CN113506066A

CN113506066A - Method and device for determining position information of building and computer equipment

Info

Publication number: CN113506066A
Application number: CN202110838908.XA
Authority: CN
Inventors: 姚铖焘; 李杨; 赵京; 沈国斌
Original assignee: Rajax Network Technology Co Ltd
Current assignee: Rajax Network Technology Co Ltd
Priority date: 2021-07-23
Filing date: 2021-07-23
Publication date: 2021-10-15

Abstract

In the embodiment of the specification, when a delivery party executes a delivery order, activity state data of the delivery party in a delivery process is acquired, and an activity track in an area where the building belongs is determined through the activity state data. According to the scheme, the position information of the building can be automatically determined by utilizing the activity state data generated by the distribution party in the process of completing the distribution business, a digital map is not needed, the point marking of the distribution party is not needed, the distribution efficiency of the distribution party is not influenced, and geographic information acquisition personnel are not needed to specially arrive at the site for acquisition; the prediction model performs prediction by using the activity trajectory data, and can acquire building position information with high reliability.

Description

Method and device for determining position information of building and computer equipment

Technical Field

The embodiment of the specification relates to the technical field of internet, in particular to a method and a device for determining position information of a building and computer equipment.

Background

Maps are widely used in various industries at present, and for map services, accurate and fine geographical location information needs to be provided.

Disclosure of Invention

In order to overcome the problems in the related art, the specification provides a method, a device and computer equipment for determining the position information of a building.

According to a first aspect of embodiments of the present specification, there is provided a position information determination method for a building, including:

acquiring a target distribution order with a distribution address matched with building description information after acquiring the building description information of a building to be detected;

acquiring the activity track data of the distributor when executing the target distribution order; the activity track data is determined by utilizing activity state data which is acquired by electronic equipment and represents the position and the posture of the distribution party, and is used for representing the activity track of the distribution party from going to the building to be tested to leaving the building to be tested in the area to which the building to be tested belongs;

and calling a prediction model to obtain the predicted position information of the building to be tested, which is predicted by the prediction model by utilizing the moving track data.

According to a second aspect of embodiments of the present specification, there is provided a position information determination method for a building, including:

after building description information of a building to be tested is obtained, a plurality of target distribution orders of which distribution addresses are matched with the building description information are obtained;

aiming at each target distribution order, acquiring the activity track data when a distributor executes the target distribution order; the activity track data is determined by utilizing activity state data which is acquired by electronic equipment and represents the position and the posture of the distribution party, and is used for representing the activity track of the distribution party from going to the building to be tested to leaving the building to be tested in the area to which the building to be tested belongs;

and determining the position information of the building to be tested according to the superposition result of the activity track data of each target distribution order.

According to a third aspect of embodiments of the present specification, there is provided a position information determining apparatus for a building, including:

an order acquisition module to: acquiring a target distribution order with a distribution address matched with building description information after acquiring the building description information of a building to be detected;

a trajectory acquisition module to: acquiring the activity track data of the distributor when executing the target distribution order; the activity track data is determined by utilizing activity state data which is acquired by electronic equipment and represents the position and the posture of the distribution party, and is used for representing the activity track of the distribution party from going to the building to be tested to leaving the building to be tested in the area to which the building to be tested belongs;

a prediction module to: and calling a prediction model to obtain the predicted position information of the building to be tested, which is predicted by the prediction model by utilizing the moving track data.

According to a fourth aspect of the embodiments of the present specification, there is provided a position information determining apparatus for a building, including:

an order acquisition module to: after building description information of a building to be tested is obtained, a plurality of target distribution orders of which distribution addresses are matched with the building description information are obtained;

a trajectory acquisition module to: aiming at each target distribution order, acquiring the activity track data when a distributor executes the target distribution order; the activity track data is determined by utilizing activity state data which is acquired by electronic equipment and represents the position and the posture of the distribution party, and is used for representing the activity track of the distribution party from going to the building to be tested to leaving the building to be tested in the area to which the building to be tested belongs;

a determination module to: and determining the position information of the building to be tested according to the superposition result of the activity track data of each target distribution order.

According to a fifth aspect of embodiments of the present specification, there is provided a computer apparatus comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the method for determining location information of a building according to the first or second aspect when executing the program.

The technical scheme provided by the embodiment of the specification can have the following beneficial effects:

in the embodiment of the description, when a delivery party executes a delivery order, the activity state data of the delivery party in the delivery process is acquired, and the activity track in the area of the building is determined through the activity state data. According to the scheme, the position information of the building can be automatically determined by utilizing the activity state data generated by the distribution party in the process of completing the distribution business, a digital map is not needed, the point marking of the distribution party is not needed, additional operation is not needed to be introduced into the distribution process of the distribution party, the distribution efficiency of the distribution party is not affected, and geographic information acquisition personnel are not needed to specially arrive at the site for acquisition; the prediction model performs prediction by using the activity trajectory data, and can acquire building position information with high reliability.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the specification.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present specification and together with the description, serve to explain the principles of the specification.

