CN112788523B

CN112788523B - Positioning method of sharing equipment and server

Info

Publication number: CN112788523B
Application number: CN202011595907.9A
Authority: CN
Inventors: 杨磊; 罗耀燊
Original assignee: Shanghai Junzheng Network Technology Co Ltd
Current assignee: Shanghai Junzheng Network Technology Co Ltd
Priority date: 2020-12-29
Filing date: 2020-12-29
Publication date: 2022-11-22
Anticipated expiration: 2040-12-29
Also published as: CN112788523A

Abstract

The specification provides a positioning method of a sharing device and a server. Based on the method, the environmental feature vectors of the full sharing equipment can be obtained firstly, then the preset first clustering processing is carried out on the full sharing equipment according to the environmental feature vectors, the sharing equipment with higher similarity among the environmental features is clustered, and a plurality of first clusters are obtained; then, according to the obtained ratio of the sharing equipment carrying the preset idle aggregation label in the first cluster through statistics, finding out a target cluster with an idle aggregation condition, which is determined based on GPS positioning data sent by the sharing equipment; and then, the position information of the sharing devices in the target cluster can be corrected in a unified way by utilizing the GPS positioning data sent by the sharing devices in the target cluster, so that the group data of the sharing devices in the cluster can be effectively utilized to correct the position information of the sharing devices in the cluster, which are abnormal in GPS positioning due to gathering and stacking of the sharing devices.

Description

Positioning method of sharing equipment and server

Technical Field

The present disclosure relates to the field of internet technologies, and in particular, to a method and a server for positioning a shared device.

Background

A situation in which shared devices are stacked together often occurs in a drop zone of a shared device (e.g., a shared bicycle, etc.). When a plurality of sharing devices are gathered and stacked together, interference is caused to the GPS signals of the sharing devices, which affects the GPS positioning of the sharing devices, and abnormal GPS positioning occurs, such as the GPS signals of the sharing devices are blocked or the GPS positioning drifts, which affects the determination of the maintenance party of the sharing devices on the positions of the sharing devices. Even if the maintainer of the shared device cannot normally acquire the GPS positioning data of part of the shared device, the shared device is lost.

Therefore, a method for accurately positioning the position information of the sharing device with abnormal GPS positioning, such as blocked GPS signal or GPS positioning drift, caused by the stacking of the sharing devices in a cluster is needed.

Disclosure of Invention

The specification provides a positioning method of a sharing device and a server, so that group data of the sharing device in a cluster is effectively utilized to correct position information of the sharing device with abnormal GPS positioning, such as GPS signal blocking or GPS positioning drifting, caused by gathering and stacking of the sharing device in the cluster.

The present specification provides a method for positioning a shared device, including:

obtaining an environment feature vector of each sharing device in a plurality of sharing devices;

performing preset first clustering processing on the plurality of sharing devices according to the environment feature vector to obtain a plurality of first clusters; the similarity between the environmental features represented by the environmental feature vectors of different sharing devices in the same first cluster is greater than a preset similarity threshold;

counting the occupation ratio of the target equipment in each first cluster; the target equipment is shared equipment carrying a preset idle aggregation label; the preset idle aggregation label is determined in advance according to GPS positioning data of the shared equipment;

determining a first cluster with the occupation ratio of the target equipment larger than a preset first occupation ratio threshold value as a target cluster;

and correcting the position information of the sharing equipment in the target cluster according to the acquired GPS positioning data sent by the sharing equipment in the target cluster.

In one embodiment, the obtaining the environment feature vector of each of the plurality of sharing devices includes:

receiving environment parameters sent by each sharing device in the plurality of sharing devices; wherein the environment parameter at least comprises base station sequence information;

and determining corresponding vector elements according to the environment parameters to establish and obtain an environment characteristic vector corresponding to the sharing equipment.

In one embodiment, the environmental parameters further include at least one of: wi-Fi fingerprint information, bluetooth scanning information and GPS positioning data.

In one embodiment, performing a preset first clustering process on the plurality of sharing devices according to the environment feature vector to obtain a plurality of first clusters includes:

counting the similarity between the same vector elements in different environment feature vectors;

determining the similarity between different environment feature vectors according to the similarity between the same vector elements in the different environment feature vectors;

according to the similarity between different environment feature vectors, carrying out clustering operation on the environment feature vectors of the sharing equipment to obtain a set of multi-cluster environment feature vectors;

and determining a plurality of first clusters according to the set of the multi-cluster environment feature vectors.

In one embodiment, in the case that the vector elements include base station sequence information, counting similarities between the same vector elements in different environment feature vectors includes:

determining the base station numbers appearing in the base station sequence information in different environment characteristic vectors;

counting the number of the same base station number in the base station sequence information in different environment characteristic vectors;

and determining the similarity between the base station sequence information in different environment characteristic vectors according to the number of the same base station number in the base station sequence information.

In one embodiment, in the case that the vector elements include GPS positioning data, counting similarities between the same vector elements in different environmental feature vectors includes:

respectively carrying out geocoding on the GPS positioning data in different environment characteristic vectors to obtain corresponding geocode characters;

and determining the similarity between the GPS positioning data in different environment characteristic vectors by calculating the similarity between different geocode characters.

In one embodiment, in the case that the vector elements include Wi-Fi fingerprint information, counting similarities between the same vector elements in different environmental feature vectors includes:

determining mac addresses appearing in Wi-Fi fingerprint information in different environment feature vectors;

counting the number of addresses of the same mac address in Wi-Fi fingerprint information in different environment feature vectors;

and determining the similarity between the Wi-Fi fingerprint information in different environment characteristic vectors according to the number of the addresses with the same mac address in the Wi-Fi fingerprint information.

In one embodiment, before counting the proportion of target devices in each first cluster, the method further comprises:

acquiring GPS positioning data sent by shared equipment;

according to the GPS positioning data, performing preset second clustering processing on the sharing equipment which sends the GPS positioning data to obtain a plurality of second clusters; the second cluster comprises sharing equipment for sending GPS positioning data, and the difference value of the GPS positioning data of different sharing equipment in the same second cluster is smaller than a preset difference threshold value;

and determining idle aggregation clusters from the plurality of second clusters, and setting preset idle aggregation labels for shared equipment in the idle aggregation clusters.

In one embodiment, determining an idle aggregated cluster from the plurality of second clusters comprises:

acquiring historical order information of shared equipment in a second cluster;

determining idle shared equipment in the second cluster according to the historical order information of the shared equipment in the second cluster;

calculating the occupation ratio of idle shared equipment in each second cluster;

and determining a second cluster with the occupation ratio of the idle sharing equipment larger than a preset second occupation ratio threshold value from the plurality of second clusters as an idle aggregation cluster.

