Loan evaluation method and device, electronic equipment and computer program product

Abstract

The invention discloses a loan evaluation method and device, electronic equipment and a computer program product. The method comprises the following steps: acquiring visitor data of a business operation site in a target time period through remote sensing equipment; vehicle data of the business operation site in the target time period are acquired through a vehicle identification device; acquiring night light intensity data of the business operation site in the target time period through the remote sensing platform; converting the visitor data of the target time period, the vehicle data of the target time period and the night light intensity data of the target time period into operation quotas, and comparing the operation quotas with reported operation quotas of the operation site to obtain a comparison result; and determining a loan issuing condition according to a comparison result. According to the method and the device, the problem that loan evaluation cannot be efficiently and accurately performed on a business operation site due to long time consumption and data deviation of a traditional production and operation loan evaluation method is solved.

Description

Technical Field

[0001] The present application relates to the field of financial technology, and specifically, to a loan assessment method, device, electronic device and computer program product. Background Art

[0002] In the process of urban construction and economic and social development, in order to better cooperate with various places, financial institutions need to conduct production and operation assessments for loans in hotels, shopping malls, factories and other places. In the traditional production and operation assessment method for loans, in terms of data collection, a large amount of human and material resources are required, which takes a long time. In terms of assessment, the use of expert assessment methods has certain data deviations, which reduces the accuracy of the data.

[0003] Traditional loan assessment methods for production and operation are time-consuming and have data biases, resulting in the inability to efficiently and accurately assess loan conditions for business premises. Currently, no effective solution has been proposed. Summary of the invention

[0004] The present application provides a loan assessment method, device, electronic equipment and computer program product to solve the problem that the traditional production and operation loan assessment method is time-consuming and has data deviations, resulting in the inability to efficiently and accurately conduct loan assessments on business premises.

[0005] According to one aspect of the present application, a loan assessment method is provided. The method includes: obtaining visitor data of a business premises in a target time period through remote sensing equipment; obtaining vehicle data of a business premises in a target time period through vehicle identification equipment; obtaining nighttime light intensity data of a business premises in a target time period through a remote sensing platform; converting visitor data, vehicle data and nighttime light intensity data of a target time period into an operating quota, and comparing the operating quota with the reported operating quota of the business premises to obtain a comparison result; and determining the issuance of a loan based on the comparison result.

[0006] Optionally, the remote sensing device includes at least a sensor and a camera, and the remote sensing device is arranged at the passage entrance of the business premises. Obtaining the visitor data of the business premises in a target time period through the remote sensing device includes: collecting the data of the passage entrance of the business premises through the sensor to obtain sensor data; uploading the sensor data to a cloud server for data analysis to obtain first human flow data; collecting video data of the passage entrance of the business premises through the camera; extracting the crowd density in the video data through object detection and tracking methods to obtain second human flow data; and determining the visitor data of the business premises in the target time period based on the first human flow data and the second human flow data.

[0007] Optionally, a vehicle identification device is set on the road leading to the business premises, and obtaining the vehicle data of the business premises in a target time period through the vehicle identification device includes: recording the license plate number data and traffic flow data of the target time period through the vehicle identification device; and confirming the license plate number data and traffic flow data of the target time period as the vehicle data of the business premises in the target time period.

[0008] Optionally, obtaining night-time light intensity data of a business premises during a target time period through a remote sensing platform includes: obtaining light intensity image information of a target area during a target time period through a remote sensing platform, wherein the business premises is located within the target area, and the light intensity image information includes at least one of the following information: building lighting intensity, maximum illumination value, and minimum illumination value within the business premises; determining night-time light intensity data of the business premises during the target time period based on the light intensity image information.

[0009] Optionally, converting the visitor data of the target time period, the vehicle data of the target time period and the night light intensity data of the target time period into the operating amount includes: obtaining the visitor data, the vehicle data and the night light intensity data of the historical time period, and building a target model based on the visitor data, the vehicle data and the night light intensity data of the historical time period; preprocessing the visitor data of the target time period, the vehicle data of the target time period and the night light intensity data of the target time period to obtain preprocessed data, wherein the preprocessing includes at least one of the following: data deduplication, cross-validation, and abnormal data elimination; converting the preprocessed data into the operating amount based on the target model.

[0010] Optionally, constructing a target model based on visitor data, vehicle data and night light intensity data of a historical time period includes: respectively determining the degree of influence of the visitor data, vehicle data and night light intensity data of the historical time period on the operating amount of the business premises; determining the weight coefficients of the visitor data of the business premises, the vehicle data of the business premises and the night light intensity data of the business premises according to the degree of influence; and determining the target model based on the weight coefficients.

[0011] Optionally, constructing a target model based on visitor data, vehicle data and night light intensity data of a historical time period includes: fitting a target curve based on the business volume, visitor data, vehicle data and night light intensity data of the business premises in the historical time period; and determining the target curve as the target model.

