiments of the present invention perform granular subdivision on the historical data of different vehicle models, and also input the subdivided data into a preset continuous learning model for learning and analysis.

[0062] In yet another preferred embodiment, the learning of the configuration information by the preset learning rules specifically includes:

[0063] Learn the combination and matching of each atomic capability according to the trigger atom, the condition atom, and the function atom, and calculate the first weight of each atomic capability according to the combination times of each atomic capability.

[0064] Specifically, when the embodiments of the present invention learn the configuration information by the preset learning rules, they learn the combination and matching of each atomic capability according to the trigger atom, the condition atom, and the function atom, and calculate the first weight of each atomic capability according to the combination times of each atomic capability. It should be noted that when new historical data arrives later, the embodiments of the present invention only need to modify the weights for different combinations, and real-time learning can be achieved.

[0065] In yet another preferred embodiment, the extracting of the matching atomic capabilities from the atomic capability recommendation set according to the scenario card editing request specifically includes:

[0066] Extract the atomic capabilities with the first weight greater than the first threshold from the atomic capability recommendation set according to the scenario card editing request, and send the atomic capabilities in descending order of the weight.

[0067] Specifically, when the user edits the scenario card, the atomic capabilities with the first weight greater than the first threshold are extracted from the atomic capability recommendation set according to the user's scenario card editing request, and the atomic capabilities are sent to the user in descending order of weight for the user to select. In this way, the user can quickly select the atomic capabilities with a high matching rate, effectively improving the user experience.

[0068] In yet another preferred embodiment, the atomic capability recommendation set further includes a scenario card template. Extracting the matching atomic capabilities from the atomic capability recommendation set according to the scenario card editing request specifically includes:

[0069] Extracting the matching atomic capabilities from the atomic capability recommendation set according to the scenario card editing request; or,

[0070] Extracting the matching scenario card template from the atomic capability recommendation set according to the scenario card editing request; or,

[0071] Extracting the matching atomic capabilities and scenario card template from the atomic capability recommendation set according to the scenario card editing request;

[0072] Wherein, the scenario card template includes multiple atomic capabilities.

[0073] Specifically, in the embodiment of the present invention, the atomic capability recommendation set further includes a scenario card template. When the user edits the scenario card, the matching atomic capabilities can be extracted from the atomic capability recommendation set only according to the user's scenario card editing request, or the matching scenario card template can be extracted from the atomic capability recommendation set only according to the user's scenario card editing request, or the matching atomic capabilities and scenario card template can be extracted from the atomic capability recommendation set at the same time according to the user's scenario card editing request for the user to select. Exemplarily, when the first atomic capability appears in the user's scenario card editing request, there will be recommendations of subsequent atomic capabilities (single or multiple) matching this atomic capability, and there may also be recommendations of subsequent scenario card templates (sets of atomic capabilities) based on this atomic capability. It should be noted that the set of atomic capabilities in this scenario card template has been used before. When the user receives the recommendation of this scenario card template, the scenario card template can be directly used. In addition, the atomic capabilities in the user's scenario card editing request may or may not be included in this scenario card template.

[0074] In yet another preferred embodiment, the learning of the configuration information through the preset learning rule specifically includes:

[0075] According to the scenario card type and the scenario card template ID, obtain the first number of times each scenario card template is used as the mother template and the second number of times it is used as the sub template;

[0076] Calculate a second weight for each of the scenario card templates for use as a master template based on the first number and the second number.

[0077] In yet another preferred embodiment, the extracting of the matching scenario card templates from the atomic capability recommendation set according to the scenario card editing request specifically includes:

[0078] Extract scenario card templates from the atomic capability recommendation set with a second weight greater than a second threshold according to the scenario card editing request as candidate scenario card templates;

[0079] Calculate the similarity between the scenario card editing request and the candidate scenario card templates, and select the candidate scenario card template with the highest similarity as the target scenario card template.