In one embodiment, determining idle shared devices in the second cluster according to the historical order information of the shared devices in the second cluster includes:

according to historical order information of the sharing equipment, determining order time closest to the current time as last using time of the sharing equipment;

calculating the time difference between the last use time and the current time of the shared equipment as the idle time of the shared equipment;

comparing the idle time of the shared equipment with a preset idle time threshold value;

and under the condition that the idle time of the shared equipment is determined to be larger than the preset idle time threshold value, determining that the shared equipment is idle shared equipment.

In one embodiment, the correcting the location information of the shared device in the target cluster according to the acquired GPS positioning data sent by the shared device in the target cluster includes:

according to the obtained GPS positioning data of the sharing equipment in the target cluster, obtaining an average value of the position information through weighting and averaging; the number of the shared devices which send the GPS positioning data in the target cluster is less than or equal to the number of the shared devices in the target cluster;

and correcting the position information of the sharing equipment in the target cluster according to the average value of the position information.

In one embodiment, the sharing device comprises at least one of: shared bicycles, shared gas vehicles and shared electric vehicles.

In one embodiment, after correcting the location information of the shared device in the target cluster, the method further comprises:

and according to the corrected position information, recalling the shared equipment which is in an idle state for a long time and is abnormally positioned by the GPS in the target cluster.

The present specification also provides a server comprising a processor and a memory for storing processor-executable instructions, the processor implementing obtaining an environmental feature vector for each of a plurality of shared devices when executing the instructions; performing preset first clustering processing on the plurality of sharing devices according to the environment feature vector to obtain a plurality of first clusters; the similarity between the environment features represented by the environment feature vectors of different sharing devices in the same first cluster is greater than a preset similarity threshold; counting the occupation ratio of the target equipment in each first cluster; the target equipment is shared equipment carrying a preset idle aggregation label; the preset idle aggregation label is determined in advance according to GPS positioning data of the shared equipment; determining a first cluster with the occupation ratio of the target equipment larger than a preset first occupation ratio threshold value as a target cluster; and correcting the position information of the sharing equipment in the target cluster according to the acquired GPS positioning data sent by the sharing equipment in the target cluster.

The present specification also provides a computer readable storage medium having stored thereon computer instructions that, when executed, enable obtaining an environmental feature vector for each of a plurality of shared devices; performing preset first clustering processing on the plurality of sharing devices according to the environment feature vector to obtain a plurality of first clusters; the similarity between the environment features represented by the environment feature vectors of different sharing devices in the same first cluster is greater than a preset similarity threshold; counting the occupation ratio of the target equipment in each first cluster; the target equipment is shared equipment carrying a preset idle aggregation label; the preset idle aggregation label is obtained in advance according to GPS positioning data of the shared equipment; determining a first cluster with the occupation ratio of the target equipment larger than a preset first occupation ratio threshold value as a target cluster; and correcting the position information of the sharing equipment in the target cluster according to the acquired GPS positioning data sent by the sharing equipment in the target cluster.

The method for positioning shared devices and the server provided in this specification may first obtain an environmental feature vector of each shared device in nearly full-scale shared devices, and then perform a preset first clustering process on the full-scale shared devices according to the environmental feature vector of the nearly full-scale shared devices, cluster out shared devices with higher similarity between environmental features represented by the environmental feature vector, and obtain a plurality of first clusters; then according to the counted occupation ratio of the sharing equipment carrying the preset idle aggregation label in each first cluster, further finding out a target cluster with the idle aggregation condition, which is determined based on the GPS positioning data sent by the sharing equipment, from the plurality of first clusters; and then the acquired GPS positioning data sent by the sharing equipment in the target cluster can be utilized to uniformly correct the position information of the sharing equipment in the target cluster, so that the group data of the sharing equipment in the cluster can be utilized to effectively correct the position information of the sharing equipment with abnormal GPS positioning, such as GPS signal shielding or GPS positioning drifting and the like, which are caused by the gathering and stacking of the sharing equipment in the cluster, and further more efficiently and accurately determine the position information of nearly the whole amount of sharing equipment, so that a sharing equipment maintainer can accurately find the sharing equipment with abnormal GPS positioning in a gathering area and in an idle state for a long time, and timely perform corresponding recall processing.

Drawings

In order to more clearly illustrate the embodiments of the present specification, the drawings required for the embodiments will be briefly described below, the drawings in the following description are only some of the embodiments described in the present specification, and other drawings may be obtained by those skilled in the art without inventive labor.

Fig. 1 is a schematic diagram of an embodiment of a structural component of a system to which a method for positioning a shared device provided in an embodiment of the present specification is applied;

fig. 2 is a flowchart illustrating a method for locating a shared device according to an embodiment of the present disclosure;

fig. 3 is a schematic diagram of an embodiment of a positioning method of a shared device provided by an embodiment of the present specification, in a scenario example;

FIG. 4 is a schematic structural component diagram of a server provided in an embodiment of the present description;

fig. 5 is a schematic structural component diagram of a positioning apparatus of a sharing device according to an embodiment of the present disclosure.

Detailed Description

In order to make those skilled in the art better understand the technical solutions in the present specification, the technical solutions in the embodiments of the present specification will be clearly and completely described below with reference to the drawings in the embodiments of the present specification, and it is obvious that the described embodiments are only a part of the embodiments of the present specification, and not all of the embodiments. All other embodiments obtained by a person skilled in the art based on the embodiments in the present specification without any inventive step should fall within the scope of protection of the present specification.

Considering that after the shared devices are put into operation, the situation that a large number of shared devices are piled up in one or several local areas is often caused for various reasons. When a large number of sharing devices are gathered and stacked together, the GPS signals of different neighboring sharing devices are mutually superimposed, and then interference is caused to normal GPS positioning of the sharing devices, and phenomena such as GPS signals of the sharing devices being blocked, or GPS positioning drifting, or even abnormal GPS positioning such as being unable to normally send GPS positioning data to a server of a management platform, are likely to occur. Therefore, a maintainer (or a manager) of the shared device is difficult to accurately determine the specific position of each shared device based on the GPS positioning data sent by the shared device, and is also difficult to accurately find the shared device with abnormal GPS positioning and long-term idle state from the aggregation area for recall, which affects the maintainer's maintenance and management of the shared device.

For the root cause of the above problem, the present specification considers that a cluster (which may be denoted as a second cluster) is obtained by performing a clustering process based on GPS positioning data on a sharing device that transmits the GPS positioning data according to the acquired GPS positioning data that is transmitted by the sharing device; and further, an idle aggregation cluster with idle aggregation conditions can be determined from the second cluster according to the order information of the shared devices, and corresponding preset idle aggregation labels are respectively set for marking the shared devices in the idle aggregation cluster.

Meanwhile, the environment feature-based clustering processing may be performed on the full-scale shared devices according to the obtained environment feature vectors of the shared devices in the full-scale shared devices, so as to obtain another cluster (which may be denoted as a first cluster).