[0012] According to another aspect of the present application, a loan evaluation device is provided. The device includes: a first acquisition unit, used to acquire visitor data of a business place in a target time period through a remote sensing device; a second acquisition unit, used to acquire vehicle data of the business place in the target time period through a vehicle identification device; a third acquisition unit, used to acquire nighttime light intensity data of the business place in the target time period through a remote sensing platform; an evaluation unit, used to convert visitor data of the target time period, vehicle data of the target time period, and nighttime light intensity data of the target time period into an operating quota, and compare the operating quota with the reported operating quota of the business place to obtain a comparison result; and a determination unit, used to determine the issuance of the loan based on the comparison result.

[0013] According to another aspect of an embodiment of the present invention, there is also provided an electronic device, comprising a processor and a memory; the memory stores computer-readable instructions, and the processor is used to execute the computer-readable instructions, wherein a loan assessment method is executed when the computer-readable instructions are executed.

[0014] According to another aspect of the present application, a computer program product is provided, including a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, any one of the above loan assessment methods is implemented.

[0015] Through this application, the following steps are adopted: obtaining visitor data of the business premises in the target time period through remote sensing equipment; obtaining vehicle data of the business premises in the target time period through vehicle identification equipment; obtaining night light intensity data of the business premises in the target time period through the remote sensing platform; converting visitor data, vehicle data and night light intensity data of the target time period into operating quotas, and comparing the operating quotas with the reported operating quotas of the business premises to obtain comparison results; determining the loan issuance status based on the comparison results, solving the problem that the traditional production and operation loan evaluation method is time-consuming and has data deviations, resulting in the inability to efficiently and accurately evaluate the loan of the business premises. The visitor data, vehicle data and night light intensity data of the business premises are collected through remote sensing technology, and the visitor data, vehicle data and night light intensity data are converted into operating quotas, thereby achieving the effect of improving evaluation efficiency and accurate evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0017] Figure 1 is a flow chart of a loan evaluation method according to an embodiment of the present application;

[0018] Figure 2 is a schematic diagram of a method for determining an operating quota according to an embodiment of the present application;

[0019] Figure 3 is a schematic diagram of a loan assessment device according to an embodiment of the present application;

[0020] Figure 4 is a schematic diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0021] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0022] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0023] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0024] It should be noted that the relevant information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for display, data for analysis, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data comply with the relevant laws, regulations and standards of the relevant regions, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or refuse to use them.

[0025] According to an embodiment of the present application, a loan assessment method is provided.

[0026] Figure 1 is a flow chart of a loan evaluation method according to an embodiment of the present application. Figure 1 As shown, the method comprises the following steps:

[0027] Step S101, obtaining visitor data of a business place in a target time period through remote sensing equipment.

[0028] It should be noted that remote sensing equipment refers to equipment that can collect data from a place far away from the target object, installed on different carriers or platforms, and can cover a wide area and provide continuous monitoring. In this embodiment, remote sensing equipment includes but is not limited to sensors, cameras, radars, hyperspectral imagers, etc., which can monitor the operating conditions of the business premises.

[0029] Business premises refer to the area where an enterprise or organization creates economic value and the main place for interaction with the outside world, that is, the place where production, processing, sales, services and other business activities are carried out. It can be various types of business operation environments, such as factories, offices, stores, warehouses, laboratories, etc. The visitor data of the business premises in the target time period refers to the visitor data of the business premises during the period to be tested. Visitor data refers to the visitor information entering the business premises, including the identity information of the visitor and the flow of visitors at different time points in the target time period. The flow of visitors at different time points can be the number of visitors per hour, the number of visitors per day, and the number of visitors per week.

[0030] In an optional implementation, the remote sensing device may be installed at the entrance of the business premises. When a visitor enters the business premises, the remote sensing device installed at the entrance of the business premises will record data, wherein the data includes the visitor's information (i.e., who the visitor is) and the number of visitors (i.e., the flow of people). For the data collected by different remote sensing devices, the data processing technology corresponding to the remote sensing device can be used to perform data analysis to obtain visitor data. For example, for sensors that do not have data analysis functions themselves, they can be uploaded to a server for data analysis to obtain visitor data; for cameras, the cameras are used to collect videos, and the video information can be analyzed through a data processing server to obtain visitor data.

[0031] Step S102, obtaining vehicle data of the business place in the target time period through the vehicle identification device.

