Charging service personalized recommendation method and device, equipment and medium

Abstract

This application discloses a method, apparatus, device, and medium for personalized charging service recommendation. The method includes: acquiring real-time vehicle data and charging pile location data and environmental data from a charging pile SaaS platform via an onboard terminal mounted on a target vehicle with charging needs; updating the dynamic and static tag profiles of the target vehicle and its associated user based on the vehicle data, charging pile location data, and environmental data; scoring each charging pile using a preset multi-dimensional scoring model based on the vehicle data, charging pile location data, environmental data, and dynamic and static tag profiles; and recommending charging services to the target vehicle based on the scores of each charging pile. By installing an onboard terminal on the target vehicle to acquire real-time data and update the dynamic and static tag profiles of the target vehicle and its associated user, subsequent recommendations based on these profiles are more closely aligned with the real-time needs of the vehicle and the corresponding user, improving the adaptation to the user's immediate charging needs.

Description

Technical Field

[0001] This application relates to the field of charging management technology, and in particular to a method, apparatus, device and medium for personalized recommendation of charging services. Background Technology

[0002] With the development of new energy vehicles, more and more users are choosing them, and correspondingly, their various charging needs will also increase.

[0003] Currently, charging station recommendations are typically based on the status of charging piles in charging stations, their distance from users, and users' historical preferences. This recommendation method is limited to users' long-term charging habits and has low adaptability to users' immediate needs. Summary of the Invention

[0004] This application provides a method, apparatus, device, and medium for personalized charging service recommendations to improve the adaptation to users' immediate charging needs.

[0005] In a first aspect, embodiments of this application provide a personalized charging service recommendation method, including: By using the on-board terminal installed on the target vehicle with charging needs, the vehicle data of the target vehicle can be obtained in real time, as well as the charging pile location data and environmental data of the charging pile SAAS platform. Based on vehicle data, pile location data, and environmental data, update the dynamic and static tag profiles of the target vehicle and the bound user. Using vehicle data, charging station data, environmental data, and dynamic / static tag profiles, each charging station is scored based on a pre-set multi-dimensional scoring model; Charging services are recommended for the target vehicle based on the rating of each charging station.

[0006] Secondly, embodiments of this application provide a personalized charging service recommendation device. The data acquisition module is used to acquire vehicle data of the target vehicle in real time through the on-board terminal installed on the target vehicle with charging needs, and to acquire charging pile location data and environmental data of the charging pile SAAS platform in real time. The profile update module is used to update the dynamic and static tag profiles of the target vehicle and the bound user based on vehicle data, pile location data, and environmental data. The scoring module is used to score each charging station based on a preset multi-dimensional scoring model, utilizing vehicle data, charging station location data, environmental data, and dynamic / static label profiles. The recommendation module is used to recommend charging services for target vehicles based on the rating of each charging station.

[0007] Thirdly, embodiments of this application also provide an electronic device, including: one or more processors and a storage device; Storage devices are used to store one or more programs; When one or more programs are executed by one or more processors, the one or more processors implement the personalized charging service recommendation method provided in any embodiment of this application.

[0008] Fourthly, embodiments of this application also provide a computer-readable storage medium storing a computer program thereon, characterized in that, when the program is executed by a processor, it implements the personalized charging service recommendation method provided in any embodiment of this application.

[0009] The technical solution of this application embodiment acquires real-time vehicle data and charging pile location data and environmental data from the charging pile SaaS platform through an on-board terminal installed on the target vehicle with charging needs. Based on the vehicle data, charging pile location data, and environmental data, the dynamic and static tag profiles of the target vehicle and its associated user are updated. Using the vehicle data, charging pile location data, environmental data, and dynamic and static tag profiles, each charging pile is scored based on a preset multi-dimensional scoring model. Charging service recommendations are then made for the target vehicle according to the score of each charging pile. Therefore, by installing an on-board terminal on the target vehicle to acquire real-time data and update the dynamic and static tag profiles of the target vehicle and its associated user, subsequent recommendations based on these profiles are more closely aligned with the real-time needs of the vehicle and the corresponding user, improving the adaptation to the user's immediate charging needs. Attached Figure Description

[0010] Figure 1 A flowchart illustrating the personalized charging service recommendation method provided in Embodiment 1 of this application; Figure 2 This is a schematic diagram of the structure of a personalized charging service recommendation device provided in Embodiment 2 of this application; Figure 3 This is a schematic diagram of the structure of a collaborative computing device provided in Embodiment 3 of this application. Detailed Implementation

[0011] The present application will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the application and not intended to limit it. Furthermore, it should be noted that, for ease of description, the accompanying drawings show only the parts relevant to the present application, not the entire structure.

