Method and device for predicting parking lot congestion probability, terminal equipment and storage medium

Abstract

The application discloses a parking lot congestion probability prediction method and device, a terminal device and a storage medium. The parking lot congestion probability prediction method comprises the following steps: determining a target time period and a plurality of target parking lot tags corresponding to a target parking lot; obtaining a corresponding target time tag score according to the target time period and the target parking lot tag, wherein the target time tag score is calculated based on a preset data screening rule; calculating a target total score of the target parking lot according to the target time tag score; and obtaining a congestion probability of the target parking lot based on the target total score and a preset attribute total score, wherein the attribute total score is calculated based on a preset scoring rule. The application aims to solve the problem that parking lots do not provide the total number of parking spaces and the number of remaining parking spaces, thereby reducing the parking efficiency.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a method, apparatus, terminal equipment, and storage medium for predicting parking lot congestion probability. Background Technology

[0002] With the development of economy and technology, the number of vehicles is increasing, and the demand for parking lots by vehicle users is also growing day by day.

[0003] Currently, many parking lots do not provide the total number of parking spaces or the number of remaining spaces. They can only determine the number of parking spaces based on the maximum number of vehicles entering and exiting the lot throughout the day, and then infer the remaining spaces based on the entry and exit data. However, there is currently no such parking platform in the domestic market. If some parking lots are not within the service scope of such a platform, it will result in the inability to find out the number of remaining parking spaces. This leads to drivers not being able to determine whether there are available parking spaces when they want to go to a certain place, forcing them to search aimlessly for parking spaces, resulting in low parking efficiency.

[0004] Therefore, parking currently suffers from low efficiency. Summary of the Invention

[0005] The main objective of this application is to provide a method, apparatus, terminal equipment, and storage medium for predicting the probability of parking lot congestion, aiming to solve the problem of low parking efficiency caused by parking lots not providing the total number of parking spaces and the number of remaining parking spaces.

[0006] To achieve the above objectives, this application provides a method for predicting the probability of parking lot congestion, the method comprising: Determine the target time period and the corresponding target parking lot labels; Based on the target time period and target parking lot label, the corresponding target time label score is obtained, and the target time label score is calculated based on preset data filtering rules; Calculate the target total score for the target parking lot based on the target time tag score; Based on the target total score and the preset attribute total score, the congestion probability of the target parking lot is obtained, and the attribute total score is calculated based on the preset scoring rules.

[0007] Optionally, before the step of determining the target time period and the several target parking lot labels corresponding to the target parking lot, the method further includes: Define several parking lot labels and several time periods; Each parking lot label is categorized under its corresponding label attribute, resulting in several label attributes; The parking lot tags for each time period are scored to obtain the corresponding time tag score; Based on the preset high score rules, the scores of one time tag for each tag attribute are added together to obtain the total score of the attribute.

[0008] Optionally, the step of scoring the parking lot tags corresponding to each time period to obtain the corresponding time tag score includes: Obtain parking records for each day within a preset date range from several parking lots; Based on the parking records, it is determined whether the parking lot has available parking spaces during the time period, thus obtaining information on several parking spaces. The time tag score is obtained by equally dividing the information of each parking space.

[0009] Optionally, the step of obtaining parking records for each day of several parking lots within a preset date period includes: The parking record is obtained by using a preset incremental strategy to obtain the historical maximum number of orders, entry count, and exit count within the specified date.

[0010] Optionally, the step of determining a plurality of parking lot labels includes: Obtain first data from a pre-defined data warehouse; and / or Call the preset interface to obtain the second data; The parking lot label is determined based on the first data and / or the second data.

[0011] Optionally, after the step of obtaining the congestion probability of the target parking lot based on the target total score and the preset attribute total score, wherein the attribute total score is calculated based on a preset scoring rule, the method further includes: Obtain the actual probability of the target parking lot; The actual probability is compared with the crowding probability to obtain a first comparison result; If the first comparison result exceeds the preset difference, then verify whether the target parking lot is a special parking lot; If so, the target parking lot will be set as a special parking lot.

[0012] Optionally, the step of verifying whether the target parking lot is a special parking lot includes: Determine other parking lot labels and / or other label attributes besides the currently described parking lot labels and / or label attributes; Based on the scoring rules, data filtering rules, other parking lot tags and / or the other tag attributes, update the total attribute score, parking lot tags and / or tag attributes; Based on the updated attribute total score, the updated parking lot label and / or the updated label attribute, the steps of determining the target time period and the target parking lot corresponding to several target parking lot labels and subsequent steps are performed to obtain the updated congestion probability. The actual probability is compared with the updated congestion probability to obtain a second comparison result; If the second comparison result does not exceed the difference, then the target parking lot does not belong to the special parking lot; If the second comparison result exceeds the difference, then return to the step of determining other parking lot labels and / or other label attributes besides the current parking lot label and / or label attributes; The cycle repeats sequentially according to a preset number of times until the cycle ends, at which point the target parking lot belongs to the special parking lot.

[0013] This application also proposes a device for predicting the probability of parking lot congestion, the device comprising: The determination module is used to determine the target time period and the target parking lot corresponding to several target parking lot labels; The calculation module is used to obtain the corresponding target time tag score based on the target time period and target parking lot tag, wherein the target time tag score is calculated based on preset data filtering rules; Calculate the target total score for the target parking lot based on the target time tag score; The prediction module is used to obtain the congestion probability of the target parking lot based on the target total score and the preset attribute total score, wherein the attribute total score is calculated based on the preset scoring rules.

