Big data intelligent analysis system based on Internet of Things

Abstract

The invention discloses a big data intelligent analysis system based on the Internet of Things, and the system comprises a data collection module, a meal delivery place analysis module, an order monitoring module and a voice output module. Whether a takeout worker needs to be reminded or not is measured in time through a stair-climbing time calculation formula of different floor structures, then a meal delivery difficult place is calculated by combining meal delivery routes of historical orders in a database and meal delivery standing time, and a difficult place reminding module in a voice output module is used for reminding the takeout worker. The order monitoring module also reports the order state of the takeout worker in real time through the order time prompting module, so that the meal delivery efficiency of the takeout worker in the meal delivery process is ensured, the situation that the takeout worker spends a lot of time in finding a specific position or asking the way is avoided, and meanwhile, due to consideration of various road conditions and personnel influences, the meal delivery efficiency is improved. The system can accurately judge according to various conditions, and the conditions of false alarm and no detection are avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of Internet of Things, and specifically to a big data intelligent analysis system based on the Internet of Things. Background Art

[0002] As the post-90s and post-00s gradually enter society, deeply influenced by the Internet, they are more willing to stay at home on weekends and use the takeaway platform to meet their daily needs. With the growth of the post-90s and post-00s, the "lazy economy" is booming, which in turn drives the takeaway delivery service industry. However, the development of the takeaway industry has also brought some problems. For example, when delivering food, deliverymen often encounter orders at some unconventional buildings or locations with hidden entrances that are difficult to find, resulting in deliverymen spending more delivery time. In the prior art, the delivery platform also provides some message sharing systems to help deliverymen inform each other of difficult delivery locations and sections, but in fact, deliverymen do not have extra time to look for the information they need in the system, and cannot effectively improve the delivery efficiency of deliverymen. Therefore, it is necessary to design a big data intelligent analysis system based on the Internet of Things with high accuracy and comprehensive scene coverage. Summary of the Invention

[0003] The purpose of the present invention is to provide a big data intelligent analysis system based on the Internet of Things to solve the problems raised in the above background art.

[0004] To solve the above technical problems, the present invention provides the following technical solutions: A big data intelligent analysis system based on the Internet of Things, including a data collection module, a delivery location analysis module, an order monitoring module, and a voice output module. The data collection module is used to collect the nearby road conditions and arrival methods of the delivery location, and solve the problems of deliverymen being blocked by obstacles on the road and unable to find the delivery entrance; the delivery location analysis module is used to estimate the approximate delivery time of the deliveryman; the order monitoring module is used to monitor the actual delivery duration of the deliveryman and judge whether the deliveryman has run out of time for delivery; the voice output module is used to give humanized reminders to the deliveryman, and greatly ensure the normal delivery of the deliveryman. The data collection module, the delivery location analysis module, the order monitoring module, and the voice output module are electrically connected to each other.

[0005] According to the above technical solution, the data collection module includes a historical order delivery route collection module, a delivery obstacle detection module, and a historical order delivery stay time module. The historical order delivery collection module is used to collect the action trajectories of deliverymen in historical orders; the delivery obstacle detection module is used to monitor whether there are factors blocking the deliveryman during the delivery process; the historical order delivery stay time analysis module is used to judge the environmental complexity of the delivery location.

[0006] According to the above technical solution, the delivery location analysis module includes an upstairs delivery time analysis module, a deliveryman stay time sensing module, and a judgment module 1. The upstairs delivery time analysis module is used to estimate the time required for the deliveryman to go upstairs for different floors; the actual stay time sensing module of the deliveryman is used to monitor whether the actual delivery time of the deliveryman has exceeded the normal delivery time; the judgment module 1 is used to comprehensively consider the upstairs delivery analysis module and the deliveryman stay time sensing module to judge whether to remind the deliveryman; the upstairs delivery time analysis module includes an elevator floor analysis sub-module and a non-elevator floor analysis sub-module. The elevator floor analysis sub-module is used to estimate the normal time required for the deliveryman to go upstairs for elevator floors, and the non-elevator floor analysis sub-module is used to estimate the normal time required for the deliveryman to go upstairs for non-elevator floors.

[0007] According to the above technical solution, the order monitoring module includes an order remaining time module and a judgment module 2. The order remaining time module is used to monitor the real-time remaining time of the deliveryman's order and obtain the estimated delivery time required by the deliveryman in the order; the judgment module 2 is used to understand the actual urgency of the order and decide whether to prompt the deliveryman.