It should be noted that the shared device included in the first cluster found in the foregoing manner is more complete than the shared device included in the second cluster found by using the GPS positioning data sent by the shared device alone. For example, the first cluster may include a sharing device that cannot normally transmit GPS positioning data (e.g., a sharing device that is lost).

And then, the two clusters can be combined, and according to the counted occupation ratio of the sharing equipment carrying the preset idle aggregation tag in the first cluster, a target cluster which is determined based on the GPS positioning data sent by the sharing equipment and has the idle aggregation condition is further found out from the plurality of first clusters.

And finally, the acquired GPS positioning data sent by the shared devices in the target cluster can be comprehensively utilized to uniformly correct the position information of the shared devices in the target cluster.

Therefore, group data of the sharing equipment in the cluster can be utilized to effectively correct the position information of the sharing equipment with abnormal GPS positioning, such as blocked GPS signals or GPS positioning drift, caused by gathering and stacking of the sharing equipment in the cluster, and the position information of almost the whole amount of sharing equipment can be determined more efficiently and accurately, so that the sharing equipment maintenance party can accurately find the sharing equipment with abnormal GPS positioning in the gathering area and in an idle state, and can timely perform corresponding recall processing.

The embodiment of the present specification provides a method for positioning a shared device, which may be specifically applied to a system including a server and a plurality of shared devices. In particular, reference may be made to fig. 1. The server and the sharing device in the system can perform specific data interaction through wireless communication and the like.

In this embodiment, the server may specifically include a background server that is applied to the management platform side of the shared device and is capable of implementing functions such as data transmission and data processing. Specifically, the server may be, for example, an electronic device having data operation, storage function and network interaction function. Alternatively, the server may be a software program running in the electronic device and providing support for data processing, storage and network interaction. In the present embodiment, the number of servers is not particularly limited. The server may specifically be one server, or may also be several servers, or a server cluster formed by several servers.

In this embodiment, the sharing device may specifically include a device sharing a bicycle, a sharing automobile, or a sharing electric vehicle. Of course, the above listed sharing devices are only illustrative. In a specific implementation, the sharing device may further include other types of sharing devices besides the listed sharing devices according to a specific application scenario and a processing requirement.

In this embodiment, the sharing device may further include a GPS positioning module, wherein the GPS positioning module may specifically include a GPS positioning chip. With the GPS positioning module described above, the sharing device can interact with a GPS satellite positioning system to obtain GPS positioning data about the sharing device (including longitude information and latitude information of the location of the sharing device). Based on the preset communication rule, when the user carries out unlocking operation or returning operation on the sharing device, the positioning module of the sharing device can be triggered to acquire the GPS positioning data of the current time point, and the GPS positioning data is sent to the server. When the user normally uses the sharing device after unlocking, or after the user finishes using the sharing device to return, based on the preset communication rule, the positioning module can acquire the GPS positioning data at the preset first time interval at every interval, and send the GPS positioning data to the server. Thus, under the condition that the GPS positioning is normal, the server can determine the position information of the sharing equipment which sends the GPS positioning data according to the received GPS positioning data.

In this embodiment, the sharing device may further be provided with an environmental parameter acquisition module. Based on a preset communication rule, the environmental parameter acquisition module can acquire and acquire surrounding environmental parameters at a preset second time interval and send the environmental parameters to the server. Thus, the server can determine the environment characteristic vectors corresponding to the sharing devices according to the acquired environment parameters acquired by the sharing devices; and then can be distinguished from GPS positioning data, through utilizing the environmental feature that environmental feature vector represents to carry out the analysis to the peripheral environmental feature of the position of sharing device, through seeking approximate environmental feature, fix a position this sharing device.

Wherein the environment parameter may include at least base station sequence information. Accordingly, the environment parameter acquiring Module may be embedded with an Identity card in a mobile communication system, such as a SIM (Subscriber Identity Module) card. The environment parameter module can be further used for searching and collecting information related to the base station, such as the base station number, the sector information of the base station, or the signal strength of the base station, in the surrounding environment to obtain corresponding base station sequence information, and the corresponding base station sequence information is sent to the server as an environment parameter.

The environmental parameters may also include Wi-Fi fingerprint information. Correspondingly, the environmental parameter acquisition module can be internally provided with a Wi-Fi scanner. And then, the environmental parameter acquisition module can be used for scanning and acquiring information related to the Wi-Fi equipment, such as the mac address of the Wi-Fi equipment, the SSID of the Wi-Fi equipment or the signal strength of the Wi-Fi equipment, in the surrounding environment to obtain Wi-Fi fingerprint information, and the Wi-Fi fingerprint information is sent to the server as an environmental parameter.

The environmental parameters may also include bluetooth scan information. Correspondingly, the environment parameter acquisition module can be internally provided with Bluetooth chips such as a low-power Bluetooth chip. And then can utilize environmental parameter collection module to external broadcast bluetooth signal, scan simultaneously and acquire the bluetooth signal of other sharing device broadcastings (also can include other unshared devices that are provided with the bluetooth chip) in the surrounding environment to obtain bluetooth scanning information (including intensity of bluetooth signal and/or the mac address of the equipment that sends this bluetooth signal etc.), send to the server as an environmental parameter.

In this embodiment, in specific implementation, on one hand, the server may first obtain GPS positioning data sent by the sharing device. Note that, because there is a GPS positioning abnormality such as a GPS signal being blocked due to the shared device being stacked together, the GPS positioning data sent by the shared device acquired by the server may not be complete. For example, as shown in fig. 3, the server can generally only obtain GPS positioning data sent by a part of the total number of sharing devices. In addition, the GPS positioning data of the shared device acquired by the server may also have an error due to GPS positioning abnormality such as GPS positioning drift caused by stacking of the shared devices together.

The server may perform a preset second clustering process on the density of the part of the sharing devices sending the GPS positioning data according to the GPS positioning data to obtain a plurality of second clusters. Each second cluster can include a plurality of sharing devices for sending the GPS positioning data, and the difference value between the GPS positioning data of different sharing devices in the same second cluster is smaller than the preset difference threshold. Thus, the server can firstly use the GPS positioning data alone to find out a plurality of second clusters formed by gathering partial sharing devices (non-full sharing devices) capable of sending the GPS positioning data through the GPS positioning.

Further, the server may screen out an idle aggregation cluster from the plurality of second clusters. The idle aggregation cluster may be specifically understood as a second cluster with more idle shared devices. In general, there are a large number of abnormal shared devices in an idle aggregation cluster with a high probability, and due to abnormal GPS positioning caused by aggregation and stacking of the shared devices, the abnormal shared devices cannot be recalled or maintained. The server may set corresponding preset idle aggregation tags for the shared devices in the idle aggregation cluster.