[0014] This application also proposes a terminal device, which includes a memory, a processor, and a parking lot congestion probability prediction program stored in the memory and executable on the processor. When the parking lot congestion probability prediction program is executed by the processor, it implements the steps of the parking lot congestion probability prediction method as described above.

[0015] This application also proposes a computer-readable storage medium storing a parking lot congestion probability prediction program, which, when executed by a processor, implements the steps of the parking lot congestion probability prediction method as described above.

[0016] The parking lot congestion probability prediction method, device, terminal equipment, and storage medium proposed in this application determine a target time period and a number of target parking lot labels corresponding to the target parking lot; and obtain a corresponding target time label score based on the target time period and target parking lot labels, wherein the target time label score is calculated based on a preset data filtering rule. Based on the target time tag score, the target total score of the target parking lot is calculated; based on the target total score and a preset attribute total score, the congestion probability of the target parking lot is obtained, whereby the attribute total score is calculated based on a preset scoring rule. By setting target parking lot tags to obtain corresponding target total scores, and based on the target total score and preset attribute total scores, the probability of whether the target parking lot has available parking spaces can be obtained. This solves the problem of low parking efficiency caused by parking lots not providing the total number of parking spaces and the number of remaining parking spaces, thus improving parking efficiency. Based on the solution of this application, starting from the real-world problem of parking difficulties, a method for predicting parking lot congestion probability based on parking lot tag scores using publicly available information and existing data is proposed, and the effectiveness of the parking lot congestion probability prediction method proposed in this application is verified. Attached Figure Description

[0017] Figure 1 This is a schematic diagram of the functional modules of the terminal equipment to which the parking lot congestion probability prediction device of this application belongs; Figure 2 This is a flowchart illustrating a first exemplary embodiment of the parking lot congestion probability prediction method of this application; Figure 3 This is a flowchart illustrating a second exemplary embodiment of the parking lot congestion probability prediction method of this application; Figure 4 This is a flowchart illustrating a third exemplary embodiment of the parking lot congestion probability prediction method of this application; Figure 5 This is a flowchart illustrating a fourth exemplary embodiment of the parking lot congestion probability prediction method of this application; Figure 6 This is a flowchart illustrating a fifth exemplary embodiment of the parking lot congestion probability prediction method of this application; Figure 7 This is a flowchart illustrating a sixth exemplary embodiment of the parking lot congestion probability prediction method of this application; Figure 8 This is a flowchart illustrating the seventh exemplary embodiment of the method for predicting parking lot congestion probability in this application.

[0018] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0019] It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit this application.

[0020] The main solution of this application embodiment is as follows: First, determine a target time period and several target parking lot labels corresponding to the target parking lot. Second, obtain a corresponding target time label score based on the target time period and target parking lot labels, where the target time label score is calculated based on a preset data filtering rule. Third, calculate the target total score of the target parking lot based on the target time label score. Fourth, obtain the congestion probability of the target parking lot based on the target total score and a preset attribute total score, where the attribute total score is calculated based on a preset scoring rule. By setting target parking lot labels to obtain a corresponding target total score, and based on the target total score and the preset attribute total score, the probability of whether the target parking lot has available parking spaces can be obtained. This solves the problem of low parking efficiency caused by parking lots not providing the total number of parking spaces and the number of remaining parking spaces, thus improving parking efficiency. Based on this application solution, starting from the real-world problem of parking difficulties, a method for predicting parking lot congestion probability based on parking lot label scores using publicly available information and existing data is proposed. The effectiveness of the proposed parking lot congestion probability prediction method is verified using this method.

[0021] This application's embodiments take into account that, currently, many parking lots do not provide the total number of parking spaces or the number of remaining spaces. They can only determine the number of parking spaces by collecting parking lot entry and exit data around the clock, using the maximum number of parking spaces in the parking lot as the starting point, and then inferring the remaining spaces based on the entry and exit data. However, there is currently no such parking platform in the domestic market. If some parking lots are not within the service scope of this parking platform, it will result in the inability to find out the number of remaining parking spaces. This leads to drivers not being able to determine whether there are available parking spaces when they want to go to a certain place, forcing them to search for parking spaces aimlessly, resulting in low parking efficiency.

[0022] Therefore, the embodiments of this application, starting from the real-world problem of parking difficulties, propose a method for predicting the probability of parking congestion based on parking lot label scores of publicly available information and existing data, and verify the effectiveness of the proposed method for predicting the probability of parking congestion.

[0023] Specifically, refer to Figure 1 , Figure 1 This diagram illustrates the functional modules of the terminal device to which the parking lot congestion probability prediction device of this application belongs. The parking lot congestion probability prediction device can be independent of the terminal device, capable of calculating time-stamped scores and predicting the congestion probability of vacant parking lots. It can be implemented on the terminal device in hardware or software form. The terminal device can be a smart mobile terminal with data processing capabilities, such as a mobile phone or tablet, or a fixed terminal device or server with data processing capabilities.

[0024] In this embodiment, the terminal device to which the parking lot congestion probability prediction device belongs includes at least an output module 110, a processor 120, a memory 130, and a communication module 140.