[0080] Specifically, in the embodiments of the present invention, each scenario card can be used as a master template or as a sub-template. In the embodiments of the present invention, according to the scenario card type and the scenario card template ID, the first number of times each scenario card template is used as a master template and the second number of times it is used as a sub-template are obtained. Then, based on the first number of times used as a master template and the second number of times used as a sub-template, the second weight for each scenario card template for use as a master template is calculated. Exemplarily, the second weight = the first number / (the first number + the second number). When the user edits a scenario card, scenario card templates with a second weight greater than the second threshold are extracted from the atomic capability recommendation set according to the user's scenario card editing request as candidate scenario card templates. Then, the similarity between the atomic capabilities selected by the user when editing the scenario card and the candidate scenario card templates is calculated, and the candidate scenario card template with the highest similarity is selected as the target scenario card template and sent to the user for selection, so that the user can quickly select a suitable scenario card template, effectively improving the user experience.

[0081] Exemplarily, please refer to Figure 3 , Figure 3 which is a schematic diagram of a recommendation interface in a vehicle atomic capability recommendation method provided by the present invention. As Figure 3 shown, when the user creates a scenario card and selects the atomic capability of air conditioning, through the continuous learning model, it is found that the three atomic capabilities of window position, door, and seat ventilation are used most frequently in combination with air conditioning, so these three atomic capabilities can be recommended to the user.

[0082] Correspondingly, the present invention also provides a vehicle atomic capability recommendation device, which can implement all the processes of the vehicle atomic capability recommendation method in the above embodiments.

[0083] Please refer to Figure 4 , Figure 4This is a schematic structural diagram of a preferred embodiment of a vehicle atomic capability recommendation device provided by the present invention. The vehicle atomic capability recommendation device includes:

[0084] An acquisition module 401, configured to acquire historical data of a user editing a scenario card;

[0085] A learning module 402, configured to input the historical data into a preset continuous learning model to obtain an atomic capability recommendation set output by the continuous learning model;

[0086] A recommendation module 403, configured to respond to a user's scenario card editing request and extract matching atomic capabilities from the atomic capability recommendation set according to the scenario card editing request.

[0087] Preferably, the acquisition module 401 is specifically configured to:

[0088] Acquire historical data of a user editing a scenario card through a vehicle terminal, an APP terminal, and a WEB terminal, and report the historical data to the cloud, so that the cloud uniformly processes the historical data through data buried points; wherein, the historical data includes user behavior, operation time, and operation content.

[0089] Preferably, the learning module 402 specifically includes:

[0090] An analysis unit 412, configured to analyze the historical data to obtain configuration information; wherein, the configuration information includes a trigger atom, a condition atom, a function atom, a scenario card type, a scenario card template ID, and a data source;

[0091] A learning unit 422, configured to input the configuration information into the continuous learning model, and learn the configuration information through a preset learning rule to obtain an atomic capability recommendation set.

[0092] Preferably, the device is further configured to:

[0093] Acquire historical data of a user editing a scenario card in different vehicle models;

[0094] Perform granularity subdivision on the historical data of different vehicle models, and input the subdivided data into a preset continuous learning model.

[0095] Preferably, the learning of the configuration information through a preset learning rule specifically includes:

[0096] Learn the combined collocation of each atomic capability according to the trigger atom, the condition atom, and the function atom, and calculate a first weight of each atomic capability according to the combination times of each atomic capability.

[0097] Preferably, extracting the matching atomic capabilities from the atomic capability recommendation set according to the scenario card editing request specifically includes:

[0098] Extracting the atomic capabilities with the first weight greater than the first threshold from the atomic capability recommendation set according to the scenario card editing request, and sending the atomic capabilities in descending order of the weight.