[0008] According to the above technical solution, the voice output module includes an obstacle avoidance module and a difficult location prompt module. The obstacle avoidance module adjusts the route in time to help the deliveryman reach the delivery location faster; the difficult location prompt module is used to give voice prompts to the deliveryman for hidden entrances or buildings during the delivery process; the order time prompt module is used for the deliveryman to understand the order time.

[0009] According to the above technical solution, the operation system of the big data intelligent analysis system mainly includes the following steps:

[0010] Step S1: Establish an information collection database, and collect and input the historical order delivery routes, delivery obstacle data, and historical order delivery stay time data respectively;

[0011] Step S2: Screen out the delivery stay time of each rider who first comes to the target delivery location in the historical order from the historical order delivery stay time data, and calculate the average delivery time T1 of this area. Transmit the screened data and the average delivery time T1 of this area to the judgment module 1;

[0012] Step S3: The judgment module 1 compares the screened data with the average delivery time T1 of this area one by one, judges the delivery difficulty of each delivery location, and marks it;

[0013] Step S4: Through the analysis of the floor in the order, obtain the normal delivery stay time T2 at the food delivery location, and transmit the normal delivery stay time T2 to Judgment Module 1;

[0014] Step S5: If Judgment Module 1 detects that the actual stay time of the rider has exceeded the normal stay time T2, and the label of this location is "difficult food delivery location", the information will be transmitted to the voice output module;

[0015] Step S6: Detect the remaining order time T3 and the estimated delivery time T4 required by the deliveryman among the remaining n orders of the deliveryman, and transmit the time data to Judgment Module 2;

[0016] Step S7: Judgment Module 2 compares the remaining order time T3 and the estimated delivery time T4 required by the deliveryman. If Judgment Module 2 calculates that this order has an urgency level, it will output a reminder signal to the difficult location reminder module, and at the same time transmit the information to the order time reminder module;

[0017] Step S8: The voice output module receives the food delivery obstacle data from the database, prompts the deliveryman to adjust the food delivery route, and at the same time, by receiving the reminder signal from the judgment module, prompts the deliveryman about the hidden buildings and entrances and exits at the food delivery location.

[0018] According to the above technical solution, in step S3, when Judgment Module 1 detects that the delivery time of ≥60% of the deliverymen in the community is higher than the average delivery time T1 in this area, Judgment Module 1 will consider this food delivery location as a difficult food delivery location and mark it as "difficult food delivery location"; when Judgment Module 1 detects that the delivery time of more than 20% but less than 60% of the deliverymen in the community is higher than the average delivery time T1 in this area, Judgment Module 1 will consider this food delivery location as a normal difficulty food delivery location and mark it as "normal food delivery location"; when Judgment Module 1 detects that only ≤20% of the deliverymen in the community have a delivery time higher than the average delivery time T1 in this area, Judgment Module 1 will consider this food delivery location as a simple food delivery location and mark it as "simple food delivery location".

[0019] According to the above technical solution, in step S4, when the deliveryman delivers to a customer on an elevator floor, if the analysis system extracts the target floor number in the order as X, the normal stay time of the deliveryman should be less than (2AX + B) seconds, where A is the time required for the deliveryman to go up one floor in the elevator, and B is the total time for the deliveryman to wait for the elevator and knock on the door; when the deliveryman delivers to a customer on a non - elevator floor, if the target floor number in the order is extracted as Y, the normal stay time of the deliveryman should be less than (2CY + D) seconds, where C is the time required for the deliveryman to climb one floor of the stairs, and D is the time for the deliveryman to wait for knocking on the door.

[0020] According to the above technical solution, in step S7, when the judgment module 2 detects that among the remaining n orders of the deliveryman, the i-th order (i≤n) has a situation where the deliveryman's estimated delivery time T4 is higher than the remaining time T3 of the order, it is determined that the current order is urgent, and a reminder signal is output to the difficult location prompt module, and the information is transmitted to the order time prompt module at the same time.