[0025] The memory 130 stores the operating system and a prediction program for parking lot congestion probability. The parking lot congestion probability prediction device can store information such as: a determined target time period and several target parking lot tags corresponding to the target parking lot; the target time tag score obtained based on the target time period and target parking lot tags; the target time tag score calculated based on preset data filtering rules; the target total score of the target parking lot calculated based on the target time tag score; the congestion probability of the target parking lot obtained based on the target total score and preset attribute total score; and the attribute total score calculated based on preset scoring rules. The output module 110 can be a display screen, etc. The communication module 140 can include a WIFI module, a mobile communication module, and a Bluetooth module, etc., and communicates with external devices or servers through the communication module 140.

[0026] When the prediction program for parking lot congestion probability in memory 130 is executed by the processor, it performs the following steps: Determine the target time period and the corresponding target parking lot labels; Based on the target time period and target parking lot label, the corresponding target time label score is obtained, and the target time label score is calculated based on preset data filtering rules; Calculate the target total score for the target parking lot based on the target time tag score; Based on the target total score and the preset attribute total score, the congestion probability of the target parking lot is obtained, and the attribute total score is calculated based on the preset scoring rules.

[0027] Furthermore, when the program predicting parking lot congestion probability in memory 130 is executed by the processor, it also performs the following steps: Define several parking lot labels and several time periods; Each parking lot label is categorized under its corresponding label attribute, resulting in several label attributes; The parking lot tags for each time period are scored to obtain the corresponding time tag score; Based on the preset high score rules, the scores of one time tag for each tag attribute are added together to obtain the total score of the attribute.

[0028] Furthermore, when the program predicting parking lot congestion probability in memory 130 is executed by the processor, it also performs the following steps: Obtain parking records for each day within a preset date range from several parking lots; Based on the parking records, it is determined whether the parking lot has available parking spaces during the time period, thus obtaining information on several parking spaces. The time tag score is obtained by equally dividing the information of each parking space.

[0029] Furthermore, when the program predicting parking lot congestion probability in memory 130 is executed by the processor, it also performs the following steps: The parking record is obtained by using a preset incremental strategy to obtain the historical maximum number of orders, entry count, and exit count within the specified date.

[0030] Furthermore, when the program predicting parking lot congestion probability in memory 130 is executed by the processor, it also performs the following steps: Obtain first data from a pre-defined data warehouse; and / or Call the preset interface to obtain the second data; The parking lot label is determined based on the first data and / or the second data.

[0031] Furthermore, when the program predicting parking lot congestion probability in memory 130 is executed by the processor, it also performs the following steps: Obtain the actual probability of the target parking lot; The actual probability is compared with the crowding probability to obtain a first comparison result; If the first comparison result exceeds the preset difference, then verify whether the target parking lot is a special parking lot; If so, the target parking lot will be set as a special parking lot.

[0032] Furthermore, when the program predicting parking lot congestion probability in memory 130 is executed by the processor, it also performs the following steps: Determine other parking lot labels and / or other label attributes besides the currently described parking lot labels and / or label attributes; Based on the scoring rules, data filtering rules, other parking lot tags and / or the other tag attributes, update the total attribute score, parking lot tags and / or tag attributes; Based on the updated attribute total score, the updated parking lot label and / or the updated label attribute, the steps of determining the target time period and the target parking lot corresponding to several target parking lot labels and subsequent steps are performed to obtain the updated congestion probability. The actual probability is compared with the updated congestion probability to obtain a second comparison result; If the second comparison result does not exceed the difference, then the target parking lot does not belong to the special parking lot; If the second comparison result exceeds the difference, then return to the step of determining other parking lot labels and / or other label attributes besides the current parking lot label and / or label attributes; The cycle repeats sequentially according to a preset number of times until the cycle ends, at which point the target parking lot belongs to the special parking lot.

[0033] This embodiment, through the above-described scheme, specifically determines a target time period and several target parking lot tags corresponding to the target parking lot; based on the target time period and target parking lot tags, it obtains a corresponding target time tag score, which is calculated based on a preset data filtering rule; based on the target time tag score, it calculates the target total score for the target parking lot; based on the target total score and a preset attribute total score, it obtains the congestion probability of the target parking lot, which is calculated based on a preset scoring rule. By setting target parking lot tags to obtain a corresponding target total score for the target parking lot, and based on the target total score and the preset attribute total score, it obtains the probability of whether the target parking lot has available parking spaces, which can solve the problem of low parking efficiency caused by parking lots not providing the total number of parking spaces and the number of remaining parking spaces, thus improving parking efficiency. Based on the scheme of this application, starting from the real-world problem of parking difficulties, it proposes a method for predicting the parking lot congestion probability based on parking lot tag scores of publicly available information and existing data, and verifies the effectiveness of the parking lot congestion probability prediction method proposed in this application.

[0034] Based on, but not limited to, the terminal device architecture described above, this application proposes method embodiments.

[0035] Reference Figure 2 , Figure 2 This is a flowchart illustrating a first exemplary embodiment of the parking lot congestion probability prediction method of this application. The parking lot congestion probability prediction method includes: Step S210: Determine the target time period and the corresponding target parking lot labels; Specifically, many parking lots currently do not provide the total number of parking spaces or the number of remaining spaces. They can only collect entry and exit data around the clock, determining the number of parking spaces based on the maximum number of vehicles parked, and then inferring the remaining spaces based on the entry and exit data. However, there is currently no such parking platform in the domestic market. If some parking lots are not within the service scope of such a platform, the number of remaining parking spaces cannot be found. This leads to drivers being unable to determine if there are available parking spaces when they want to go to a certain place, forcing them to search aimlessly for parking spaces, resulting in low parking efficiency. Against this background, a method for predicting the probability of parking lot congestion based on parking lot tag ratings using publicly available information and existing data is proposed. First, the target time period and several target parking lot tags corresponding to the target parking lot are determined. For example, the target time period is determined to be weekdays from 8 AM to 12 AM and parking lot A is determined. Based on the weekdays from 8 AM to 12 AM time period, the characteristics of parking lot A are determined, such as geographical features and nature features, which can determine several target parking lot tags. For example, the three tags for parking lot A are "Nanshan District", "Shopping Center", and "Nearby Integrated Parking Garage".