Fig. 1A is a flowchart illustrating a method for determining location information of a building according to an exemplary embodiment of the present description.

FIG. 1B is a diagram illustrating distribution location data according to an exemplary embodiment.

Fig. 2 is a flow chart illustrating a method for determining location information of a building according to an exemplary embodiment of the present description.

Fig. 3 is a hardware configuration diagram of a computer device in which a location information determining apparatus of a building according to an exemplary embodiment is shown in the present specification.

Fig. 4 is a block diagram of a location information determining apparatus for a building shown in the present specification according to an exemplary embodiment.

Fig. 5 is a block diagram of another location information determining apparatus for a building shown in this specification according to an exemplary embodiment.

Detailed Description

Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present specification. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the specification, as detailed in the appended claims.

The terminology used in the description herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the description. As used in this specification and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.

It should be understood that although the terms first, second, third, etc. may be used herein to describe various information, these information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, the first information may also be referred to as second information, and similarly, the second information may also be referred to as first information, without departing from the scope of the present specification. The word "if" as used herein may be interpreted as "at … …" or "when … …" or "in response to a determination", depending on the context.

POI (Point of Interest), a term in the field of geographic information systems, generally refers to all geographic objects that can be abstracted as points, especially some geographic entities closely related to people's lives, such as schools, banks, restaurants, gas stations, hospitals, cells or supermarkets, etc. In the field of geographic information systems, each POI includes information including a name and geographic location information (i.e., geographic coordinates, specifically including longitude and latitude), and may further include other information such as a category to which the POI belongs.

POI is commonly used in maps, and map services are currently widely applied to various industries. For map services, the number of POIs represents the value of the whole system to a certain extent, and the finer the constructed POIs are, the better and more accurate the map services can provide. In the construction process of the POI, an image is generally obtained by means of aerial photography and the like, a graph of a geographic object is drawn through the image to construct a digital map, and then geographic position information and the like are added to each geographic object on the graph, so that the POI is constructed. The geographic information acquisition method requires geographic information acquisition personnel to arrive at a site treading point and acquire actual geographic position information by using equipment.

In some scenarios, the user has high requirements for refinement of POIs, for example, in a navigation scenario, assuming that POIs required by the user cannot be constructed, a map may not provide services such as accurate route planning for the user. For example, a user wants to navigate to a certain building in a certain cell, however, due to the limitation of the POI, a map manufacturer can locate the cell, multiple buildings are distributed in the cell, and the existing map does not record the specific geographic location information of each building, so that the user cannot be accurately navigated to each building in the cell, and thus a better navigation service cannot be provided for the user. Due to the influence of semi-closed environment factors in the interior of a district and other areas, the existing map manufacturers have the phenomena of more or less error marks and missing on building position information in the district.

As described above, in the existing method, a digital map needs to be constructed, a large amount of manpower and material resources need to be consumed to acquire geographical location information, and reliability of the geographical location information reported by geographical information acquisition personnel may not be guaranteed.

Based on this, the embodiments of the present disclosure provide a method for determining geographic location information with a completely new concept, where when a distribution party executes a distribution order, an activity state data of the distribution party in a distribution process is obtained, and an activity track in an area where a building belongs is determined through the activity state data, and since the activity track of the distribution party covers an actual location of the building during distribution, the geographic location information of the building can be automatically predicted by using a prediction model.

According to the scheme, the position information of the building can be automatically determined by utilizing the activity state data generated by the distribution party in the process of completing the distribution business, a digital map is not needed, the point is not needed to be made by the distribution party, additional operation is not needed to be introduced into the distribution process of the distribution party, the distribution efficiency of the distribution party is not affected, geographic information acquisition personnel are not needed to specially arrive at the site for acquisition, and the position information of the building with high reliability can be acquired.

As shown in fig. 1A, it is a flowchart of a method for determining geographical location information according to an exemplary embodiment, and includes the following steps:

in step 102, after building description information of a building to be tested is obtained, a target distribution order matched with the building description information in a distribution address is obtained;

in step 104, acquiring the activity track data of the delivery party when executing the target delivery order; the activity track data is determined by utilizing activity state data which is acquired by electronic equipment and represents the position and the posture of the distribution party, and is used for representing the activity track of the distribution party from going to the building to be tested to leaving the building to be tested in the area to which the building to be tested belongs;

in step 106, a prediction model is called to obtain the predicted position information of the building to be tested, which is predicted by the prediction model by using the activity track data.