[0032] Among them, the vehicle identification device is a system integrated with multiple sensors, cameras, license plate recognition technology, etc., which is used to automatically identify and process vehicle-related information. The location where the vehicle identification device is set depends on the needs. For example, when the business premises need to monitor and manage the entry and exit of vehicles, the vehicle identification device can be set at the entrance and exit. The vehicle data may include vehicle type, vehicle color, license plate number data, traffic flow data, etc. In this embodiment, the vehicle data obtained by the vehicle identification device includes license plate number data and traffic flow data. License plate number data can be obtained through license plate recognition technology, and traffic flow data refers to the number of vehicles passing through within a period of time.

[0033] It should be noted that the vehicle identification device counts the number of vehicles passing through the target time period and associates it with the time series graph, so that the traffic flow data of the time series graph can be obtained. For example, the time interval of the target time period is determined to be one hour, and the 24 hours of a day are divided into 24 time periods, each hour is a target time period, the horizontal axis is each target time period, and the vertical axis is the number of vehicles passing through each target time period, forming the traffic flow data of the time series graph.

[0034] Step S103, obtaining nighttime light intensity data of the business premises during the target time period through the remote sensing platform.

[0035] It should be noted that the nighttime light intensity data of business premises refers to the light intensity of buildings in business premises that operate at night. Obtaining the nighttime light intensity data of business premises includes at least the following steps: collecting nighttime light image data through a remote sensing platform, then performing image preprocessing to improve image quality, analyzing the pixel values ​​of the light image and converting them into brightness measurements, identifying areas with concentrated and sparse lights based on brightness distribution, and evaluating light intensity by comparing brightness levels in different areas.

[0036] Among them, the remote sensing platform refers to a platform or system that includes remote sensing equipment and can process the collected data. The remote sensing platform can include optical sensors, image processing software, calibration equipment, light intensity assessment models, etc., among which the optical sensor is used to capture light images at night; the image processing software is used to receive, process and analyze the light image data collected from the optical sensor, and can perform image enhancement, classification and other operations; the calibration equipment is calibrated when the collected light image data may have errors; the light intensity assessment model is an assessment model established by analyzing the brightness and distribution of light images, which is used to analyze and evaluate the light intensity. The technologies involved include image segmentation, feature extraction and brightness quantization.

[0037] Step S104, converting the visitor data of the target time period, the vehicle data of the target time period and the night light intensity data of the target time period into the operating quota, and comparing the operating quota with the reported operating quota of the business place to obtain a comparison result.

[0038] It should be noted that the operating limit refers to the funds actually required for the business premises to be able to operate. For example, in order to build a factory, the operating limit includes the cost of renting the site, the cost of purchasing machinery, water and electricity costs, etc. The reported operating limit of the business premises is the value estimated by the owner of the business premises, and is reported to the financial institution for loan evaluation.

[0039] In order to avoid certain deviations in the reported operating amount of the business premises, the objectively estimated operating amount and the subjectively estimated operating amount can be compared to obtain a comparison result. The comparison result includes at least one of the following: the reported operating amount is too high, the reported operating amount is too low, and the reported operating amount is close to the actual amount. For example, assuming that the reported operating amount is 150,000 yuan, but the operating amount is determined to be 100,000 yuan based on the visitor data of the target time period, the vehicle data of the target time period, and the night light intensity data of the target time period, it means that the estimated operating amount is too high.

[0040] Step S105, determining the loan issuance status based on the comparison result.

[0041] The loan issuance refers to the amount of the loan issued. As the party issuing the loan, the financial institution evaluates the business premises from multiple angles to ensure that the loan funds are a reasonable amount. For example, when the reported operating amount is lower than the subjectively estimated operating amount, the financial institution can be reminded to verify. When the reported operating amount is too high, the financial institution will reduce the issuance of loans to achieve the purpose of risk control.

[0042] The loan assessment method provided in the embodiment of the present application obtains visitor data of the business premises in the target time period through remote sensing equipment; obtains vehicle data of the business premises in the target time period through vehicle identification equipment; obtains night light intensity data of the business premises in the target time period through a remote sensing platform; converts visitor data of the target time period, vehicle data of the target time period and night light intensity data of the target time period into operating quotas, and compares the operating quota with the reported operating quota of the business premises to obtain a comparison result; and determines the loan issuance status based on the comparison result. This solves the problem that the traditional loan assessment method for production and operation is time-consuming and has data deviations, resulting in the inability to efficiently and accurately conduct loan assessments on business premises. The visitor data, vehicle data and night light intensity data of the business premises are collected through remote sensing technology, and the visitor data, vehicle data and night light intensity data are converted into operating quotas, thereby achieving the effect of improving assessment efficiency and accurate assessment.

[0043] The business premises uses remote sensing equipment to collect data on visitors. Optionally, the remote sensing equipment includes at least a sensor and a camera. The remote sensing equipment is set at the passage entrance of the business premises. Obtaining the visitor data of the business premises in a target time period through the remote sensing equipment includes: collecting data at the passage entrance of the business premises through sensors to obtain sensor data; uploading the sensor data to a cloud server for data analysis to obtain first human flow data; collecting video data of the passage entrance of the business premises through a camera; extracting crowd density in the video data through object detection and tracking methods to obtain second human flow data; and determining the visitor data of the business premises in the target time period based on the first human flow data and the second human flow data.