[0036] It should be noted that, since the busy conditions are different for each time period, in this embodiment, when a vehicle is looking for a parking space, the target time period is first determined, and then the target parking lot tag corresponding to the target time period is used. The target time period is set according to the actual situation, including but not limited to the current time period and future time periods.

[0037] Step S220: Based on the target time period and target parking lot label, obtain the corresponding target time label score, which is calculated based on a preset data filtering rule; Specifically, data filtering rules are used to determine a parking lot label and calculate the congestion level of all parking lots under that label. A score is then assigned based on this congestion level to obtain a time-label score. It should be noted that parking lots with multiple labels are unaffected, and grouped data can be repeated; however, each target parking lot has only one label for the same attribute. Based on the pre-determined labels, corresponding scores can be obtained. For example, the label "Nanshan District" corresponds to a score of 50, the label "Shopping Center" corresponds to a score of 40, and the label "Nearby integrated parking garage" corresponds to a score of 60.

[0038] Step S230: Calculate the target total score of the target parking lot based on the target time tag score; Specifically, based on the target parking lot label score obtained in the previous step S220, the target total score of the target parking lot is calculated to be 50+40+60=150 points.

[0039] Step S240: Based on the target total score and the preset attribute total score, the congestion probability of the target parking lot is obtained. The attribute total score is calculated based on the preset scoring rules.

[0040] Specifically, based on the target total score and attribute total score, the probability to be adjusted is obtained. This probability is then adjusted using a preset accuracy rate to determine the probability of whether the target parking lot has available parking spaces. The determination of whether parking spaces are available, along with the probability, is provided to the user to facilitate their travel decision.

[0041] The scoring rules are used to add up the highest time tag scores for each tag attribute. If there are multiple highest scores for the same tag attribute, any one of the highest scores is selected to obtain the total attribute score.

[0042] To determine the probability that the target parking lot has available parking spaces: α=S1 / S β 100% In the formula, S1 is the target total score, S is the attribute total score, and β is the accuracy.

[0043] It's important to note that the initial value of β is 1, and it's calculated after each time data on parking lot occupancy is obtained. This can be verified in reverse: based on order inventory data, the accuracy of the results returned by all parking lots within a given time period is analyzed. This β value is stored in a database. As orders increase, β will get closer and closer to 1. Thus, with the increase in order data, the accuracy of vehicle tag judgments regarding parking space vacancy can be better verified and corrected. Furthermore, big data analytics platforms can quantify people's experiences, making the results more scientific, systematic, and accurate.

[0044] Assuming the pre-calculated total attribute score is 200 points, and the target total score S1 calculated in the previous step S220 is 150 points, then the probability of whether the target parking lot has available parking spaces is 150 / 200 / 1. 100% = 75%.

[0045] This embodiment, through the above-described scheme, specifically determines a target time period and several target parking lot tags corresponding to the target parking lot; based on the target time period and target parking lot tags, it obtains a corresponding target time tag score, which is calculated based on a preset data filtering rule; based on the target time tag score, it calculates the target total score for the target parking lot; based on the target total score and a preset attribute total score, it obtains the congestion probability of the target parking lot, which is calculated based on a preset scoring rule. By setting target parking lot tags to obtain a corresponding target total score, and based on the target total score and the preset attribute total score, it obtains the probability of whether the target parking lot has available parking spaces, which can solve the problem of low parking efficiency caused by parking lots not providing the total number of parking spaces and the number of remaining parking spaces, thus improving parking efficiency.

[0046] Reference Figure 3 , Figure 3 This is a flowchart illustrating a second exemplary embodiment of the parking lot congestion probability prediction method of this application. Based on the above... Figure 2 In the embodiment shown, before step S210, which involves determining the target time period and the corresponding target parking lot labels, the following steps are included: Step S310: Determine a number of parking lot labels and a number of time periods; Specifically, parking lots are tagged, and public information and inventory data are analyzed based on time periods to indicate whether a parking lot has available parking spaces. The analysis also identifies which tags are feasible, such as parking lot location tags and business district tags.

[0047] In this embodiment, firstly, time periods are determined, which are set according to actual conditions, such as morning peak hours, evening peak hours, and off-peak hours. For example, time periods can be defined as segments of 4 hours each. Weekday time periods are 8 AM to 12 AM, and holiday time periods are 4 PM to 8 PM. Then, some tags are defined based on actual conditions. SQL is then used to clean order data, user data, and data obtained from third parties according to different time periods, allowing the parking lots to be tagged with the defined tags. For example, tags include, but are not limited to: Nanshan District, High-tech Zone, integrated parking garages near government facilities, entertainment centers, etc.

[0048] For the existing data portion, including but not limited to parking lot data from business partnerships, these parking lots are tagged to determine the relationship between the tags and peak traffic periods. Machine learning or big data analytics are then used to analyze the impact of each tag on parking space availability.