The solution of this embodiment is applicable to a distribution scenario in which a business party providing a distribution service may distribute a distribution order of a user to a distribution party, and the distribution party distributes an item according to a distribution address.

The delivery party, i.e. the delivery capacity with delivery capability, in this embodiment means a party for delivering the articles, including but not limited to a dispenser, a robot, a drone or an unmanned vehicle, etc.

In this embodiment, the distribution party distributes the items according to the distribution address, which includes the distribution process of the distribution party in the area where the building is located; in a delivery scenario, such as take-out, a delivery party first arrives at a building (a residential area or a garden where the building belongs), then arrives at the building, and then goes upstairs to deliver an item to a user.

Taking a take-out scene as an example, at time A, a delivery party receives a delivery order; and at the time B, the distributor starts from the shop after arriving at the shop to pick up goods, and finally arrives at the distribution address of the distribution order at the time C to deliver the goods to the user. In practical applications, from time a to time B and from time B to time C, the distributor may go to other stores to pick up other items of distribution orders, and may also go to other distribution addresses to deliver the items to the users. In a word, after the order distribution is delivered at the time A and until the order delivery is finished at the time C, the delivery party is located in the area of the building for a period of time and arrives at the building to deliver the takeaway to the user.

Taking express delivery scenes as an example, in some scenes, after a delivery party takes out a plurality of goods to be delivered from a delivery site, the delivery party starts from the delivery site, arrives at delivery addresses of the goods one by one, and delivers the goods to users, so that for each order, the delivery party can be located in an area where a building is located for a period of time and arrives at the building to rapidly deliver the goods to the users.

In the leg-running scenario, the delivery party may arrive at user a to pick up the goods, and then depart from user a to deliver the goods to user B designated by user a. In this scenario, for each order, whether user a or user B, the delivery party is within the area of the building for a period of time and arrives at the building for delivery to the user.

In summary, during the process of executing the delivery order, the moving track of the delivery party covers the actual position of the building, so that the position information of the building can be determined from the moving track of the delivery party.

Based on the above concept, the scheme proposed by the embodiment can be used for acquiring the geographical location information of the building. The building of the embodiment can be a building in a district, a garden, a hospital or a school, and the like, the area to which the building belongs is the upper POI to which the building belongs, namely the district, the garden, the hospital or the school, and the like, and because the building in the area to which the building belongs has one or more than one building, the geographical position information of the building can be automatically and accurately determined by using the scheme of the embodiment.

For a building to be tested with unknown position information, a business side faces a challenge that the building to be tested is known to exist in an area where the building belongs, but the geographic coordinate of the building to be tested is unknown, and the specific position of the building to be tested is unknown. The moving tracks of the distribution side can cover the actual positions of the buildings, but the track points of the moving tracks represented by the moving track data are the actual positions of the buildings at all, which is the problem to be solved by the scheme of the embodiment.

Based on this, the present embodiment adopts a machine learning manner to determine the location information of the building. In the field of machine learning, a model is generally expressed through modeling, a function for evaluating the model is constructed, and finally the evaluation function is optimized according to sample data and an optimization method, so that the model is adjusted to a set accuracy standard.

This model is referred to as a prediction model in the present embodiment, and the task of the prediction model is to predict the position information of the building to be tested using the activity state data of the delivery side in the plurality of delivery orders. The prediction model is trained by using sample data in advance, wherein the sample data corresponds to a plurality of historical delivery orders for each building marked with position information, each historical delivery order corresponds to activity state data of a delivery party when the delivery party executes the historical delivery order, and activity track data determined based on the activity state data. The activity state data is data which is collected by electronic equipment and represents the position and the posture of the distribution party, and the activity track data is used for representing the activity track of the distribution party from going to the historical building to leaving the historical building in the region where the historical building belongs.

As an example, building data of a building for which accurate position information has been determined may be acquired in advance, and the building data may include position information (geographical position coordinates) of the building and building description information of the building; the building description information here may be text information describing a location of the building, for example, a certain building of a certain street and a certain cell of a certain city and a certain district. According to the building description information, historical delivery orders with delivery addresses matched with the building description information can be obtained.

In this embodiment, according to authorization approval of the user, order data may be obtained from a historical delivery order, and the order data may be desensitized to ensure privacy of the user. Usually, the order data includes a delivery address, the delivery address is filled by a user, and the delivery address generally includes specific building information; such as a building in a certain cell. For buildings needing to obtain the geographical position information, the historical delivery orders sent to the buildings can be determined through delivery addresses in the historical delivery orders. In this embodiment, the distribution address is matched with the building description information, which may mean that the distribution address includes the building description information, and the matching process may be implemented by text matching, text similarity calculation, and the like.

