Data storage method and vehicle

Abstract

The present disclosure relates to the technical field of intelligent cockpit, and provides a data storage method and a vehicle, which solve the technical problem of low reuse rate of general data in different scenarios. The method comprises: receiving to-be-stored data sent by a terminal device, determining a running scenario corresponding to the terminal device, and determining a target independent storage area corresponding to the running scenario from a plurality of independent storage areas; dividing the to-be-stored data into a plurality of data segments, determining a target attribute feature of each data segment, and determining a data type of each data segment according to the target attribute feature; in response to the target attribute feature not satisfying a preset determination condition, determining the data type of each data segment by using a pre-trained data classification model; storing a data segment of a user type data type to a general storage area; and / or storing a data segment of a scene type data type to the target independent storage area. In this way, the reuse rate of general data in the general storage area can be improved.

Description

Technical Field

[0001] This disclosure relates to the field of intelligent cockpit technology, and more particularly to a data storage method and a vehicle. Background Technology

[0002] With the development of the automotive industry, vehicle models can be equipped with model processing platforms to process large model data. These platforms can also store data from multiple scenarios. However, storing data from different scenarios in the same area can lead to low reuse rates of general data across different scenarios.

[0003] In view of this, how to improve the reuse rate of general data in different scenarios has become an urgent technical problem to be solved. Summary of the Invention

[0004] In view of this, the purpose of this disclosure is to propose a data storage method and a vehicle to improve the reusability of general data in different scenarios.

[0005] Based on the above objectives, the first aspect of this disclosure proposes a data storage method applied to a model processing platform, the model processing platform comprising: a general storage area and multiple independent storage areas; the method comprising:

[0006] Upon receiving data to be stored from a terminal device, the system determines the operating scenario corresponding to the terminal device and identifies the target independent storage area corresponding to the operating scenario from the multiple independent storage areas. The data to be stored is divided into multiple data segments, the target attribute features of each data segment are determined, and the data type of each data segment is determined based on the target attribute features; In response to the target attribute feature not meeting the preset judgment condition, the data type of each data segment is determined using a pre-trained data classification model; wherein, the judgment condition is a pre-set condition for determining whether the target attribute feature can determine the data type. Store the data segment of type user to the general storage area; and / or, The data segment whose data type is scene type is stored in the target independent storage area.

[0007] Based on the same inventive concept, a second aspect of this disclosure proposes a vehicle including electronic equipment, the electronic equipment including a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the program to implement the method described in the first aspect.

[0008] As can be seen from the above, the data storage method and vehicle provided in this disclosure are as follows: Upon receiving data to be stored from a terminal device, the operating scenario corresponding to the terminal device is determined, and a target independent storage area corresponding to the operating scenario is determined from multiple independent storage areas. The data to be stored is divided into multiple data segments, and the target attribute characteristics of each data segment are determined. The data type of each data segment is determined based on the target attribute characteristics. When the target attribute characteristics do not meet the preset judgment conditions, it indicates that the data type of the current data segment cannot be accurately determined based on the target attribute characteristics. In this case, a pre-trained data classification model is used to determine the data type of each data segment, avoiding the problem of inaccurate data type determination due to directly determining the data type based on the target attribute characteristics. Data segments with user data type are stored in a general storage area. User-type data segments are general data under multiple operating scenarios, improving the reusability of general data. General data in the general storage area can be directly accessed and reused in all operating scenarios, thereby reducing the repeated collection and storage of general data. Data segments with scenario data type are stored in a target independent storage area. Scenario-type data segments are scenario data related to the corresponding operating scenario. Scenario data can be stored in different independent storage areas under different operating scenarios, improving the isolation and security between scenario data under different operating scenarios. Attached Figure Description

[0009] To more clearly illustrate the technical solutions in this disclosure or related technologies, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the accompanying drawings described below are only embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0010] Figure 1 This is a schematic diagram of the data storage system according to an embodiment of the present disclosure; Figure 2 This is a flowchart of a data storage method according to an embodiment of the present disclosure; Figure 3 This is a schematic diagram of the structure of a data storage system based on multiple operating scenarios according to an embodiment of this disclosure; Figure 4 This is a schematic diagram of the structure of a data storage device according to an embodiment of the present disclosure; Figure 5 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present disclosure. Detailed Implementation

[0011] To make the objectives, technical solutions, and advantages of this disclosure clearer, the following detailed description is provided in conjunction with specific embodiments and the accompanying drawings.

[0012] It should be noted that, unless otherwise defined, the technical or scientific terms used in the embodiments of this disclosure should have the ordinary meaning understood by one of ordinary skill in the art to which this disclosure pertains. The terms "first," "second," and similar terms used in the embodiments of this disclosure do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element or object preceding the word encompasses the elements or objects listed following the word and their equivalents, without excluding other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. Terms such as "upper," "lower," "left," and "right" are used only to indicate relative positional relationships; when the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0013] The following are definitions of terms used in this disclosure: Model processing platform: The model processing platform is an optional in-vehicle intelligent edge computing box (Artificial Intelligence Box, or AI Box) used to process large model data on the vehicle.

[0014] Head Unit System (HUT): The head unit system is the core multimedia control device of the vehicle's center console.

[0015] Based on the background technology description, a model processing platform (AI BOX) can be optionally installed on the vehicle. The model processing platform (AI BOX) is an edge computing extension device (incremental computing power platform) designed for the vehicle's smart cockpit. It mainly solves the problem of insufficient artificial intelligence (AI) computing power in the onboard host system (HUT). Without changing the hardware of the onboard host system (HUT), it connects to an independent model processing platform (AI BOX) via Ethernet or other means to support the processing of large model data.

[0016] The demand for artificial intelligence (AI) is booming, with related needs appearing in various scenarios such as cars, homes, and mobile phones. However, using AI services from public clouds faces issues such as high costs for authentication tokens and concerns about data privacy. Personal private devices like model processing platforms (AI BOX) can better solve these problems.

[0017] Users have artificial intelligence (AI) needs across all scenarios. These needs are both common and somewhat different across different scenarios. However, the current in-vehicle model processing platform (AI BOX) is in its early stages and is mainly used in in-vehicle scenarios. It has not been optimized for services across all scenarios.

[0018] Meanwhile, the storage method of the model processing platform (AI BOX) has the following defects: user data is stored in a mixed manner across different terminal devices and different usage scenarios, making it impossible to distinguish between the user's general preferences throughout the entire life cycle, the basic data that remains unchanged across scenarios, and the personalized data specific to a single scenario; there are problems such as low cross-scenario data reuse rate, redundant storage of duplicate data, fragmented memory when switching scenarios, poor isolation of privacy data, and waste of resources for repeated computation of model inference, making it impossible to achieve the dual requirements of reusing general user data across all scenarios and independently isolating and storing data in a single scenario.

[0019] As mentioned above, how to improve the reusability of general data in different scenarios has become an important research question.

[0020] Figure 1 This is a schematic diagram of the data storage system according to an embodiment of the present disclosure. Figure 1 As shown, the data storage system 100 may include a terminal device 110 and a model processing platform 120. A medium (e.g., a network) may be provided between the terminal device 110 and the model processing platform 120 to create a communication link. This network may include various connection types, such as wired, wireless communication links, or fiber optic cables, etc.