[0049] For publicly available information, by querying the area and construction year of the community (the required number of parking spaces varies depending on the government's requirements at different times), one can roughly estimate the number of parking spaces and generate a tag indicating the year of construction (newer communities generally have more parking spaces available). Furthermore, by knowing that there is a government-built integrated parking garage nearby, one can obtain a tag indicating "integrated parking garage nearby," which undoubtedly has a significant impact on the number of remaining parking spaces.

[0050] Step S320: Classify each parking lot label into its corresponding label attribute to obtain several label attributes; Specifically, parking lots with the same tag attributes generally have a consistent level of parking space occupancy within a certain time period. For example, "old residential areas" generally have no available parking spaces at night, and large event centers generally have no parking spaces during a certain time on weekend afternoons. This application embodiment uses data analysis methods to digitize and visualize people's daily experiences. The final result is to obtain tag information that can be associated with remaining parking spaces and their corresponding scores. After obtaining the parking lot profile (i.e., after tagging the parking lots), the existing order data in the database is categorized by parking lot name, and the historical maximum number of parking spaces for that parking lot (i.e., the number of entries minus the number of exits) is obtained. Data filtering is performed on tags for a specific tag attribute. For example, data filtering is performed on all tags under the tag attribute "geographical location." For example, tags under the "geographical location" tag attribute include, but are not limited to, tags such as "Nanshan District" and "Futian District." Calculations can be performed specifically for parking lots corresponding to the "Nanshan District" tag.

[0051] Step S330: Score the parking lot tag corresponding to each time period to obtain the corresponding time tag score; Specifically, parking lots with the same label are filtered out (parking lots with multiple labels are not affected, and grouped data can be repeated).

[0052] Step S340: Based on the preset high score rules, add up the scores of one time tag for each tag attribute to obtain the total score of the attribute.

[0053] Specifically, the highest-scoring tag under each tag attribute is calculated for different time periods. If two tags have the same score, only one is selected. For example, if "Nanshan District" is the highest-scoring tag under the "Geographic Location" tag attribute, then 50 points are selected for that tag. If "Shopping Park" is the highest-scoring tag under the "Business District" tag attribute, then 80 points are selected for that tag. If "Owns an Integrated Garage" is the highest-scoring tag under the "Does It Own an Integrated Garage?" tag attribute, then 70 points are selected for that tag. The total score S = 50 + 80 + 70 = 200 points.

[0054] This embodiment, through the above-described scheme, specifically involves determining several parking lot labels and several time periods; classifying each parking lot label under a corresponding label attribute to obtain several label attributes; scoring the parking lot labels corresponding to each time period to obtain the corresponding time label score; and, based on a preset high-score rule, adding one time label score for each label attribute to obtain the total attribute score. By labeling target parking lots and classifying labels through analysis of publicly available information and existing data, this approach addresses the problem of low parking efficiency caused by parking lots not providing the total number of parking spaces and the number of remaining parking spaces.

[0055] Reference Figure 4 , Figure 4 This is a flowchart illustrating a third exemplary embodiment of the parking lot congestion probability prediction method of this application. Based on the above... Figure 3 In the embodiment shown, step S330 involves scoring the parking lot tag corresponding to each time period to obtain the corresponding time tag score, including: Step S410: Obtain parking records for each day of several parking lots within a preset date period; Specifically, the statistics show the number of parking spaces that reach their maximum capacity within a preset timeframe. For example, the maximum number of parking spaces reached in July; or the maximum number of parking spaces reached within a six-month period.

[0056] Step S420: Based on the parking records, determine whether the parking lot has available parking spaces during the time period to obtain information on several parking spaces; Specifically, if a parking lot provides parking spaces, the availability of spaces during a specific time period can be determined directly based on order data. If a parking lot does not provide parking spaces, the maximum historical order count is analyzed to determine the number of available spaces for that lot. The availability of spaces during a specific time period is then determined through order analysis. An incremental strategy is used to replenish the maximum number of available spaces. If the number of orders each day exceeds this historical threshold, the number of available spaces is updated. For example, on August 1st, within a weekday from 8 AM to 12 AM, tagged "Nanshan District," there are 100 parking lots. 50 of these are considered crowded during the weekday 8 AM to 12 AM period, thus providing the parking space availability information.

[0057] Step S430: Divide the situation of each parking space equally to obtain the time tag score.

[0058] Specifically, based on the obtained time periods, the parking lots are divided into time-period zones. The more parking lots in a certain zone, the greater the impact of this label on the parking lots. For weekdays from 8 AM to 12 AM, the specific average calculation is as follows: According to the previous step S420, on August 1st, the label "Nanshan District" has 100 parking lots from 8 AM to 12 AM on weekdays, and 50 of them meet the criteria for crowded parking lots. Therefore, the ratio is 50 / 100. 100% = 50 points, meaning the "Nanshan District" tag on August 1st is worth 50 points. Similarly, the tag for August 2nd during the weekday 8 AM - 12 AM time period is worth 40 points, and the tag for August 3rd during the weekday 8 AM - 12 AM time period is worth 60 points. Therefore, the time tag score for "Nanshan District" is (50 + 40 + 60) / 3 = 50 points.

[0059] This embodiment, through the above-described scheme, specifically obtains the parking records of several parking lots for each day within a preset date; based on the parking records, it determines whether the parking lot has available parking spaces during the specified time period, obtaining several parking space statuses; and then calculates the time tag score by equally dividing each parking space status. By obtaining parking records for several days and calculating the target total score by differentiating time periods, the problem of low parking efficiency caused by parking lots not providing the total number of parking spaces and the number of remaining parking spaces can be solved, thereby improving the accuracy of predicting parking efficiency and the probability of parking lot congestion.