The activity status data of this embodiment can be acquired by using the collected data of the electronic device carried by the delivery party. The electronic device carried by the delivery party in this embodiment may include one or more of the following combinations: the portable equipment of handing such as smart mobile phone, or be wearable portable equipment such as intelligent bracelet or smart wrist-watch, can also include other electronic equipment such as configuration on takeaway case or removal instrument (for example storage battery car). The electronic device may be configured with a data collecting unit for collecting data, and the data collecting unit is configured to collect movement status data of the electronic device, where the movement status data represents an activity status of a distributor, and this embodiment is referred to as activity status data. In some examples, in order to analyze and obtain the movement track of the distribution party in the area of the building in each target distribution order, the positioning data may be obtained by using data collected by an electronic device carried by the distribution party, and further, the movement state data may further include attitude data in consideration of data drift caused by the positioning data in indoor environments, building shelters, and the like.

In some examples, a positioning unit is configured on the electronic device for collecting positioning information of the device; as an example, the Positioning unit herein may include a satellite-based Positioning unit, such as a gps (global Positioning system) Positioning unit or a beidou satellite Positioning unit, and may also be a GLONASS or galileo satellite Positioning unit, and the Positioning information may include longitude and latitude and altitude.

In other examples, the electronic device is provided with a communication unit, and the communication unit may acquire the positioning information including the latitude and longitude through communication with the base station.

In other examples, a Wi-Fi (wireless communication technology) unit may be further configured on the electronic device, and the positioning information including the longitude and latitude may be acquired based on a WiFi positioning manner.

In other examples, an Inertial Measurement Unit IMU is configured on the electronic device, and the IMU (Inertial Measurement Unit) is composed of three single-axis acceleration sensors and three single-axis angular velocity sensors (gyroscopes), and may measure IMU data including acceleration data and angular velocity data of the carrier in a three-dimensional space, based on which, the IMU may be installed in a portable device, such as a wearable portable device or a handheld portable device, and posture information, such as orientation or velocity, of the electronic device where the IMU is located may be resolved according to the IMU data measured by the IMU.

Therefore, the unit for acquiring data is configured in the electronic equipment carried by the delivery party, the data can be acquired at each sampling time, the position information and the posture information of each sampling time can be acquired based on the data acquired at each sampling time, so that the activity state data is formed, and the activity track data of the delivery party can be acquired by using the activity state data. In some examples, the process of acquiring the activity track data of the distribution party by using the activity state data may be executed by the client side, and the client acquires the activity track data according to the activity state data acquired by the electronic device and then sends the activity track data to the server side; in other examples, the client may send the activity status data to the server for execution by the server.

The electronic equipment can continuously acquire the activity state data of the distribution party according to the setting, when the distribution party executes the distribution service, other distribution orders can be executed in a cross mode in the distribution process of one distribution order, and based on the requirement of the building prediction task, the activity state data of the distribution party is used for determining the activity track data of the distribution party going to the building to be detected to leaving the building to be detected in the area where the building to be detected belongs to when the distribution party executes the target distribution order, so that the activity track data covering the actual position of the building to be detected can be obtained.

The activity track data can be determined in various ways.

As an example, the server may obtain the start time and the end time of each delivery order. The distribution order is distributed to the distribution party by the business party, the distribution party can confirm to receive the distributed distribution order through the client, and the distribution party can trigger the 'goods delivery' operation through the client after delivering goods so as to submit the information that the distribution order completes distribution to the server, so that the server can determine the starting time and the ending time of the distribution order. As can be seen from the above analysis, the delivering party moves in other areas before the delivering party is in the area of the building during the period from the starting time of the delivery order to the ending time of the delivery order. In this embodiment, in consideration of the time dimension, data may be obtained from the end time of the delivery order, for example, activity track data may be obtained from activity state data collected within a set time period before and after the end time of the delivery order, the set time period may be flexibly configured as required, for example, the set time period may be determined by analyzing the historical delivery behavior of the delivery party, and it is analyzed how long the delivery party usually needs to reach the building after entering the area where the building belongs and how long the delivery party usually needs to leave the building after the delivery is completed. Alternatively, the set time period may be determined in a finer granularity manner, such as by combining a plurality of distribution orders in the area of the building by a plurality of different distribution parties, most of which are common. How long it takes to reach the building and how long it usually takes to leave the building after the distribution is complete

In other examples, the location data includes location information for a plurality of sampling times, the location information includes specific geographic coordinates, and the area of the building has a time that can determine the time when the distribution party enters the area of the building and the time when the distribution party enters the area of the building through the geographic coordinates.

