CN112101865A

CN112101865A - Waiting time obtaining method and device, computer equipment and readable storage medium

Info

Publication number: CN112101865A
Application number: CN202010960358.4A
Authority: CN
Inventors: 赵京
Original assignee: Lazas Network Technology Shanghai Co Ltd
Current assignee: Lazas Network Technology Shanghai Co Ltd
Priority date: 2020-09-14
Filing date: 2020-09-14
Publication date: 2020-12-18
Anticipated expiration: 2040-09-14
Also published as: CN112101865B

Abstract

The invention discloses a waiting time obtaining method and device, computer equipment and a readable storage medium, relates to the technical field of Internet, obtains environment data and behavior data, calculates the credibility of a time window corresponding to the environment data and the behavior data, further determines the waiting time, calculates the waiting time by utilizing multivariate data, solves the problem that the coverage range of a single signal-based geographic fence is too large or too small, and improves the calculation accuracy. The method comprises the following steps: acquiring a plurality of environmental data and a plurality of behavior data of a target distribution facility in a historical distribution process; mapping the plurality of environment data and the plurality of behavior data to a plurality of time windows of a historical distribution process, and calculating a plurality of credibility of the plurality of time windows; determining an arrival time window and a departure time window in a plurality of time windows according to the plurality of degrees of confidence; the time interval between the arrival time window and the departure time window is taken as the waiting time.

Description

Waiting time obtaining method and device, computer equipment and readable storage medium

Technical Field

The present invention relates to the field of internet technologies, and in particular, to a method and an apparatus for obtaining latency, a computer device, and a readable storage medium.

Background

With the continuous development of internet technology, in most service industries, the user has higher and higher requirements on experience, so that more and more services can be provided for the user by the terminal, for example, the take-out industry becomes an important component of daily life of people, and the take-out industry enables people to enjoy consumption and services without leaving the home. In the take-out industry nowadays, many platforms providing take-out services are equipped with delivery personnel, during the peak period of take-out, the pressure of meal delivery of merchants rises straightly, the meal delivery speed is much lower than that in idle time, and the delivery personnel are forced to eat at the merchants and the like. If the meal time is long, the meal delivery efficiency of a delivery person is easily reduced, even the meal delivery is overtime, and finally a series of contradictions are likely to be caused between the delivery person and a merchant due to responsibility identification.

In the related art, when the waiting time of the distribution personnel is counted at present, the arrival time and the departure time of the distribution personnel need to be acquired, and the time interval between the arrival time and the departure time is used as the waiting time of the distribution personnel. The same means can be used to determine whether the delivery staff arrives and leaves, and the determination of whether the delivery staff arrives can be realized by a GPS (Global Positioning System) provided by the delivery staff and the provision of the delivery staff, for example. The specific implementation logic is that if the delivery personnel report to the platform that the delivery personnel has arrived and the GPS displays that the distance between the delivery personnel and the shop or the customer is less than the threshold value, the delivery personnel is determined to have arrived, and the arrival time of the delivery personnel can be continuously output based on the current time. And subsequently, judging whether the distribution personnel leave or not and outputting the leaving time in the same way, and further acquiring the waiting time of the distribution personnel.

In the process of implementing the invention, the inventor finds that the related art has at least the following problems:

the GPS can be influenced by signals, the precision of the GPS is lower indoors and at the position with poorer signals, the situation of continuous jumping can occur, and the distance between a distribution worker and a store or a customer is difficult to accurately judge. The reporting of the distribution personnel is an individual behavior, a cheating space exists, the distribution personnel can report falsely, the accuracy of the waiting time acquired by the platform is low under the influence of two factors, the waiting time is difficult to convince as a basis for solving disputes, an effective informatization means is lacked, and the intelligent process of the catering service is influenced.

Disclosure of Invention

In view of the above, the present invention provides a method and an apparatus for obtaining a waiting time, a computer device, and a readable storage medium, and mainly aims to solve the problems that the accuracy of the waiting time obtained by the current platform is low, the waiting time is difficult to convince as a basis for solving disputes, an effective informatization means is lacked, and the intelligent progress of the food and beverage service is affected.

According to a first aspect of the present invention, there is provided a latency acquisition method, including:

acquiring a plurality of environmental data and a plurality of behavior data of a target distribution facility in a historical distribution process;

mapping the plurality of environment data and the plurality of behavior data to a plurality of time windows of the historical distribution process, and calculating a plurality of credibility of the plurality of time windows, wherein the plurality of credibility indicates occurrence probability of the environment data and behavior data corresponding to the plurality of time windows;

determining an arrival time window and a departure time window in the plurality of time windows according to the plurality of degrees of confidence;

and taking the time interval between the arrival time window and the departure time window as the waiting time.

In another embodiment, the obtaining a plurality of environmental data and a plurality of behavior data of the target distribution facility during the historical distribution process includes:

extracting a plurality of terminal signals uploaded by terminal equipment of the target distribution facility in the historical distribution process, wherein the plurality of terminal signals at least comprise inertia signals, Bluetooth signals, wireless signals, magnetic induction signals and cellular signals;

dividing the plurality of terminal signals into a plurality of signal groups based on the uploading time of the plurality of terminal signals, wherein the uploading time of at least one terminal signal included in each of the plurality of signal groups is consistent;

and respectively carrying out signal analysis on the plurality of signal groups to obtain the plurality of environment data and the plurality of behavior data.

In another embodiment, the performing signal analysis on the signal groups to obtain the environmental data and the behavior data respectively includes:

for each of the plurality of signal groups, reading a plurality of target signals included in the signal group;

determining the environment of the target distribution equipment at the uploading time corresponding to the signal group based on the plurality of target signals to obtain environment data, wherein the environment data is at least any one of indoor environment and outdoor environment;

determining the use state of the terminal equipment at the uploading time corresponding to the signal group and the motion state of the target distribution facility at the uploading time corresponding to the signal group according to the target signals, and obtaining behavior data based on the use state and the motion state, wherein the behavior data is at least any one of waiting behavior and distribution behavior;

and respectively reading each signal group in the plurality of signal groups, and outputting the environmental data and the behavior data of each signal group to obtain the plurality of environmental data and the plurality of behavior data.

In another embodiment, said deriving behavioural data based on said use state and said movement state comprises:

setting the waiting behavior as the behavior data when the use status indicates that the terminal device executes a user instruction and the motion status indicates that the target distribution facility is stationary or the motion speed of the motion status is less than a speed threshold;

setting the delivery behavior as the behavior data when the usage state indicates that the terminal device is in standby and the motion state indicates that the delivery facility moves or a motion speed of the motion state is greater than or equal to the speed threshold.