[0044] When the remote sensing device is a sensor, the data of the channel entrance of the business premises is collected by the sensor and packaged, and the packaged data is sent to the cloud server through network transmission. Before network transmission, the first person flow data needs to be preprocessed. For example, the data preprocessing can include data cleaning, format conversion, compression and other operations, and then the preprocessed first person flow data is encapsulated into a format suitable for network transmission. For example, the format of network transmission can be a data packet or a message, wherein the metadata of the data packet or message includes at least one of the following: timestamp, device identification, data type. The sensor needs to be connected to the network, which can be a wired network, a wireless network, a cellular network, a low-power wide area network, etc. In addition, before network transmission, a suitable communication protocol is selected according to the needs, and the sensor establishes a connection with the cloud server according to the selected communication protocol, and then performs the process of data uploading. After the cloud server receives the data uploaded by the sensor, it processes and analyzes it to obtain the first person flow data.

[0045] When the remote sensing device is a camera, video data of the channel entrance of the business premises is collected. The video data can be stored locally or on a cloud server. The crowd density in the video data is extracted through the object detection and tracking method model deployed on the local or cloud server. The crowd density refers to the crowd density information at each moment. For example, if the crowd density per hour is 30 people, the crowd density is determined as the second human flow data.

[0046] It should be noted that, on the one hand, when there are visitor data obtained by multiple remote sensing devices, for example, when visitor data is obtained by sensors and cameras at the same time, it will cause the sensors and cameras to repeatedly count the flow of people. Therefore, it is necessary to adopt a method to limit repeated counting, remove the first flow of people data and the second flow of people data to obtain the total flow of people data, and use the total flow of people data as visitor data to avoid data duplication and omission. On the other hand, for the same person, it can only be counted once within a period of time, to avoid multiple counts of multiple times through the access control remote sensing device within the period of time, resulting in data distortion. For example, visitor A passed the access control 3 times within a period of time, but will only be counted as passing the access control once within the short period of time.

[0047] Through this embodiment, sensors and cameras are used to collect data, and the collected data is processed to obtain first human flow data and second human flow data, respectively. The visitor data of the business premises in the target time period is determined based on the first human flow data and the second human flow data, thereby avoiding data duplication and omission and achieving the effect of accurately collecting visitor data.

[0048] In addition to collecting visitor data, the business premises also need to collect data on vehicles entering and exiting. Optionally, a vehicle identification device is set up on the road leading to the business premises. The vehicle data of the business premises in a target time period is obtained through the vehicle identification device, including: recording the license plate number data and vehicle flow data of the target time period through the vehicle identification device; and confirming the license plate number data and vehicle flow data of the target time period as the vehicle data of the business premises in the target time period.

[0049] Before setting up the vehicle identification device, first determine the roads leading to the business premises. If there are N entrances to the business premises, then determine that the roads for setting up the vehicle identification device are N, and the number of vehicle identification devices is N. The vehicle identification device is used to record the license plate number data and traffic flow data of the target time period, wherein the license plate number data is identified and obtained by the license plate detection technology configured in the vehicle identification device, and the license plate detection technology can be implemented through three models: license plate positioning, license plate correction, and license plate recognition. The traffic flow data is determined based on the license plate number data of the target time period, indicating how many vehicles passed during the target time period. For example, if the license plate number data of the N entrances of the business premises obtained within a period of time is 20, it can be obtained that the traffic flow during this period is 20 vehicles. In addition, in order to intuitively show the change of traffic flow over time, the traffic flow data can be expressed as a time series diagram of the target time period and the traffic flow within the target time period. The time series diagram of this embodiment refers to a chart of the change of traffic flow over time.

[0050] Through this embodiment, a vehicle identification device is set to obtain the license plate data and traffic flow data of the business premises in the target time period, and the vehicle data in the target time period is determined based on the license plate data and traffic flow data, thereby achieving the effect of accurately collecting vehicle data.

[0051] Some business premises are still in operation at night, so night light intensity is used as one of the indicators for evaluating business premises. Optionally, obtaining night light intensity data of the business premises in a target time period through a remote sensing platform includes: obtaining light intensity image information of a target area in a target time period through a remote sensing platform, wherein the business premises are set within the target area, and the light intensity image information includes at least one of the following information: building lighting intensity, maximum illumination value and minimum illumination value within the business premises; determining night light intensity data of the business premises in the target time period based on the light intensity image information.