[0021] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: the present invention sets up a data collection module, a food delivery location analysis module, an order monitoring module and a voice output module. The upstairs delivery time analysis module utilizes the characteristic that the deliveryman's position is basically stationary when he goes upstairs to deliver food, and timely calculates whether the deliveryman needs to be reminded through the upstairs time calculation formula of different floor structures. Then, the delivery route and the delivery stop time of the historical orders in the database are combined to calculate the difficult delivery locations, and the difficult location prompt module in the voice output module is used to prompt the deliveryman. The order monitoring module will also report the order status of the deliveryman in real time through the order time prompt module, which ensures the delivery efficiency of the deliveryman during the delivery process and avoids the deliveryman spending a lot of time looking for a specific location or asking for directions. At the same time, considering the influence of various road conditions and personnel, the system can accurately judge according to various situations, and there will be no false alarms or undetected situations. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0023] Figure 1 It is a schematic diagram of the system module composition of the present invention. DETAILED DESCRIPTION

[0024] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0025] See also Figure 1 The present invention provides a technical solution: a big data intelligent analysis system based on the Internet of Things, comprising:

[0026] A data collection module, a delivery location analysis module, an order monitoring module, and a voice output module. The data collection module is used to collect the road conditions and arrival methods of the delivery locations, solving the problems of delivery workers being blocked by obstacles on the road and unable to find the delivery entrance; the delivery location analysis module is used to estimate the approximate delivery time of the delivery workers; the order monitoring module is used to monitor the remaining order time of the delivery workers to determine whether the delivery workers are already in a situation where they will not be able to deliver the food in time; the voice output module is used to give humanized reminders to the delivery workers, greatly ensuring the normal delivery of the delivery workers. The data collection module, the delivery location analysis module, the order monitoring module, and the voice output module are interconnected. In the upstairs delivery time analysis module, taking advantage of the characteristic that the position of the delivery worker is basically stationary when going upstairs to deliver food, through the upstairs time calculation formula for different floor structures, it timely calculates whether the delivery worker needs to be reminded, and then combines the delivery routes and delivery stay times of historical orders in the database to deduce the difficult delivery locations, and uses the difficult location reminder module in the voice output module to remind the delivery worker. The order monitoring module will also report the order status of the delivery worker in real time through the order time reminder module, ensuring the delivery efficiency of the delivery worker during the delivery process, avoiding the delivery worker spending a lot of time looking for specific locations or asking for directions. At the same time, due to considering various road conditions and personnel impacts, the system can accurately judge according to various situations and will not have false alarms or undetected situations.

[0027] The data collection module includes a historical order delivery route collection module, a delivery obstacle detection module, and a historical order delivery stay time module. The historical order delivery collection module is used to collect the action trajectories of delivery workers in historical orders; the delivery obstacle detection module is used to monitor whether there are factors blocking the delivery workers during the delivery process. For example, external factors such as access control and road condition repairs will have an adverse impact on the delivery routes of delivery workers; the historical order delivery stay time analysis module is used to judge the environmental complexity of the delivery location.

[0028] The delivery location analysis module includes an upstairs delivery time analysis module, a delivery worker stay time sensing module, and a judgment module 1. The upstairs delivery time analysis module is used to estimate the time required for the delivery worker when facing different floors; the actual stay time sensing module of the delivery worker is used to monitor whether the actual delivery time of the delivery worker has exceeded the normal delivery time; the judgment module 1 is used to comprehensively consider the upstairs delivery analysis module and the delivery worker stay time sensing module to judge whether to remind the delivery worker; the upstairs delivery time analysis module includes an elevator floor analysis sub-module and a non-elevator floor analysis sub-module. The elevator floor analysis sub-module is used to estimate the time normally required for the delivery worker to go upstairs and deliver food to the elevator floors, and the non-elevator floor analysis sub-module is used to estimate the time normally required for the delivery worker to go upstairs and deliver food to the non-elevator floors.

[0029] The order monitoring module includes an order remaining time module and a second judgment module. The order remaining time module is used to monitor the real-time remaining time of the order of the deliveryman and obtain the estimated delivery time required by the deliveryman for the order. The second judgment module is used to understand the actual urgency of the order and decide whether to prompt the deliveryman.

[0030] The voice output module includes an obstacle avoidance module and a difficult location prompt module. The obstacle avoidance module adjusts the route in time to help the deliveryman reach the food delivery location faster and reduce the situation where external factors such as access control and road maintenance increase the delivery time of the deliveryman. The difficult location prompt module is used to give voice prompts to the deliveryman for hidden entrances or buildings during the food delivery process, so that the deliveryman can go upstairs to deliver food in time. The order time prompt module is used for the deliveryman to understand the order time and adjust the delivery speed in time.

