Parking space searching method and system based on NLP technology

Abstract

The embodiment of the invention provides a parking space searching method and system based on an NLP technology, and the method comprises the steps: receiving a parking request of a user, carrying out the keyword analysis of the parking request, and obtaining a parking intention; a parking lot roadside unit is connected to acquire parking lot image data; comparing the parking lot image data based on the parking intention to perform feature matching, screening a parking space set, and listing parking space features of each parking space in the parking space set; acquiring historical parking data of the vehicle, extracting historical parking space features of the historical parking data and corresponding historical parking requests as input data, and performing neural network model training to obtain distribution weights corresponding to the parking space features after training; and calculating parking space priorities in the parking space set based on the parking space features and the distribution weights, and performing parking space recommendation based on the parking space priorities.

Description

Technical Field

[0001] The present invention relates to the field of vehicle parking technology, and in particular to a parking space search method and system based on NLP technology. Background Art

[0002] With the popularization and development of vehicles, the demand for parking has also increased. Parking-related vehicle technology and other related technologies are also developing day by day. However, the premise of parking is to have parking spaces for vehicles. Therefore, as the number of vehicles increases, the number and area of parking lots are also increasing to provide parking spaces for more vehicles.

[0003] However, as parking lots grow larger, finding a parking space becomes increasingly difficult. Drivers often have to drive around narrow parking lots for a while before finding a spot, wasting resources and impacting the user experience. Furthermore, the parking space found by drivers is often not the most suitable for them. For example, there might be a vacant space closer, but the driver may have taken a detour to find a space further away. As a result, the parking space they find may not be the most suitable for them, further impacting the user's parking experience. Summary of the Invention

[0004] In response to the problems existing in the prior art, an embodiment of the present invention provides a parking space search method and system based on NLP technology.

[0005] An embodiment of the present invention provides a parking space search method based on NLP technology, the method comprising: receiving a parking request from a user, performing keyword analysis on the parking request, and obtaining parking intention; Connect to the parking lot roadside unit to obtain parking lot image data; Performing feature matching by comparing parking lot image data based on the parking intention, screening a set of parking spaces, and listing parking space features of each parking space in the set of parking spaces; Obtaining historical parking data of the vehicle, extracting historical parking space features and corresponding historical parking requests from the historical parking data as input data, performing neural network model training, and obtaining allocation weights corresponding to the parking space features after training; The parking space priorities in the parking space set are calculated based on the parking space characteristics and the allocation weights, and parking space recommendations are made based on the parking space priorities.

[0006] In one embodiment, the method further comprises: Acquiring historical driving data of the user, performing parking data statistics on the historical driving data, and forming parking keywords for the user based on the statistical results; Combined with the parking keywords, the user's parking request is converted into a digitized parking intention.

[0007] In one embodiment, the method further comprises: Performing model classification of a neural network model based on the historical parking requests, iteratively training the model under different model classifications using the historical parking space features and historical parking data as input data, and outputting the user's parking tendency under the current model classification; A feature weight of the historical parking space feature is allocated based on the parking tendency, where the historical parking space feature includes a feature type and a feature value.

[0008] In one embodiment, the parking space features include basic features and real-time features; The basic features include: parking areas, parking examples and special parking spaces; The real-time features include: parking route congestion level and parking difficulty.

[0009] In one embodiment, the data sources of the collision severity level include: A parking space confirmation instruction from a user is received, and a travel route is planned based on a target parking space corresponding to the confirmation instruction, wherein the travel route refers to the real-time feature. An embodiment of the present invention provides a parking space search system based on NLP technology, the system comprising: a request module, configured to receive a user's parking request, perform keyword analysis on the parking request, and obtain parking intention; An image module is used to connect to the parking lot roadside unit to obtain parking lot image data; a feature module for performing feature matching based on the parking intention and comparing the parking lot image data, filtering a set of parking spaces, and listing parking space features of each parking space in the set of parking spaces; A weight module is configured to obtain historical parking data of vehicles, extract historical parking space features and corresponding historical parking requests from the historical parking data as input data, perform neural network model training, and obtain allocation weights corresponding to the parking space features after training; The parking space recommendation module is configured to calculate the parking space priority in the parking space set based on the parking space characteristics and the allocation weights, and recommend parking spaces based on the parking space priority.