On the other hand, because the receiving and sending mode of the environmental parameters is different from the GPS positioning data, the influence of the gathering and stacking is small, and the server can acquire the environmental parameters sent by each sharing device in a plurality of sharing devices (almost all sharing devices); and according to the environment parameters sent by the sharing equipment, environment characteristic vectors respectively corresponding to the sharing equipment are constructed. The environment feature vector may be used to characterize the environment features around the location of the corresponding sharing device.

It should be noted that, compared to the sharing device capable of normally transmitting GPS positioning data, the number of sharing devices capable of normally transmitting environment parameters is often greater, and even almost the entire number of sharing devices can normally transmit environment parameters.

The server may perform preset first clustering processing based on the environmental features on the plurality of sharing devices according to the environmental feature vector of each sharing device, to obtain a plurality of first clusters. Each first cluster may include a plurality of sharing devices, and the similarity between the environmental features represented by the environmental feature vectors of different sharing devices in the same first cluster is greater than a preset similarity threshold.

Thus, the server can find out a plurality of first clusters formed by gathering of sharing devices capable of sending environment parameters by approximate matching of environment features by using the environment feature vector, in contrast to using the GPS positioning data. The number of the shared devices included in the first cluster is usually greater than the number of the shared devices included in the second cluster. For example, the first cluster found in the above manner may include a shared device that cannot normally transmit GPS positioning data.

Further, the server may detect target devices in each first cluster that carry a preset idle aggregation tag, and count the percentage of the target devices in each first cluster. And then, a first cluster with the target device occupation ratio larger than a preset first occupation ratio threshold value can be determined from the first clusters to serve as a target cluster. The target cluster may be specifically understood as a shared device cluster in which an idle aggregation condition exists.

Then, the server comprehensively utilizes the acquired GPS positioning data sent by the plurality of sharing devices in the target cluster, eliminates errors caused by accumulation of the sharing devices in a single GPS positioning data in a weighting averaging mode, and obtains an average value of more accurate position information for the target cluster; further, the average value of the position information may be used to uniformly correct the position information of the shared devices in the target cluster. For the sharing equipment with abnormal positioning caused by the gathering and stacking of the sharing equipment in the target cluster, the server can find out the sharing equipment and can accurately determine the position information of the sharing equipment.

Therefore, the position information of the sharing equipment with abnormal GPS positioning, such as blocked GPS signals or GPS positioning drift, caused by gathering and stacking of the sharing equipment in the cluster can be effectively corrected, the position information of almost the whole amount of sharing equipment can be determined efficiently and accurately, the sharing equipment maintainer can accurately find the sharing equipment with abnormal GPS positioning in the gathering area and in an idle state for a long time according to the position information, and corresponding recall processing and corresponding maintenance are carried out in time.

Referring to fig. 2, an embodiment of the present disclosure provides a method for positioning a shared device. The method can be applied to the server side. In particular implementations, the method may include the following.

S201: an environmental feature vector of each of a plurality of sharing devices is obtained.

In one embodiment, the sharing device may specifically include a device sharing a bicycle, a sharing automobile, or a sharing electric vehicle. Of course, the above listed sharing devices are only illustrative. In a specific implementation, the sharing device may further include other types of sharing devices besides the listed sharing devices according to a specific application scenario and a processing requirement.

In one embodiment, the environmental feature vector may be specifically understood as vector data generated based on the environmental parameters acquired by the sharing device and used for characterizing the ambient environmental features of the corresponding location where the sharing device is located.

In an embodiment, considering that the aggregated stacking of the shared devices often has a relatively large influence on the GPS positioning of the shared devices and a relatively small influence on the acquisition and transmission of other characteristic parameters, the multiple shared devices may be specifically understood as full-scale shared devices already released for operation or most shared devices in the full-scale shared devices already released for operation.

In an embodiment, the obtaining of the environment feature vector of each of the multiple sharing devices may be implemented as follows.

S1: receiving environment parameters sent by each sharing device in the plurality of sharing devices; wherein the environment parameter at least comprises base station sequence information;

s2: and determining corresponding vector elements according to the environment parameters to establish and obtain environment characteristic vectors corresponding to the sharing equipment.

In this embodiment, the base station sequence information may specifically include information related to the base station, such as a base station number in an environment around a location where the sharing device is located, sector information of the base station, or signal strength of the base station.

In one embodiment, the environment parameter may include, in addition to base station sequence information, at least one of: wi-Fi fingerprint information, bluetooth scanning information, GPS positioning data and the like.

The Wi-Fi fingerprint information may specifically include information related to the Wi-Fi device, such as a mac address of the Wi-Fi device, an SSID of the Wi-Fi device, or a signal strength of the Wi-Fi device in an environment around a location where the sharing device is located.

The bluetooth scanning information may specifically include the strength of the bluetooth signal broadcast by other sharing devices scanned in the surrounding environment of the location where the sharing device is located, and/or the mac address of the device sending the bluetooth signal.

The GPS positioning data may specifically include longitude information and latitude information about a location where the sharing device is located, which are determined by GPS positioning.

Of course, it should be noted that the above listed environmental parameters are only illustrative. In particular, other types of environmental parameters may be introduced and used depending on the particular application scenario and processing requirements. The present specification is not limited to these.

In this embodiment, the environment parameters at least include base station sequence information, which is because the base station sequence information is more stable and reliable than other types of environment parameters, and can more reliably represent the environment characteristics of the location where the sharing device is located.

In an embodiment, the sharing device may collect the environmental parameters around the location at every second preset time interval according to a preset communication rule, and send the environmental parameters to the server.

Correspondingly, the server can obtain the environmental parameters collected by the sharing equipment, and determine the elements corresponding to the vectors according to the environmental parameters, so that the vector elements can be combined to establish and obtain the environmental characteristic vectors respectively corresponding to the sharing equipment.

Specifically, the server may use the acquired base station sequence information acquired by a sharing device as a first vector element, use the Wi-Fi fingerprint information acquired by the sharing device as a second vector element, and use the bluetooth scanning information acquired by the sharing device as a third vector element, so as to combine to obtain a vector that simultaneously includes the three vector elements as an environment feature vector corresponding to the sharing device.

S202: performing preset first clustering processing on the plurality of sharing devices according to the environment feature vector to obtain a plurality of first clusters; and the similarity between the environment features represented by the environment feature vectors of different sharing devices in the same first cluster is greater than a preset similarity threshold.

In this embodiment, the server may use the above environment feature vector to find multiple shared devices clustered together or nearby in the physical space by finding shared devices with similar environment features at the location, and establish a corresponding first cluster.

Each first cluster may include a plurality of sharing devices, and the environmental features of the locations represented by the environmental feature vectors of different sharing devices included in the same first cluster are the same or have higher similarity, for example, the similarity is greater than a preset similarity threshold. The preset similarity threshold value can be flexibly set according to a specific application scene and precision requirements.