In another embodiment, said mapping said plurality of environmental data and said plurality of behavioral data to a plurality of time windows of said historical delivery process comprises:

based on preset dividing time, time division is carried out on the historical distribution process to obtain a plurality of time windows, and the time length of each time window in the time windows is equal to the preset dividing time length;

determining target uploading time corresponding to each environmental data or each behavior data for the plurality of environmental data and each environmental data or each behavior data in the plurality of behavior data;

inquiring a target time window of the target uploading time in the plurality of time windows, mapping each environmental data or each behavior data to the target time window, and completing the mapping between the plurality of environmental data and the plurality of behavior data and the plurality of time windows.

In another embodiment, said calculating a plurality of degrees of confidence for said plurality of time windows comprises:

training a time sequence model on the plurality of environment data and the plurality of behavior data by adopting the plurality of time windows to generate a distribution process time sequence model, wherein the distribution process time sequence model comprises an estimated state corresponding to each time window in the plurality of time windows;

for each time window in the plurality of time windows, acquiring a corresponding target estimation state of the time window in the distribution process time sequence model;

when the target environment data and the target behavior data corresponding to the time window are matched with the target estimation state, setting the environment credibility of the target environment data and the behavior credibility of the target behavior data as first default values, and forming the credibility of the time window based on the environment credibility and the behavior credibility;

when any one of the target environment data or the target behavior data corresponding to the time window is not matched with the target estimated state, calculating a difference value between a standard value and a second default value, taking the difference value as the credibility of the data which are not matched with the target estimated state, and taking the second default value as the credibility of the data which are matched with the target estimated state to obtain the credibility of the time window;

when the target environment data or the target behavior data corresponding to the time window are not matched with the target estimation state, setting the environment credibility of the target environment data and the behavior credibility of the target behavior data as third default values, and forming the credibility of the time window based on the environment credibility and the behavior credibility;

and respectively calculating the credibility of the plurality of time windows to obtain the plurality of credibility.

In another embodiment, said determining an arrival time window and a departure time window in said plurality of time windows based on said plurality of degrees of confidence comprises:

setting a window label for each time window in the plurality of time windows according to the plurality of credibility, wherein the window label is at least any one of an arrival label or a departure label;

obtaining a plurality of continuous candidate time windows with window labels as the arrival labels from the plurality of time windows, and adopting the plurality of candidate time windows to form a window queue, wherein the window labels of the window queue in the previous time window and the next time window of the plurality of time windows are the departure labels;

and taking the candidate time window arranged at the head of the window queue as the arrival time window, and taking the candidate time window arranged at the tail of the window queue as the departure time window.

In another embodiment, said setting a window label for each of said plurality of time windows according to said plurality of degrees of confidence comprises:

for each time window in the multiple time windows, obtaining target credibility corresponding to the time window, and comparing the target environment credibility and the target behavior credibility included in the target credibility;

if the target environment credibility is consistent with the target behavior credibility, setting a window label matched with the environment data and the behavior data of the time window for the time window;

if the target environment credibility is inconsistent with the target behavior credibility, extracting specified credibility from the target environment credibility and the target behavior credibility, and setting a window label matched with data corresponding to the specified credibility for the time window, wherein the specified credibility is greater than the other credibility except the specified credibility in the target environment credibility and the target behavior credibility.

In another embodiment, before setting a window label for each of the plurality of time windows according to the plurality of degrees of confidence, the method further comprises:

extracting credibility to be adjusted from the plurality of credibility, wherein the credibility to be adjusted comprises environment credibility and behavior credibility which are lower than a credibility threshold;

determining a time window to be adjusted corresponding to the credibility to be adjusted, and extracting a previous time window and a later time window of the time window to be adjusted;

determining a standard time window in the previous time window and the later time window, wherein the standard time window comprises environmental data and behavior data which are inconsistent with the environmental data and behavior data of the time window to be adjusted;

and assigning the environmental data and the behavior data included in the standard time window and the credibility corresponding to the standard time window to the time window to be adjusted to obtain the adjusted time window to be adjusted, and setting a window label based on the adjusted time window to be adjusted.

According to a second aspect of the present invention, there is provided a latency acquisition apparatus, comprising:

the acquisition module is used for acquiring a plurality of environmental data and a plurality of behavior data of the target distribution facility in the historical distribution process;

a calculation module, configured to map the plurality of environmental data and the plurality of behavior data to a plurality of time windows of the historical distribution process, and calculate a plurality of reliabilities of the plurality of time windows, where the plurality of reliabilities indicate occurrence probabilities of the environmental data and the behavior data corresponding to the plurality of time windows;

a determining module configured to determine an arrival time window and a departure time window in the plurality of time windows according to the plurality of degrees of confidence;

the determining module is further configured to use a time interval between the arrival time window and the departure time window as a waiting time.

In another embodiment, the obtaining module includes:

the extraction unit is used for extracting a plurality of terminal signals uploaded by terminal equipment of the target distribution facility in the historical distribution process, wherein the terminal signals at least comprise inertia signals, Bluetooth signals, wireless signals, magnetic induction signals and cellular signals;

the dividing unit is used for dividing the plurality of terminal signals into a plurality of signal groups based on the uploading time of the plurality of terminal signals, and the uploading time of at least one terminal signal included in each of the plurality of signal groups is consistent;

and the analysis unit is used for respectively carrying out signal analysis on the plurality of signal groups to obtain the plurality of environment data and the plurality of behavior data.

In another embodiment, the parsing unit is configured to, for each of the plurality of signal groups, read a plurality of target signals included in the signal group; determining the environment of the target distribution equipment at the uploading time corresponding to the signal group based on the plurality of target signals to obtain environment data, wherein the environment data is at least any one of indoor environment and outdoor environment; determining the use state of the terminal equipment at the uploading time corresponding to the signal group and the motion state of the target distribution facility at the uploading time corresponding to the signal group according to the target signals, and obtaining behavior data based on the use state and the motion state, wherein the behavior data is at least any one of waiting behavior and distribution behavior; and respectively reading each signal group in the plurality of signal groups, and outputting the environmental data and the behavior data of each signal group to obtain the plurality of environmental data and the plurality of behavior data.

In another embodiment, the parsing unit is configured to set the waiting behavior as the behavior data when the usage status indicates that the terminal device executes a user instruction and the motion status indicates that the target distribution facility is stationary or a motion speed of the motion status is less than a speed threshold; setting the delivery behavior as the behavior data when the usage state indicates that the terminal device is in standby and the motion state indicates that the delivery facility moves or a motion speed of the motion state is greater than or equal to the speed threshold.

In another embodiment, the calculation module includes:

the dividing unit is used for carrying out time division on the historical distribution process based on preset dividing duration to obtain a plurality of time windows, and the duration of each time window in the plurality of time windows is equal to the preset dividing duration;

the determining unit is used for determining target uploading time corresponding to each environmental data or each behavior data for the plurality of environmental data and each environmental data or each behavior data in the plurality of behavior data;

the mapping unit is used for inquiring a target time window in which the target uploading time is located in the plurality of time windows, mapping each environmental data or each behavior data to the target time window, and completing mapping between the plurality of environmental data and the plurality of behavior data and the plurality of time windows.