[0021] The terminal device 110 here can be either hardware or software. When the terminal device 110 is hardware, it can be various electronic devices with a display screen, including but not limited to smartphones, tablets, vehicle terminal equipment, e-book readers, MP3 players, laptops, and desktop computers (PCs). When the terminal device 110 is software, it can be installed in the electronic devices listed above. It can be implemented as multiple software programs or software modules (e.g., to provide distributed services) or as a single software program or software module. No specific limitations are made here.

[0022] It should be noted that the data storage method provided in this embodiment can be executed by the model processing platform 120. It should be understood that... Figure 1 The number of terminal devices shown is merely illustrative. Depending on implementation needs, any number of terminal devices can be used.

[0023] This disclosure is combined with the following Figure 1 The above application scenarios are used to describe the data storage method according to exemplary embodiments of this disclosure. It should be noted that the above application scenarios are shown only to facilitate understanding of the spirit and principles of this disclosure, and the embodiments of this disclosure are not limited in any way. Rather, the embodiments of this disclosure can be applied to any applicable scenario.

[0024] Based on the above description, such as Figure 2As shown, the data storage method proposed in this embodiment is applied to a model processing platform, which includes a general storage area and multiple independent storage areas; the method includes: Step 201: Receive the data to be stored from the terminal device, determine the operating scenario corresponding to the terminal device, and determine the target independent storage area corresponding to the operating scenario from the multiple independent storage areas.

[0025] In practical implementation, the model processing platform (AI BOX) can be an optional in-vehicle intelligent edge computing box. The model processing platform (AI BOX) includes a general storage area and multiple independent storage areas. The general storage area and multiple independent storage areas can be storage areas in the memory of the model processor (AI BOX). The memory can be Universal Flash Storage (UFS) or Embedded MultiMedia Card (EMMC), etc., which are memory that will not lose data after the vehicle is powered off.

[0026] Data to be stored from different terminal devices will be stored in different independent storage areas. For example, multiple independent storage areas include: vehicle storage area, mobile storage area, home storage area, and office storage area.

[0027] When data to be stored is received from the vehicle head unit (HUT), the corresponding vehicle operation scenario is determined, and the corresponding target independent storage area is designated as the vehicle storage area. When data to be stored is received from a mobile terminal device, the corresponding mobile operation scenario is determined, and the corresponding target independent storage area is designated as the mobile storage area. When data to be stored is received from a home terminal device, the corresponding home operation scenario is determined, and the corresponding target independent storage area is designated as the home storage area. When data to be stored is received from an office mobile device, the corresponding office operation scenario is determined, and the corresponding target independent storage area is designated as the office storage area.

[0028] In addition, when a new terminal device sends data to be stored to the model processor (AI BOX), a new independent storage area can be created in the model processor (AI BOX) to store the data sent by the new terminal device.

[0029] Step 202: Divide the data to be stored into multiple data segments, determine the target attribute features of each data segment, and determine the data type of each data segment based on the target attribute features.

[0030] In practice, the data to be stored includes multiple data segments. By dividing the data into multiple segments, data segments of different data types can be classified and stored. Among them, the target attribute features include: person identification features and terminal device features.

[0031] Specifically, the data type of each data segment is determined sequentially, thereby achieving categorized storage of each data segment. For the current data segment among multiple data segments, the target attribute characteristics of the current data segment are determined.

[0032] Step 203: In response to the target attribute feature not meeting the preset judgment condition, the data type of each data segment is determined using a pre-trained data classification model; wherein, the judgment condition is a pre-set condition for determining whether the target attribute feature can determine the data type.

[0033] In practice, the judgment condition is a pre-set condition used to determine whether the target attribute features can determine the data type. When the target attribute features do not meet the pre-set judgment condition, it means that the data type of the current data segment cannot be accurately determined based on the target attribute features. In this case, a pre-trained data classification model is used to determine the data type of the current data segment.

[0034] For example, if the data to be stored is "User A habitually sets the air conditioning temperature to 24℃ in the vehicle cabin", and the data segments include "User A" and "Air conditioning temperature 24℃", then the data type of the data segment "User A" is determined to be user type, and the data type of the data segment "Air conditioning temperature 24℃" is determined to be data type.

[0035] Step 204: Store the data segment of type user to the general storage area.

[0036] In practice, the user-type data segment can be data that remains fixed throughout the user's entire lifecycle and across all operating scenarios, does not change with switching of terminal devices / operating scenarios, and is universally reusable across all operating scenarios. The user-type data segment includes at least one of the following: basic user data, global attribute data, general preference data, and global event data.

[0037] For example, in the data segments "User A" and "Air Conditioner Temperature 24℃", the data segment "User A" is a general data related to the user that remains unchanged in all operating scenarios. Therefore, the user-type data segment "User A" is stored in the general storage area to facilitate the reuse of this general data "User A" in the future.

[0038] And / or, in step 205, store the data segment whose data type is scene type to the target independent storage area.

[0039] In practice, scenario-type data segments can be data generated only within a single operating scenario, adapted only to the corresponding operating scenario, and changing with the operating scenario. Scenario-type data segments include at least one of the following: data collected by terminal devices, scenario-specific behavioral habits, scenario-specific inference results, and scenario-bound personalized data.

[0040] For example, in the data segments "User A" and "Air Conditioner Temperature 24℃", the data segment "Air Conditioner Temperature 24℃" is scene data related to the vehicle operation scenario. Therefore, the scene type data segment "Air Conditioner Temperature 24℃" is stored in the target independent storage area, and the scene data "Air Conditioner Temperature 24℃" can only be called under the same operation scenario.

[0041] Through the above embodiments, data to be stored is received from a terminal device, the corresponding operating scenario of the terminal device is determined, and a target independent storage area corresponding to the operating scenario is determined from multiple independent storage areas. The data to be stored is divided into multiple data segments, and the target attribute features of each data segment are determined. The data type of each data segment is determined based on the target attribute features. When the target attribute features do not meet the preset judgment conditions, it means that the data type of the current data segment cannot be accurately determined based on the target attribute features. In this case, a pre-trained data classification model is used to determine the data type of each data segment, avoiding the problem of inaccurate data type determination caused by directly determining the data type based on the target attribute features. Data segments with user data type are stored in a general storage area. User data segments are general data under multiple operating scenarios, improving the reusability of general data. General data in the general storage area can be directly accessed and reused in all operating scenarios, thereby reducing the repeated collection and storage of general data. Data segments with scenario data type are stored in a target independent storage area. Scenario data segments are scenario data related to the corresponding operating scenario. Storing scenario data under different operating scenarios into different independent storage areas can improve the isolation and security between scenario data under different operating scenarios.

[0042] In some embodiments, step 202 includes: Step 2031: Determine the target confidence level of the target attribute features for each data segment.

[0043] In practice, the target confidence level is a parameter used to represent the accuracy of the target attribute features. The preset judgment condition can be that the target confidence level is greater than or equal to a preset confidence threshold.