[0010] In one embodiment, the system further comprises: A historical data module, configured to obtain a user's historical driving data, perform parking data statistics on the historical driving data, and form a parking keyword for the user based on the statistical results; The conversion module is used to convert the user's parking request into a digitized parking intention in combination with the parking keyword.

[0011] In one embodiment, the system further comprises: a training module configured to perform model classification of a neural network model using the historical parking requests, iteratively train the model using the historical parking space features and historical parking data as input data under different model classifications, and output the user's parking tendency under the current model classification; An allocation module is configured to allocate feature weights of the historical parking space features based on the parking tendency, where the historical parking space features include feature types and feature values. An embodiment of the present invention provides an electronic device, including a processor and a memory; The processor is connected to the memory; The memory is used to store executable program code; The processor reads the executable program code stored in the memory to run a program corresponding to the executable program code, so as to execute the method described in one or more embodiments.

[0012] An embodiment of the present invention provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the above-mentioned parking space search method based on NLP technology are implemented.

[0013] In view of the above, one or more embodiments of this specification receive a user's parking request, perform keyword analysis on the parking request, and obtain parking intent; connect to a parking lot roadside unit to obtain parking lot image data; compare the parking lot image data with the parking lot image data based on the parking intent for feature matching, filter a set of parking spaces, and list the parking space features of each parking space in the set; obtain historical parking data for the vehicle, extract historical parking space features from the historical parking data and corresponding historical parking requests as input data, train a neural network model, and obtain allocation weights corresponding to the trained parking space features; calculate parking space priorities within the parking space set based on the parking space features and allocation weights, and make parking space recommendations based on the parking space priorities. This enables real-time NLP technology to obtain parking lot data and user parking requests, perform parking space screening, and train based on keywords and historical data to determine parking space priorities and make parking space priority recommendations. This provides users with personalized parking space recommendations that are most suitable for them, while avoiding detours in the parking lot, helping users quickly find parking spaces, and conserving resources, thereby improving their parking experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0015] Figure 1 This is a flowchart of a parking space search method based on NLP technology provided in one embodiment of this specification.

[0016] Figure 2 This is a structural diagram of a parking space search system based on NLP technology provided in one embodiment of this specification.

[0017] Figure 3 This is a structural diagram of an electronic device provided by an embodiment of this specification. DETAILED DESCRIPTION

[0018] The subject matter described herein will now be discussed with reference to example embodiments. It should be understood that these embodiments are discussed only to enable those skilled in the art to better understand and implement the subject matter described herein, and are not intended to limit the scope of protection, applicability, or examples set forth in the claims. The functions and arrangements of the elements discussed may be changed without departing from the scope of protection of this specification. Various examples may omit, replace, or add various processes or components as needed. For example, the described method may be performed in an order different from the order described, and various steps may be added, omitted, or combined. In addition, features described relative to some examples may also be combined in other examples.

[0019] As used herein, the term "including" and its variations are open terms meaning "including but not limited to". The term "based on" means "based at least in part on". The terms "one embodiment" and "an embodiment" mean "at least one embodiment". The term "another embodiment" means "at least one other embodiment". The terms "first", "second", etc. may refer to different or the same objects. Other definitions may be included below, whether explicit or implicit. Unless the context clearly indicates otherwise, the definition of a term is consistent throughout the specification.

[0020] like Figure 1 As shown, an embodiment of the present invention provides a parking space search method based on NLP technology, comprising: Step S102: receiving a parking request from a user, performing keyword analysis on the parking request, and obtaining parking intention.

[0021] Specifically, when receiving a user's parking request, the parking request is analyzed. This can include not only traditional user input on the dashboard, but also receiving user voice data, converting it into text data through voice recognition, and extracting keywords from the text data related to the parking request. Parking requests are typically concise and can be basic user requests for parking, such as "park nearby," which indicates a preference for a space near the parking lot entrance; or "park and charge," which indicates a preference for a space near a charging station.