[0012] Example 1 Figure 1This is a flowchart illustrating the personalized charging service recommendation method provided in Embodiment 1 of this application. It should be noted that this method can run on a system computing device equipped with the necessary hardware, such as... Figure 1 As shown, the method includes: Step 101: Obtain vehicle data in real time through the on-board terminal installed on the target vehicle with charging needs, and obtain charging pile location data and environmental data from the charging pile SAAS platform in real time.

[0013] The on-board terminal can connect to the vehicle bus via the target vehicle's OBD interface to obtain the target vehicle's data. Furthermore, the target vehicle with charging needs refers to any type of vehicle that requires charging at a charging station, including pure electric vehicles, plug-in hybrid vehicles, and range-extended vehicles.

[0014] In a specific example, OBD boxes can be installed in the automotive aftermarket and combined with VIN information obtained through vehicle-to-charging station interaction to collect and analyze data from new energy vehicles. This method combines the advantages of two data sources, effectively overcoming the limitations of a single approach.

[0015] The OBD box, acting as a dynamic data acquisition terminal, is installed in the vehicle and connects to the vehicle's CAN bus via the OBD-II interface to acquire real-time vehicle operating status data. During vehicle-charging station interaction, i.e., the charging process, it can serve as a supplementary source for static attributes and authentication. For example, during the charging handshake phase, the charging station communicates with the vehicle's BMS, which includes the vehicle's VIN code. The SaaS platform can record associated data such as "VIN code - charging station - charging time - charging amount".

[0016] In addition, the vehicle data collected in this step includes, but is not limited to, battery status parameters, vehicle attribute parameters, and driving status parameters.

[0017] Specifically, battery status parameters may include real-time SOC (remaining charge), battery type (ternary lithium / lithium iron phosphate), and current battery temperature; vehicle attribute data may include vehicle model, nominal battery capacity, and maximum charging power (e.g., 60kW / 120kW / 250kW); driving status data may include real-time location (latitude and longitude), remaining driving range, current energy consumption rate (kWh / 100km), navigation destination, average vehicle speed, and the status of high-power electrical appliances such as air conditioning.

[0018] This OBD box can use the TLS1.3 encryption protocol to transmit data to the cloud server in real time via 4G / 5G cellular networks, ensuring data security and real-time performance.

[0019] It should be noted that if the data collected in the above process involves privacy data, it should be used within the authorized scope only after obtaining authorization from the user (the owner of the target vehicle).

[0020] In addition, the charging pile SaaS platform, based on a cloud computing microservice architecture, realizes the core functions of "data fusion - profile building - intelligent recommendation - service output" and supports multi-tenant (charging pile operators, power grid companies) access.

[0021] In this embodiment, the platform may specifically involve the following three modules: a data fusion center, a user profile construction module, and a personalized recommendation engine.

[0022] This step involves the data input function of the data fusion center. Specifically, the input data can include maintenance data and environmental data. More specifically, the charging pile data can include the location, type, power, interface type, real-time status (idle / occupied / faulty), price, and historical usage rate of the charging pile.

[0023] Environmental data can include real-time traffic conditions (connected to the city traffic API), weather (temperature / rain / snow / strong wind), and holiday information.

[0024] Furthermore, it can also obtain users' historical data, such as charging records, payment methods, and feedback ratings, as a supplement to subsequent operations.

[0025] Step 102: Update the dynamic and static tag profiles of the target vehicle and the bound user based on vehicle data, pile location data and environmental data.

[0026] In this step, vehicle data, pile location data, and environmental data can be fused and correlated to obtain fused data of the target vehicle; based on the fused data, the dynamic and static tags in the profiles of the target vehicle and the bound user are updated.

[0027] It should be noted that this step involves the data fusion function of the aforementioned data fusion center, as well as the function of the user profile construction module.

[0028] Specifically, a distributed database (such as HBase) is used to store massive amounts of data, and stream processing technology (Kafka + Flink) is used to achieve real-time data cleaning (removing outliers), format conversion (unifying data field specifications), and association and fusion (such as associating "vehicle location - road conditions - surrounding stake locations"), providing a standardized dataset for upper-layer modules.