[0031] The operation system of the big data intelligent analysis system mainly includes the following steps:

[0032] Step S1: Establish an information collection database, and collect and input the historical order food delivery routes, food delivery obstacle data, and historical order food delivery stay time data respectively;

[0033] Step S2: Screen out the food delivery stay time of each rider who comes to the target food delivery location for the first time in the historical order from the historical order food delivery stay time data, and calculate the average food delivery duration T1 of this area. Transmit the screened data and the average food delivery duration T1 of this area to the first judgment module; The food delivery duration of each area will vary. Traffic in the city center is prone to congestion, and the average duration will be longer than that of normal areas. Similarly, the road conditions in the suburbs are poor, there are few main roads, and the deliveryman needs to spend time, and the average duration will also be longer than that of normal areas. By calculating the average food delivery duration of each area, the deviation of factors such as different road conditions from the average duration calculation can be effectively reduced, and the food delivery duration of the riders in the big data can be accurately counted.

[0034] Step S3: The first judgment module compares the screened data with the average food delivery duration T1 of this area one by one, and judges whether this food delivery location belongs to a difficult food delivery location, and marks the difficult food delivery location;

[0035] Step S4: Through the analysis of the floors in the order, obtain the normal food delivery stay time T2 of the food delivery location, and transmit the normal food delivery stay time T2 to the first judgment module;

[0036] Step S5: If the first judgment module detects that the actual stay time of the rider has exceeded the normal stay time T2, and there is a label of a difficult food delivery location in this place, the information will be transmitted to the voice output module;

[0037] Step S6: Detect the remaining time T3 of the deliveryman's order and the estimated delivery time T4 required by the deliveryman, and transmit the time data to the second judgment module;

[0038] Step S7: The second judgment module compares the remaining time T3 of the order with the estimated delivery time T4 required by the deliveryman. If the second judgment module calculates that the order has an urgency level, it outputs a reminder signal to the difficult location prompt module and transmits the information to the order time prompt module at the same time.

[0039] The voice output module receives the food delivery obstacle data from the database, prompts the deliveryman to adjust the food delivery route, and at the same time, by receiving the reminder signal from the judgment module, prompts the deliveryman about the concealed buildings and entrances and exits of the food delivery location.

[0040] In step S3, when the first judgment module detects that the delivery time of ≥60% of the deliverymen in the community is higher than the average delivery time T1 of this area, the first judgment module will consider this delivery location as a difficult delivery location and mark it as "difficult delivery location"; when the first judgment module detects that the delivery time of more than 20% but less than 60% of the deliverymen in the community is higher than the average delivery time T1 of this area, the first judgment module will consider this delivery location as a normal difficulty delivery location and mark it as "normal delivery location"; when the first judgment module detects that only ≤20% of the deliverymen in the community have a delivery time higher than the average delivery time T1 of this area, the first judgment module will consider this delivery location as an easy delivery location and mark it as "easy delivery location".

[0041] The first judgment module calculates the proportion of the number of deliverymen whose delivery time is higher than the average delivery time T1 of this area by comparing the time of the deliveryman's first delivery with the average delivery time T1 of this area. By dividing three different proportion criteria of the number of people, the delivery communities are distinguished into three different delivery difficulties and marked with different difficulty labels, reducing unnecessary prompts for the deliverymen and reducing the operation burden of the system.

[0042] In step S4, when the deliveryman delivers to the customer on the elevator floor, the analysis system extracts the target floor number X in the order. Then the normal stay time of the deliveryman should be less than (2AX + B) seconds, where A is the time required for the deliveryman to go up one floor in the elevator, and B is the total time for the deliveryman to wait for the elevator and knock on the door; when the deliveryman delivers to the customer on the non - elevator floor, the target floor number Y in the order is extracted. Then the normal stay time of the deliveryman should be less than (2CY + D) seconds, where C is the time required for the deliveryman to climb one floor of the stairs, and D is the time for the deliveryman to knock on the door and wait.