[0022] Furthermore, the relevant data extracted by keywords may include keywords related to fields such as "parking space for disabled persons", "parking space for charging piles", and "parking space No. 8" regarding parking space type, number, time limit, etc. Based on the acquired user parking keywords, the user's parking intention can be further determined. Compared with parking requests, parking intentions can convert users' simple parking requests into specific parking intentions, where parking intentions can include "parking space within 5m of charging piles", "parking space within 100m of parking lot entrance", "parking in zone A", "parking space with no other vehicles within 3m to the left and right of the parking space, easy to park", etc.

[0023] The keyword analysis process for converting parking requests into parking intentions can be combined with historical driving data or big data analysis. For example, historical driving data may show that users typically park within 100 meters of the parking lot entrance. Or, when their vehicle battery level is below 20%, they typically park in a parking space with a charging station. Based on this historical driving data, targeted parking keywords are generated for the user. These keywords can be combined with the user's parking requests to determine the corresponding parking intention. Furthermore, if historical driving data is insufficient for analysis, keyword extraction can be performed using big data parking data to determine the user's parking intention. This allows the system to convert relatively simple user instructions into specific parking intention data, improving the user's parking experience while also providing a data foundation for subsequent data training.

[0024] Step S104: Connect to the parking lot roadside unit to obtain parking lot image data.

[0025] Specifically, the vehicle terminal connects to the parking lot's roadside unit (RSU) using the vehicle-road collaboration protocol to obtain real-time data streams from the parking lot, such as parking space status and congestion index. This data can also be combined with an image data device to identify camera video streams forwarded by the RSU, combined with parking lot map data to identify parking spaces and determine the occupancy status of all parking spaces within the parking lot. Furthermore, this data can be combined with parking space demarcation markers, such as parking space dividing lines and area dividing lines, to create structured zoning for the parking lot.

[0026] Furthermore, parking lot image data can be combined with video stream data from the parking lot to construct a 3D map of the parking lot. For example, a SLAM map can be combined with the parking space coordinates, accessible paths, and occluded areas summarized in the video stream to construct a 3D map. Furthermore, parking space attributes (such as type and distance to the elevator) and dynamic data (such as remaining time and congestion index) can be encoded as vectors in the 3D map, providing a more concise representation of the parking lot situation.

[0027] Step S106 , performing feature matching based on the parking intention and comparing the parking lot image data, screening a parking space set, and listing parking space features of each parking space in the parking space set.

[0028] Specifically, based on feature matching between the parking intention and the parking lot image data, a set of parking spaces that meet the parking intention is determined. For example, if the parking intention is "parking space within 5 meters of a charging station," all available parking spaces within 5 meters of the charging station in the parking lot are used as features. These features are then matched against the parking spaces in the parking lot image data to select a set of parking spaces that meet these features. These spaces are then highlighted in the parking lot image data for the user to select. Furthermore, the corresponding parking space features can be further displayed near each parking space in the parking space set.

[0029] Among them, parking space features can display the current actual situation of the parking space, and can include basic features and real-time features. Basic features are general characteristics of the parking space, including the area where the parking space is located, the distance to the parking space, whether it is a special parking space (charging station parking space, disabled parking space, etc.), etc. Real-time features are the real-time situation of vehicles. For example, for the current situation of the parking lot, the route to some parking spaces may be occupied by other vehicles, making it difficult to reach the parking space. In this case, the unique feature "Congested route to parking space" can be marked next to the parking space. It can also include the difficulty of parking, etc. Real-time features can be adjusted in real time according to the situation of the parking lot.

[0030] Step S108 , obtaining historical parking data of the vehicle, extracting historical parking space features and corresponding historical parking requests from the historical parking data as input data, performing neural network model training, and obtaining allocation weights corresponding to the parking space features after training.