[0044] Specifically, the data type of each data segment is determined sequentially, thereby achieving categorized storage of each data segment. For the current data segment among multiple data segments, a target confidence level for the current data segment is determined, so that the data type determination method for the current data segment can be selected based on the target confidence level.

[0045] When the target confidence level is greater than or equal to the preset confidence level threshold, it means that the data type of the current data segment can be accurately determined based on the target attribute characteristics, and the data type of the current data segment is determined based on the target attribute characteristics.

[0046] For example, if the preset confidence threshold is 0.8 and the target confidence of the target attribute feature of the current data segment is 0.9, then the data type of the current data segment is determined based on the target attribute feature.

[0047] Step 2032: In response to the target confidence level being less than a preset confidence threshold, the data type of each data segment is determined using a pre-trained data classification model.

[0048] In practice, when the target confidence level is less than the preset confidence level threshold, it means that the data type of the current data segment cannot be accurately determined based on the target attribute characteristics. In this case, the data type of the current data segment is determined by using a pre-trained data classification model.

[0049] For example, if the preset confidence threshold is 0.8 and the target confidence of the target attribute feature of the current data segment is 0.6, then the data type of the current data segment can be determined using a pre-trained data classification model.

[0050] The above scheme determines the target confidence level of the target attribute features for each data segment. When the target confidence level is less than a preset confidence threshold, a pre-trained data classification model is used to determine the data type of each data segment. This approach ensures that the target confidence level accurately determines the target attribute features. When the target confidence level is less than the preset confidence threshold, it indicates that the data type of the current data segment cannot be accurately determined based on the target attribute features. In this case, the pre-trained data classification model is used to determine the data type of the current data segment, avoiding the problem of inaccurate data type determination caused by directly relying on target attribute features.

[0051] In some embodiments, step 2031 includes: Step 2031A: Extract keywords from each data segment and determine the matching confidence between the target attribute feature and the keywords.

[0052] In practice, matching confidence refers to the degree of matching between the target attribute features and the keywords in the data segment. Specifically, for the current data segment among multiple data segments, keywords are extracted from the current data segment; the similarity between the target data features and the keywords is determined, and the similarity is mapped to a preset range to obtain the matching confidence.

[0053] For example, if the current data segment is "air conditioner temperature 24℃" and the target attribute feature is the terminal device feature, the keyword "air conditioner" is extracted from the current data segment, and the matching confidence between the target attribute feature and the keyword "air conditioner" is determined.

[0054] Step 2031B: Determine the historical data segments that match each data segment and the historical attribute features corresponding to the historical data segments from the pre-stored database, and determine the consistency confidence between the target attribute features and the historical attribute features.

[0055] In practical implementation, consistency confidence refers to the degree of consistency between the target attribute feature and similar historical attribute features. Specifically, for the current data segment among multiple data segments, historical data segments matching the current data segment and the corresponding historical attribute features are determined from a pre-stored database; it is then determined whether the target attribute feature and the historical attribute feature are consistent; if the target attribute feature and the historical attribute feature are consistent, a first pre-set confidence level is used as the consistency confidence level; if the target attribute feature and the historical attribute feature are inconsistent, a second pre-set confidence level is used as the consistency confidence level; wherein, the first pre-set confidence level is greater than the second pre-set confidence level.

[0056] The database stores the mapping relationship between historical data segments and historical attribute features. For example, the mapping relationship stored in the database includes: the historical attribute feature corresponding to the historical data segments "User A" and "User B" is the person identification feature, and the historical attribute feature corresponding to the historical data segments "Air Conditioner Temperature 22℃" and "Air Conditioner Temperature 25℃" is the terminal device feature.

[0057] For example, the current data segment is "air conditioner temperature 24℃", the target attribute feature is the terminal device feature, the first preset confidence level is 0.8, and the second preset confidence level is 0.5. From the pre-stored database, a historical data segment "air conditioner temperature 22℃" is determined to match the current data segment. The historical attribute feature corresponding to the historical data segment "air conditioner temperature 22℃" is determined to be the terminal device feature. Since the target attribute feature and the historical attribute feature are consistent (both are terminal device features), the consistency confidence level between the target attribute feature and the historical attribute feature is determined to be 0.8.

[0058] Step 2031C: Determine the context information of the keyword from each data segment, and determine the context confidence between the target attribute feature and the context information.

[0059] In practice, contextual confidence refers to the degree of matching between the target attribute features and the contextual information of keywords in the data segment. Specifically, for the current data segment among multiple data segments, the contextual information of keywords is extracted from the current data segment; the relevance between the target data features and the contextual information is determined, and the relevance is mapped to a preset range to obtain the contextual confidence.

[0060] For example, if the current data segment is "air conditioner temperature 24℃" and the target attribute feature is the terminal device feature, the context information "temperature" is extracted from the current data segment, and the context confidence between the target attribute feature and the context information "temperature" is determined.

[0061] Step 2031D: The matching confidence, the consistency confidence, and the context confidence are weighted to obtain the target confidence of the target attribute feature.

[0062] In practice, the matching confidence, consistency confidence, and context confidence are weighted to obtain the target confidence of the target attribute feature. ,in, For target confidence level, As the first weighting coefficient, To match confidence levels, This is the second weighting coefficient. For consistency confidence, This is the third weighting coefficient. Contextual confidence.

[0063] The above scheme extracts keywords from each data segment and determines the matching confidence between the target attribute feature and the keywords. Historical data segments matching each data segment and their corresponding historical attribute features are determined from a pre-stored database, and the consistency confidence between the target attribute feature and the historical attribute features is determined. Contextual information of the keywords is determined from each data segment, and the contextual confidence between the target attribute feature and the contextual information is determined. The matching confidence, consistency confidence, and contextual confidence are weighted to obtain the target confidence of the target attribute feature. In this way, the target confidence comprehensively considers the matching confidence, consistency confidence, and contextual confidence of the target attribute feature, making the target confidence more accurate. Based on the target confidence, the accuracy of the target attribute feature can be determined, and thus, the data type determination method can be accurately selected.

[0064] In some embodiments, step 202 includes: Step 202A: Determine whether the target attribute features of each data segment match the preset character identifier features.

[0065] In practice, for the current data segment among multiple data segments, the data type of the current data segment is determined to be user type by judging whether the target attribute features of the current data segment match the preset character identification features.

[0066] Step 202B: In response to the target attribute feature matching the preset character identifier feature, the data type of each data segment is determined to be user type.

[0067] In practice, for the current data segment among multiple data segments, if the target attribute features match the preset character identifier features, then the data type of the current data segment is determined to be user type.

[0068] The preset character identification features include at least one of the following: character identity features, cross-scene features, terminal-independent features, relationship matching features, user preference features, and general tag features.

[0069] Specifically, the system sequentially checks whether the target attribute features of the current data segment match the following features: person identity, cross-scene, terminal-independent, relationship matching, user preference, and general tag features. If the target attribute features match any one of these features, the data type of the current data segment is determined to be user type. If the target attribute features do not match any of these features, the system determines whether the data type of the current data segment is scene type.

[0070] Step 202C: Determine whether the target attribute features of each data segment match the preset terminal device features.