In another embodiment, the calculation module includes:

a training unit, configured to train a time sequence model on the multiple environmental data and the multiple behavior data by using the multiple time windows, and generate a distribution process time sequence model, where the distribution process time sequence model includes an estimated state corresponding to each of the multiple time windows;

the acquisition unit is used for acquiring a corresponding target estimated state of each time window in the plurality of time windows in the distribution process time sequence model;

the setting unit is used for setting the environment credibility of the target environment data and the behavior credibility of the target behavior data as first default values when the target environment data and the target behavior data corresponding to the time window are matched with the target estimation state, and forming the credibility of the time window based on the environment credibility and the behavior credibility;

the setting unit is further configured to calculate a difference between a standard value and a second default value when any one of the target environment data or the target behavior data corresponding to the time window is not matched with the target estimation state, use the difference as the reliability of the data that is not matched with the target estimation state, and use the second default value as the reliability of the data that is matched with the target estimation state, so as to obtain the reliability of the time window;

the setting unit is further configured to set, when the target environment data or the target behavior data corresponding to the time window are not matched with the target estimation state, the environment reliability of the target environment data and the behavior reliability of the target behavior data to third default values, and form the reliability of the time window based on the environment reliability and the behavior reliability;

the setting unit is further configured to calculate the credibility of the plurality of time windows respectively to obtain the plurality of credibility.

In another embodiment, the determining module includes:

a setting unit, configured to set a window label for each of the multiple time windows according to the multiple credibility, where the window label is at least one of an arrival label or a departure label;

an obtaining unit, configured to obtain multiple consecutive candidate time windows with window tags as the arrival tags in the multiple time windows, and form a window queue using the multiple candidate time windows, where the window tags of a previous time window and a next time window in the multiple time windows in the window queue are both the departure tags;

and the determining unit is used for taking the candidate time window arranged at the head of the window queue as the arrival time window and taking the candidate time window arranged at the tail of the window queue as the departure time window.

In another embodiment, the setting unit is configured to, for each time window of the multiple time windows, obtain a target reliability corresponding to the time window, and compare a target environment reliability and a target behavior reliability included in the target reliability; if the target environment credibility is consistent with the target behavior credibility, setting a window label matched with the environment data and the behavior data of the time window for the time window; if the target environment credibility is inconsistent with the target behavior credibility, extracting specified credibility from the target environment credibility and the target behavior credibility, and setting a window label matched with data corresponding to the specified credibility for the time window, wherein the specified credibility is greater than the other credibility except the specified credibility in the target environment credibility and the target behavior credibility.

In another embodiment, the determining module further includes:

a first extraction unit, configured to extract a confidence level to be adjusted from the multiple confidence levels, where the confidence level to be adjusted includes an environmental confidence level and a behavior confidence level that are both lower than a confidence level threshold;

the second extraction unit is used for determining a time window to be adjusted corresponding to the credibility to be adjusted and extracting a previous time window and a next time window of the time window to be adjusted;

the determining unit is further configured to determine a standard time window in the previous time window and the subsequent time window, where the environment data and the behavior data included in the standard time window are inconsistent with the environment data and the behavior data included in the time window to be adjusted;

and the adjusting unit is used for assigning the environmental data and the behavior data which are included by the standard time window and the credibility corresponding to the standard time window to the time window to be adjusted to obtain the adjusted time window to be adjusted, and setting a window label based on the adjusted time window to be adjusted.

According to a third aspect of the present invention, there is provided a computer device comprising a memory storing a computer program and a processor implementing the steps of the method of the first aspect when the processor executes the computer program.

According to a fourth aspect of the present invention, there is provided a readable storage medium having stored thereon a computer program which, when executed by a processor, carries out the steps of the method of the first aspect as set forth above.

By means of the technical scheme, the method, the device, the computer equipment and the readable storage medium for obtaining the waiting time are provided by the invention, the environment data and the behavior data of the target distribution facility in the historical distribution process are obtained, the environment data and the behavior data are mapped to the time window of the historical distribution process, the credibility of the time window is calculated, the arrival time window and the departure time window are determined in the time window according to the credibility, the time interval between the arrival time window and the departure time window is used as the waiting time, the waiting time of the distribution personnel is calculated by utilizing multivariate data of the distribution personnel in the distribution process, the problem that the geographic coverage range is too large or the coverage range is too small based on a single signal is solved, the waiting time is obtained by adopting an effective informatization means, and the accuracy of the calculation of the waiting time is improved, the waiting time is convincing, and the intelligent process of the catering service is promoted.

The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.

Drawings

Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:

fig. 1 shows a flowchart of a latency obtaining method according to an embodiment of the present invention;

fig. 2A is a schematic flowchart illustrating a latency obtaining method according to an embodiment of the present invention;

fig. 2B is a flowchart illustrating a waiting time obtaining method according to an embodiment of the present invention;

fig. 3A is a schematic structural diagram illustrating a latency obtaining apparatus according to an embodiment of the present invention;

fig. 3B is a schematic structural diagram illustrating a latency obtaining apparatus according to an embodiment of the present invention;

fig. 3C is a schematic structural diagram illustrating a latency obtaining apparatus according to an embodiment of the present invention;

fig. 3D is a schematic structural diagram illustrating a latency obtaining apparatus according to an embodiment of the present invention;

fig. 3E is a schematic structural diagram illustrating a latency obtaining apparatus according to an embodiment of the present invention;

fig. 3F is a schematic structural diagram illustrating a latency obtaining apparatus according to an embodiment of the present invention;

fig. 4 shows a schematic device structure diagram of a computer apparatus according to an embodiment of the present invention.

Detailed Description

Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.

An embodiment of the present invention provides a method for acquiring a waiting time, as shown in fig. 1, the method includes:

101. a plurality of environmental data and a plurality of behavior data of a target distribution facility in a historical distribution process are obtained.

102. The method comprises the steps of mapping a plurality of environment data and a plurality of behavior data to a plurality of time windows of a historical distribution process, and calculating a plurality of credibility of the plurality of time windows, wherein the credibility indicates the occurrence probability of the environment data and the behavior data corresponding to the time windows.

103. An arrival time window and a departure time window are determined among the plurality of time windows based on the plurality of degrees of confidence.