[0031] Specifically, historical parking data for a vehicle is obtained, and historical parking space features and corresponding historical parking requests are extracted from this data. These features, combined with the parking spaces associated with these historical parking requests, are used as input data for neural network model training. The neural network model can determine the weighted relationship between historical parking space features and parking spaces under different parking requests (corresponding to these historical parking requests). In other words, the neural network model is trained using parking requests as training categories. For example, taking the historical parking data for "nearby parking" as an example, all historical parking data for "nearby parking" is obtained. Then, historical parking space features for each parking session are obtained. These historical parking space features can include feature types such as "whether it is a charging space," "whether it is a disabled space," or "whether it is a narrow (difficult) parking space." They can also include feature values, such as the proximity range for "nearby parking," e.g., "50 meters from the parking lot entrance," "30 meters from the parking lot entrance," etc. These historical parking space features are iteratively trained to determine the user's parking preference for "nearby parking" requests. For example, if more than 90% of users park within 50m of the parking lot entrance, the weight of this feature can be adjusted to 0.9, and the corresponding weight for "parking lot entrance greater than 50m" can be adjusted to 0.1. Furthermore, if 90% of users park within 50m of the parking lot entrance due to the presence of a charging station, the weight of the "charging station presence" feature can be adjusted accordingly, and this weight will affect the weight of the "parking lot entrance greater than 50m" feature. The weights of the above features are for illustrative purposes only and are not intended to be limiting.

[0032] Step S110 , calculating the parking space priorities in the parking space set based on the parking space characteristics and the allocation weights, and recommending parking spaces based on the parking space priorities.

[0033] Specifically, the final calculation result of each parking space in the parking space set is calculated in combination with the parking space characteristics and the corresponding allocation weights, and based on the final calculation result, the parking space priority of each parking space in the parking space combination is sorted for users to choose, so as to provide users with parking options corresponding to parking spaces according to their personalized needs, thereby improving the user's parking experience.

[0034] Furthermore, after the user selects the corresponding parking option in the parking space set, the optimal route to the corresponding parking space is planned for the user, so that the user can reach the corresponding parking space according to the flow line instructions. Among them, the optimal route planning refers to real-time characteristics, such as the congestion level of the parking space route and the difficulty of parking, and provides the user with the optimal route in real time.

[0035] An embodiment of the present invention provides a parking space search method based on NLP technology. The method receives a user's parking request, performs keyword analysis on the parking request, and obtains parking intent. The method then connects to the parking lot roadside unit to obtain parking lot image data. Based on the parking intent, the method performs feature matching against the parking lot image data, filters a set of parking spaces, and lists the parking space features of each parking space in the set. The method then obtains historical parking data for the vehicle, extracts historical parking space features from the historical parking data and corresponding historical parking requests as input data, trains a neural network model, and obtains allocation weights corresponding to the trained parking space features. The method then calculates the priority of parking spaces in the parking space set based on the parking space features and allocation weights, and recommends parking spaces based on the parking space priority. This method can provide users with personalized parking space recommendations that best suit their needs, while avoiding detours in the parking lot and helping them quickly find parking spaces, thus saving resources and improving their parking experience.

[0036] See Figure 2 , Figure 2 This is a schematic diagram of the structure of a parking space search system based on NLP technology provided in an embodiment of the present application. Figure 2 As shown, the system includes: The request module S202 is configured to receive a parking request from a user, perform keyword analysis on the parking request, and obtain parking intention; Image module S204, used to connect to the parking lot roadside unit to obtain parking lot image data; A feature module S206 is configured to perform feature matching based on the parking intention and the parking lot image data, filter a set of parking spaces, and list parking space features of each parking space in the set of parking spaces; A weighting module S208 is configured to obtain historical parking data of vehicles, extract historical parking space features and corresponding historical parking requests from the historical parking data as input data, perform neural network model training, and obtain allocation weights corresponding to the parking space features after training; The parking space recommendation module S210 is configured to calculate the parking space priority in the parking space set based on the parking space characteristics and the allocation weights, and recommend parking spaces based on the parking space priority.