[0060] Reference Figure 5 , Figure 5 This is a flowchart illustrating a fourth exemplary embodiment of the parking lot congestion probability prediction method of this application. Based on the above... Figure 4 In the embodiment shown, step S410 involves acquiring parking records for each day of a plurality of parking lots within a preset date period, including: Step S510: Using a preset incremental strategy, obtain the historical maximum number of orders, number of entries, and number of exits within the specified date to obtain the parking record.

[0061] Specifically, regarding the incremental strategy: As the number of order data in the parking lot increases, it's necessary to maintain a table showing the maximum number of parking records and the date the maximum value was generated. If the maximum number of parking records exceeds the current value, order data after the generated date is cleaned using data filtering rules and added to the overall data table. If the parking lot provides parking spaces, the availability of spaces during a specific time period can be determined directly based on order data. If the parking lot does not provide parking spaces, the historical maximum number of orders is analyzed to determine the parking space availability for that time period, and the availability of spaces is then determined through order data cleansing. The incremental strategy replenishes the maximum number of parking spaces; if the number of orders each day exceeds this historical threshold, the maximum number of parking spaces is updated.

[0062] This embodiment, through the above-described scheme, specifically uses a preset incremental strategy to obtain the historical maximum number of orders, entry numbers, and exit numbers within the specified date, thus obtaining the parking record. Based on the parking record, it determines whether the parking lot has available parking spaces during the specified time period, obtaining several parking space statuses. Each parking space status is then evenly distributed to obtain the time tag score. Through the incremental strategy, as order data is updated, the vehicle tag's judgment of parking space availability can be verified and corrected, improving the accuracy of predicting parking lot congestion probability.

[0063] Reference Figure 6 , Figure 6 This is a flowchart illustrating a fifth exemplary embodiment of the parking lot congestion probability prediction method of this application. Based on the above... Figure 3 In the embodiment shown, step S310, determining several parking lot tags and several time periods includes: Step S610: Obtain the first data through a preset data warehouse; Specifically, data warehouses are used for data cleaning of large amounts of data, such as the Greenplum data warehouse, which includes, but is not limited to, obtaining specific tag attributes through technologies such as SQL and Java, such as Nanshan District and shopping centers.

[0064] And / or in step S620, call a preset interface to obtain the second data; Specifically, since the GPS coordinates of the parking lot are known, the business districts near the location can be searched. For the business districts near the parking lot, the relevant data can be obtained by calling the map provider's interface, and data analysis can be performed.

[0065] Step S630: Determine the parking lot tag based on the first data and / or the second data.

[0066] Specifically, tags obtained from data warehouses using technologies such as SQL and Java, along with relevant data obtained by calling data interfaces, can be used as parking lot tags for calculating corresponding time tag scores.

[0067] This embodiment uses the above-described scheme to obtain first data from a pre-defined data warehouse; and / or to obtain second data by calling a pre-defined interface; and determines the parking lot label based on the first data and / or the second data. By obtaining publicly available information and existing data, it marks whether the parking lot has available parking spaces, that is, it realizes big data analysis, making the prediction of the probability of congestion in vacant parking lots more accurate. This can solve the problem of low parking efficiency caused by parking lots not providing the total number of parking spaces and the number of remaining parking spaces, and improve parking efficiency.

[0068] Reference Figure 7 , Figure 7This is a flowchart illustrating a sixth exemplary embodiment of the parking lot congestion probability prediction method of this application. Based on the above... Figure 3 In the illustrated embodiment, step S240, based on the target total score and the preset attribute total score, obtains the congestion probability of the target parking lot. After the attribute total score is calculated based on the preset scoring rules, the method further includes: Step S710: Obtain the actual probability of the target parking lot; Specifically, the actual probability of the target parking lot is obtained, and this actual probability is compared with the predicted congestion probability of the target parking lot to ensure that the predicted probability is accurate.

[0069] Step S720: Compare the actual probability with the crowding probability to obtain a first comparison result; Specifically, the actual probability is compared with the calculated congestion probability to obtain the comparison result, thereby verifying whether the target parking lot is a special parking lot.

[0070] Step S730: If the first comparison result exceeds a preset difference, then verify whether the target parking lot is a special parking lot; Specifically, if the comparison result exceeds the preset difference, it may be because the target parking lot is a special parking lot, or it may be because some parking lot labels and / or label attributes are missing. Therefore, it is necessary to verify whether the target parking lot is a special parking lot.

[0071] Step S740: If yes, then set the target parking lot as a special parking lot.

[0072] Specifically, due to various practical reasons, some parking lots are classified as special parking lots. If the target parking lot is a special parking lot, then the parking lot will be designated as a special parking lot, and no further predictions will be made for that target parking lot.

[0073] This embodiment, through the above-described scheme, specifically obtains the actual probability of the target parking lot; compares the actual probability with the congestion probability to obtain a first comparison result; if the first comparison result exceeds a preset difference, it verifies whether the target parking lot is a special parking lot; if so, it sets the target parking lot as a special parking lot. By verifying whether the target parking lot is a special parking lot and excluding special parking lots, the accuracy of predicting the parking lot congestion probability can be improved.