[0052] Light intensity image information refers to information of an image or pattern represented by light intensity. The building lighting intensity in a business premises refers to the average light intensity provided by the lighting system on the building, the maximum illumination value refers to the maximum light intensity measured in the business premises, and the minimum illumination value refers to the minimum light intensity measured in the business premises. By determining at least one piece of information in the light intensity image information, the operation status of the business premises at night can be obtained, thereby determining the nighttime light intensity of the business premises.

[0053] Through this embodiment, a remote sensing platform is used to collect the night light intensity of the business premises during the target time period, thereby ensuring the operation of the business premises at night, thereby achieving the effect of accurately evaluating the night light intensity of the business premises.

[0054] Figure 2 Schematic diagram of a method for determining a business quota according to an embodiment of the present application. Figure 2 As shown, converting visitor data, vehicle data and nighttime light intensity data of a target time period into operating quotas includes:

[0055] Step S201, obtaining visitor data, vehicle data and night light intensity data of a historical time period, and building a target model according to the visitor data, vehicle data and night light intensity data of the historical time period.

[0056] Determining the operating quota requires considering data from three perspectives: visitor data, vehicle data, and night light intensity data. The target model is constructed using visitor data, vehicle data, and night light intensity data from a historical period. The model is used to characterize the impact of visitor data, vehicle data, and night light intensity data of the business premises on the operating quota. After completing the target model construction.

[0057] Step S202, preprocessing the visitor data of the target time period, the vehicle data of the target time period and the night light intensity data of the target time period to obtain preprocessed data, wherein the preprocessing includes at least one of the following: data deduplication, cross-validation, and abnormal data removal.

[0058] It should be noted that in order to avoid deviations in the collected visitor data, vehicle data and night light data, thereby affecting the loan assessment of the business premises, data deduplication can be used to limit the recording of duplicate data. For the same visitor or the same vehicle, it can only be counted once within a period of time to avoid data distortion caused by multiple access control. Cross-validation methods can also be used to conduct comprehensive verification from multiple different angles to obtain more accurate results. For example, card swiping records and video surveillance recordings can be used to verify whether each access event is correctly recorded. The collected data may also be abnormal, so the method of eliminating abnormal data is used. For example, through real-time detection and feedback mechanisms to ensure that the system detects problems in a timely manner and gives prompts or alarms. When a suspected abnormal situation occurs (for example, multiple consecutive card swiping), the relevant user account is immediately closed, and the additional services such as the count generated by this account are suspended; when the movement trajectory of the object captured by the camera is detected to be inconsistent with the normal situation, the monitoring personnel are notified in time to verify and troubleshoot.

[0059] Step S203: convert the preprocessed data into operating amounts based on the target model.

[0060] The visitor data, vehicle data and night light intensity data of the target time period are preprocessed and input into the target model, and the output result is the operating amount.

[0061] Through this embodiment, the preprocessing method is used on the collected data to achieve the effect of improving the data quality, and then the target model is used to determine the operating amount of the target time period, thereby achieving the effect of accurately evaluating the operating amount.

[0062] In an optional embodiment, the target model can be constructed by determining weight coefficients. Optionally, constructing the target model based on visitor data, vehicle data and night light intensity data of a historical time period includes: respectively determining the degree of influence of the visitor data, vehicle data and night light intensity data of the historical time period on the operating amount of the business premises; determining the weight coefficients of the visitor data of the business premises, the vehicle data of the business premises and the night light intensity data of the business premises according to the degree of influence; and determining the target model based on the weight coefficients.

[0063] The visitor data, vehicle data and night light intensity data of different business premises have different impacts on the operating amount, and their total proportion in the evaluation of the operating amount is also different. The degree of impact of the visitor data, vehicle data and night light intensity data of the historical time period on the operating amount of the business premises is determined based on the proportion. For example, in terms of the weight coefficient of visitor data, in the business premises of office buildings, the proportion of visitor data in the operating amount is higher than that of vehicle data and night light intensity data. Therefore, the weight coefficient of visitor data is larger than the weight coefficient of vehicle data and the weight coefficient of night light intensity; in terms of the weight coefficient of vehicle data, in the business premises of hotels, the proportion of vehicle data is similar to that of visitor data, so the weight coefficients of the two are closer; in terms of the weight coefficient of night light intensity data, in the business premises of offices, most of the operating time is during the day, so the weight coefficient of night light intensity data is 0; in the business premises of factories that work continuously at night, the weight coefficient of night light intensity data is a non-zero decimal.

[0064] Through this embodiment, the weight coefficients of the three types of data are determined according to the degree of influence of visitor data, vehicle data and night light intensity data in the historical time period on the operating amount of the business premises, thereby achieving the effect of accurately determining the operating amount.

[0065] In an optional implementation, the target model can be constructed by fitting a target curve. Optionally, the target curve is fitted based on the business volume, visitor data, vehicle data, and night light intensity data of the business premises in a historical time period; the target curve is determined as the target model.