[0071] In practice, for the current data segment among multiple data segments, the data type of the current data segment is determined to be a scenario type by judging whether the target attribute characteristics of the current data segment match the preset terminal device characteristics.

[0072] Step 202D: In response to the target attribute feature matching the preset terminal device feature, the data type of each data segment is determined to be a scene type.

[0073] In practice, for the current data segment among multiple data segments, if the target attribute features match the preset terminal device features, then the data type of the current data segment is determined to be a scene type.

[0074] The preset terminal device features include at least one of the following: terminal collection features, environmental data features, device binding features, interaction mode features, spatiotemporal constraint features, and semantic scene features.

[0075] Specifically, the system sequentially determines whether the target attribute features of the current data segment match the terminal acquisition features, environmental data features, device binding features, interaction mode features, spatiotemporal constraint features, and semantic scene features. If the target attribute features match any one of these features, the data type of the current data segment is determined to be a scene type. If the target attribute features do not match any of these features, the system determines whether the data type of the current data segment is a user type.

[0076] The above method determines whether the target attribute features of each data segment match preset character identifier features. If the target attribute features match the preset character identifier features, the data type of each data segment is determined to be user type. Thus, by determining whether the target attribute features match the preset character identifier features, the data type of each data segment can be quickly and accurately determined. Similarly, the method determines whether the target attribute features of each data segment match preset terminal device features. If the target attribute features match the preset terminal device features, the data type of each data segment is determined to be scene type. This method also allows for quick and accurate determination of the data type of each data segment.

[0077] In some embodiments, step 203 includes: Step 203A: Using a pre-trained data classification model, determine the correlation between each data segment and the running scenario.

[0078] In practice, for the current data segment among multiple data segments, a pre-trained data classification model is used to determine the correlation between the current data segment and the running scenario. This correlation can be the semantic similarity between the current data segment and the running scenario.

[0079] Step 203B: In response to the correlation degree being less than a preset correlation threshold, the data type of each data segment is determined to be a user type.

[0080] In practice, for the current data segment among multiple data segments, if the correlation is less than the preset correlation threshold, it indicates that the correlation between the current data segment and the running scenario is low, and the data type of the current data segment is determined to be user type.

[0081] For example, the preset association threshold is 0.2. When the association degree is less than 0.2, it indicates that the association degree between the current data segment and the running scenario is low, and the data type of the current data segment is determined to be user type.

[0082] Alternatively, in step 203C, in response to the correlation degree being greater than or equal to a preset correlation threshold, the data type of each data segment is determined to be a scene type.

[0083] In practice, for the current data segment among multiple data segments, if the correlation degree is greater than or equal to the preset correlation threshold, it indicates that the correlation degree between the current data segment and the running scenario is high, and the data type of the current data segment is determined to be the scenario type.

[0084] For example, the preset association threshold is 0.2. When the association degree is greater than or equal to 0.2, it indicates that the association degree between the current data segment and the running scenario is high, and the data type of the current data segment is determined to be the scenario type.

[0085] The above approach utilizes a pre-trained data classification model to determine the correlation between each data segment and the operational scenario. When the correlation is less than a preset correlation threshold, the data type of each data segment is determined to be a user type. When the correlation is greater than or equal to the preset correlation threshold, the data type of each data segment is determined to be a scenario type. In this way, by using a pre-trained data classification model, the data type of each data segment can be determined more quickly and accurately, ensuring the accuracy of the data type for each segment.

[0086] In some embodiments, after step 205, the method further includes: Step 205A: Upon receiving update data from the terminal device, retrieve the stored data associated with the update data from the general storage area and the independent storage area.

[0087] In practice, when receiving updated data from a terminal device, since the general storage area and the independent storage area already contain associated stored data, it is necessary to determine whether to retain the previously stored data when classifying and storing the updated data. The previously stored data refers to data associated with the updated data but inconsistent with it, stored in the general storage area and the independent storage area.

[0088] For example, the updated data received by the model processing platform (AI BOX) is "User A habitually sets the air conditioning temperature to 26°C in the vehicle cabin", and the stored data retrieved from the general storage area and the independent storage area is "User A" and "Air conditioning temperature 24°C".

[0089] Step 205B: Determine whether the updated data and the stored data meet the consistency condition.

[0090] In practice, it is determined whether the updated data and the already stored data meet the consistency conditions, thereby determining whether to retain the already stored data when classifying and storing the updated data. The consistency conditions are pre-defined criteria used to determine whether there is a conflict between the updated data and the already stored data.

[0091] Step 205C: In response to the consistency condition between the updated data and the stored data, the updated data is stored in the general storage area and / or the independent storage area, and the stored data is deleted.

[0092] In practice, when the updated data and the already stored data meet the consistency condition, it indicates that the already stored data has become invalid. Therefore, when classifying and storing the updated data, the already stored data is not retained. This ensures that the data stored in the general storage area and / or independent storage area is the latest data sent by the terminal device, while deleting the already valid stored data reduces data storage pressure.

[0093] For example, the model processing platform (AI BOX) receives updated data stating "User A habitually sets the air conditioning temperature to 26℃ in the vehicle cabin," while the stored data is "User A" and "Air conditioning temperature 24℃." When the updated data and the stored data meet the consistency condition, it indicates that User A's habit of setting the air conditioning temperature has changed. In this case, the updated data is stored in the general storage area and / or the independent storage area, and the stored data is deleted.

[0094] Step 205D: In response to the lack of consistency between the updated data and the stored data, the updated data is stored in the general storage area and / or the independent storage area, and the stored data is retained.

[0095] In practice, when the updated data does not meet the consistency condition with the already stored data, it means that the already stored data is still valid. Therefore, when the updated data is categorized and stored, the already stored data is retained. This ensures that the data stored in the general storage area and / or independent storage area is the latest data sent from the terminal device, while retaining the still valid already stored data to avoid the loss of valid data.

[0096] For example, the model processing platform (AI BOX) receives updated data stating "User A habitually sets the air conditioning temperature to 26℃ in the vehicle cabin during winter," while the stored data includes "User A," "Summer," and "Air conditioning temperature 24℃." When the updated data and the stored data do not meet the consistency condition, indicating that User A's air conditioning temperature habits vary at different times, the updated data is stored in a general storage area and / or a separate storage area, while the stored data is retained.

[0097] The above scheme receives updated data from the terminal device and retrieves the associated stored data from the general storage area and the independent storage area. It then determines whether the updated data and the stored data meet the consistency requirements. If they do, the updated data is stored in the general storage area and / or the independent storage area, and the stored data is deleted. This ensures that the data stored in the general storage area and / or the independent storage area is the latest data from the terminal device, while deleting already effective stored data reduces data storage pressure. If the updated data and the stored data do not meet the consistency requirements, the updated data is stored in the general storage area and / or the independent storage area, while the stored data is retained. This ensures that the data stored in the general storage area and / or the independent storage area is the latest data from the terminal device, while retaining still valid stored data to prevent the loss of valid data.

[0098] In some embodiments, after step 205, the method further includes: Step 205a: Receive a data access request from the terminal device, determine the operating scenario corresponding to the terminal device, and determine the target independent storage area corresponding to the operating scenario.