104. The time interval between the arrival time window and the departure time window is taken as the waiting time.

According to the method provided by the embodiment of the invention, the environmental data and the behavior data of the target distribution facility in the historical distribution process are obtained, the environmental data and the behavior data are mapped to the time window of the historical distribution process, the credibility of the time window is calculated, the arrival time window and the departure time window are determined in the time window according to the credibility, the time interval between the arrival time window and the departure time window is used as the waiting time, the waiting time of the distribution personnel is calculated by utilizing the multivariate data of the distribution personnel in the distribution process, the problem that the coverage range of the geographic fence is too large or the coverage range is too large based on a single signal is solved, the waiting time is ensured to be obtained by adopting an effective informatization means, the accuracy of the calculation of the waiting time is improved, the waiting time is convincing, and the intelligent process of catering services is promoted.

An embodiment of the present invention provides a method for acquiring a waiting time, as shown in fig. 2A, the method includes:

201. a plurality of environmental data and a plurality of behavior data of a target distribution facility in a historical distribution process are obtained.

Currently, there is a problem in the take-out industry, which is how to effectively determine whether and how long a deliverer has waited at a store of a merchant or a customer during the delivery of a commodity. In the peak time period of take-out, due to the fact that the pressure of the business for taking meals rises straightly, the speed of taking meals is reduced greatly compared with that of taking meals in idle time, even the situation of a burst of orders can occur, and the distribution personnel can be forced to wait in a store. However, since there is no effective method for determining whether the delivery personnel have waited once, the platform cannot effectively obtain the waiting time of the delivery personnel, cannot predict the waiting time according to the waiting time, and cannot provide an effective suggestion to the delivery personnel according to the waiting time, so that a series of problems may be caused in the process of practical application. First, the wait of the delivery personnel in the store can cause the efficiency of the meal delivery to be reduced and even time out. Secondly, the long waiting time of the deliverer can cause contradiction between the deliverer and the merchant due to responsibility identification, the platform is required to carry out arbitration, and strong evidence of arbitration is lacked in the platform. Therefore, two methods for acquiring the waiting time of the delivery personnel currently exist, one method is to determine whether the delivery personnel arrives at the store through the GPS and the provision of the delivery personnel, and the specific judgment logic is to determine that the delivery personnel arrives at the store, start timing and stop timing when the platform detects that the delivery personnel leaves the store in the same manner based on the fact that the distance between the delivery personnel and the store is smaller than a preset distance threshold value by the GPS, so as to acquire the waiting time of the delivery personnel. Another method is to determine when the delivery personnel arrives at the store and leaves the store through bluetooth and WiFi (Wireless-Fidelity, Wireless network), and the specific judgment logic is that the merchant's bluetooth and WiFi are set in the store of the merchant, if the terminal held by the delivery personnel sets the bluetooth and WiFi connection with the merchant successfully, the delivery personnel can be determined to arrive at the store, and the time counting is started, and if the connection is disconnected, the delivery personnel can be determined to have left the store, and the time counting is stopped, so as to obtain the waiting time.

However, the inventors have recognized that there are certain drawbacks to obtaining the wait time for the delivery personnel in both of the above-described manners. The first method has the disadvantages that the accuracy of the GPS is influenced by the environment, the GPS has poor accuracy in a closed space such as an indoor space, an elevator, a staircase, and a corridor, and the GPS is continuously jumped, and a great error exists when the distance between a distributor and a store is determined by using the GPS alone. Moreover, the initiative of the preparation belonging to the distribution personnel is that a cheating space exists, and it is quite possible that the distribution personnel does not arrive but reports to the platform that the preparation has arrived, which is unfair for the merchant. The second method has the disadvantages that the distance of bluetooth communication is too short, and bluetooth compatibility is poor, so that it is likely that distribution personnel have arrived but cannot connect to the bluetooth of the store. The WiFi has long communication distance and certain penetrating power, and sometimes the distribution personnel are connected to the WiFi of the store when the distribution personnel are located downstairs of the store or at a certain distance from the store, so that the combined judgment of the Bluetooth and the WiFi is possible to have certain errors and failures. Therefore, the invention provides a method for acquiring waiting time, which acquires environment data and behavior data by acquiring data of environments where distribution personnel are located and behaviors of the distribution personnel in a historical distribution process, calculates the credibility of the environment data and the behavior data corresponding to the distribution personnel in each time slice by adopting a mode of establishing a time sequence model, determines when the distribution personnel arrive at a store and leave from the store based on the time slice with high credibility, further acquires the waiting time of the distribution personnel, calculates the waiting time of the distribution personnel by utilizing multivariate data modeling of the distribution personnel in the distribution process, solves the problem that the coverage range of a geo-fence based on a single signal is too large or too small, and improves the accuracy of the calculation of the waiting time. In the following, the present invention is described by taking an example of determining whether a distributor arrives at a store and the waiting time of the distributor in the store, but in the process of practical application, the same logic may be used to determine whether the distributor arrives at a customer and the waiting time of the customer, and the present invention does not specifically limit the waiting time of the distributor in which process the distributor is specifically determined.

Therefore, in order to implement the present invention, it is necessary to collect environmental data and behavior data of the distribution personnel during the distribution process. It should be noted that, in the embodiment of the present invention, a target delivery facility is taken as an example for description, where the target delivery facility may be a selected takeout person, courier, delivery robot, delivery box, or the like, and as long as a facility having a delivery function can acquire a waiting time for the target delivery facility, a specific style of the delivery facility is not limited in the present invention. When acquiring a plurality of environmental data and a plurality of behavior data of a target distribution facility in a historical distribution process, each distribution facility carries a terminal device for communication, and the current terminal device is generally provided with a plurality of sensors with different functions, such as an IMU sensor for sensing acceleration or angular velocity of the distribution facility and the like, a magnetic sensor for sensing magnetic property change of a sensitive element caused by external factors and the like, and various modules for communicating with the outside, such as a bluetooth module, a wireless module, a cellular module and the like, so that the plurality of environmental data and the behavior data of the target distribution facility in the historical distribution process can be summarized and counted through various types of signals which are uploaded to a platform by the terminal device in the historical distribution process. The process of specifically acquiring the plurality of environmental data and the plurality of behavior data is as follows: firstly, a plurality of terminal signals uploaded by terminal equipment of a target distribution facility in a historical distribution process are extracted, wherein the plurality of terminal signals at least comprise inertia signals, Bluetooth signals, wireless signals, magnetic induction signals and cellular signals. It should be noted that, after the plurality of terminal signals are extracted, considering that the terminal signals are likely to have errors, terminal signals that are completely opposite to most of the terminal signals are likely to exist in the continuously uploaded terminal signals, and in order to reduce errors in subsequent determination of the waiting time, after the plurality of terminal signals are obtained, abnormal value filtering, denoising and filtering processing may be performed on the plurality of terminal signals, that is, data preprocessing may be performed on the obtained terminal signals, so that abnormal terminal signals are discarded. Then, the plurality of terminal signals are divided into a plurality of signal groups based on the uploading time of the plurality of terminal signals, the uploading time of at least one terminal signal included in each signal group in the plurality of signal groups is consistent, that is, the signals uploaded at the same time are divided into the same signal group, and then the signal group is analyzed, so that the environment and the behavior of the target distribution facility at the uploading time of the signal group can be obtained, and the environment and the behavior are integrated to judge whether the target distribution facility arrives or leaves at the uploading time. And finally, respectively carrying out signal analysis on the plurality of signal groups to obtain a plurality of environmental data and a plurality of behavior data.