[0043] The time calculation method of A varies according to the configurations of different elevators. The elevators in old residential areas run at a slower speed, generally one meter per second. From this, it can be deduced that the time for a deliveryman to go up one floor in the elevator is 5 seconds. While the elevators in high-end residential areas or office buildings run at a faster speed, generally two meters per second. When delivering to residents on high floors, the elevator running speed will exceed two meters per second. Generally speaking, the maximum value of the single-time duration of a deliveryman in the elevator, that is, AX, will not exceed one minute.

[0044] When a deliveryman delivers to a customer on a non-elevator floor, since the highest floor of non-elevator floors is generally 6, we can almost ignore the impact of physical exertion on the deliveryman climbing the stairs.

[0045] By analyzing different building types in the order and using corresponding calculation formulas for precise calculation, the situation where map navigation cannot accurately locate the delivery position of a deliveryman in a relatively close area is improved; and through the time detection system for the deliveryman staying in a small area, the deliveryman who has not found the delivery position is reminded in time, improving the delivery efficiency of the deliveryman.

[0046] In step S7, when the second judgment module detects that among the remaining n orders of the deliveryman, for the i-th order (i ≤ n), the estimated delivery time T4 of the deliveryman is higher than the remaining time T3 of the order, it is determined that the current order has an urgency level, and a reminder signal is output to the difficult location reminder module, and at the same time, the information is transmitted to the order time reminder module.

[0047] If the estimated delivery time T4 of each order of the deliveryman is less than the remaining time of the order, it means that the longer the remaining delivery time of the deliveryman, the less the need for system reminder; similarly, if there are more orders with the estimated delivery time T4 higher than the remaining time T3 of the order, it means that the remaining delivery time of the deliveryman is more urgent and the more the need for system reminder.

[0048] The system detects the situation of the remaining orders of the deliveryman, timely judges whether there is a situation where the deliveryman may not be able to deliver the subsequent orders in time, and reminds the deliveryman, enabling the deliveryman to clearly understand that there may be a time urgency in the remaining orders and make timely adjustments, reducing the delivery mistakes of the deliveryman.

[0049] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or elements inherent to such process, method, article or device.

[0050] Finally, it should be noted that the above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A big data intelligent analysis system based on the Internet of Things, characterized in that: It includes a data collection module, a delivery location analysis module, an order monitoring module, and a voice output module. The data collection module is used to collect the road conditions near the delivery location and the arrival methods, so as to solve the problems that deliverymen are blocked by obstacles on the road and cannot find the delivery entrance. The delivery location analysis module is used to estimate the approximate delivery time of the deliveryman. The order monitoring module is used to monitor the actual delivery duration of the deliveryman and judge whether the deliveryman has encountered a situation where it is too late to deliver the order. The voice output module is used to give humanized reminders to the deliveryman, greatly ensuring the normal delivery of the deliveryman. The data collection module, the delivery location analysis module, the order monitoring module, and the voice output module are electrically connected to each other.

2. The big data intelligent analysis system based on the Internet of Things according to claim 1, wherein: The data collection module includes a historical order delivery route collection module, a delivery obstacle detection module, and a historical order delivery stay time module. The historical order delivery collection module is used to collect the action trajectories of deliverymen in historical orders. The delivery obstacle detection module is used to monitor whether there are factors blocking the deliveryman during the delivery process. The historical order delivery stay time analysis module is used to judge the environmental complexity of the delivery location.

3. The big data intelligent analysis system based on the Internet of Things according to claim 2, characterized in that: The delivery location analysis module includes an upstairs delivery time analysis module, a deliveryman's actual stay time sensing module, and a judgment module 1. The upstairs delivery time analysis module is used to estimate the time required for the deliveryman to deliver food to different floors. The deliveryman's actual stay time sensing module is used to monitor whether the actual delivery time of the deliveryman has exceeded the normal delivery time. The judgment module 1 is used to comprehensively consider the upstairs delivery analysis module and the deliveryman's actual stay time sensing module to judge whether to remind the deliveryman. The upstairs delivery time analysis module includes an elevator floor analysis sub-module and a non-elevator floor analysis sub-module. The elevator floor analysis sub-module is used to estimate the normal time required for the deliveryman to deliver food to the elevator floor. The non-elevator floor analysis sub-module is used to estimate the normal time required for the deliveryman to deliver food to the non-elevator floor.