[0029] In this embodiment, user profiles are referred to as dynamic and static tag profiles. They are constructed based on a dual dimension of "dynamic + static" to create multi-tag user profiles, which is the core foundation for realizing personalized recommendations.

[0030] Among them, the static tags may include behavior preferences, service requirements, and payment characteristics. Specifically, the behavior preferences may include common charging periods (such as night charging from 22:00 to 6:00), average charging amount (such as charging to 80% each time), preferred pile type (fast charging / slow charging), preferred operator); The service requirements may include whether additional services are needed (rest area, catering, toilet, free parking), requirements for the charging environment (above ground / underground); the payment characteristics may include payment method preferences (charge after use / prepay before charging), price sensitivity (such as only selecting pile positions with ≤1.5 yuan / kWh).

[0031] The dynamic tags, on the other hand, may include vehicle status, specifically, the current SOC (such as 35%, marked as "medium battery level, need to charge midway"), whether the remaining range can reach the destination (such as "remaining range 150km, destination 200km, need to charge"), charging urgency (such as marked as "urgent" when SOC≤20%, marked as "regular" when 20%<SOC<80%, marked as "planned" when SOC≥80%).

[0032] Based on the relationships between the rain and each tag in the obtained fusion data, construct and update the static and dynamic tag portraits of the target vehicle and the bound user. It should be noted that the target vehicle and the bound user can be regarded as an individual.

[0033] To reduce unnecessary tag updates, different update times are set for static tags and dynamic tags in this embodiment. Specifically, first, it is determined whether the key parameters in the fusion data have changed compared with the previous time. If they have changed, update the dynamic tags and / or static tags corresponding to the key parameters; if they have not changed, update the static tags according to the preset tag update period, and update the dynamic tags in real time.

[0034] Among them, the key parameters are parameters strongly related to charging requirements. In a specific example, they may include, but are not limited to, changes in SOC and user behavior. For example, when the SOC drops from 40% to 20% or the user generates a new behavior (such as first selecting a charging station with catering for the first time), update the corresponding tags in real time to ensure that the portrait is consistent with the user's current requirements.

[0035] Step 103: Use the vehicle data, pile position data, environmental data, and static and dynamic tag portraits to score each charging pile based on a preset multi-dimensional scoring model.

[0036] In this step, vehicle data includes vehicle attribute data. To reduce the computational burden of subsequent scoring, charging piles can be screened first, followed by scoring. Specifically, vehicle attribute data and charging pile location data can be used to screen charging piles, resulting in a candidate pile set. Using dynamic and static tag profiles and environmental data, and based on a preset multi-dimensional scoring model, each charging pile in the candidate pile set is scored.

[0037] When screening charging stations, mismatched stations can be filtered out based on vehicle attribute data and station location data to ensure that "charging is possible and fast charging" is recommended. In a specific example, the following two filtering conditions can be included: Power mismatch (e.g., vehicles that support a maximum of 60kW should exclude 200kW supercharging stations to avoid wasting resources); Abnormal status (faulty pile, pile position that has been occupied for a long time (e.g., occupied for more than 4 hours continuously).

[0038] After obtaining the candidate charging pile set, the weights of each dimension of the preset multi-dimensional scoring model can be dynamically adjusted using dynamic and static label profiles. For any charging pile in the candidate set, the charging pile is scored based on the adjusted dimensions, dynamic and static label profiles, and environmental data.

[0039] First, the pre-defined multi-dimensional scoring model can be explained. This model includes various dimensions and basic weights, as shown in Table 1: Table 1 Based on this, this embodiment can adjust the weights of each dimension according to the user's immediate needs. In a specific example, it may include: Emergency charging (SOC≤20%): The weight of the basic efficiency factor is increased to 45%, the economic factor is reduced to 5%, and priority is given to "the fastest arrival"; Planned charging (SOC≥80%): The weight of the basic efficiency factor is reduced to 10%, the weight of the economic factor is increased to 30%, and the weight of the user preference factor is increased to 25%, prioritizing "low price + matching preferences"; Severe weather (rain / snow / extreme temperature): The weight of the environmental adaptation factor is increased to 15%, prioritizing "environmental adaptation"; User-manually set mode (e.g., the APP selects "cheapest"): the weight of the economic factor is increased to 60%, and other factors are reduced proportionally.