In other examples, the positioning information at the sampling moments can also determine the moving speed and speed change of the distribution party, and based on the moving speed and speed change, the time period for the distribution party to enter the area of the building or enter the building can be determined; for example, in some scenarios, the distribution party usually travels using a battery car, and usually slows down when entering the cell, or stops the vehicle and walks through the cell, then arrives at a building and walks to deliver goods to the user, and then leaves the cell in the same manner. Based on the movement speed, the movement track of the distribution party in the area of the building can be determined by analyzing the movement speed. For example, the activity speed information in a plurality of different states, for example, the preset activity speed information of the riding speed outside the cell, the preset activity speed information of the riding speed in the cell, the preset activity speed information of the walking speed in the cell, and the like, may be predetermined, and the activity speed of the distribution party in different states may be determined by comparing the collected data with the preset activity speed information in a plurality of different states, thereby determining the time period for the distribution party to enter the area where the building is located or enter the building.

In some examples, because the positioning unit is interfered by the environment, the positioning information cannot be acquired when the positioning unit is inside a building, so that data loss or data drift is caused; based on the above, the embodiment may further determine the posture of the device by using the acquired result of the IMU, and further determine the activity speed and the activity posture of the distributor. In other examples, the activity location and activity speed may also be determined in conjunction with the positioning data and the pose data.

In other examples, the status of the delivery party going upstairs or downstairs may be determined based on the position data and attitude data; for example, the distribution party may have different postures in riding, walking, going upstairs, going downstairs and the like, and the state of the distribution party going upstairs or downstairs in the building can be determined by combining the position data and the posture data of the distribution party. As an example, preset posture data in various different postures can be predetermined, the collected posture data is compared with the preset posture data, if the collected posture data is matched with one of the preset posture data, the posture of the distribution party represented by the collected posture data can be determined according to the posture corresponding to the preset posture data, and thus the posture data of the distribution party going upstairs or downstairs in the building can be determined.

In other examples, the data may also be interpolated as needed; for example, the positioning unit is interfered by environment influence, and cannot acquire positioning information in a building, so that data loss is caused, and the positioning data loss can be discovered from adjacent positioning information at two sampling moments; as an example, assuming that it is found from most of the acquired positioning data that the respective positioning information is generally sampled at a sampling frequency of 1 second, it can be determined that the sampling frequency of the positioning unit is 1 second; based on the analysis of the sampling time of each positioning information in the activity state data of the delivery order, if the sampling time difference between two adjacent positioning information of the sampling time is greater than 1 second and exceeds a set threshold (the set threshold may be configured as required), it may be determined that there is information missing between the two positioning information, and the filling of the positioning information between the two positioning information may be performed, for example, it is determined that 1 positioning information needs to be inserted between the two positioning information, and then the interpolation processing is performed according to the two positioning information.

In this embodiment, according to the above processing, the activity trajectory data of the delivery party when executing the historical delivery order may be comprehensively analyzed and acquired. In practical application, the activity track data can be obtained by processing in one or any one of the above manners, or can be obtained by processing in a plurality of manners. The activity track data represents the activity track from the historical building to the historical building of the distribution party in the region where the historical building belongs. As an example, the activity track data represents an activity track from the delivering party to the building to be tested to leave the building to be tested in the area where the building to be tested belongs, the data may be composed of a plurality of data points, for example, the data may be composed of a plurality of data points at different sampling times, information carried by the data points may include geographic position information, sampling times, postures and the like, and the activity track data points also carry posture information (for example, information representing postures such as orientation, walking posture, upstairs posture or downstairs posture) of the delivering party, activity speed, and state information (for example, information representing states such as riding, walking, upstairs or downstairs).

Based on the above, the data of the historical delivery orders can be processed in the above manner, and the activity trajectory data is obtained as sample data to train the prediction model. The prediction model can be flexibly selected according to needs, such as a logistic regression model, a random forest model, a Bayesian method model, a support vector machine model or a neural network model, and the like; in some examples, the activity trajectory data of this embodiment includes data acquired at different sampling times, so a prediction model based on LSTM (Long Short-Term Memory) may be adopted, and such a model is sensitive to time information and has a better performance for longer time series data; the generalization capability of the model is improved by adding a BN (Batch Normalization) layer and the like according to needs.

In this embodiment, there may be a plurality of historical delivery orders corresponding to each building, so that the prediction model can be trained well by using the multi-order data of the buildings.