[0099] In practice, when the model processing platform (AI BOX) receives a data request from a terminal device, it determines the operating scenario corresponding to the terminal device and the target independent storage area corresponding to that scenario. This ensures that multiple independent storage areas are isolated from each other, allowing the terminal device to accurately access data from both the general storage area and the corresponding target independent storage area, preventing data access issues across different operating scenarios.

[0100] For example, when the model processing platform (AI BOX) receives a data request from the vehicle host system (HUT), it determines the vehicle operation scenario corresponding to the HUT and the corresponding vehicle storage area. When the model processing platform (AI BOX) receives a data request from a mobile terminal device, it determines the mobile operation scenario corresponding to the mobile terminal device and the corresponding mobile storage area. When the model processing platform (AI BOX) receives a data request from a home terminal device, it determines the home operation scenario corresponding to the home terminal device and the corresponding home storage area. When the model processing platform (AI BOX) receives a data request from an office terminal device, it determines the office operation scenario corresponding to the office terminal device and the corresponding office storage area.

[0101] Step 205b: Retrieve user data from the general storage area and retrieve scene data from the target independent storage area.

[0102] In practice, when the target independent storage area is an in-vehicle storage area, user data is retrieved from the general storage area, and in-vehicle scene data is retrieved from the in-vehicle storage area. When the target independent storage area is a mobile storage area, user data is retrieved from the general storage area, and mobile scene data is retrieved from the mobile storage area. When the target independent storage area is a home storage area, user data is retrieved from the general storage area, and home scene data is retrieved from the home storage area. When the target independent storage area is an office storage area, user data is retrieved from the general storage area, and office scene data is retrieved from the office storage area.

[0103] For example, when it is recognized that user A gets into the car and turns on the air conditioner, the model processing platform (AI BOX) receives the air conditioner data call request from the vehicle host system (HUT). The model processing platform (AI BOX) calls the user data "user A" from the general storage area and the scene data "air conditioner temperature 24℃" from the vehicle storage area.

[0104] Step 205c: Determine control parameters based on the user data and the scene data, and send the control parameters to the terminal device.

[0105] In practice, the model processing platform (AI BOX) determines control parameters based on user data and scene data, and sends the control parameters to the terminal device. The terminal device then controls the operation of the corresponding functional modules based on the control parameters.

[0106] For example, user data is "User A", and scene data is "Air conditioning temperature 24℃". The model processing platform (AI BOX) generates the control parameter "Control the vehicle air conditioning temperature to 24℃" and sends the control parameter "to the vehicle host system (HUT). The vehicle host system (HUT) controls the air conditioning in the vehicle based on the control parameter "Control the vehicle air conditioning temperature to 24℃".

[0107] The above scheme receives data request requests from terminal devices, determines the corresponding operating scenario for the terminal device, and identifies the target independent storage area for that scenario. User data is retrieved from the general storage area, and scenario data is retrieved from the target independent storage area. Control parameters are determined based on the user data and scenario data and sent to the terminal device. In this way, multiple independent storage areas are isolated from each other, allowing the terminal device to accurately access data from both the general storage area and the corresponding target independent storage area, preventing data retrieval across operating scenarios.

[0108] In some embodiments, step 201 includes: Step 201A: Receive the data to be stored from the vehicle terminal device, determine the vehicle operation scenario corresponding to the vehicle terminal device, and determine the vehicle storage area corresponding to the vehicle operation scenario from the multiple independent storage areas.

[0109] In practice, Figure 3 This is a schematic diagram of the structure of a data storage system based on multiple operating scenarios according to an embodiment of this disclosure. For example... Figure 3 As shown, the data storage system based on multiple operating scenarios includes: vehicle cabin environment, mobile terminal devices, office terminal devices, and home terminal devices. The vehicle cabin environment includes: a model processing platform (AI BOX), an in-vehicle host system (HUT), and a vehicle networking system (Telematics BOX, or TBOX for short). The model processing platform (AI BOX) includes: an artificial intelligence (AI) communication architecture, a large model, and multiple storage areas. The AI ​​communication architecture is used for data transmission between the model processing platform (AIBOX) and the in-vehicle host system (HUT). The large model is used to process the data to be stored, and the multiple storage areas are used for classifying and storing the data to be stored.

[0110] Multiple storage areas include: a general storage area and independent storage areas. Independent storage areas include: an in-vehicle storage area, a mobile storage area, an office storage area, and a home storage area. The general storage area stores general user-related data for all operating scenarios; the in-vehicle storage area stores scenario data related to in-vehicle operation; the mobile storage area stores scenario data related to mobile operation; the office storage area stores scenario data related to office operation; and the home storage area stores scenario data related to home operation.

[0111] Specifically, the vehicle-mounted host system (HUT) collects data to be stored in the vehicle operation scenario and transmits the data to the model processing platform (AI BOX) via Ethernet. The model processing platform (AI BOX) extracts user data segments and vehicle scenario data segments from the data to be stored in the vehicle operation scenario, stores the user data segments in the general storage area, and stores the vehicle scenario data segments in the vehicle storage area.

[0112] Alternatively, in step 201B, the data to be stored sent by the mobile terminal device is received, the mobile operation scenario corresponding to the mobile terminal device is determined, and the mobile storage area corresponding to the mobile operation scenario is determined from the multiple independent storage areas.

[0113] In practice, mobile terminal devices collect data to be stored in mobile operation scenarios and transmit this data to the model processing platform (AI BOX) via the vehicle-to-everything (TBOX) system. The AI ​​BOX extracts user data segments and mobile scene data segments from the data to be stored in the mobile operation scenarios, storing the user data segments in a general storage area and the mobile scene data segments in a mobile storage area.

[0114] Alternatively, in step 201C, the data to be stored sent by the home terminal device is received, the home operation scenario corresponding to the home terminal device is determined, and the home storage area corresponding to the home operation scenario is determined from the multiple independent storage areas.

[0115] In practice, home terminal devices collect data to be stored in home operation scenarios and transmit this data to the model processing platform (AI BOX) via the vehicle-to-everything (TBOX) system. The AI ​​BOX extracts user data segments and office scene data segments from the data to be stored in office operation scenarios, storing the user data segments in the general storage area and the office scene data segments in the office storage area.

[0116] Alternatively, in step 201D, the data to be stored is received from the office terminal device, the office operation scenario corresponding to the office terminal device is determined, and the office storage area corresponding to the office operation scenario is determined from the multiple independent storage areas.

[0117] In practice, office terminal devices collect data to be stored in office operation scenarios and transmit this data to the model processing platform (AI BOX) via the vehicle-to-everything (TBOX) system. The AI ​​BOX extracts user data segments and home scene data segments from the data to be stored in home operation scenarios, storing the user data segments in the general storage area and the home scene data segments in the home storage area.