[0040] Based on the adjusted weights mentioned above, the comprehensive score of the candidate charging stations can be calculated (the sum of the scores of each dimension × the corresponding weights). A Top 3 to 5 recommendation list is generated in descending order of the scores, and a "Recommendation Reason" is added to each recommendation (e.g., "Recommended Charging Station A: 5km away, estimated arrival time is 10 minutes, currently available, matches your 250kW fast charging needs, and comes with a free rest area").

[0041] Step 104: Recommend charging services for the target vehicle based on the rating of each charging station.

[0042] In this step, a list of recommended charging stations can be generated for the target vehicle based on the rating of each charging station. Furthermore, to improve the real-time accuracy of the recommendations, the status of the recommended charging stations and vehicle data can be monitored in real time, and the list of recommended charging stations can be adjusted as the status and vehicle data change.

[0043] Specifically, data changes are monitored in real time as the user navigates to the recommended location: If the status of a pile changes (e.g., the original recommended pile is occupied): immediately recalculate the score, generate a new recommendation list and push it to the user; Abnormal vehicle battery consumption (such as a sudden increase in energy consumption rate): triggers a warning (such as "Current energy consumption is higher than expected, and the remaining battery may not be able to reach the recommended charging station. It is recommended to switch to charging station B, which is 3 kilometers away").

[0044] In addition, this embodiment can also provide a way to handle competing demands. For example, when the same charging pile is recommended to multiple users at the same time, the charging pile can be marked based on the expected arrival of other vehicles to avoid the situation where other users take the charging pile first, causing the user to still have to go to the charging pile, thus further reducing the time wasted by the user.

[0045] Specifically, for any charging station in the charging station list, the competitive recommendation information of the charging station is monitored; if the competitive recommendation information indicates that other users can arrive at the charging station earlier, the charging station is marked as competing in the charging station list.

[0046] Once a charging station displays a competition indicator, users can go to other charging stations to charge their devices in advance.

[0047] In addition, in this embodiment, user feedback on the recommendation results (click rate, confirmation rate, charging completion rate, satisfaction rating (1~5 stars)) can also be recorded. Incremental learning algorithms (such as SGD stochastic gradient descent) are used to update the recommendation model parameters weekly and optimize the weight of the rating dimension and the filtering logic. For example, if a user rejects the recommendation peg with "no rest area" three times in a row, the weight of "additional services" in the "user preference factor" will be increased.

[0048] In this embodiment, By using onboard terminals installed on target vehicles with charging needs, real-time vehicle data is acquired, along with charging pile location data and environmental data from the charging pile SaaS platform. Based on this data, the dynamic and static profiles of the target vehicle and its associated user are updated. Using these data, a pre-defined multi-dimensional scoring model, each charging pile is scored. Charging service recommendations are then made for the target vehicle based on each charging pile's score. In this way, by installing onboard terminals on target vehicles to acquire real-time data and update the dynamic and static profiles of the target vehicle and its associated user, subsequent profile-based recommendations are more closely aligned with the real-time needs of the vehicle and the corresponding user, improving the adaptation to the user's immediate charging requirements.

[0049] Example 2 Figure 2 This is a schematic diagram of a personalized charging service recommendation device provided in Embodiment 2 of this application. The personalized charging service recommendation device provided in this embodiment can execute the personalized charging service recommendation method provided in any embodiment of this application, and has the corresponding functional modules and beneficial effects of executing the method. This device can be implemented in software and / or hardware, and is applied to a collaborative computing device. The collaborative computing device is equipped with memory, a hardware filter, and a vector processor. The vector processor stores force calculation microcode, such as… Figure 2 As shown, the personalized charging service recommendation device specifically includes: a data acquisition module 201, a profile update module 202, a rating module 203, and a recommendation module 204.

[0050] The data acquisition module is used to acquire vehicle data of the target vehicle in real time through the vehicle terminal installed on the target vehicle with charging needs, and to acquire charging pile location data and environmental data of the charging pile SAAS platform in real time. The profile update module is used to update the dynamic and static tag profiles of the target vehicle and the bound user based on vehicle data, pile location data, and environmental data. The scoring module is used to score each charging station based on a preset multi-dimensional scoring model, utilizing vehicle data, charging station location data, environmental data, and dynamic / static label profiles. The recommendation module is used to recommend charging services for target vehicles based on the rating of each charging station.