In the process of being executed by the distribution party in each distribution order, the distribution party can move forward to the building after entering the entrance and exit of the area where the building is located, then reach the building to deliver goods to the door, then leave the building, and finally leave the building from the entrance and exit of the area where the building is located. If the area of the building is provided with only one entrance, the moving tracks of the distribution parties in the area of the building in each distribution order are basically the same in the process that the distribution parties enter and leave the area of the building in each distribution order, and particularly, the distribution parties leave the area of the building after converging to the building. As shown in fig. 1B, a schematic diagram of positioning data of a distribution party according to an exemplary embodiment is shown, where a cell is taken as an example, a distribution order indicates that there are multiple buildings in the cell, but a digital map for building the buildings is not located in the cell, the cell has multiple entrances and exits, and for a case where there are multiple entrances and exits in an area where the buildings are located, distribution parties may enter or leave from different entrances and exits from the buildings in different distribution orders, but movement tracks of the distribution parties in the distribution orders are collected to the buildings and then leave, and as shown in fig. 1B, positioning information entering the building to be tested from a north gate and positioning information entering the building to be tested from a west gate are shown, and movement tracks of the different distribution orders all coincide with an actual position of the buildings.

Based on this, in some examples, in the training data of the prediction model, a plurality of sample data are corresponding to each historical building with known position information, and the sample data enable the prediction model to learn the association between a plurality of pieces of activity track data and the position information of the historical building according to the superposition result of the plurality of pieces of activity track data in the sample data. In the training data of this embodiment, for a building with known location information, a plurality of historical delivery orders are associated, the plurality of historical delivery orders are respectively associated with activity state data of a delivery party when the delivery party executes the historical delivery orders, and activity track data of the delivery party in an area to which the building belongs is determined by using the activity state data. Through the mode, as the sample data comprises the data of the plurality of activity tracks surrounding the same building, during training, the prediction model can be indicated to obtain the coincidence result of the activity tracks of the distribution party in the area of the building in each target distribution order, and the state of the distribution party in the building to be tested can be determined from the coincidence result, for example, the distribution party can be in the same building in a time period in the plurality of historical distribution orders, the states of the distribution parties in different historical distribution orders in the time period are consistent, for example, the positioning information is consistent, the states of going upstairs and going downstairs are consistent, and the consistency is that the data shows that the data of the activity tracks of the different historical distribution orders can coincide, so that the highest range of the track coincidence program is the position of the building when the data consistency is highest, the highest overlapping degree is when the distribution side is at a building, and therefore the positioning information collected at this time is the position information of the building. Based on the design, the building with known position information corresponds to a plurality of historical delivery orders, so that the prediction model can be better trained according to a plurality of activity tracks around the same building, and the commonalities of the activity tracks can be learned.

After the prediction model is trained, the prediction model can be used for predicting the position information of the building with unknown position information. During prediction, the data processing process is consistent with the data processing in the training stage, and after the building description information of the building to be tested can be obtained, a target delivery order matched with the building description information in a delivery address is obtained; acquiring activity track data representing that the delivery party moves to the building to be tested to leave the building to be tested in the area to which the building to be tested belongs when the delivery party executes the target delivery order; the activity track data is determined by utilizing activity state data which is collected by electronic equipment and represents the position and the posture of the delivery party; and calling a prediction model to obtain the predicted position information of the building to be tested, which is predicted by the prediction model by utilizing the moving track data.

The output result of the prediction model of this embodiment may be the position information of the building to be measured and the confidence of the position information. As an example, the data input to the prediction model may be movement trajectory data of one target delivery order, and the prediction model outputs position information of the building to be tested predicted based on the movement trajectory data and a confidence of the position information.

In this embodiment, for a building to be tested, even if there is only one delivery order, the prediction model may output the position information and the confidence level obtained by using the delivery order prediction.

In other examples, if the building to be tested has a plurality of delivery orders, the position information of the building to be tested can be further accurately obtained by combining a plurality of target delivery orders. As an example, there are a plurality of target delivery orders matching the building description information; the prediction result of the prediction model comprises: position information of the building to be detected and confidence of the position information; the method further comprises the following steps: obtaining each prediction result output by the prediction model and corresponding to each target delivery order; determining the final position information of the building to be tested according to the weight of each predicted position information of the building to be tested; wherein the weight is determined based on a confidence of the respective location information.

In this embodiment, for a plurality of target delivery orders of the building to be tested, the prediction model outputs a predicted position information and a confidence level according to each target delivery order, and this embodiment may process the plurality of predicted position information and confidence levels to comprehensively analyze more accurate position information. In this embodiment, the position information of the building to be tested is determined based on the weight of the predicted position information of each building to be tested, so that fusion or clustering of the predicted position information is realized.