[0074] Reference Figure 8 , Figure 8 This is a flowchart illustrating a seventh exemplary embodiment of the parking lot congestion probability prediction method of this application. Based on the above... Figure 7 In the embodiment shown, step S730, verifying whether the target parking lot is a special parking lot, includes: Step S810: Determine other parking lot labels and / or other label attributes besides the currently stated parking lot label and / or the label attributes; Specifically, since it's impossible to determine whether the congestion level of parking lots in a certain area is consistent, it indicates that some factors are different, meaning that the parking lot labels and / or label attributes are different. Therefore, it is necessary to re-acquire other parking lot labels and / or other label attributes besides the currently acquired ones; that is, to retrieve any missed parking lot labels or label attributes.

[0075] Step S820: Based on the scoring rules, data filtering rules, other parking lot tags and / or the other tag attributes, update the total attribute score, parking lot tags and / or tag attributes; Specifically, based on the previous steps S310 to S340, the missing tags and tag attributes are retrieved (mined) again, and the total attribute score, parking lot tags and / or tag attributes are updated.

[0076] Step S830: Based on the updated attribute total score, the updated parking lot label and / or the updated label attribute, perform the steps of determining the target time period and the target parking lot corresponding to several target parking lot labels and the subsequent steps to obtain the updated congestion probability. Specifically, if new parking lot labels and / or label attributes can be discovered, the congestion probability of the target parking lot is recalculated.

[0077] Step S840: Compare the actual probability with the updated congestion probability to obtain a second comparison result; Specifically, the actual probability is compared with the updated crowding probability to ensure that the crowding probability is accurate and improve the accuracy of the prediction.

[0078] Step S850: If the second comparison result does not exceed the difference, then the target parking lot does not belong to the special parking lot; Specifically, the difference is set according to the actual situation, and this application embodiment does not limit it. For example, the difference is 0.1. If a new parking lot label and / or label attribute is discovered, and the difference between the actual probability and the updated congestion probability is less than 0.1, then the target parking lot does not belong to a special parking lot, and the predicted congestion level is accurate.

[0079] Step S860: If the second comparison result exceeds the difference, return to the step of determining other parking lot labels and / or other label attributes besides the current parking lot label and / or the label attribute; Specifically, if new parking lot labels and / or label attributes are discovered, but the difference between the actual probability and the updated congestion probability is still greater than or equal to 0.1, then the target parking lot is a special parking lot, and the predicted congestion level is inaccurate.

[0080] Step S870: Repeat the cycle sequentially according to a preset number of times until the cycle ends, then the target parking lot belongs to the special parking lot.

[0081] Specifically, the process is repeated sequentially according to a preset number of times until the cycle ends. If the updated congestion probability is still greater than the preset difference, then the target parking lot is considered a special parking lot.

[0082] This embodiment, through the above scheme, specifically involves determining other parking lot labels and / or other label attributes besides the currently stated parking lot label and / or label attributes; updating the total attribute score, parking lot label and / or label attributes based on the scoring rules, data filtering rules, other parking lot labels and / or other label attributes; based on the updated total attribute score, updated parking lot label and / or updated label attributes, executing the steps of determining the target time period and several target parking lot labels corresponding to the target parking lot, and subsequent steps, to obtain the updated congestion probability; comparing the actual probability with the updated congestion probability to obtain a second comparison result; if the second comparison result does not exceed the difference, then the target parking lot does not belong to the special parking lot; if the second comparison result exceeds the difference, returning to the step of determining other parking lot labels and / or other label attributes besides the currently stated parking lot label and / or label attributes; repeating this process sequentially a preset number of times until the loop ends, then the target parking lot belongs to the special parking lot. By determining whether the target parking lot is a special parking lot, missing parking lot tags and / or tag attributes can be obtained, improving the accuracy of parking lot congestion probability prediction.

[0083] Furthermore, this application also proposes a device for predicting the probability of parking lot congestion, the device comprising: The determination module is used to determine the target time period and the target parking lot corresponding to several target parking lot labels; The calculation module is used to obtain the corresponding target time tag score based on the target time period and target parking lot tag, wherein the target time tag score is calculated based on preset data filtering rules; Calculate the target total score for the target parking lot based on the target time tag score; The prediction module is used to obtain the congestion probability of the target parking lot based on the target total score and the preset attribute total score, wherein the attribute total score is calculated based on the preset scoring rules.

[0084] The principle and implementation process of predicting parking lot congestion probability in this embodiment can be found in the above embodiments, and will not be repeated here.

[0085] Furthermore, this application also proposes a terminal device, which includes a memory, a processor, and a parking lot congestion probability prediction program stored in the memory and executable on the processor. When the parking lot congestion probability prediction program is executed by the processor, it implements the steps of the parking lot congestion probability prediction method as described above.

[0086] Since the program for predicting the congestion probability of this parking lot is executed by the processor, it adopts all the technical solutions of all the aforementioned embodiments, and therefore has at least all the beneficial effects brought about by all the technical solutions of all the aforementioned embodiments, which will not be repeated here.

[0087] Furthermore, embodiments of this application also propose a computer-readable storage medium storing a parking lot congestion probability prediction program, which, when executed by a processor, implements the steps of the parking lot congestion probability prediction method as described above.

[0088] Since the program for predicting the congestion probability of this parking lot is executed by the processor, it adopts all the technical solutions of all the aforementioned embodiments, and therefore has at least all the beneficial effects brought about by all the technical solutions of all the aforementioned embodiments, which will not be repeated here.