The process of signal analysis of a signal group is described by taking any one of a plurality of signal groups as an example, and the specific process is as follows: first, for each of a plurality of signal groups, a plurality of target signals included in a read signal group are read. And secondly, determining the environment of the target distribution equipment at the uploading time corresponding to the signal group based on the plurality of target signals to obtain environment data, wherein the environment data is at least any one of indoor environment and outdoor environment. Since the target signal may include an inertial signal, a bluetooth signal, a wireless signal, a magnetic induction signal, and a cellular signal, and different types of terminal signals have different characteristics, for example, the bluetooth signal, the wireless signal, and the magnetic induction signal are prone to bounce indoors, and a simple use of one of the signals to determine whether the target distribution facility is indoors is prone to cause false positive and false negative examples. In view of this, when determining the environmental data, it is necessary to combine different types of terminal signals to determine which type of environment the distribution facility is currently located in, for example, since the humidity and temperature change after entering the room, the speed of the target distribution facility slows down, the terminal device is likely to be successfully connected to WiFi in the store, and the communication quality in the store is worse than that outside, so it is possible to determine whether the distribution facility is located indoors based on the magnetic induction signal, the inertia signal, the wireless signal, and the cellular signal. Further, since the target distribution facility ascends or descends along with the elevator when the elevator is taken, the speed of the elevator is high, and the environment in the elevator is different from that in the indoor and outdoor spaces, it is possible to determine whether the distribution facility is in the elevator car based on the magnetic induction signal and the inertia signal. Also, since only the strong penetration of WiFi causes the wireless signal to change when the target distribution facility is around a store, whether the distribution facility is around a store or not can be determined based on the wireless signal, and the like.

After determining the environmental data, it is also necessary to obtain behavioral data of the target distribution facility based on the plurality of target signals. The movement state of the distribution facility in the distribution process can be roughly divided into a macroscopic state and a microscopic state, wherein the macroscopic state comprises a riding state, a rapid walking state, a slow walking state, a static state and the like. The microscopic states include the behavior states generated by the distribution facility based on the terminal equipment, such as making a phone call, placing a phone in a pocket, holding a phone for use, holding a free-swinging phone, and so on. Whether macro-stateful or micro-stateful, is directly related to whether the distribution facility has reached a store. Generally, when the distribution facility is in a store, only two macroscopic states of rest and travel are provided, and a microscopic state of making a call, using a phone by hand and the like is possible. On the contrary, when the distribution facility is outdoors, the macro state such as riding, walking at the highest speed and the like can be obtained, and the micro state such as placing a telephone in a pocket, holding the telephone by hand and swinging the telephone at will can be obtained, that is, when the distribution facility is in or out of a store, the macro state and the micro state are obviously mutually exclusive, so that the behavior data of the target distribution facility can be obtained based on a plurality of target signals. The specific process of obtaining behavior data is as follows: according to the plurality of target signals, the using state of the terminal equipment at the uploading time corresponding to the signal group and the motion state of the target distribution facility at the uploading time corresponding to the signal group are determined, and behavior data are obtained based on the using state and the motion state, wherein the behavior data are at least any one of waiting behaviors and distribution behaviors. Specifically, when the use state indicating terminal device executes a user instruction and the motion state indicates that the motion speed of the target distribution facility is stationary or the motion state is less than the speed threshold, the waiting behavior is set as the behavior data. That is, the terminal device executing the user instruction of the distribution facility may determine that the distribution facility is using the terminal device, and the distribution facility is stationary or slowly traveling, and the combination of the two may directly indicate that the distribution facility is waiting in a store, and the waiting behavior may be set as the behavior data. When the use state indicates that the terminal device is in standby and the movement speed of the movement state indicates that the distribution facility is moving or the movement state is equal to or greater than the speed threshold, the distribution behavior is set as the behavior data. That is, the terminal device is not used by the distribution facility, may be in a pocket of the distribution facility, and the distribution facility is riding or walking at an extremely high speed, and the combination of the two can directly indicate that the distribution facility is being distributed outdoors without waiting in a store, so the distribution behavior is set as the behavior data.

Through the above process, the signal analysis of the target signal included in the signal group is realized, and the environmental data and the behavior data of the signal group are generated according to the actual situation in the signal group. By repeating the above process, each signal group in the plurality of signal groups can be read, and the environmental data and the behavior data of each signal group are output to obtain a plurality of environmental data and a plurality of behavior data. It should be noted that, the processes of outputting the environment data and the behavior data do not have an obvious sequence, and may be executed simultaneously or sequentially, which is not specifically limited in the present invention.

202. The plurality of environmental data and the plurality of behavioral data are mapped to a plurality of time windows of the historical delivery process.

In the embodiment of the present invention, after the plurality of environmental data and the plurality of behavior data are determined, in order to integrate and study the plurality of environmental data and the plurality of behavior data, a time-series model needs to be established based on the plurality of environmental data and the plurality of behavior data, so that the plurality of environmental data and the plurality of behavior data can be analyzed for reliability in the following. The time sequence model is established by modeling data according to time slices, so that a historical distribution process is divided into a plurality of time slices, one time slice is a time window, a plurality of environment data and a plurality of behavior data are respectively mapped into different time windows, and the time sequence model is established according to different data of the time windows. Specifically, when mapping a plurality of environmental data and a plurality of behavior data to a plurality of time windows of a historical distribution process, firstly, time division needs to be performed on the historical distribution process based on a preset division duration to obtain a plurality of time windows, wherein the duration of each time window in the plurality of time windows is equal to the preset division duration. Then, for each environmental data or each behavior data in the plurality of environmental data and the plurality of behavior data, determining a target uploading time corresponding to each environmental data or each behavior data, inquiring a target time window of the target uploading time in the plurality of time windows, mapping each environmental data or each behavior data to the target time window, and completing mapping between the plurality of environmental data and the plurality of behavior data and the plurality of time windows.