[0051] Furthermore, the profile update module is specifically used for: Vehicle data, pile location data, and environmental data are fused and correlated to obtain fused data of the target vehicle; The dynamic and static tags in the profiles of the target vehicle and its associated user are updated based on the fused data.

[0052] Furthermore, the profile update module is specifically used for: Determine whether the key parameters in the fused data have changed compared to the previous data. If they have changed, update the dynamic and / or static labels corresponding to the key parameters. If no changes occur, static tags will be updated according to the preset tag update cycle, and dynamic tags will be updated in real time.

[0053] Furthermore, vehicle data includes vehicle attribute data; The rating module is specifically used for: By using vehicle attribute data and charging pile location data, a candidate set of charging piles is obtained; Using dynamic and static tag profiles and environmental data, and based on a pre-set multi-dimensional scoring model, each charging pile in the candidate pile set is scored.

[0054] Furthermore, the scoring module is specifically used for: The weights of each dimension of the preset multi-dimensional scoring model are dynamically adjusted using dynamic and static tag profiles. For any charging pile in the candidate set, the charging pile is scored based on the adjusted weighted dimensions, dynamic and static label profiles, and environmental data.

[0055] Furthermore, the recommendation module is specifically used for: Recommend a list of charging stations for the target vehicle based on the rating of each charging station; The system monitors the status of recommended charging stations and vehicle data in real time, and adjusts the list of recommended charging stations as the status and vehicle data change.

[0056] Furthermore, the recommendation module is specifically used for: For any charging station in the charging station list, monitor the competitive recommendation information of the charging station; When competitive recommendation information indicates that other users can reach the charging station earlier, the charging station will be competitively marked in the charging station list.

[0057] Example 3 Figure 3 This is a schematic diagram of the structure of a collaborative computing device provided in Embodiment 3 of this application, as shown below. Figure 3 As shown, the collaborative computing device includes a processor 310, a memory 320, an input device 330, and an output device 340; the number of processors 310 in the collaborative computing device can be one or more. Figure 3 Taking a processor 310 as an example; the processor 310, memory 320, input device 330, and output device 340 in the collaborative computing device can be connected via a bus or other means. Figure 3 Taking the example of a connection between China and Israel via a bus.

[0058] The memory 320, as a computer-readable storage medium, can be used to store software programs, computer-executable programs, and modules, such as the program instructions / modules corresponding to the cross-application task invocation method in this embodiment of the invention. The processor 310 executes various functional applications and data processing of the collaborative computing device by running the software programs, instructions, and modules stored in the memory 320, thereby realizing the aforementioned personalized charging service recommendation method. By using the on-board terminal installed on the target vehicle with charging needs, the vehicle data of the target vehicle can be obtained in real time, as well as the charging pile location data and environmental data of the charging pile SAAS platform. Based on vehicle data, pile location data, and environmental data, update the dynamic and static tag profiles of the target vehicle and the bound user. Using vehicle data, charging station data, environmental data, and dynamic / static tag profiles, each charging station is scored based on a pre-set multi-dimensional scoring model; Charging services are recommended for the target vehicle based on the rating of each charging station.

[0059] Furthermore, based on vehicle data, charging pile data, and environmental data, the dynamic and static tag profiles of the target vehicle and its associated user are updated, including: Vehicle data, pile location data, and environmental data are fused and correlated to obtain fused data of the target vehicle; The dynamic and static tags in the profiles of the target vehicle and its associated user are updated based on the fused data.

[0060] Furthermore, based on the fused data, the dynamic and static tags in the profiles of the target vehicle and the bound user are updated, including: Determine whether the key parameters in the fused data have changed compared to the previous data. If they have changed, update the dynamic and / or static labels corresponding to the key parameters. If no changes occur, static tags will be updated according to the preset tag update cycle, and dynamic tags will be updated in real time.

[0061] Furthermore, vehicle data includes vehicle attribute data; Using vehicle data, charging station location data, environmental data, and dynamic / static tag profiles, and based on a pre-set multi-dimensional scoring model, each charging station is scored, including: By using vehicle attribute data and charging pile location data, a candidate set of charging piles is obtained; Using dynamic and static tag profiles and environmental data, and based on a pre-set multi-dimensional scoring model, each charging pile in the candidate pile set is scored.