[0099] Preferably, the atomic capability recommendation set further includes scenario card templates, and the apparatus is further configured to:

[0100] Obtaining the first number of times each scenario card template is used as a mother template and the second number of times it is used as a child template according to the scenario card type and the scenario card template ID;

[0101] Calculating the second weight of each scenario card template used as a mother template according to the first number of times and the second number of times;

[0102] Extracting the scenario card templates with the second weight greater than the second threshold from the atomic capability recommendation set according to the scenario card editing request as candidate scenario card templates;

[0103] Calculating the similarity between the scenario card editing request and the candidate scenario card templates, and selecting the candidate scenario card template with the highest similarity as the target scenario card template.

[0104] In specific implementation, the working principle, control process and achieved technical effects of the vehicle atomic capability recommendation apparatus provided by the embodiments of the present invention are correspondingly the same as those of the vehicle atomic capability recommendation method in the above embodiments, and will not be elaborated herein.

[0105] Please refer to Figure 5 , Figure 5 which is a schematic structural diagram of a preferred embodiment of a terminal device provided by the present invention. The terminal device includes a processor 501, a memory 502, and a computer program stored in the memory 502 and configured to be executed by the processor 501. When the processor 501 executes the computer program, it implements the vehicle atomic capability recommendation method described in any of the above embodiments.

[0106] Preferably, the computer program can be divided into one or more modules / units (such as computer program 1, computer program 2,...). The one or more modules / units are stored in the memory 502 and executed by the processor 501 to complete the present invention. The one or more modules / units can be a series of computer program instruction segments capable of performing specific functions, and these instruction segments are used to describe the execution process of the computer program in the terminal device.

[0107] The processor 501 may be a Central Processing Unit (CPU), or may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor, or the processor 501 may also be any conventional processor. The processor 501 is the control center of the terminal device and connects various parts of the terminal device through various interfaces and lines.

[0108] The memory 502 mainly includes a program storage area and a data storage area. Among them, the program storage area can store an operating system, application programs required for at least one function, etc., and the data storage area can store relevant data, etc. In addition, the memory 502 may be a high-speed random access memory, or may also be a non-volatile memory, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc., or the memory 502 may also be other volatile solid-state storage devices.

[0109] It should be noted that the above terminal device may include, but is not limited to, a processor and a memory. Those skilled in the art can understand that Figure 5 the structural schematic diagram is only an example of the above terminal device and does not limit the above terminal device. It may include more or fewer components than shown in the figure, or combine some components, or different components.

[0110] An embodiment of the present invention also provides a computer-readable storage medium. The computer-readable storage medium includes a stored computer program. Among them, when the computer program runs, it controls the device where the computer-readable storage medium is located to execute the vehicle atomic capability recommendation method described in any one of the above embodiments.

[0111] An embodiment of the present invention provides a method, device, equipment and storage medium for recommending atomic capabilities of a vehicle. By obtaining historical data of a user editing a scenario card; inputting the historical data into a preset continuous learning model to obtain an atomic capability recommendation set output by the continuous learning model; and in response to a scenario card editing request of the user, extracting a matching atomic capability or scenario card template from the atomic capability recommendation set according to the scenario card editing request. The embodiment of the present invention uses a continuous learning method to analyze the operation behavior of the user on the scenario card, and recommends atomic capabilities with a high matching rate or appropriate scenario card templates for the user when editing the scenario card, thereby effectively improving the user experience.

[0112] It should be noted that the system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated. The components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. In addition, in the drawings of the system embodiments provided by the present invention, the connection relationship between the modules indicates that they have a communication connection, which can be specifically implemented as one or more communication buses or signal lines. Those of ordinary skill in the art can understand and implement it without creative efforts.

[0113] The above is the preferred embodiment of the present invention. It should be pointed out that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and refinements can be made, and these improvements and refinements are also regarded as the protection scope of the present invention.

Claims

1. A vehicle atomic capability recommendation method, characterized in that, Including: Obtaining historical data of the user's edited scenario card; Inputting the historical data into a preset continuous learning model to obtain an atomic capability recommendation set output by the continuous learning model; Responding to the user's scenario card editing request and extracting matching atomic capabilities from the atomic capability recommendation set according to the scenario card editing request.