[0066] The corresponding relationship between the three independent variables of visitor data, vehicle data, and night light intensity data and the operating amount is determined by fitting the target curve. After the target curve is fitted, the point on the target curve can be determined based on the real-time visitor data, vehicle data, and night light intensity data. The operating amount corresponding to the point is the predicted operating amount.

[0067] Furthermore, the predicted operating amount given by the fitting curve is compared with the reported operating amount of the business place to obtain a comparison result. For example, if the predicted operating amount is lower than 20% of the reported operating amount, an early warning is issued.

[0068] Through the embodiment of the present application, the target model is determined by using a curve fitting method, thereby achieving the effect of accurately determining the operating amount.

[0069] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0070] The embodiment of the present application also provides a loan evaluation device. It should be noted that the loan evaluation device of the embodiment of the present application can be used to execute the loan evaluation method provided in the embodiment of the present application. The loan evaluation device provided in the embodiment of the present application is introduced below.

[0071] Figure 3 Schematic diagram of a loan evaluation device according to an embodiment of the present application. Figure 3 As shown, the device includes: a first acquisition unit 301, a second acquisition unit 302, a third acquisition unit 303, an evaluation unit 304, and a determination unit 305.

[0072] The first acquisition unit 301 is used to acquire visitor data of a business place in a target time period through a remote sensing device.

[0073] The second acquisition unit 302 is used to acquire vehicle data of the business place in the target time period through the vehicle identification device.

[0074] The third acquisition unit 303 is used to acquire nighttime light intensity data of the business premises in a target time period through a remote sensing platform.

[0075] The evaluation unit 304 is used to convert the visitor data of the target time period, the vehicle data of the target time period and the night light intensity data of the target time period into an operating quota, and compare the operating quota with the reported operating quota of the business place to obtain a comparison result.

[0076] The determination unit 305 is used to determine the loan issuance status according to the comparison result.

[0077] The loan evaluation device provided in the embodiment of the present application uses a first acquisition unit 301 to use a remote sensing device to obtain visitor data of the business premises in the target time period; uses a second acquisition unit 302 to use a vehicle identification device to obtain vehicle data of the business premises in the target time period; uses a third acquisition unit 303 to use a remote sensing platform to obtain nighttime light intensity data of the business premises in the target time period; uses an evaluation unit 304 to convert visitor data, vehicle data and nighttime light intensity data of the target time period into operating quotas, and compares the operating quota with the reported operating quota of the business premises to obtain a comparison result; and determines the loan issuance status according to the comparison result through a determination unit 305. The problem that the traditional loan evaluation method for production and operation is time-consuming and has data deviations, resulting in the inability to efficiently and accurately evaluate the loan of the business premises is solved. The visitor data, vehicle data and nighttime light intensity data of the business premises are collected by remote sensing technology, and the visitor data, vehicle data and nighttime light intensity data are converted into operating quotas, thereby achieving the effect of improving evaluation efficiency and accurate evaluation.

[0078] Optionally, in the loan assessment device provided in the embodiment of the present application, the first acquisition unit includes: a sensor sub-unit, used to collect data of the channel entrance of the business premises through a sensor to obtain sensor data; upload the sensor data to a cloud server for data analysis to obtain first human flow data; a camera sub-unit, used to collect video data of the channel entrance of the business premises through a camera; extract crowd density in the video data through object detection and tracking methods to obtain second human flow data; determine the visitor data of the business premises in the target time period based on the first human flow data and the second human flow data.

[0079] Optionally, in the loan assessment device provided in the embodiment of the present application, the second acquisition unit includes: a vehicle identification subunit, used to record the license plate number data and vehicle flow data of the target time period through a vehicle identification device; and a first determination subunit, used to determine the license plate number data and vehicle flow data of the target time period as vehicle data of a certain business premises in the target time period.

[0080] Optionally, in the loan assessment device provided in the embodiment of the present application, the third acquisition unit includes: an acquisition subunit, used to acquire light intensity image information of the target area in the target time period through a remote sensing platform, wherein the business premises is set within the target area, and the light intensity image information includes at least one of the following information: the building lighting intensity, the maximum illumination value and the minimum illumination value within the business premises; a second determination subunit, used to determine the night light intensity data of the business premises in the target time period based on the light intensity image information.

[0081] Optionally, in the loan assessment device provided in the embodiment of the present application, the assessment unit includes: a construction subunit, used to obtain visitor data, vehicle data and night light intensity data of a historical time period, and to construct a target model based on the visitor data, vehicle data and night light intensity data of the historical time period; a preprocessing subunit, used to preprocess the visitor data of the target time period, the vehicle data of the target time period and the night light intensity data of the target time period to obtain preprocessed data, wherein the preprocessing includes at least one of the following: data deduplication, cross-validation, and abnormal data removal; a conversion subunit, used to convert the preprocessed data into an operating amount based on the target model.