[0062] Furthermore, utilizing dynamic and static tag profiles and environmental data, and based on a pre-defined multi-dimensional scoring model, each charging station in the candidate set is scored, including: The weights of each dimension of the preset multi-dimensional scoring model are dynamically adjusted using dynamic and static tag profiles. For any charging pile in the candidate set, the charging pile is scored based on the adjusted weighted dimensions, dynamic and static label profiles, and environmental data.

[0063] Furthermore, charging service recommendations are made for the target vehicle based on the rating of each charging station, including: Recommend a list of charging stations for the target vehicle based on the rating of each charging station; The system monitors the status of recommended charging stations and vehicle data in real time, and adjusts the list of recommended charging stations as the status and vehicle data change.

[0064] Furthermore, the methods also include: For any charging station in the charging station list, monitor the competitive recommendation information of the charging station; When competitive recommendation information indicates that other users can reach the charging station earlier, the charging station will be competitively marked in the charging station list.

[0065] The memory 320 may primarily include a program storage area and a data storage area. The program storage area may store the operating system and at least one application program required for a given function; the data storage area may store data created based on terminal usage. Furthermore, the memory 320 may include high-speed random access memory and non-volatile memory, such as at least one disk storage device, flash memory, or other non-volatile solid-state storage device. In some instances, the memory 320 may further include memory remotely located relative to the processor 310, which can be connected to a collaborative computing device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0066] Example 4 Embodiment 4 of this application also provides a storage medium containing computer-executable instructions, which, when executed by a computer processor, are used to perform a personalized charging service recommendation method, the method comprising: By using the on-board terminal installed on the target vehicle with charging needs, the vehicle data of the target vehicle can be obtained in real time, as well as the charging pile location data and environmental data of the charging pile SAAS platform. Based on vehicle data, pile location data, and environmental data, update the dynamic and static tag profiles of the target vehicle and the bound user. Using vehicle data, charging station data, environmental data, and dynamic / static tag profiles, each charging station is scored based on a pre-set multi-dimensional scoring model; Charging services are recommended for the target vehicle based on the rating of each charging station.

[0067] Furthermore, based on vehicle data, charging pile data, and environmental data, the dynamic and static tag profiles of the target vehicle and its associated user are updated, including: Vehicle data, pile location data, and environmental data are fused and correlated to obtain fused data of the target vehicle; The dynamic and static tags in the profiles of the target vehicle and its associated user are updated based on the fused data.

[0068] Furthermore, based on the fused data, the dynamic and static tags in the profiles of the target vehicle and the bound user are updated, including: Determine whether the key parameters in the fused data have changed compared to the previous data. If they have changed, update the dynamic and / or static labels corresponding to the key parameters. If no changes occur, static tags will be updated according to the preset tag update cycle, and dynamic tags will be updated in real time.

[0069] Furthermore, vehicle data includes vehicle attribute data; Using vehicle data, charging station location data, environmental data, and dynamic / static tag profiles, and based on a pre-set multi-dimensional scoring model, each charging station is scored, including: By using vehicle attribute data and charging pile location data, a candidate set of charging piles is obtained; Using dynamic and static tag profiles and environmental data, and based on a pre-set multi-dimensional scoring model, each charging pile in the candidate pile set is scored.

[0070] Furthermore, utilizing dynamic and static tag profiles and environmental data, and based on a pre-defined multi-dimensional scoring model, each charging station in the candidate set is scored, including: The weights of each dimension of the preset multi-dimensional scoring model are dynamically adjusted using dynamic and static tag profiles. For any charging pile in the candidate set, the charging pile is scored based on the adjusted weighted dimensions, dynamic and static label profiles, and environmental data.

[0071] Furthermore, charging service recommendations are made for the target vehicle based on the rating of each charging station, including: Recommend a list of charging stations for the target vehicle based on the rating of each charging station; The system monitors the status of recommended charging stations and vehicle data in real time, and adjusts the list of recommended charging stations as the status and vehicle data change.

[0072] Furthermore, the methods also include: For any charging station in the charging station list, monitor the competitive recommendation information of the charging station; When competitive recommendation information indicates that other users can reach the charging station earlier, the charging station will be competitively marked in the charging station list.

[0073] Of course, the computer-executable instructions provided in the embodiments of this application are not limited to the above-described method operations, but can also execute related operations in the personalized charging service recommendation method provided in any embodiment of this application.

[0074] Based on the above description of the implementation methods, those skilled in the art can clearly understand that this application can be implemented using software and necessary general-purpose hardware, and of course, it can also be implemented using hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk, or optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods of the various embodiments of this application.