2. The vehicle atomic capability recommendation method according to claim 1, characterized in that The obtaining of the historical data of the user's edited scenario card specifically includes: Obtaining historical data of the user's edited scenario card through the vehicle end, the APP end, and the WEB end, and reporting the historical data to the cloud so that the cloud uniformly processes the historical data through data logging; wherein, the historical data includes user behavior, operation time, and operation content.

3. The vehicle atomic capability recommendation method according to claim 2, wherein The inputting of the historical data into a preset continuous learning model to obtain an atomic capability recommendation set output by the continuous learning model specifically includes: Parsing the historical data to obtain configuration information; wherein, the configuration information includes trigger atoms, condition atoms, function atoms, scenario card types, scenario card template IDs, and data sources; Inputting the configuration information into the continuous learning model and learning the configuration information through preset learning rules to obtain an atomic capability recommendation set.

4. The vehicle atomic capability recommendation method according to claim 3, wherein The method further includes: Obtaining historical data of the user's edited scenario card in different vehicle models; Subdividing the historical data of different vehicle models by granularity and inputting the subdivided data into a preset continuous learning model.

5. The vehicle atomic capability recommendation method according to claim 3 or 4, characterized in that The learning of the configuration information through preset learning rules specifically includes: Learning the combined collocations of each atomic capability according to the trigger atoms, the condition atoms, and the function atoms, and calculating the first weight of each atomic capability according to the combination times of each atomic capability.

6. The vehicle atomic capability recommendation method according to claim 5, wherein The extracting of the matching atomic capabilities from the atomic capability recommendation set according to the scenario card editing request specifically includes: Extracting the atomic capabilities with the first weight greater than a first threshold from the atomic capability recommendation set according to the scenario card editing request, and sending down the atomic capabilities in descending order of the weight.

7. The vehicle atomic capability recommendation method according to claim 3 or 4, characterized in that If the atomic capability recommendation set further includes scenario card templates, then the extracting of the matching atomic capabilities from the atomic capability recommendation set according to the scenario card editing request specifically includes: Extracting the matching atomic capabilities from the atomic capability recommendation set according to the scenario card editing request; or, Extracting the matching scenario card templates from the atomic capability recommendation set according to the scenario card editing request; or, Extracting the matching atomic capabilities and scenario card templates from the atomic capability recommendation set according to the scenario card editing request; wherein, the scenario card template includes multiple atomic capabilities.

8. The vehicle atomic capability recommendation method according to claim 7, wherein The learning of the configuration information through preset learning rules specifically includes: Obtaining the first number of times each scenario card template is used as a parent template and the second number of times it is used as a sub-template according to the scenario card type and the scenario card template ID; Calculating the second weight of each scenario card template used as a parent template according to the first number of times and the second number of times.

9. The vehicle atomic capability recommendation method according to claim 8, wherein, Extracting a matching scenario card template from the atomic capability recommendation set according to the scenario card editing request specifically includes: Extracting a scenario card template with a second weight greater than a second threshold from the atomic capability recommendation set according to the scenario card editing request as a candidate scenario card template; Calculating the similarity between the scenario card editing request and the candidate scenario card template, and selecting the candidate scenario card template with the highest similarity as the target scenario card template.

10. A vehicle atomic capability recommendation device, characterized in that, It includes: An acquisition module for acquiring historical data of a user editing a scenario card; A learning module for inputting the historical data into a preset continuous learning model to obtain an atomic capability recommendation set output by the continuous learning model; A recommendation module for responding to a user's scenario card editing request and extracting a matching atomic capability from the atomic capability recommendation set according to the scenario card editing request.

11. A terminal device, characterized in that, It includes a processor and a memory, and a computer program is stored in the memory, and the computer program is configured to be executed by the processor. When the processor executes the computer program, the vehicle atomic capability recommendation method described in any one of claims 1 to 9 is implemented.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program. When the device where the computer-readable storage medium is located executes the computer program, the vehicle atomic capability recommendation method described in any one of claims 1 to 9 is implemented.

Images