In other examples, the data volume collected in different target delivery orders may be different, some target delivery orders may collect more data, some target delivery orders may collect less data, and the reliability is higher when the data volume is large. For example, the weight of each piece of predicted location information may be determined by using a confidence level and a data amount, the confidence level is positively correlated with the data amount, and the greater the confidence level and the greater the data amount are, the greater the weight of the piece of predicted location information is, so that the final location information of the building to be measured can be determined by using the weight of each piece of predicted location information.

Fig. 2 shows another method for determining location information of a building according to an exemplary embodiment, which includes the following steps, as shown in fig. 2:

in step 202, after building description information of a building to be tested is obtained, a plurality of target delivery orders of which delivery addresses are matched with the building description information are obtained;

in step 204, for each target delivery order, acquiring activity track data when a delivery party executes the target delivery order; the activity track data is determined by utilizing activity state data which is acquired by electronic equipment and represents the position and the posture of the distribution party, and is used for representing the activity track of the distribution party from going to the building to be tested to leaving the building to be tested in the area to which the building to be tested belongs;

in step 206, the position information of the building to be tested is determined according to the superposition result of the activity track data of each target delivery order.

Similar to the embodiment described in fig. 1A and 1B, in this embodiment, the position information of the building may not be predicted in a model manner, but may be determined by the movement trajectory data of a plurality of target delivery orders. In this embodiment, the distribution addresses of the multiple target distribution orders are located in the building to be tested, so that the distribution parties are located in the building to be tested within a time period, and the statuses of the distribution parties in the different distribution orders within the time period are consistent, for example, the positioning information is consistent, the statuses of going upstairs and going downstairs are consistent, and the consistency is that the activity track data of the different distribution orders overlap when the data shows that the data consistency is the highest, so that the highest range of the track overlapping program is the location of the building, and the highest degree of overlap is the location of the distribution parties when the data shows the highest, so that the positioning information collected at this time is the location information of the building. Based on the data, the activity track data is composed of a plurality of data points, the activity track data containing the data points is subjected to coincidence analysis, and the position information of the building to be detected can be determined by utilizing the coincidence result.

In some examples, the range with the highest track coincidence degree in the data of each movable track represents the position of the building to be tested.

In some examples, the activity state data includes: and the position data and the attitude data are determined by utilizing the data collected by the positioning unit, the communication unit and the IMU unit in the electronic equipment.

In some examples, the activity trace data is determined by:

determining the moving position and moving speed of a delivery party according to at least any one of the position data and the posture data;

determining the change of the distribution party in the riding state and the walking state according to the activity position and the activity speed;

determining the time when the delivery party enters the area to which the building belongs according to the position information of the area to which the building belongs and the position data; and

and determining the state of the delivery party going upstairs or downstairs according to the position data and the posture data.

For the above embodiments, reference may be made to the description of the embodiment shown in fig. 1A, which is not repeated herein.

In correspondence with the aforementioned embodiments of the location information determining method for a building, the present specification also provides embodiments of a location information determining apparatus for a building and a computer device to which the apparatus is applied.

The embodiment of the position information determining apparatus of the building in the present specification can be applied to a computer device, such as a server or a terminal device. The device embodiments may be implemented by software, or by hardware, or by a combination of hardware and software. The software implementation is taken as an example, and as a logical device, the device is formed by reading corresponding computer program instructions in the nonvolatile memory into the memory for operation through the processor in which the file processing is located. From a hardware aspect, as shown in fig. 3, a hardware structure diagram of a computer device in which the location information determining apparatus of a building is located in this specification is shown, except for the processor 310, the memory 330, the network interface 320, and the nonvolatile memory 340 shown in fig. 3, in an embodiment, the computer device in which the location information determining apparatus 331 of the building is located may also include other hardware according to an actual function of the computer device, which is not described again.

As shown in fig. 4, fig. 4 is a block diagram of an apparatus shown in this specification according to an exemplary embodiment, the apparatus comprising:

an order acquisition module 41 configured to: acquiring a target distribution order with a distribution address matched with building description information after acquiring the building description information of a building to be detected;

a trajectory acquisition module 42 for: acquiring the activity track data of the distributor when executing the target distribution order; the activity track data is determined by utilizing activity state data which is acquired by electronic equipment and represents the position and the posture of the distribution party, and is used for representing the activity track of the distribution party from going to the building to be tested to leaving the building to be tested in the area to which the building to be tested belongs;

a prediction module 43 configured to: and calling a prediction model to obtain the predicted position information of the building to be tested, which is predicted by the prediction model by utilizing the moving track data.

In some examples, there are multiple target delivery orders matching the building description information; the prediction result of the prediction model comprises: predicting position information of a building to be tested and confidence of the predicting position information; the method further comprises the following steps:

obtaining each prediction result output by the prediction model and corresponding to each target delivery order;

determining the position information of the building to be tested according to the weight of each predicted position information of the building to be tested; wherein the weight is determined based on a confidence of the predicted location information.