[0082] Optionally, in the loan assessment device provided in the embodiment of the present application, the construction subunit includes: a first determination module, used to respectively determine the degree of influence of visitor data, vehicle data and night light intensity data of a historical time period on the operating amount of a business premises; a weight coefficient module, used to determine the weight coefficients of the visitor data of the business premises, the vehicle data of the business premises and the night light intensity data of the business premises according to the degree of influence; and a second determination module, used to determine the target model based on the weight coefficient.

[0083] Optionally, in the loan assessment device provided in the embodiment of the present application, the construction subunit also includes: a fitting module for fitting a target curve according to the operating amount, visitor data, vehicle data and night light intensity data of the business premises in a historical time period; and a third determination module for determining the target curve as a target model.

[0084] The loan evaluation device comprises a processor and a memory. The first acquisition unit 301, the second acquisition unit 302, the third acquisition unit 303, the evaluation unit 304 and the determination unit 305 are all stored in the memory as program units. The processor executes the program units stored in the memory to implement corresponding functions.

[0085] The processor contains a kernel, which calls the corresponding program unit from the memory. One or more kernels can be set, and the evaluation efficiency and accuracy can be improved by adjusting the kernel parameters.

[0086] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0087] The embodiment of the present application also provides an electronic device, Figure 4 is a schematic diagram of an electronic device according to an embodiment of the present application, wherein the electronic device 40 comprises a processor and a memory; the memory stores computer-readable instructions, and the processor is used to run the computer-readable instructions, wherein the computer-readable instructions execute a loan assessment method when they are run. The electronic device in this article may be a server, a PC, a PAD, a mobile phone, etc.

[0088] An embodiment of the present application also provides a computer program product, including a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the program has the following method steps: obtaining visitor data of a business premises during a target time period through a remote sensing device; obtaining vehicle data of the business premises during a target time period through a vehicle identification device; obtaining nighttime light intensity data of the business premises during a target time period through a remote sensing platform; converting the visitor data of the target time period, the vehicle data of the target time period, and the nighttime light intensity data of the target time period into an operating quota, and comparing the operating quota with the reported operating quota of the business premises to obtain a comparison result; and determining the issuance of the loan based on the comparison result.

[0089] When the computer program is executed by the processor, there is also a program of the following method steps: the remote sensing device includes at least a sensor and a camera, the remote sensing device is set at the channel entrance of the business premises, and obtaining the visitor data of the business premises in the target time period through the remote sensing device includes: collecting the data of the channel entrance of the business premises through the sensor to obtain sensor data; uploading the sensor data to the cloud server for data analysis to obtain first human flow data; collecting video data of the channel entrance of the business premises through the camera; extracting the crowd density in the video data through object detection and tracking methods to obtain second human flow data; determining the visitor data of the business premises in the target time period based on the first human flow data and the second human flow data.

[0090] When the computer program is executed by the processor, there is also a program of the following method steps: a vehicle identification device is set on the road leading to the business premises, and the vehicle data of the business premises in a target time period is obtained through the vehicle identification device, including: recording the license plate number data and vehicle flow data of the target time period through the vehicle identification device; and determining the license plate number data and vehicle flow data of the target time period as the vehicle data of the business premises in the target time period.

[0091] When the computer program is executed by the processor, there is also a program with the following method steps: obtaining the night light intensity data of the business premises in the target time period through the remote sensing platform includes: obtaining the light intensity image information of the target area in the target time period through the remote sensing platform, wherein the business premises is set in the target area, and the light intensity image information includes at least one of the following information: the building lighting intensity, the maximum illumination value and the minimum illumination value in the business premises; determining the night light intensity data of the business premises in the target time period based on the light intensity image information.

[0092] Optionally, converting the visitor data of the target time period, the vehicle data of the target time period and the night light intensity data of the target time period into the operating amount includes: obtaining the visitor data, the vehicle data and the night light intensity data of the historical time period, and building a target model based on the visitor data, the vehicle data and the night light intensity data of the historical time period; preprocessing the visitor data of the target time period, the vehicle data of the target time period and the night light intensity data of the target time period to obtain preprocessed data, wherein the preprocessing includes at least one of the following: data deduplication, cross-validation, and abnormal data elimination; converting the preprocessed data into the operating amount based on the target model.

[0093] When the computer program is executed by the processor, there is also a program with the following method steps: constructing a target model based on visitor data, vehicle data and night light intensity data of a historical time period, including: respectively determining the degree of influence of the visitor data, vehicle data and night light intensity data of the historical time period on the operating amount of the business premises; determining the weight coefficients of the visitor data of the business premises, the vehicle data of the business premises and the night light intensity data of the business premises according to the degree of influence; and determining the target model based on the weight coefficients.