In an embodiment, the above-mentioned performing, according to the environment feature vector, a preset first clustering process on the multiple sharing devices to obtain multiple first clusters, which may include content in specific implementation.

S1: counting the similarity between the same vector elements in different environment feature vectors;

s2: determining the similarity between different environment feature vectors according to the similarity between the same vector elements in the different environment feature vectors;

s3: according to the similarity between different environment feature vectors, carrying out clustering operation on the environment feature vectors of the sharing equipment to obtain a set of multi-cluster environment feature vectors;

s4: and determining a plurality of first clusters according to the set of the multi-cluster environment feature vectors.

In one embodiment, in specific implementation, the same type vector element in any two environment feature vectors corresponding to different sharing devices may be compared to determine a similarity between the type vector elements in the two environment feature vectors.

In this embodiment, the way of calculating the similarity may be different for different kinds of vector elements.

In an embodiment, in the case that the vector element includes base station sequence information, the similarity between the same vector elements in different environment feature vectors is counted, and the specific implementation may include the following: determining the base station numbers appearing in the base station sequence information in different environment characteristic vectors; counting the number of the same base station number in the base station sequence information in different environment characteristic vectors; and determining the similarity between the base station sequence information in different environment characteristic vectors according to the number of the same base station number in the base station sequence information.

In one embodiment, in the case that the vector elements include GPS positioning data, the similarity between the same vector elements in different environment feature vectors is counted, and the following steps may be included in implementation: respectively carrying out geocoding on the GPS positioning data in different environment characteristic vectors to obtain corresponding geocode characters; and determining the similarity between the GPS positioning data in different environment characteristic vectors by calculating the similarity between different geocode characters.

In an embodiment, in a case that a vector element includes Wi-Fi fingerprint information, counting similarities between the same vector elements in different environment feature vectors may specifically include the following: determining mac addresses appearing in Wi-Fi fingerprint information in different environment feature vectors; counting the number of addresses of the same mac address in Wi-Fi fingerprint information in different environment feature vectors; and determining the similarity between the Wi-Fi fingerprint information in different environment characteristic vectors according to the number of the addresses with the same mac address in the Wi-Fi fingerprint information.

In one embodiment, in the case that the vector elements include bluetooth scanning information, counting similarities between the same vector elements in different environment feature vectors may specifically include the following: determining mac addresses appearing in the Bluetooth scanning information in different environment feature vectors; counting the number of addresses of the same mac address in the Bluetooth scanning information in different environment characteristic vectors; and determining the similarity between the Bluetooth scanning information in different environment characteristic vectors according to the address quantity of the same mac address in the Bluetooth scanning information.

In an embodiment, after the similarity between various vector elements in different environment feature vectors is obtained by calculation in the above manner, the linear weighting and fusion of the similarity between the various vector elements may be further performed according to a preset first weight, so as to obtain a comprehensive similarity as the similarity between different environment feature vectors.

The preset first weight can be flexibly determined according to the effect of the environment parameters corresponding to different types of vector elements on representing environment characteristics, the reliability degree and other factors. For example, since the base station is fixed and the mobile communication network is reliable, the base station sequence information is more accurate and more reliable than other environment parameters when representing the environment characteristics, and the weight value of the vector element corresponding to the base station sequence information can be set to be relatively larger.

In an embodiment, the environment feature vectors of the sharing device may be further clustered according to the similarity between different environment feature vectors to obtain a set of multi-cluster environment feature vectors. The similarity between every two environmental feature vectors contained in the set of each cluster of environmental feature vectors is high. Further, a plurality of first clusters may be determined from the set of multiple clusters of environmental feature vectors. That is, the shared devices corresponding to the environmental feature vectors included in the same set of environmental feature vectors may be divided into a first cluster.

Therefore, the situation that the GPS positioning data is independently relied on can be avoided, the environment characteristic vector obtained by combining various environment parameters is utilized, the plurality of shared devices gathered together are found according to the similarity of the environment characteristics of the positions of the shared devices reflected by the environment characteristic vector, and the corresponding first cluster is established. The plurality of first clusters thus found can better cover the full or large portion of shared devices (including shared devices with GPS positioning anomalies).

S203: counting the occupation ratio of the target equipment in each first cluster; the target equipment is shared equipment carrying a preset idle aggregation label; the preset idle aggregation tag is determined in advance according to GPS positioning data of the shared device.

In an embodiment, the preset idle aggregation tag may be specifically understood as a shared device used for indicating that there is an idle aggregation condition in a second cluster (referred to as an idle aggregation cluster) clustered based on GPS positioning data in advance. The target device may be specifically understood as a sharing device carrying the preset idle aggregation flag.

In an idle aggregation cluster in which an idle aggregation condition usually exists, a phenomenon that a plurality of shared devices are aggregated and stacked to influence GPS positioning often exists; there is also a relatively high probability that multiple shared devices may be in an idle state for long periods of time, with relatively more recall and maintenance processing being required.

It should be noted that the idle aggregation cluster is obtained by filtering a second cluster obtained by clustering based on GPS positioning data. Therefore, the number of shared devices included in the idle aggregation cluster is not always complete, and there is a relatively high probability that the shared devices actually existing in the idle aggregation cluster are missed, but are not found due to GPS positioning anomaly and are classified in the idle aggregation cluster. The determination of idle clusters and the setting of the preset idle aggregation flag will be described in detail later.

In an embodiment, in a specific implementation, the server may sequentially detect whether the shared devices in each first cluster carry a preset idle aggregation tag, and determine the detected shared devices carrying the preset idle aggregation tag as the target devices. Further, the server may count the number of the target devices in each first cluster and the total number of the shared devices in each first cluster, and calculate the target device proportion of each first cluster.

S204: and determining a first cluster with the occupation ratio of the target equipment larger than a preset first occupation ratio threshold value as a target cluster.

In an embodiment, the target cluster may be specifically understood as a first cluster in which an idle aggregation condition exists. The target cluster is obtained by screening the first cluster obtained by clustering based on the environmental feature vector. Therefore, compared with the idle cluster obtained based on the GPS positioning data clustering, the shared devices included in the target cluster are more complete.

In an embodiment, in specific implementation, the target device occupancy of each first cluster may be compared with a preset first occupancy threshold, and according to a comparison result, the first cluster whose target device occupancy is greater than the preset first occupancy threshold is determined as the target cluster. The specific value of the preset first proportion threshold value can be flexibly set according to specific conditions and precision requirements.

In this embodiment, the target cluster may further include, in addition to the shared device with normal GPS positioning, a GPS positioning anomaly (including a shared device in which the server does not receive the transmitted GPS positioning data, and/or a shared device in which the server is not divided into clusters for limiting aggregation due to an error such as an offset in positioning based on the received transmitted GPS positioning data).