[0037] In another embodiment, a parking space search system based on NLP technology further includes: A historical data module, configured to obtain a user's historical driving data, perform parking data statistics on the historical driving data, and form a parking keyword for the user based on the statistical results; The conversion module is used to convert the user's parking request into a digitized parking intention in combination with the parking keyword.

[0038] In another embodiment, a parking space search system based on NLP technology further includes: a training module configured to perform model classification of a neural network model using the historical parking requests, iteratively train the model using the historical parking space features and historical parking data as input data under different model classifications, and output the user's parking tendency under the current model classification; An allocation module is configured to allocate feature weights of the historical parking space features based on the parking tendency, where the historical parking space features include feature types and feature values.

[0039] Those skilled in the art will clearly understand that the technical solutions of the embodiments of the present application can be implemented with the help of software and / or hardware. "Unit" and "module" in this specification refer to software and / or hardware that can independently perform or cooperate with other components to perform specific functions, where the hardware can be, for example, a field-programmable gate array (FPGA) or an integrated circuit (IC).

[0040] Each processing unit and / or module in the embodiments of the present application may be implemented by an analog circuit that implements the functions described in the embodiments of the present application, or may be implemented by software that executes the functions described in the embodiments of the present application. See also Figure 3 , which shows a schematic diagram of the structure of an electronic device involved in an embodiment of the present application, the electronic device can be used to implement Figure 1 The method in the embodiment shown. Figure 3 As shown, the electronic device 300 may include: at least one processor 301 , at least one network interface 304 , a user interface 303 , a memory 305 , and at least one communication bus 302 .

[0041] The communication bus 302 is used to implement the connection and communication between these components.

[0042] The user interface 303 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 303 may also include a standard wired interface and a wireless interface.

[0043] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0044] The processor 301 may include one or more processing cores. The processor 301 utilizes various interfaces and circuits to connect various components within the electronic device 300. It executes instructions, programs, code sets, or instruction sets stored in the memory 305, and accesses data stored in the memory 305 to perform various functions and process data within the electronic device 300. Optionally, the processor 301 may be implemented using at least one of the following hardware forms: a digital signal processing (DSP), a field-programmable gate array (FPGA), or a programmable logic array (PLA). The processor 301 may integrate one or a combination of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. The CPU primarily processes the operating system, user interface, and application programs; the GPU is responsible for rendering and drawing content displayed on the display; and the modem handles wireless communications. It is understood that the modem may also be implemented independently of the processor 301 and implemented on a separate chip.

[0045] Among them, the memory 305 may include a random access memory (RAM) or a read-only memory (Read-Only Memory). Optionally, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 305 may also be optionally at least one storage device located away from the aforementioned processor 301. As Figure 3 As shown, the memory 305 as a computer storage medium may include an operating system, a network communication module, a user interface module, and program instructions.

[0046] exist Figure 3In the electronic device 300 shown, the user interface 303 is mainly used to provide an input interface for the user and obtain data input by the user; and the processor 301 can be used to call the image-generated interactive application stored in the memory 305 and perform the following operations: receiving the user's parking request, performing keyword analysis on the parking request, and obtaining parking intention; connecting to the parking lot roadside unit to obtain parking lot image data; performing feature matching based on the parking lot image data compared with the parking intention, filtering a parking space set, and listing the parking space features of each parking space in the parking space set; obtaining historical parking data of the vehicle, extracting historical parking space features of the historical parking data and corresponding historical parking requests as input data, performing neural network model training, and obtaining the allocation weights corresponding to the parking space features after training; calculating the parking space priority in the parking space set based on the parking space features and the allocation weights, and making parking space recommendations based on the parking space priority. The present application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above method. The computer-readable storage medium may include, but is not limited to, any type of disk, including a floppy disk, an optical disk, a DVD, a CD-ROM, a microdrive, a magneto-optical disk, a ROM, a RAM, an EPROM, an EEPROM, a DRAM, a VRAM, a flash memory device, a magnetic card or an optical card, a nanosystem (including a molecular memory IC), or any type of medium or device suitable for storing instructions and / or data.