[0118] The above scheme receives data to be stored from in-vehicle terminal devices, determines the corresponding in-vehicle operating scenario, and identifies the corresponding in-vehicle storage area from multiple independent storage areas. Similarly, it receives data to be stored from mobile terminal devices, determines the corresponding mobile operating scenario, and identifies the corresponding mobile storage area from multiple independent storage areas. Likewise, it receives data to be stored from home terminal devices, determines the corresponding home operating scenario, and identifies the corresponding home storage area from multiple independent storage areas. Finally, it receives data to be stored from office terminal devices, determines the corresponding office operating scenario, and identifies the corresponding office storage area from multiple independent storage areas. This allows for the rapid and accurate identification of the corresponding independent storage area based on the operating scenario of each terminal device, enabling the storage of scenario-related data segments in the appropriate independent storage area.

[0119] In some embodiments, step 201 includes: Step 2011: Receive data to be stored from multiple terminal devices, determine the first terminal device with the first priority from the multiple terminal devices according to the preset priority, and determine the first running scenario corresponding to the first terminal device.

[0120] In practice, when the model processing platform (AI BOX) receives data to be stored from multiple terminal devices, in order to ensure that the data to be stored in all operating scenarios can be classified and stored in sequence according to the preset priority, the data to be stored from multiple terminal devices is classified and stored in sequence.

[0121] For example, the preset priorities, in descending order, are: in-vehicle host system, mobile terminal device, home terminal device, and office terminal device. When the model processing platform (AI BOX) receives data to be stored from both the in-vehicle host system and the home terminal device, it determines that the first terminal device with the highest priority is the in-vehicle host system, and identifies the corresponding in-vehicle operating scenario. Therefore, it prioritizes the classification and storage of data from the higher-priority in-vehicle operating scenario.

[0122] Step 2012: Determine whether the data to be stored in the first terminal device is stored in the general storage area and / or the first independent storage area.

[0123] In specific implementation, it is determined whether the data to be stored on the first terminal device is stored in the general storage area and / or the first independent storage area, thereby determining whether the data to be stored on the first terminal device has been classified and stored. The first independent storage area is the independent storage area corresponding to the first operating scenario.

[0124] For example, when the model processing platform (AI BOX) receives data to be stored from both the vehicle-mounted host system and the home terminal device, it determines that the first terminal device with the highest priority is the vehicle-mounted host system, and judges whether the data to be stored by the vehicle-mounted host system is stored in the general storage area and / or the first independent storage area, thereby determining whether the data to be stored by the vehicle-mounted host system has been classified and stored.

[0125] Step 2013: In response to the storage of the data to be stored by the first terminal device being stored in the general storage area and / or the first independent storage area, a second terminal device with a second priority is determined from multiple terminal devices according to a preset priority, and a second operating scenario corresponding to the second terminal device is determined.

[0126] In specific implementation, when the data to be stored from the first terminal device is stored in the general storage area and / or the first independent storage area, it indicates that the data to be stored from the first terminal device has been classified and stored. Then, the data to be stored from the next priority terminal device is classified and stored according to a preset priority. Specifically, a second terminal device with a second priority is determined from multiple terminal devices according to the preset priority, and a second operating scenario corresponding to the second terminal device is determined.

[0127] For example, when the model processing platform (AI BOX) receives data to be stored from both the vehicle host system and the home terminal device, it determines that the first terminal device with the first priority is the vehicle host system. After the data to be stored from the vehicle host system is stored in the general storage area and / or the first independent storage area, it determines that the second terminal device with the second priority is the home terminal device and determines the home operation scenario corresponding to the home terminal device, thereby classifying and storing the data to be stored in the home operation scenario with the second priority.

[0128] The above scheme receives data to be stored from multiple terminal devices. Based on a preset priority, a first-priority terminal device is selected from the multiple terminal devices, and its corresponding first operating scenario is determined. It is then determined whether the data to be stored from the first terminal device is stored in a general storage area and / or a first independent storage area. If the data is stored in the general storage area and / or the first independent storage area, a second-priority terminal device is selected from the multiple terminal devices based on a preset priority, and its corresponding second operating scenario is determined. In this way, by classifying and storing the data to be stored from multiple terminal devices according to the preset priority, it is possible to achieve classified storage of data in all operating scenarios.

[0129] Through the above embodiments, data to be stored is received from a terminal device, the corresponding operating scenario of the terminal device is determined, and a target independent storage area corresponding to the operating scenario is determined from multiple independent storage areas. The data to be stored is divided into multiple data segments, and the target attribute features of each data segment are determined. The data type of each data segment is determined based on the target attribute features. When the target attribute features do not meet the preset judgment conditions, it means that the data type of the current data segment cannot be accurately determined based on the target attribute features. In this case, a pre-trained data classification model is used to determine the data type of each data segment, avoiding the problem of inaccurate data type determination caused by directly determining the data type based on the target attribute features. Data segments with user data type are stored in a general storage area. User data segments are general data under multiple operating scenarios, improving the reusability of general data. General data in the general storage area can be directly accessed and reused in all operating scenarios, thereby reducing the repeated collection and storage of general data. Data segments with scenario data type are stored in a target independent storage area. Scenario data segments are scenario data related to the corresponding operating scenario. Storing scenario data under different operating scenarios into different independent storage areas can improve the isolation and security between scenario data under different operating scenarios.

[0130] It should be noted that the method of this disclosure embodiment can be executed by a single device, such as a computer or server. The method of this embodiment can also be applied to a distributed scenario, where multiple devices cooperate to complete the task. In such a distributed scenario, one of these devices may execute only one or more steps of the method of this disclosure embodiment, and the multiple devices will interact with each other to complete the method described.

[0131] It should be noted that the above description describes some embodiments of this disclosure. Other embodiments are within the scope of the appended claims of this disclosure. In some cases, the actions or steps described in the claims of this disclosure may be performed in a different order than that shown in the above embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0132] Based on the same inventive concept, corresponding to any of the above-described embodiments, this disclosure also provides a data storage device.

[0133] refer to Figure 4 The data storage device includes a model processing platform, which comprises a general-purpose storage area and multiple independent storage areas; the device includes: The running scenario determination module 301 is configured to receive data to be stored from the terminal device, determine the running scenario corresponding to the terminal device, and determine the target independent storage area corresponding to the running scenario from the multiple independent storage areas. The first data type determination module 302 is configured to divide the data to be stored into multiple data segments, determine the target attribute features of each data segment, and determine the data type of each data segment based on the target attribute features; The second data type determination module 303 is configured to determine the data type of each data segment using a pre-trained data classification model in response to the target attribute feature not meeting a preset judgment condition; wherein the judgment condition is a preset condition for determining whether the target attribute feature can determine the data type. The first storage module 304 is configured to store data segments of user type to the general storage area; and / or, The second storage module 305 is configured to store data segments of the data type being scene type to the target independent storage area.

[0134] In some embodiments, the second data type determining module 303 includes: The target confidence determination unit is configured to determine the target confidence of the target attribute features of each data segment; The second data type determination unit is configured to determine the data type of each data segment using a pre-trained data classification model in response to the target confidence level being less than a preset confidence level threshold.

[0135] In some embodiments, the target confidence determination unit includes: The matching confidence determination subunit is configured to extract keywords from each data segment and determine the matching confidence between the target attribute feature and the keywords; The consistency confidence determination subunit is configured to determine, from a pre-stored database, a historical data segment that matches each data segment and the historical attribute features corresponding to the historical data segment, and to determine the consistency confidence between the target attribute features and the historical attribute features; The context confidence determination subunit is configured to determine the context information of the keyword from each data segment and to determine the context confidence between the target attribute feature and the context information; The target confidence determination subunit is configured to perform weighted processing on the matching confidence, the consistency confidence, and the context confidence to obtain the target confidence of the target attribute feature.