Through the embodiment, the irregular full-idle aggregation areas obtained by clustering based on the GPS positioning data can be utilized to find the corresponding target cluster with complete shared equipment. In addition, the target cluster which is found out from the plurality of first clusters and has the idle aggregation condition through the method has a high probability of having more shared devices which are in the idle state for a long time and are abnormally positioned by the GPS.

S205: and correcting the position information of the sharing equipment in the target cluster according to the acquired GPS positioning data sent by the sharing equipment in the target cluster.

In one embodiment, considering that the distances between the sharing devices in the same target cluster are often relatively close, it is considered that GPS positioning data sent by a plurality of sharing devices in the target cluster can be comprehensively utilized to determine an average value of location information for the sharing devices in the target cluster; and then, the average value of the position information is utilized to uniformly correct the position information of the sharing equipment in the target cluster, so that more accurate position information of each sharing equipment in the target cluster including the sharing equipment with abnormal GPS positioning can be obtained.

In an embodiment, the correcting the location information of the sharing device in the target cluster according to the obtained GPS positioning data sent by the sharing device in the target cluster may include the following steps.

S1: according to the obtained GPS positioning data of the sharing equipment in the target cluster, obtaining an average value of the position information through weighting and averaging; the number of the shared devices in the target cluster for sending the GPS positioning data is less than or equal to the number of the shared devices in the target cluster;

s2: and correcting the position information of the sharing equipment in the target cluster according to the average value of the position information.

It should be noted that, because the target cluster further includes shared devices that cannot normally receive the positioning data due to aggregation stacking, the number of actual shared devices in the target cluster is often greater than or equal to the number of shared devices that send the GPS positioning data and are determined by the server through the received GPS positioning data.

In an embodiment, in the specific correction, a sharing device for which the server does not receive the sent GPS positioning data may be found from the target cluster, and the location information of the sharing device may be set as an average value of the location information. Further, a shared device in the target cluster, which has a large error (e.g., positioning drift occurs) based on the transmitted GPS positioning data, may be found by position comparison according to the average value of the position information, and the position information of the shared device may be set as the average value of the position information.

In an embodiment, during the specific correction, the shared devices in the target cluster may also be set to be the corrected location information in a unified manner without distinguishing the shared devices in the target cluster.

In an embodiment, besides the processing of using the average value of the location information determined based on the GPS positioning data to correct the location information of the shared device in the target cluster, the implementation may further include: determining a reference value of the position information according to the environmental parameters of the sharing equipment in the target cluster; and then the average value of the position information determined based on the GPS positioning data and the reference value of the position information determined based on the environmental parameters are combined together, so that the position information of the shared equipment in the target cluster is corrected more accurately.

In this embodiment, because the environmental feature vectors of each sharing device in the full amount of sharing devices are obtained first, and then the full amount of sharing devices are subjected to the preset first clustering process according to the full amount of environmental feature vectors, the sharing devices with higher similarity between the environmental features represented by the environmental feature vectors are clustered, and a plurality of first clusters are obtained; then according to the counted occupation ratio of the sharing equipment carrying the preset idle aggregation label in each first cluster, further finding out a target cluster with the idle aggregation condition, which is determined based on the GPS positioning data sent by the sharing equipment, from the plurality of first clusters; the acquired GPS positioning data sent by the sharing devices in the target cluster can be used for uniformly correcting the position information of the sharing devices in the target cluster, so that the cluster data of the sharing devices in the cluster can be used for effectively correcting the position information of the sharing devices with abnormal GPS positioning, such as GPS signal shielding or GPS positioning drifting, caused by gathering and stacking of the sharing devices in the cluster, and the position information of the whole sharing devices can be determined more efficiently and accurately.

In an embodiment, after the location information of the shared device in the target cluster is corrected, when the method is implemented, the following may be further included: and according to the corrected position information, recalling the shared equipment which is in an idle state for a long time and is abnormally positioned by the GPS in the target cluster.

In this embodiment, with the above embodiments, the server may determine location information of the total or most of the shared devices in the target cluster in which the idle aggregation condition exists.

Further, the server may detect the received GPS positioning data sent from the shared device in the target cluster; and according to the corrected position information, shared equipment with abnormal GPS positioning (including blocked GPS signals or GPS positioning drift) in the target cluster is determined.

Calculating idle time aiming at the shared equipment with abnormal GPS positioning in the target cluster; and according to the idle time, further screening out shared equipment which is in an idle state for a long time from the shared equipment with abnormal GPS positioning in the target cluster, wherein the shared equipment can be recorded as shared equipment to be recalled.

When the idle time is specifically calculated, the order time closest to the current time can be obtained and determined according to the historical order information of the shared device with abnormal GPS positioning in the target cluster, and the order time is used as the last time of using the shared device with abnormal GPS positioning in the target cluster; calculating the time difference between the last use time and the current time to obtain the idle time of the shared equipment; further, according to the idle time, a shared device with a longer idle time (e.g., a preset idle time threshold) may be found and determined as a shared device in an idle state for a long time. The specific value of the preset idle time threshold can be flexibly set according to the maintenance management requirement of the maintenance party of the shared device.

Then, the server can obtain the equipment number and the position information of the equipment to be recalled; generating a recall processing request carrying the equipment number of the equipment to be called and the position information; and sending the recall processing request to maintenance personnel. Therefore, maintenance personnel can go to the area where the corresponding target cluster is located according to the position information and find the shared equipment to be recalled in the area according to the equipment number of the equipment to be recalled. And then the shared equipment to be recalled can be recalled correspondingly so as to be maintained in detail later.

In an embodiment, before counting the proportion of the target devices in each first cluster, when the method is implemented, the following may be further included.

S1: acquiring GPS positioning data sent by sharing equipment;

s2: according to the GPS positioning data, performing preset second clustering processing on the sharing equipment which sends the GPS positioning data to obtain a plurality of second clusters; the second cluster comprises sharing equipment for sending GPS positioning data, and the difference value of the GPS positioning data of different sharing equipment in the same second cluster is smaller than a preset difference threshold value;

s3: and determining idle aggregation clusters from the plurality of second clusters, and setting preset idle aggregation labels for shared equipment in the idle aggregation clusters.

Through the embodiment, the server can perform clustering based on the GPS positioning data on the sharing equipment capable of sending the GPS positioning data according to the received GPS positioning data, find out a plurality of sharing equipment clustered together, and obtain a plurality of corresponding second clusters. However, it should be noted that the above clustering process solely depends on the GPS positioning data sent by the sharing device.