203. A plurality of degrees of confidence for a plurality of time windows is calculated.

In the embodiment of the invention, after the mapping between the data and the time windows is completed, a plurality of credibility of a plurality of time windows can be calculated according to the data corresponding to each time window. The credibility indicates the occurrence probability of the environmental data and the behavior data corresponding to the time windows, that is, the credibility indicates how many percent of the distribution facilities are in the states indicated by the environmental data and the behavior data of the time windows in the current time window, and the credibility is used for marking each time window, and marking the state of the target distribution facility on the time window, so as to determine the arrival of the target distribution facility in which time window and the departure of the target distribution facility in which time window are determined. Therefore, first, a plurality of time windows are adopted to train a time sequence model for a plurality of environment data and a plurality of behavior data, and a distribution process time sequence model is generated. The distribution process time sequence model actually predicts which state the target distribution facility should be in each time window according to global environment data and behavior data and by combining all duration experienced in the whole historical distribution process, and accordingly compares the estimated state with the environment data and the behavior data actually corresponding to the time windows in the follow-up process and determines the probability of the percentage of the time windows to actually generate the corresponding environment data and the corresponding behavior data.

After the distribution process time sequence model is built, for each time window in the multiple time windows, the corresponding target estimation state of the time window in the distribution process time sequence model is obtained. When the target environment data and the target behavior data corresponding to the time window are matched with the target estimation state, it is indicated that the state estimated based on the distribution process time sequence model is consistent with the states corresponding to the environment data and the behavior data corresponding to the time window, and when the three are consistent, the reliability of the environment data and the reliability of the behavior data are very high, so the environment reliability of the target environment data and the behavior reliability of the target behavior data are set as first default values, and the reliability of the time window is formed based on the environment reliability and the behavior reliability. Wherein the first default value may be 100% in practice, and 100% is used to prove the consistency of the three. Further, when any one of the target environment data or the target behavior data corresponding to the time window is not matched with the target estimation state, it indicates that data collection may be wrong, and the credibility of the data is questioned, so that a second default value is obtained, a difference value between the standard value and the second default value is calculated, the difference value is used as the credibility of the data which are not matched with the target estimation state, the second default value is used as the credibility of the data which are matched with the target estimation state, and the credibility of the time window is obtained. Here, the second default value may actually be 66%, and the standard value may actually be 1, for example, assuming that the target estimation state is a waiting state, the environmental data indicates that the store is waiting, and the behavior data indicates that the distribution is underway, the environmental reliability set for the environmental data may be 66%, and the behavior reliability set for the behavior data may be 1-66% — 34%. Further, when the target environment data or the target behavior data corresponding to the time window are not matched with the target estimation state, considering that the target estimation state is obtained for global big data, the data of the time window before and after the current time window are comprehensively considered, and the persuasion is stronger than that of the environment data and the behavior data, so that a third default value can be obtained, the environment credibility of the target environment data and the behavior credibility of the target behavior data are set as the third default value, and the credibility of the time window is formed based on the environment credibility and the behavior credibility, wherein the third default value can be a lower value actually, for example, 1%, and 1% is used for emphasizing that the environment data and the behavior data are opposite to the target estimation state. Alternatively, consistency between the target environment data and the target behavior data may be considered, and the environment reliability of the target environment data and the behavior reliability of the target behavior data may be set to be a difference between the standard value and the second default value, thereby taking into consideration the possibility of the environment data and the behavior data. It should be noted that the set data is an example, and in the process of practical application, each numerical value may also be calculated by using big data, or the environmental data and the behavior data of each time window may also be directly evaluated based on the generated delivery process time sequence model, and the delivery process time sequence model directly outputs the environmental reliability and the behavior reliability.

By repeatedly executing the above processes, the credibility of a plurality of time windows can be respectively calculated, and a plurality of credibility can be obtained.

204. An arrival time window and a departure time window are determined among the plurality of time windows based on the plurality of degrees of confidence.

In an embodiment of the present invention, after determining the plurality of degrees of confidence, an arrival time window and a departure time window may be determined in the plurality of time windows according to the plurality of degrees of confidence. As can be seen from the content in step 203, the environment reliability and the behavior reliability corresponding to some time windows are very low and may reach 1%, and this reliability is likely to be caused by an error in determining the environment data and the behavior data, and the environment data and the behavior data need to be adjusted to improve the reliability thereof, so as to ensure that the subsequent marking of the time window is accurate. When the reliability is adjusted, first, the reliability to be adjusted needs to be extracted from a plurality of reliabilities, where the reliability to be adjusted is actually lower than a reliability threshold, that is, both the environmental reliability and the behavior reliability included therein may be 2% or 50%, and the present invention is not limited to this specifically. And then, starting to adjust the data of the time window to be adjusted corresponding to the credibility to be adjusted. The adjusting mechanism is adjusted by integrating a previous time window and a next time window of the time window to be adjusted, so that the previous time window and the next time window of the time window to be adjusted need to be extracted, a standard time window is determined in the previous time window and the next time window, and environmental data and behavior data included in the standard time window are inconsistent with environmental data and behavior data included in the time window to be adjusted. That is, if the previous time window or the subsequent time window is consistent with the environmental data and behavior data included in the time window to be adjusted, and the time window consistent with the time window to be adjusted is not extracted because of low reliability, it indicates that the time window is authentic, and the data included in the time window to be adjusted needs to be adjusted according to the time window inconsistent with the data, so that the time window inconsistent with the data of the time window to be adjusted is taken as the standard time window. And finally, assigning the environment data and the behavior data included in the standard time window and the credibility corresponding to the standard time window to the time window to be adjusted to obtain the adjusted time window to be adjusted, and setting a window label based on the adjusted time window to be adjusted in the subsequent process. For example, if the environmental data indication in the time window to be adjusted is indoor, the behavior data indication is waiting, the environmental data indication in the previous time window is outdoor, the behavior data indication is delivered, the environmental data indication in the later time window is indoor, and the behavior data indication is waiting, the previous time window is the standard time window, the time window to be adjusted is adjusted to the environmental data indication according to the previous time window and is outdoor, the behavior data indication is delivered, and the reliability of the previous time window is also set in the window to be adjusted. It should be noted that, it is likely that the data of the previous time window and the data of the next time window are not consistent with the data of the window to be adjusted, and it is indicated that the data of the previous time window and the data of the next time window are consistent, so that any time window is selected from the previous time window and the next time window to adjust the time window to be adjusted.

In the process of practical application, the adjustment process of the time windows may be performed based on a recursive model, that is, the environment data, the behavior data, and the reliability corresponding to each time window obtained in the process are all input into the recursive model, and the recursive model determines and adjusts the time windows with lower reliability. Specifically, the recursive model may be LSTM (Long Short-Term Memory), GRU (Gate Recurrent Unit), etc., and the present invention does not limit the specific content of the recursive model.