[0089] Compared to existing technologies, the parking lot congestion probability prediction method, device, terminal equipment, and storage medium proposed in this application determine a target time period and several target parking lot tags corresponding to the target parking lot; obtain a corresponding target time tag score based on the target time period and target parking lot tags, the target time tag score being calculated based on a preset data filtering rule; calculate the target total score of the target parking lot based on the target time tag score; and obtain the congestion probability of the target parking lot based on the target total score and a preset attribute total score, the attribute total score being calculated based on a preset scoring rule. By setting target parking lot tags to obtain a corresponding target total score, and based on the target total score and the preset attribute total score, the probability of whether the target parking lot has available parking spaces can be obtained, which can solve the problem of low parking efficiency caused by parking lots not providing the total number of parking spaces and the number of remaining parking spaces, thus improving parking efficiency. Based on the solution of this application, starting from the real-world problem of parking difficulties, a method for predicting parking lot congestion probability based on parking lot tag scores of publicly available information and existing data is proposed, and the effectiveness of the parking lot congestion probability prediction method proposed in this application is verified.

[0090] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0091] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0092] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by 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 is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, controlled terminal, or network device, etc.) to execute the methods of each embodiment of this application.

[0093] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A method for predicting the probability of parking lot congestion, characterized in that, The method for predicting the probability of parking lot congestion includes the following steps: Determine the target time period and the corresponding target parking lot labels; Based on the target time period and target parking lot label, the corresponding target time label score is obtained, and the target time label score is calculated based on preset data filtering rules; Calculate the target total score for the target parking lot based on the target time tag score; Based on the target total score and the preset attribute total score, the congestion probability of the target parking lot is obtained, and the attribute total score is calculated based on the preset scoring rules.

2. The method for predicting parking lot congestion probability as described in claim 1, characterized in that, Before the step of determining the target time period and the corresponding target parking lot labels, the method further includes: Define several parking lot labels and several time periods; Each parking lot label is categorized under its corresponding label attribute, resulting in several label attributes; The parking lot tags for each time period are scored to obtain the corresponding time tag score; Based on the preset high score rules, the scores of one time tag for each tag attribute are added together to obtain the total score of the attribute.

3. The method for predicting parking lot congestion probability as described in claim 2, characterized in that, The step of scoring the parking lot tags corresponding to each time period to obtain the corresponding time tag score includes: Obtain parking records for each day within a preset date range from several parking lots; Based on the parking records, it is determined whether the parking lot has available parking spaces during the time period, thus obtaining information on several parking spaces. The time tag score is obtained by equally dividing the information of each parking space.

4. The method for predicting parking lot congestion probability as described in claim 3, characterized in that, The steps for obtaining parking records for each day of several parking lots within a preset date period include: The parking record is obtained by using a preset incremental strategy to obtain the historical maximum number of orders, entry count, and exit count within the specified date.

5. The method for predicting parking lot congestion probability as described in claim 2, characterized in that, The steps for determining several parking lot labels include: Obtain first data from a pre-defined data warehouse; and / or Call the preset interface to obtain the second data; The parking lot label is determined based on the first data and / or the second data.

6. The method for predicting parking lot congestion probability as described in claim 2, characterized in that, After the step of obtaining the congestion probability of the target parking lot based on the target total score and the preset attribute total score, where the attribute total score is calculated based on preset scoring rules, the method further includes: Obtain the actual probability of the target parking lot; The actual probability is compared with the crowding probability to obtain a first comparison result; If the first comparison result exceeds the preset difference, then verify whether the target parking lot is a special parking lot; If so, the target parking lot will be set as a special parking lot.

7. The method for predicting parking lot congestion probability as described in claim 6, characterized in that, The step of verifying whether the target parking lot is a special parking lot includes: Determine other parking lot labels and / or other label attributes besides the currently described parking lot labels and / or label attributes; Based on the scoring rules, data filtering rules, other parking lot tags and / or the other tag attributes, update the total attribute score, parking lot tags and / or tag attributes; Based on the updated attribute total score, the updated parking lot label and / or the updated label attribute, the steps of determining the target time period and the target parking lot corresponding to several target parking lot labels and subsequent steps are performed to obtain the updated congestion probability. The actual probability is compared with the updated congestion probability to obtain a second comparison result; If the second comparison result does not exceed the difference, then the target parking lot does not belong to the special parking lot; If the second comparison result exceeds the difference, then return to the step of determining other parking lot labels and / or other label attributes besides the current parking lot label and / or label attributes; The cycle repeats sequentially according to a preset number of times until the cycle ends, at which point the target parking lot belongs to the special parking lot.

8. A device for predicting the probability of parking lot congestion, characterized in that, The device for predicting the probability of parking lot congestion includes: The determination module is used to determine the target time period and the target parking lot corresponding to several target parking lot labels; The calculation module is used to obtain the corresponding target time tag score based on the target time period and target parking lot tag, wherein the target time tag score is calculated based on preset data filtering rules; Calculate the target total score for the target parking lot based on the target time tag score; The prediction module is used to obtain the congestion probability of the target parking lot based on the target total score and the preset attribute total score, wherein the attribute total score is calculated based on the preset scoring rules.

9. A terminal device, characterized in that, The terminal device includes a memory, a processor, and a parking lot congestion probability prediction program stored in the memory and executable on the processor. When the parking lot congestion probability prediction program is executed by the processor, it implements the steps of the parking lot congestion probability prediction method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a prediction program for parking lot congestion probability, which, when executed by a processor, implements the steps of the method for predicting parking lot congestion probability as described in any one of claims 1-7.

Images