4. An Internet of Things-based big data intelligent analysis system according to claim 3, characterized in that: The order monitoring module includes an order remaining time module and a judgment module 2. The order remaining time module is used to monitor the real-time remaining time of the deliveryman's order and obtain the estimated delivery time required by the deliveryman in the order. The judgment module 2 is used to understand the actual urgency of the order and decide whether to prompt the deliveryman.

5. An Internet of Things-based big data intelligent analysis system according to claim 4, characterized in that: The voice output module includes an obstacle avoidance module and a difficult location prompt module. The obstacle avoidance module adjusts the route in time to help the deliveryman reach the delivery location faster. The difficult location prompt module is used to give voice prompts to the deliveryman for hidden entrances or buildings during the delivery process. The order time prompt module is used for the deliveryman to know the order time.

6. The big data intelligent analysis system based on the Internet of Things according to claim 5, characterized in that: The operation system of the big data intelligent analysis system mainly includes the following steps: Step S1: Establish an information collection database, and collect and input the historical order delivery routes, delivery obstacle data, and historical order delivery stay time data respectively. Step S2: Filter out the delivery stay times of each rider who comes to the target delivery location for the first time in the historical orders from the historical order delivery stay time data, and calculate the average delivery time T1 for this area. Transmit the filtered data and the average delivery time T1 for this area to Judgment Module 1; Step S3: Judgment Module 1 compares the filtered data with the average delivery time T1 for this area one by one, judges the delivery difficulty of each delivery location, and marks it; Step S4: Through the analysis of the floors in the order, obtain the normal delivery stay time T2 of the delivery location, and transmit the normal delivery stay time T2 to Judgment Module 1; Step S5: If Judgment Module 1 detects that the actual stay time of the rider has exceeded the normal stay time T2, and the label of this place is "difficult delivery location", it will transmit the information to the voice output module; Step S6: Detect the remaining order time T3 and the estimated delivery time T4 required by the deliveryman in the remaining n orders of the deliveryman, and transmit the time data to Judgment Module 2; Step S7: Judgment Module 2 compares the remaining order time T3 and the estimated delivery time T4 required by the deliveryman. If Judgment Module 2 calculates that this order has an urgency level, it will output a reminder signal to the difficult location prompt module, and at the same time transmit the information to the order time prompt module; Step S8: The voice output module receives the delivery obstacle data from the database, prompts the deliveryman to adjust the delivery route, and at the same time, by receiving the reminder signal from the judgment module, prompts the deliveryman about the hidden buildings and entrances and exits of the delivery location.

7. An Internet of Things-based big data intelligent analysis system according to claim 6, characterized in that: In the said Step S3, when Judgment Module 1 detects that the delivery times of ≥60% of the deliverymen in the community are higher than the average delivery time T1 for this area, Judgment Module 1 will consider this delivery location as a difficult delivery location and mark it as "difficult delivery location"; when Judgment Module 1 detects that the delivery times of more than 20% but less than 60% of the deliverymen in the community are higher than the average delivery time T1 for this area, Judgment Module 1 will consider this delivery location as a normal difficulty delivery location and mark it as "normal delivery location"; when Judgment Module 1 detects that only ≤20% of the deliverymen in the community have delivery times higher than the average delivery time T1 for this area, Judgment Module 1 will consider this delivery location as an easy delivery location and mark it as "easy delivery location".

8. An Internet of Things-based big data intelligent analysis system according to claim 7, characterized in that: In the said Step S4, when the deliveryman delivers to a customer on an elevator floor, the analysis system extracts the target floor number in the order as X, then the normal stay time of the deliveryman should be less than (2AX + B) seconds, where A is the time required for the deliveryman to go up one floor in the elevator, and B is the total time for the deliveryman to wait for the elevator and knock on the door; when the deliveryman delivers to a customer on a floor without an elevator, the target floor number in the order is extracted as Y, then the normal stay time of the deliveryman should be less than (2CY + D) seconds, where C is the time required for the deliveryman to climb one flight of stairs, and D is the time for the deliveryman to knock on the door and wait.

9. An Internet of Things-based big data intelligent analysis system according to claim 8, characterized in that: In step S7, when the second judgment module detects that for the i-th order (i ≤ n) among the remaining n orders of the deliveryman, the estimated delivery time T4 of the deliveryman for this order is higher than the remaining time T3 of the order, it is determined that the current order has an urgency level, and a reminder signal is output to the difficult location reminder module. Meanwhile, the information is transmitted to the order time reminder module.

Images