[0047] It should be noted that for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by this application.

[0048] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0049] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interface, and the indirect coupling or communication connection of the device or unit can be electrical or other forms.

[0050] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0051] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0052] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a memory and includes a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM), random access memory (RAM), mobile hard disk, magnetic disk, or optical disk, etc., various media that can store program code.

[0053] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be completed by instructing related hardware through a program. The program may be stored in a computer-readable memory, which may include a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0054] The foregoing description of this specification describes specific embodiments. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A parking space search method based on NLP technology, the method comprising: receiving a parking request from a user, performing keyword analysis on the parking request, and obtaining parking intention; Connect to the parking lot roadside unit to obtain parking lot image data; Performing feature matching by comparing parking lot image data based on the parking intention, screening a set of parking spaces, and listing parking space features of each parking space in the set of parking spaces; Obtaining historical parking data of the vehicle, extracting historical parking space features and corresponding historical parking requests from the historical parking data as input data, performing neural network model training, and obtaining allocation weights corresponding to the parking space features after training; The parking space priorities in the parking space set are calculated based on the parking space characteristics and the allocation weights, and parking space recommendations are made based on the parking space priorities.

2. The method according to claim 1, characterized in that The keyword analysis of the parking request to obtain the parking intention includes: Acquiring historical driving data of the user, performing parking data statistics on the historical driving data, and forming parking keywords for the user based on the statistical results; Combined with the parking keywords, the user's parking request is converted into a digitized parking intention.

3. The method according to claim 2, characterized in that The neural network model training process includes: Performing model classification of a neural network model based on the historical parking requests, iteratively training the model under different model classifications using the historical parking space features and historical parking data as input data, and outputting the user's parking tendency under the current model classification; A feature weight of the historical parking space feature is allocated based on the parking tendency, where the historical parking space feature includes a feature type and a feature value.

4. The method according to claim 1, wherein The parking space features include basic features and real-time features; The basic features include: parking areas, parking examples and special parking spaces; The real-time features include: parking route congestion level and parking difficulty.

5. The method according to claim 4, characterized in that The method further comprises: A parking space confirmation instruction from a user is received, and a travel route is planned based on a target parking space corresponding to the confirmation instruction, wherein the travel route refers to the real-time feature.

6. A parking space search system based on NLP technology, characterized in that: The system comprises: a request module, configured to receive a user's parking request, perform keyword analysis on the parking request, and obtain parking intention; An image module is used to connect to the parking lot roadside unit to obtain parking lot image data; a feature module for performing feature matching based on the parking intention and comparing the parking lot image data, filtering a set of parking spaces, and listing parking space features of each parking space in the set of parking spaces; A weight module is configured to obtain historical parking data of vehicles, extract historical parking space features and corresponding historical parking requests from the historical parking data as input data, perform neural network model training, and obtain allocation weights corresponding to the parking space features after training; The parking space recommendation module is configured to calculate the parking space priority in the parking space set based on the parking space characteristics and the allocation weights, and recommend parking spaces based on the parking space priority.

7. The system according to claim 6, characterized in that The system further comprises: A historical data module, configured to obtain a user's historical driving data, perform parking data statistics on the historical driving data, and form a parking keyword for the user based on the statistical results; The conversion module is used to convert the user's parking request into a digitized parking intention in combination with the parking keyword.

8. The system according to claim 7, characterized in that The system further comprises: a training module configured to perform model classification of a neural network model using the historical parking requests, iteratively train the model using the historical parking space features and historical parking data as input data under different model classifications, and output the user's parking tendency under the current model classification; An allocation module is configured to allocate feature weights of the historical parking space features based on the parking tendency, where the historical parking space features include feature types and feature values.

9. An electronic device comprising a processor and a memory; The processor is connected to the memory; The memory is used to store executable program code; The processor reads the executable program code stored in the memory to run a program corresponding to the executable program code, so as to execute the method according to any one of claims 1 to 5.

10. A computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the method according to any one of claims 1 to 5 when executed by a processor.

Images