After the adjustment of the reliability is completed, the reliability and the data corresponding to all the current time windows are relatively accurate, so that a window label can be set for each of the multiple time windows according to the multiple reliabilities, and the window label is used to indicate the state of the target distribution facility in each time window, specifically, the window label is at least one of an arrival label or a departure label. When setting the window label, regarding that, in some time windows, the environment credibility and the behavior credibility are different, and the difference is high or low, and the low time does not reach the adjustment standard, so that the target credibility corresponding to the time window needs to be obtained, and the target environment credibility and the target behavior credibility included in the target credibility are compared. If the target environment credibility and the target behavior credibility are consistent, the states indicated by the environment data and the behavior data in the time window are consistent and more credible, so that a window label matched with the environment data and the behavior data of the time window is set for the time window. If the target environment reliability and the target behavior reliability are inconsistent, a specified reliability needs to be extracted from the target environment reliability and the target behavior reliability, a window label matched with data corresponding to the specified reliability is set for the time window, wherein the specified reliability is greater than the other reliability except the specified reliability in the target environment reliability and the target behavior reliability, that is, a greater reliability is determined from the two reliabilities, and the window label matched with the data corresponding to the greater reliability is set for the time window. For example, assuming that the environment confidence level corresponding to the environment data in the time window is 66%, and the behavior confidence level corresponding to the behavior data is 34%, the window label set for the time window is matched with the environment data.

After setting a window label for each time window in a plurality of time windows according to a plurality of credibility, acquiring a plurality of continuous candidate time windows with the window labels as arrival labels in the plurality of time windows, and forming a window queue by adopting the plurality of candidate time windows, wherein the window labels of the last time window and the next time window in the plurality of time windows in the window queue are both departure labels. That is, assuming that the window label of the time window a is a leave label, the window labels of the time windows B to E are arrival labels, the next time window of the time window E is F, and the window label of the time window F is a leave label, the window queue is the time windows B to E. Then, the candidate time window arranged at the head of the window queue is used as an arrival time window, and the candidate time window arranged at the tail of the window queue is used as a departure time window. Continuing with the above example, assuming that the window queue is time windows B through E, the arrival time window is B and the departure time window is E. Since the recursive model has a characteristic of recursively processing data based on time, it can be realized based on the recursive model when determining the arrival time window and the departure time window.

205. The time interval between the arrival time window and the departure time window is taken as the waiting time.

In the embodiment of the invention, after the arrival time window and the departure time window are determined, the time interval between the arrival time window and the departure time window can be used as the waiting time. In particular, a starting point in time of the arrival time window may be determined, an ending point in time of the departure time window may be determined, and the time interval between the starting point in time and the ending point in time may be taken as the waiting time.

In summary, the whole process is summarized as follows:

referring to fig. 2B, a plurality of terminal signals acquired by the terminal device are acquired, outlier filtering, denoising, and filtering are performed on the plurality of terminal signals, and environmental data and behavior data of the distribution facility in the distribution process are acquired based on the processed plurality of terminal signals. The method comprises the steps of modeling through environment data and behavior data to obtain a time sequence model, determining the credibility of the environment data and the credibility of the behavior data through the time sequence model, adjusting the credibility based on a recursive network, determining the arrival time and the departure time of the distribution facility, and further obtaining the waiting time of the distribution facility.

Further, as a specific implementation of the method shown in fig. 1, an embodiment of the present invention provides a latency obtaining apparatus, as shown in fig. 3A, the apparatus includes: an acquisition module 301, a calculation module 302 and a determination module 303.

The obtaining module 301 is configured to obtain a plurality of environmental data and a plurality of behavior data of a target distribution facility in a historical distribution process;

the calculating module 302 is configured to map the plurality of environmental data and the plurality of behavior data to a plurality of time windows of the historical distribution process, and calculate a plurality of credibility of the plurality of time windows, where the plurality of credibility indicates occurrence probabilities of the environmental data and the behavior data corresponding to the plurality of time windows;

the determining module 303 is configured to determine an arrival time window and a departure time window in the plurality of time windows according to the plurality of credibility;

the determining module 303 is further configured to use a time interval between the arrival time window and the departure time window as the waiting time.

In a specific application scenario, as shown in fig. 3B, the obtaining module 301 includes: an extraction unit 3011, a division unit 3012, and an analysis unit 3013.

The extracting unit 3011 is configured to extract a plurality of terminal signals uploaded by the terminal device of the target distribution facility in the historical distribution process, where the terminal signals at least include an inertia signal, a bluetooth signal, a wireless signal, a magnetic induction signal, and a cellular signal;

the dividing unit 3012 is configured to divide the plurality of terminal signals into a plurality of signal groups based on the uploading time of the plurality of terminal signals, where the uploading time of at least one terminal signal included in each of the plurality of signal groups is consistent;

the analyzing unit 3013 is configured to perform signal analysis on the plurality of signal groups respectively to obtain the plurality of environmental data and the plurality of behavior data.

In a specific application scenario, the parsing unit 3013 is configured to, for each signal group of the plurality of signal groups, read a plurality of target signals included in the signal group; determining the environment of the target distribution equipment at the uploading time corresponding to the signal group based on the plurality of target signals to obtain environment data, wherein the environment data is at least any one of indoor environment and outdoor environment; determining the use state of the terminal equipment at the uploading time corresponding to the signal group and the motion state of the target distribution facility at the uploading time corresponding to the signal group according to the target signals, and obtaining behavior data based on the use state and the motion state, wherein the behavior data is at least any one of waiting behavior and distribution behavior; and respectively reading each signal group in the plurality of signal groups, and outputting the environmental data and the behavior data of each signal group to obtain the plurality of environmental data and the plurality of behavior data.

In a specific application scenario, the parsing unit 3013 is configured to set the waiting behavior as the behavior data when the usage status indicates that the terminal device executes a user instruction and the motion status indicates that the target distribution facility is stationary or a motion speed of the motion status is less than a speed threshold; setting the delivery behavior as the behavior data when the usage state indicates that the terminal device is in standby and the motion state indicates that the delivery facility moves or a motion speed of the motion state is greater than or equal to the speed threshold.

In a specific application scenario, as shown in fig. 3C, the calculating module 302 includes: a dividing unit 3021, a determining unit 3022 and a mapping unit 3023.

The dividing unit 3021 is configured to perform time division on the historical distribution process based on a preset division duration to obtain a plurality of time windows, where a duration of each of the plurality of time windows is equal to the preset division duration;

the determining unit 3022 is configured to determine, for each environmental data or each behavior data in the plurality of environmental data and the plurality of behavior data, a target upload time corresponding to each environmental data or each behavior data;

the mapping unit 3023 is configured to query a target time window where the target upload time is located in the multiple time windows, map each environmental data or each behavior data to the target time window, and complete mapping between the multiple environmental data and the multiple behavior data and the multiple time windows.

In a specific application scenario, as shown in fig. 3D, the calculating module 302 includes: a training unit 3024, an acquisition unit 3025 and a setting unit 3026.