[0075] It is worth noting that in the embodiments of the above-mentioned device, the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific names of each functional unit are only for easy differentiation and are not used to limit the scope of protection of this application.

[0076] Note that the above description is merely a preferred embodiment and the technical principles employed in this application. Those skilled in the art will understand that this application is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made without departing from the scope of protection of this application. Therefore, although this application has been described in detail through the above embodiments, this application is not limited to the above embodiments. Many other equivalent embodiments may be included without departing from the concept of this application, and the scope of this application is determined by the scope of the appended claims.

Claims

1. A method for personalized recommendation of charging services, characterized in that, include: The vehicle data of the target vehicle is obtained in real time through the on-board terminal installed on the target vehicle with charging needs, and the charging pile location data and environmental data of the charging pile SAAS platform are also obtained in real time. Based on the vehicle data, the pile location data, and the environmental data, update the dynamic and static tag profiles of the target vehicle and the bound user; Using the vehicle data, the charging pile location data, the environmental data, and the dynamic and static label profiles, a score is given for each charging pile based on a preset multi-dimensional scoring model; Based on the rating of each charging station, a charging service recommendation is made for the target vehicle.

2. The method according to claim 1, characterized in that, The step of updating the dynamic and static tag profiles of the target vehicle and the bound user based on the vehicle data, the pile location data, and the environmental data includes: The vehicle data, the pile location data, and the environmental data are fused and correlated to obtain the fused data of the target vehicle; The dynamic and static tags in the profiles of the target vehicle and the bound user are updated based on the fused data.

3. The method according to claim 2, characterized in that, The step of updating the dynamic and static tags in the profiles of the target vehicle and the bound user based on the fused data includes: Determine whether the key parameters in the fused data have changed compared to the previous time. If they have changed, update the dynamic and / or static labels corresponding to the key parameters. If no changes occur, the static tags are updated according to the preset tag update cycle, and the dynamic tags are updated in real time.

4. The method according to claim 1, characterized in that, The vehicle data includes vehicle attribute data; The method utilizes the vehicle data, the charging pile location data, the environmental data, and the dynamic / static tag profile to score each charging pile based on a preset multi-dimensional scoring model, including: The charging piles are filtered using the vehicle attribute data and the charging pile location data to obtain a candidate set of charging piles; Using the dynamic and static label profiles and the environmental data, and based on a preset multi-dimensional scoring model, each charging pile in the candidate pile set is scored.

5. The method according to claim 4, characterized in that, The step of using the dynamic and static tag profiles and the environmental data to score each charging pile in the candidate pile set based on a preset multi-dimensional scoring model includes: The weights of each dimension of the preset multi-dimensional scoring model are dynamically adjusted using the dynamic and static label profiles. For any charging pile in the candidate pile set, the charging pile is scored based on the dynamic and static label profile and the environmental data, according to the adjusted weighted dimensions.

6. The method according to claim 1, characterized in that, The method of recommending charging services for the target vehicle based on the rating of each charging station includes: A list of recommended charging stations is provided for the target vehicle based on the rating of each charging station. The system monitors the status of recommended charging stations and vehicle data in real time, and adjusts the list of recommended charging stations when the status and vehicle data change.

7. The method according to claim 6, characterized in that, The method further includes: For any charging pile in the charging pile list, monitor the competitive recommendation information of the charging pile; If the competitive recommendation information indicates that other users can reach the charging station earlier, the charging station will be competitively marked in the charging station list.

8. A personalized charging service recommendation device, characterized in that, The device includes: The data acquisition module is used to acquire vehicle data of the target vehicle in real time through the vehicle terminal installed on the target vehicle with charging needs, and to acquire charging pile location data and environmental data of the charging pile SAAS platform in real time. The profile update module is used to update the dynamic and static tag profiles of the target vehicle and the bound user based on the vehicle data, the pile location data and the environmental data; The scoring module is used to score each charging pile based on a preset multi-dimensional scoring model, using the vehicle data, the charging pile location data, the environmental data, and the dynamic and static label profile. The recommendation module is used to recommend charging services for the target vehicle based on the rating of each charging station.

9. An electronic device, characterized in that, include: One or more processors and storage devices; The storage device is used to store one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the personalized charging service recommendation method as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by the processor, the program implements the personalized charging service recommendation method as described in any one of claims 1-7.

Images