In some examples, the weight of each piece of predicted location information is further determined based on the number of data points in the activity trace data corresponding to the piece of predicted location information, and the weight is positively correlated to the number of data points.

In some examples, in the training data of the prediction model, a plurality of sample data correspond to each historical building with known position information, and the sample data enable the prediction model to learn the association between a plurality of pieces of activity track data and the position information of the historical building according to the superposition result of the plurality of pieces of activity track data in the sample data.

In some examples, the activity trace data is determined by:

As shown in fig. 5, fig. 5 is a block diagram of an apparatus shown in this specification according to an exemplary embodiment, the apparatus comprising:

an order acquisition module 51 for: after building description information of a building to be tested is obtained, a plurality of target distribution orders of which distribution addresses are matched with the building description information are obtained;

a trajectory acquisition module 52 configured to: aiming at each target distribution order, acquiring the activity track data when a distributor executes the target distribution order; the activity track data is determined by utilizing activity state data which is acquired by electronic equipment and represents the position and the posture of the distribution party, and is used for representing the activity track of the distribution party from going to the building to be tested to leaving the building to be tested in the area to which the building to be tested belongs;

a prediction module 53 for: and determining the position information of the building to be tested according to the superposition result of the activity track data of each target distribution order.

And representing the position of the building to be tested in the range with the highest track coincidence degree in the data of each movable track.

In some examples, the activity trace data is determined by:

Embodiments of the present specification further provide a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor executes the program to implement the method for determining location information of a building according to the foregoing embodiments.

The implementation process of the functions and actions of each module in the device for determining location information of a building is detailed in the implementation process of the corresponding steps in the method for determining location information of a building, and is not described herein again.

For the device embodiments, since they substantially correspond to the method embodiments, reference may be made to the partial description of the method embodiments for relevant points. The above-described embodiments of the apparatus are merely illustrative, wherein the modules described as separate parts may or may not be physically separate, and the parts displayed as modules may or may not be physical modules, may be located in one place, or may be distributed on a plurality of network modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution in the specification. One of ordinary skill in the art can understand and implement it without inventive effort.

The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.

Other embodiments of the present description will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This specification is intended to cover any variations, uses, or adaptations of the specification following, in general, the principles of the specification and including such departures from the present disclosure as come within known or customary practice within the art to which the specification pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the specification being indicated by the following claims.

It will be understood that the present description is not limited to the precise arrangements described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present description is limited only by the appended claims.

The above description is only a preferred embodiment of the present disclosure, and should not be taken as limiting the present disclosure, and any modifications, equivalents, improvements, etc. made within the spirit and principle of the present disclosure should be included in the scope of the present disclosure.

Claims

1. A method for determining location information of a building, comprising:

acquiring the activity track data of a distributor when executing the target distribution order; the activity track data is determined by utilizing activity state data which is acquired by electronic equipment and represents the position and the posture of the distribution party, and is used for representing the activity track of the distribution party from going to the building to be tested to leaving the building to be tested in the area to which the building to be tested belongs;

2. The method of claim 1, wherein a plurality of target delivery orders are matched with the building description information; the prediction result of the prediction model comprises: predicting position information of a building to be tested and confidence of the predicting position information; the method further comprises the following steps:

3. The method of claim 2, wherein the weight of each predicted location information is further determined based on the number of data points in the activity trace data corresponding to the predicted location information, and the weight is positively correlated to the number of data points.

4. The method of claim 1, wherein a plurality of sample data correspond to each historical building with known position information in the training data of the prediction model, and the sample data enable the prediction model to learn the association between a plurality of pieces of activity track data and the position information of the historical building according to the superposition result of the plurality of pieces of activity track data in the sample data.

5. The method of claim 1, the activity state data comprising: and the position data and the attitude data are determined by utilizing the data collected by the positioning unit, the communication unit and the IMU unit in the electronic equipment.

6. The method of claim 5, the activity trace data determined by:

7. A method for determining location information of a building, comprising:

8. The method according to claim 7, wherein the range with the highest track coincidence degree in the data of the movable tracks represents the position of the building to be tested.

9. The method of claim 7, the activity state data comprising: and the position data and the attitude data are determined by utilizing the data collected by the positioning unit, the communication unit and the IMU unit in the electronic equipment.

10. The method of claim 7, wherein the activity trace data is determined by:

11. A position information determining apparatus for a building, comprising:

12. A position information determining apparatus for a building, comprising:

13. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of any of claims 1 to 10 when executing the program.