Therefore, as shown in fig. 3, the shared devices included in the second cluster clustered by the server based on the received GPS positioning data are not complete and have errors with respect to the shared devices included in the actual aggregation area. For example, the second cluster may miss a shared device that cannot normally transmit GPS positioning data due to the GPS signal being blocked. For another example, the first cluster may further include a shared device that is erroneously clustered into the second cluster due to GPS positioning drift, and the shared device does not actually belong to the second cluster. In contrast, the shared devices included in the first cluster obtained by the server based on the environmental parameter clustering are relatively more complete, have smaller errors, and are closer to the actual aggregation area.

In an embodiment, the performing, according to the GPS positioning data, a preset second clustering process on a sharing device that sends the GPS positioning data may include: according to the received GPS positioning data, longitude information and latitude information of the sent GPS positioning data are determined; according to a preset density threshold value, carrying out density clustering on longitude information and latitude information of shared equipment for sending GPS positioning data so as to obtain a plurality of clusters; and determining a plurality of shared devices which are gathered together and have dense distribution density according to the plurality of clusters to obtain a plurality of corresponding second clusters.

In an embodiment, the determining the idle aggregation cluster from the plurality of second clusters may include the following steps.

S1: acquiring historical order information of shared equipment in a second cluster;

s2: determining idle sharing equipment in the second cluster according to the historical order information of the sharing equipment in the second cluster;

s3: calculating the occupation ratio of idle shared equipment in each second cluster;

s4: and determining a second cluster with the occupation ratio of the idle sharing equipment larger than a preset second occupation ratio threshold value from the plurality of second clusters as an idle aggregation cluster.

With the above embodiment, a second cluster with a higher idle shared device (e.g., a shared device in an idle state for a long time) percentage may be further found from the plurality of second clusters obtained by clustering based on the GPS positioning data as an idle cluster in which an idle cluster condition exists.

In an embodiment, the determining, according to the historical order information of the shared devices in the second cluster, an idle shared device in the second cluster may include the following steps in specific implementation.

S1: according to historical order information of the sharing equipment, determining order time closest to the current time as last using time of the sharing equipment;

s2: calculating the time difference between the last use time and the current time of the shared equipment as the idle time of the shared equipment;

s3: comparing the idle time of the shared equipment with a preset idle time threshold value;

s4: and under the condition that the idle time of the shared equipment is determined to be larger than the preset idle time threshold value, determining that the shared equipment is idle shared equipment.

In an embodiment, the sharing device may specifically include at least one of: shared bicycles, shared gas vehicles and shared electric vehicles. Of course, the above listed sharing devices are only illustrative. In specific implementation, the method can be applied to other devices needing positioning except for the shared device according to specific application scenarios and service requirements. For example, the method can be applied to rental equipment (including rented bicycles, rented electric vehicles, rented automobiles and the like) so that the rental equipment which is abnormal in GPS positioning and is in an idle state for a long time due to gathering and stacking can be accurately determined and obtained, and then the rental equipment can be timely recalled and maintained.

As can be seen from the above, in the positioning method for sharing devices provided in the embodiments of the present specification, since the environmental feature vectors of each sharing device in the full-scale sharing device are obtained first, and then the full-scale sharing device is subjected to the preset first clustering process according to the full-scale environmental feature vectors, the sharing devices with higher similarity between the environmental features represented by the environmental feature vectors are clustered, so as to obtain a plurality of first clusters; then according to the counted occupation ratio of the sharing equipment carrying the preset idle aggregation label in each first cluster, further finding out a target cluster with the idle aggregation condition, which is determined based on the GPS positioning data sent by the sharing equipment, from the plurality of first clusters; the acquired GPS positioning data sent by the sharing devices in the target cluster can be used for uniformly correcting the position information of the sharing devices in the target cluster, so that the cluster data of the sharing devices in the cluster can be used for effectively correcting the position information of the sharing devices with abnormal GPS positioning, such as GPS signal shielding or GPS positioning drifting caused by gathering and stacking of the sharing devices in the cluster, the position information of the whole amount of sharing devices can be determined more efficiently and accurately, a sharing device maintainer can accurately find the sharing devices with abnormal GPS positioning in a gathering area and in an idle state for a long time, and corresponding recall processing can be performed in time.

Embodiments of the present specification further provide a server, including a processor and a memory for storing processor-executable instructions, where the processor, when implemented, may perform the following steps according to the instructions: obtaining an environment feature vector of each sharing device in a plurality of sharing devices; according to the environment feature vector, performing preset first clustering processing on the plurality of sharing devices to obtain a plurality of first clusters; the similarity between the environment features represented by the environment feature vectors of different sharing devices in the same first cluster is greater than a preset similarity threshold; counting the occupation ratio of the target equipment in each first cluster; the target equipment is shared equipment carrying a preset idle aggregation label; the preset idle aggregation label is determined in advance according to GPS positioning data of the shared equipment; determining a first cluster with the occupation ratio of the target equipment larger than a preset first occupation ratio threshold value as a target cluster; and correcting the position information of the sharing equipment in the target cluster according to the acquired GPS positioning data sent by the sharing equipment in the target cluster.

In order to more accurately complete the above instructions, referring to fig. 4, another specific server is provided in the embodiments of the present specification, wherein the server includes a network communication port 401, a processor 402, and a memory 403, and the above structures are connected by an internal cable, so that the structures may perform specific data interaction.

The network communication port 401 may be specifically configured to obtain an environment feature vector of each shared device in the multiple shared devices.

The processor 402 may be specifically configured to perform a preset first clustering process on the multiple sharing devices according to the environment feature vector to obtain multiple first clusters; the similarity between the environmental features represented by the environmental feature vectors of different sharing devices in the same first cluster is greater than a preset similarity threshold; counting the occupation ratio of the target equipment in each first cluster; the target equipment is shared equipment carrying a preset idle aggregation label; the preset idle aggregation label is determined in advance according to GPS positioning data of the shared equipment; determining a first cluster with the occupation ratio of the target equipment larger than a preset first occupation ratio threshold value as a target cluster; and correcting the position information of the sharing equipment in the target cluster according to the acquired GPS positioning data sent by the sharing equipment in the target cluster.

The memory 403 may be specifically configured to store a corresponding instruction program.

In this embodiment, the network communication port 401 may be a virtual port bound to different communication protocols, so as to send or receive different data. For example, the network communication port may be port No. 80 responsible for web data communication, port No. 21 responsible for FTP data communication, or port No. 25 responsible for mail data communication. In addition, the network communication port can also be a communication interface or a communication chip of an entity. For example, it may be a wireless mobile network communication chip, such as GSM, CDMA, etc.; it can also be a Wifi chip; it may also be a bluetooth chip.

In this embodiment, the processor 402 may be implemented in any suitable manner. For example, the processor may take the form of, for example, a microprocessor or processor and a computer-readable medium that stores computer-readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, an Application Specific Integrated Circuit (ASIC), a programmable logic controller, an embedded microcontroller, and so forth. The description is not intended to be limiting.