[0094] When the computer program is executed by the processor, there is also a program with the following method steps: constructing a target model based on visitor data, vehicle data and night light intensity data of a historical time period, including: fitting a target curve based on the business amount, visitor data, vehicle data and night light intensity data of the business premises in the historical time period; determining the target curve as the target model.

[0095] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0096] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0097] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0098] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0099] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0100] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0101] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0102] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0103] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A loan assessment method, characterized in that: include: Obtain visitor data of business premises during target time periods through remote sensing equipment; Acquiring vehicle data of the business premises during the target time period through a vehicle identification device; Acquire nighttime light intensity data of the business premises during the target time period through a remote sensing platform; converting the visitor data of the target time period, the vehicle data of the target time period, and the nighttime light intensity data of the target time period into an operating quota, and comparing the operating quota with the reported operating quota of the business place to obtain a comparison result; The loan issuance status is determined based on the comparison results.

2. The method according to claim 1, characterized in that The remote sensing device includes at least a sensor and a camera. The remote sensing device is arranged at the entrance of the passage of the business premises. The visitor data of the business premises in the target time period is obtained by the remote sensing device, including: Collecting data of the passage entrance of the business place through the sensor to obtain sensor data; Uploading the sensor data to a cloud server for data analysis to obtain first human flow data; Collecting video data of the passage entrance of the business premises through the camera; Extracting the crowd density in the video data by object detection and tracking methods to obtain second crowd flow data; The visitor data of the business premises in a target time period is determined according to the first human flow data and the second human flow data.

3. The method according to claim 1, characterized in that: The vehicle identification device is arranged on the road leading to the business site, and obtaining the vehicle data of the business site in the target time period through the vehicle identification device includes: Recording the license plate number data and vehicle flow data of the target time period by the vehicle identification device; The license plate number data and the vehicle flow data of the target time period are determined as the vehicle data of the business place in the target time period.

4. The method according to claim 1, characterized in that: The nighttime light intensity data of the business premises during the target time period obtained through the remote sensing platform includes: Acquire light intensity image information of a target area in a target time period through the remote sensing platform, wherein the business premises are located in the target area, and the light intensity image information includes at least one of the following information: building lighting intensity, maximum illumination value, and minimum illumination value in the business premises; The nighttime light intensity data of the business premises during the target time period is determined based on the light intensity image information.

5. The method according to claim 1, characterized in that Converting the visitor data of the target time period, the vehicle data of the target time period, and the nighttime light intensity data of the target time period into the operating quota includes: Acquire visitor data, vehicle data, and nighttime light intensity data for a historical time period, and construct a target model based on the visitor data, vehicle data, and nighttime light intensity data for the historical time period; Preprocessing the visitor data of the target time period, the vehicle data of the target time period, and the night light intensity data of the target time period to obtain preprocessed data, wherein the preprocessing includes at least one of the following: data deduplication, cross-validation, and abnormal data elimination; The preprocessed data is converted into the operating amount based on the target model.

6. The method according to claim 5, characterized in that Building a target model based on visitor data, vehicle data, and nighttime light intensity data for the historical period includes: Determine respectively the influence of the visitor data, vehicle data and night light intensity data of the historical time period on the operating amount of the business place; Determining weight coefficients of visitor data of the business premises, vehicle data of the business premises, and nighttime light intensity data of the business premises according to the degree of influence; The target model is determined based on the weight coefficients.

7. The method according to claim 5, characterized in that Building a target model based on visitor data, vehicle data, and nighttime light intensity data for the historical period includes: Fitting a target curve according to the business volume, visitor data, vehicle data, and nighttime light intensity data of the business place during the historical period; The target curve is determined as the target model.

8. A loan evaluation device, characterized in that: include: A first acquisition unit, used to acquire visitor data of the business premises in a target time period through a remote sensing device; A second acquisition unit, configured to acquire vehicle data of the business place in the target time period through a vehicle identification device; A third acquisition unit is used to acquire nighttime light intensity data of the business premises during the target time period through a remote sensing platform; An evaluation unit, configured to convert the visitor data of the target time period, the vehicle data of the target time period, and the nighttime light intensity data of the target time period into an operating quota, and compare the operating quota with the reported operating quota of the business place to obtain a comparison result; The determination unit is used to determine the loan issuance status according to the comparison result.

9. An electronic device, comprising a memory and a processor, characterized in that: The memory stores a computer program, and the processor is configured to execute the loan assessment method according to any one of claims 1 to 7 through the computer program.

10. A computer program product, characterized in that The invention comprises a non-volatile computer-readable storage medium storing a computer program, wherein the computer program implements the loan assessment method according to any one of claims 1 to 7 when executed by a processor.

Images