The training unit 3024 is configured to train a time sequence model on the plurality of environmental data and the plurality of behavior data by using the plurality of time windows, and generate a distribution process time sequence model, where the distribution process time sequence model includes an estimated state corresponding to each of the plurality of time windows;

the obtaining unit 3025 is configured to obtain, for each time window in the multiple time windows, a target estimated state corresponding to the time window in the distribution process time sequence model;

the setting unit 3026 is configured to, when the target environment data and the target behavior data corresponding to the time window are matched with the target estimation state, set the environment reliability of the target environment data and the behavior reliability of the target behavior data to first default values, and form the reliability of the time window based on the environment reliability and the behavior reliability;

the setting unit 3026 is further configured to, when any one of the target environment data or the target behavior data corresponding to the time window is not matched with the target estimated state, calculate a difference between a standard value and a second default value, use the difference as the reliability of the data that is not matched with the target estimated state, use the second default value as the reliability of the data that is matched with the target estimated state, and obtain the reliability of the time window;

the setting unit 3026 is further configured to, when the target environment data or the target behavior data corresponding to the time window are not matched with the target estimation state, set the environment reliability of the target environment data and the behavior reliability of the target behavior data to third default values, and form the reliability of the time window based on the environment reliability and the behavior reliability;

the setting unit 3026 is further configured to calculate the credibility of the plurality of time windows, respectively, to obtain the plurality of credibility.

In a specific application scenario, as shown in fig. 3E, the determining module 303 includes: a setting unit 3031, an obtaining unit 3032 and a determining unit 3033.

The setting unit 3031 is configured to set a window label for each of the plurality of time windows according to the plurality of credibility, where the window label is at least one of an arrival label or a departure label;

the obtaining unit 3032 is configured to obtain multiple consecutive candidate time windows with window tags as the arrival tags in the multiple time windows, and form a window queue using the multiple candidate time windows, where the window tags of the window queue in a previous time window and a next time window of the multiple time windows are both the departure tags;

the determining unit 3033 is configured to use the candidate time window arranged at the head of the window queue as the arrival time window, and use the candidate time window arranged at the tail of the window queue as the departure time window.

In a specific application scenario, the setting unit 3031 is configured to obtain, for each time window of the multiple time windows, a target reliability corresponding to the time window, and compare a target environment reliability and a target behavior reliability included in the target reliability; if the target environment credibility is consistent with the target behavior credibility, setting a window label matched with the environment data and the behavior data of the time window for the time window; if the target environment credibility is inconsistent with the target behavior credibility, extracting specified credibility from the target environment credibility and the target behavior credibility, and setting a window label matched with data corresponding to the specified credibility for the time window, wherein the specified credibility is greater than the other credibility except the specified credibility in the target environment credibility and the target behavior credibility.

In a specific application scenario, as shown in fig. 3F, the determining module 303 further includes: a first extraction unit 3034, a second extraction unit 3035 and an adjustment unit 3036.

The first extracting unit 3034 is configured to extract a confidence level to be adjusted from the multiple confidence levels, where the confidence level to be adjusted includes an environmental confidence level and a behavior confidence level that are both lower than a confidence level threshold;

the second extracting unit 3035 is configured to determine a time window to be adjusted corresponding to the confidence level to be adjusted, and extract a previous time window and a subsequent time window of the time window to be adjusted;

the determining unit 3033 is further configured to determine a standard time window in the previous time window and the subsequent time window, where the environment data and the behavior data included in the standard time window are inconsistent with the environment data and the behavior data included in the time window to be adjusted;

the adjusting unit 3036 is configured to assign the environmental data and the behavior data included in the standard time window and the reliability corresponding to the standard time window to the time window to be adjusted, obtain the adjusted time window to be adjusted, and set a window label based on the adjusted time window to be adjusted.

According to the device provided by the embodiment of the invention, the environmental data and the behavior data of the target distribution facility in the historical distribution process are acquired, the environmental data and the behavior data are mapped to the time window of the historical distribution process, the credibility of the time window is calculated, the arrival time window and the departure time window are determined in the time window according to the credibility, the time interval between the arrival time window and the departure time window is used as the waiting time, the waiting time of the distribution personnel is calculated by utilizing the multivariate data of the distribution personnel in the distribution process, the problem that the coverage range of the geographic fence is too large or too large based on a single signal is solved, the waiting time is ensured to be acquired by adopting an effective informatization means, the accuracy of the calculation of the waiting time is improved, the waiting time is convincing, and the intelligent process of catering services is promoted.

It should be noted that other corresponding descriptions of the functional units related to the latency obtaining apparatus provided in the embodiment of the present invention may refer to the corresponding descriptions in fig. 1 and fig. 2A to fig. 2B, and are not described herein again.

In an exemplary embodiment, referring to fig. 4, there is further provided a device, where the device 400 includes a communication bus, a processor, a memory, and a communication interface, and may further include an input/output interface and a display device, where the functional units may communicate with each other through the bus. The memory stores a computer program, and the processor is configured to execute the program stored in the memory and execute the latency acquisition method in the above embodiments.

A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the latency retrieval method.

Through the above description of the embodiments, those skilled in the art will clearly understand that the present application can be implemented by hardware, and also by software plus a necessary general hardware platform. Based on such understanding, the technical solution of the present application may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (which may be a CD-ROM, a usb disk, a removable hard disk, etc.), and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method according to the implementation scenarios of the present application.

Those skilled in the art will appreciate that the figures are merely schematic representations of one preferred implementation scenario and that the blocks or flow diagrams in the figures are not necessarily required to practice the present application.

Those skilled in the art will appreciate that the modules in the devices in the implementation scenario may be distributed in the devices in the implementation scenario according to the description of the implementation scenario, or may be located in one or more devices different from the present implementation scenario with corresponding changes. The modules of the implementation scenario may be combined into one module, or may be further split into a plurality of sub-modules.

The above application serial numbers are for description purposes only and do not represent the superiority or inferiority of the implementation scenarios.

The above disclosure is only a few specific implementation scenarios of the present application, but the present application is not limited thereto, and any variations that can be made by those skilled in the art are intended to fall within the scope of the present application.

Claims

1. A latency acquisition method, comprising:

2. The method of claim 1, wherein the obtaining a plurality of environmental data and a plurality of behavioral data of the target distribution facility during historical distribution comprises:

3. The method of claim 2, wherein the performing signal analysis on the plurality of signal groups to obtain the plurality of environmental data and the plurality of behavior data comprises:

4. The method of claim 3, wherein deriving behavioral data based on the usage state and the motion state comprises:

5. The method of claim 1, wherein mapping the plurality of environmental data and the plurality of behavioral data to a plurality of time windows of the historical delivery process comprises:

6. The method of claim 1, wherein said calculating a plurality of degrees of confidence for said plurality of time windows comprises:

7. The method of claim 1, wherein said determining an arrival time window and a departure time window among said plurality of time windows based on said plurality of degrees of confidence comprises:

8. A latency acquisition apparatus, comprising:

9. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 7 when executing the computer program.

10. A readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 7.