[0136] In some embodiments, the first data type determining module 302 includes: The first feature matching unit is configured to determine whether the target attribute features of each data segment match the preset character identifier features; The first user type determination unit is configured to determine the data type of each data segment as a user type in response to the target attribute feature matching the preset character identifier feature; The second feature matching unit is configured to determine whether the target attribute features of each data segment match the preset terminal device features. The first scene type determination unit is configured to determine the data type of each data segment as a scene type in response to the target attribute feature matching the preset terminal device feature.

[0137] In some embodiments, the second data type determining module 303 includes: The correlation determination unit is configured to use a pre-trained data classification model to determine the correlation between each data segment and the running scenario; The second user type determination unit is configured to determine the data type of each data segment as a user type in response to the correlation degree being less than a preset correlation threshold; or, The second scene type determination unit is configured to determine the data type of each data segment as a scene type in response to the correlation degree being greater than or equal to a preset correlation threshold.

[0138] In some embodiments, the apparatus further includes a data update module, the data update module comprising: The stored data retrieval unit is configured to receive updated data sent by the terminal device and retrieve the stored data associated with the updated data from the general storage area and the independent storage area; The consistency judgment unit is configured to determine whether the updated data and the stored data meet the consistency conditions. The first storage unit is configured to, in response to a consistency condition being met between the updated data and the stored data, store the updated data in the general storage area and / or the independent storage area, and delete the stored data. The second storage unit is configured to, in response to a lack of consistency between the updated data and the stored data, store the updated data in the general storage area and / or the independent storage area, and retain the stored data.

[0139] In some embodiments, the apparatus further includes a data retrieval module, the data retrieval module comprising: The scenario determination unit is configured to receive a data call request from a terminal device, determine the scenario corresponding to the terminal device, and determine the target independent storage area corresponding to the scenario. The data retrieval unit is configured to retrieve user data from the general storage area and scene data from the target independent storage area; The control parameter determination unit is configured to determine control parameters based on the user data and the scene data, and send the control parameters to the terminal device.

[0140] In some embodiments, the running scenario determination module 301 includes: The vehicle operation scenario determination unit is configured to receive data to be stored from the vehicle terminal device, determine the vehicle operation scenario corresponding to the vehicle terminal device, and determine the vehicle storage area corresponding to the vehicle operation scenario from the multiple independent storage areas; or... A mobile operation scenario determination unit is configured to receive data to be stored from a mobile terminal device, determine the mobile operation scenario corresponding to the mobile terminal device, and determine the mobile storage area corresponding to the mobile operation scenario from the plurality of independent storage areas; or... A home operation scenario determination unit is configured to receive data to be stored from a home terminal device, determine the home operation scenario corresponding to the home terminal device, and determine the home storage area corresponding to the home operation scenario from the plurality of independent storage areas; or... The office operation scenario determination unit is configured to receive data to be stored from an office terminal device, determine the office operation scenario corresponding to the office terminal device, and determine the office storage area corresponding to the office operation scenario from the multiple independent storage areas.

[0141] In some embodiments, the running scenario determination module 301 includes: The first running scenario determination unit is configured to receive data to be stored from multiple terminal devices, determine the first terminal device with the first priority from the multiple terminal devices according to the preset priority, and determine the first running scenario corresponding to the first terminal device. The data storage judgment unit is configured to determine whether the data to be stored in the first terminal device is stored in the general storage area and / or the first independent storage area; The second operating scenario determination unit is configured to, in response to the storage of data to be stored by the first terminal device being stored in the general storage area and / or the first independent storage area, determine a second terminal device with a second priority from multiple terminal devices according to a preset priority, and determine the second operating scenario corresponding to the second terminal device.

[0142] For ease of description, the above apparatus is described in terms of its functions, divided into various modules. Of course, in implementing this disclosure, the functions of each module can be implemented in one or more software and / or hardware.

[0143] The apparatus of the above embodiments is used to implement the corresponding data storage method in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0144] Based on the same inventive concept, corresponding to the methods of any of the above embodiments, this disclosure also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the data storage method described in any of the above embodiments.

[0145] Figure 5 This embodiment illustrates a more specific hardware structure of an electronic device, which may include a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. The processor 1010, memory 1020, input / output interface 1030, and communication interface 1040 are interconnected internally via the bus 1050.

[0146] The processor 1010 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0147] The memory 1020 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 1020 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program code is stored in the memory 1020 and is called and executed by the processor 1010.

[0148] The input / output interface 1030 is used to connect input / output modules to realize information input and output. Input / output modules can be configured as components within the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Input devices may include keyboards, mice, touchscreens, microphones, various sensors, etc., while output devices may include displays, speakers, vibrators, indicator lights, etc.

[0149] The communication interface 1040 is used to connect the communication module (not shown in the figure) to enable communication between this device and other devices. The communication module can communicate via wired means (such as USB (Universal Serial Bus), network cable, etc.) or wireless means (such as mobile network, WIFI (Wireless Fidelity), Bluetooth, etc.).

[0150] Bus 1050 includes a pathway for transmitting information between various components of the device, such as processor 1010, memory 1020, input / output interface 1030, and communication interface 1040.

[0151] It should be noted that although the above-described device only shows the processor 1010, memory 1020, input / output interface 1030, communication interface 1040, and bus 1050, in specific implementations, the device may also include other components necessary for normal operation. Furthermore, those skilled in the art will understand that the above-described device may only include the components necessary for implementing the embodiments of this specification, and not necessarily all the components shown in the figures.

[0152] The electronic devices described above are used to implement the corresponding data storage methods in any of the foregoing embodiments and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0153] Based on the same inventive concept, corresponding to the methods of any of the above embodiments, this disclosure also provides a non-transitory computer-readable storage medium that stores computer instructions for causing the computer to execute the data storage method as described in any of the above embodiments.

[0154] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transfer medium that can be used to store information accessible by a computing device.

[0155] The computer instructions stored in the storage medium of the above embodiments are used to cause the computer to execute the data storage method as described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0156] Based on the same inventive concept, corresponding to the methods of any of the above embodiments, this application also provides a vehicle, including the data storage device, or electronic device, or storage medium in the above embodiments, wherein the vehicle device implements the data storage method described in any of the above embodiments.

[0157] The vehicles described in the above embodiments are used to implement the data storage method described in any of the foregoing embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0158] Based on the same inventive concept, corresponding to any of the above embodiments, this application also provides a computer program product, including computer program instructions. When the computer program instructions are run on a computer, the computer executes the data storage method as described in any of the above embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0159] It is understood that before using the technical solutions of the various embodiments in this disclosure, users will be informed of the type, scope of use, and usage scenarios of the personal information involved in an appropriate manner, and user authorization will be obtained.

[0160] For example, upon receiving a user's active request, a prompt message is sent to the user to explicitly inform them that the requested operation will require the acquisition and use of the user's personal information. This allows the user to independently choose, based on the prompt message, whether to provide personal information to the software or hardware such as electronic devices, applications, servers, or storage media performing the operations of this disclosed technical solution.

[0161] As an optional but not limited implementation, in response to a user's active request, sending a prompt message to the user can be done via a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0162] It is understood that the above notification and user authorization process are merely illustrative and do not constitute a limitation on the implementation of this disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of this disclosure.

[0163] Those skilled in the art should understand that the discussion of any of the above embodiments is merely exemplary and is not intended to imply that the scope of this disclosure is limited to these examples; within the framework of this disclosure, the technical features of the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations of different aspects of the embodiments of this disclosure as described above, which are not provided in detail for the sake of brevity.

[0164] Additionally, to simplify the description and discussion, and to avoid obscuring the embodiments of this disclosure, the provided drawings may or may not show well-known power / ground connections to integrated circuit (IC) chips and other components. Furthermore, the apparatus may be shown in block diagram form to avoid obscuring the embodiments of this disclosure, and this also takes into account the fact that the details of implementation of these block diagram apparatuses are highly dependent on the platform on which the embodiments of this disclosure will be implemented (i.e., these details should be fully understood by those skilled in the art). While specific details (e.g., circuits) have been set forth to describe exemplary embodiments of this disclosure, it will be apparent to those skilled in the art that the embodiments of this disclosure can be implemented without these specific details or with variations thereof. Therefore, these descriptions should be considered illustrative rather than restrictive.

[0165] Although this disclosure has been described in conjunction with specific embodiments thereof, many substitutions, modifications, and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may be used with the embodiments discussed.

[0166] This disclosure is intended to cover all such substitutions, modifications, and variations that fall within the broad scope of this disclosure. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this disclosure should be included within the protection scope of this disclosure.

Claims

1. A data storage method, characterized in that, The method is applied to a model processing platform, which includes a general-purpose storage area and multiple independent storage areas; the method includes: Upon receiving data to be stored from a terminal device, the system determines the operating scenario corresponding to the terminal device and identifies the target independent storage area corresponding to the operating scenario from the multiple independent storage areas. The data to be stored is divided into multiple data segments, the target attribute features of each data segment are determined, and the data type of each data segment is determined based on the target attribute features; In response to the target attribute feature not meeting the preset judgment condition, the data type of each data segment is determined using a pre-trained data classification model; wherein, the judgment condition is a pre-set condition for determining whether the target attribute feature can determine the data type. Store the data segment of type user to the general storage area; and / or, The data segment whose data type is scene type is stored in the target independent storage area.

2. The method according to claim 1, characterized in that, In response to the target attribute feature not meeting the preset conditions, the data type of each data segment is determined using a pre-trained data classification model, including: Determine the target confidence level of the target attribute features for each data segment; If the target confidence level is less than a preset confidence threshold, the data type of each data segment is determined using a pre-trained data classification model.

3. The method according to claim 2, characterized in that, Determining the target confidence level of the target attribute features for each data segment includes: Extract keywords from each data segment and determine the matching confidence between the target attribute feature and the keywords; Determine the historical data segments that match each data segment from the pre-stored database and the historical attribute features corresponding to the historical data segments, and determine the consistency confidence between the target attribute features and the historical attribute features; Contextual information of the keyword is determined from each data segment, and contextual confidence between the target attribute feature and the contextual information is determined; The target confidence score of the target attribute feature is obtained by weighting the matching confidence score, the consistency confidence score, and the context confidence score.

4. The method according to claim 1, characterized in that, Determining the data type of each data segment based on the target attribute features includes: Determine whether the target attribute features of each data segment match the preset character identification features; In response to the target attribute feature matching the preset character identifier feature, the data type of each data segment is determined to be user type; Determine whether the target attribute features of each data segment match the preset terminal device features; In response to the target attribute feature matching the preset terminal device feature, the data type of each data segment is determined to be a scene type.

5. The method according to claim 1, characterized in that, The step of determining the data type of each data segment using a pre-trained data classification model includes: Using a pre-trained data classification model, the correlation between each data segment and the operating scenario is determined; If the correlation degree is less than a preset correlation threshold, then the data type of each data segment is determined to be a user type; or, If the correlation degree is greater than or equal to a preset correlation threshold, then the data type of each data segment is determined to be a scene type.

6. The method according to claim 1, characterized in that, After storing the data segment whose data type is scene type to the target independent storage area, the method further includes: Upon receiving update data from the terminal device, retrieve the stored data associated with the update data from the general storage area and the independent storage area; Determine whether the updated data and the stored data meet the consistency condition; In response to the consistency condition being met between the updated data and the stored data, the updated data is stored in the general storage area and / or the independent storage area, and the stored data is deleted. If the updated data does not meet the consistency condition with the stored data, the updated data is stored in the general storage area and / or the independent storage area, and the stored data is retained.

7. The method according to claim 1, characterized in that, After storing the data segment whose data type is scene type to the target independent storage area, the method further includes: Upon receiving a data access request from a terminal device, determine the operating scenario corresponding to the terminal device and the target independent storage area corresponding to the operating scenario; User data is retrieved from the general storage area, and scene data is retrieved from the target independent storage area; Control parameters are determined based on the user data and the scene data, and the control parameters are sent to the terminal device.

8. The method according to claim 1, characterized in that, The process of receiving data to be stored from a terminal device, determining the operating scenario corresponding to the terminal device, and determining the target independent storage area corresponding to the operating scenario from the plurality of independent storage areas includes: Upon receiving data to be stored from the vehicle-mounted terminal device, the system determines the vehicle operation scenario corresponding to the vehicle-mounted terminal device and identifies the vehicle storage area corresponding to the vehicle operation scenario from among the multiple independent storage areas; or... Upon receiving data to be stored from a mobile terminal device, the system determines the mobile operating scenario corresponding to the mobile terminal device and identifies the mobile storage area corresponding to the mobile operating scenario from among the multiple independent storage areas; or... Upon receiving data to be stored from a home terminal device, the system determines the home operating scenario corresponding to the home terminal device and identifies the home storage area corresponding to the home operating scenario from among the multiple independent storage areas; or... Upon receiving data to be stored from an office terminal device, the system determines the office operation scenario corresponding to the office terminal device and identifies the office storage area corresponding to the office operation scenario from among the multiple independent storage areas.

9. The method according to claim 1, characterized in that, The process of receiving data to be stored from a terminal device and determining the corresponding operating scenario for the terminal device includes: Upon receiving data to be stored from multiple terminal devices, the system determines the first terminal device with the highest priority from among the multiple terminal devices according to a preset priority, and determines the first operating scenario corresponding to the first terminal device. Determine whether the data to be stored in the first terminal device is stored in the general storage area and / or the first independent storage area; In response to the storage of data to be stored by the first terminal device being stored in the general storage area and / or the first independent storage area, a second terminal device with a second priority is determined from multiple terminal devices according to a preset priority, and a second operating scenario corresponding to the second terminal device is determined.

10. A vehicle, characterized in that, The device includes an electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor, when executing the program, implements the method as claimed in any one of claims 1 to 9.

Images