In this embodiment, the memory 403 may include multiple layers, and in a digital system, the memory may be any memory as long as it can store binary data; in an integrated circuit, a circuit without a real form and with a storage function is also called a memory, such as a RAM, a FIFO and the like; in the system, the storage device in physical form is also called a memory, such as a memory bank, a TF card and the like.

An embodiment of the present specification further provides a computer storage medium based on the above positioning method for a shared device, where the computer storage medium stores computer program instructions, and when the computer program instructions are executed, the computer storage medium implements: obtaining an environment feature vector of each sharing device in a plurality of sharing devices; performing preset first clustering processing on the plurality of sharing devices according to the environment feature vector to obtain a plurality of first clusters; the similarity between the environment features represented by the environment feature vectors of different sharing devices in the same first cluster is greater than a preset similarity threshold; counting the occupation ratio of the target equipment in each first cluster; the target equipment is shared equipment carrying a preset idle aggregation label; the preset idle aggregation label is obtained in advance according to GPS positioning data of the shared equipment; determining a first cluster with the occupation ratio of the target equipment larger than a preset first occupation ratio threshold value as a target cluster; and correcting the position information of the sharing equipment in the target cluster according to the acquired GPS positioning data sent by the sharing equipment in the target cluster.

In this embodiment, the storage medium includes, but is not limited to, a Random Access Memory (RAM), a Read-Only Memory (ROM), a Cache (Cache), a Hard Disk (HDD), or a Memory Card (Memory Card). The memory may be used to store computer program instructions. The network communication unit may be an interface for performing network connection communication, which is set in accordance with a standard prescribed by a communication protocol.

In this embodiment, the functions and effects specifically realized by the program instructions stored in the computer storage medium can be explained by comparing with other embodiments, and are not described herein again.

Referring to fig. 5, in a software level, an embodiment of the present specification further provides a positioning apparatus for a shared device, where the apparatus may specifically include the following structural modules.

The obtaining module 501 may be specifically configured to obtain an environment feature vector of each shared device in the multiple shared devices;

the clustering module 502 may be specifically configured to perform a preset first clustering process on the multiple sharing devices according to the environment feature vector to obtain multiple first clusters; the similarity between the environment features represented by the environment feature vectors of different sharing devices in the same first cluster is greater than a preset similarity threshold;

the statistics module 503 may be specifically configured to count a percentage of target devices in each first cluster; the target equipment is shared equipment carrying a preset idle aggregation label; the preset idle aggregation label is obtained in advance according to GPS positioning data of the shared equipment;

the determining module 504 is specifically configured to determine, as a target cluster, a first cluster in which the proportion of the target device is greater than a preset first proportion threshold;

the correcting module 505 may be specifically configured to correct, according to the obtained GPS positioning data sent by the sharing device in the target cluster, the location information of the sharing device in the target cluster.

In an embodiment, when the obtaining module 501 is implemented specifically, the obtaining module may receive an environmental parameter sent by each sharing device of the multiple sharing devices; wherein the environment parameter at least comprises base station sequence information; and determining corresponding vector elements according to the environment parameters to establish and obtain environment characteristic vectors corresponding to the sharing equipment.

In an embodiment, the environmental parameter may specifically further include at least one of: wi-Fi fingerprint information, bluetooth scanning information, GPS positioning data and the like.

In one embodiment, when the clustering module 502 is implemented, the similarity between the same vector elements in different environment feature vectors can be counted; determining the similarity between different environment feature vectors according to the similarity between the same vector elements in the different environment feature vectors; according to the similarity between different environment feature vectors, carrying out clustering operation on the environment feature vectors of the sharing equipment to obtain a set of multi-cluster environment feature vectors; and determining a plurality of first clusters according to the set of the multi-cluster environment feature vectors.

In one embodiment, in the case that the vector element includes base station sequence information, when the clustering module 502 is implemented, the base station numbers appearing in the base station sequence information in different environment feature vectors may be determined; counting the number of the same base station number in the base station sequence information in different environment characteristic vectors; and determining the similarity between the base station sequence information in different environment characteristic vectors according to the number of the same base station number in the base station sequence information.

In an embodiment, in a case that the vector element includes GPS positioning data, when the clustering module 502 is implemented specifically, geocoding may be performed respectively according to the GPS positioning data in different environment feature vectors to obtain corresponding geocode characters; and determining the similarity between the GPS positioning data in different environment characteristic vectors by calculating the similarity between different geocode characters.

In one embodiment, in the case that the vector elements include Wi-Fi fingerprint information, the clustering module 502, when implemented in detail, may determine mac addresses appearing in the Wi-Fi fingerprint information in different environmental feature vectors; counting the number of addresses of the same mac address in Wi-Fi fingerprint information in different environment feature vectors; and determining the similarity between the Wi-Fi fingerprint information in different environment characteristic vectors according to the address number of the same mac address in the Wi-Fi fingerprint information.

In one embodiment, before counting the occupation ratio of the target devices in each first cluster, the apparatus is further configured to acquire GPS positioning data sent by the sharing device; according to the GPS positioning data, performing preset second clustering processing on the sharing equipment which sends the GPS positioning data to obtain a plurality of second clusters; the second cluster comprises sharing equipment for sending GPS positioning data, and the difference value of the GPS positioning data of different sharing equipment in the same second cluster is smaller than a preset difference threshold value; and determining idle aggregation clusters from the plurality of second clusters, and setting preset idle aggregation labels for shared equipment in the idle aggregation clusters.

In an embodiment, when the apparatus is implemented specifically, the apparatus may be further configured to obtain historical order information of the shared device in the second cluster; determining idle shared equipment in the second cluster according to the historical order information of the shared equipment in the second cluster; calculating the occupation ratio of idle shared equipment in each second cluster; and determining a second cluster with the occupation ratio of the idle sharing equipment larger than a preset second occupation ratio threshold value from the plurality of second clusters as an idle aggregation cluster.

In an embodiment, when the apparatus is implemented specifically, the apparatus may be further configured to determine, according to historical order information of the shared device, an order time closest to a current time as a last use time of the shared device; calculating the time difference between the last use time and the current time of the shared equipment as the idle time of the shared equipment; comparing the idle time of the shared equipment with a preset idle time threshold value; and under the condition that the idle time of the shared equipment is determined to be larger than the preset idle time threshold, determining that the shared equipment is idle shared equipment.

In an embodiment, when the correcting module 505 is specifically implemented, the correcting module may be configured to obtain an average value of the location information by weighting and averaging according to the obtained GPS positioning data of the shared device in the target cluster; the number of the shared devices which send the GPS positioning data in the target cluster is less than or equal to the number of the shared devices in the target cluster; and correcting the position information of the sharing equipment in the target cluster according to the average value of the position information.

In an embodiment, the sharing device may specifically include at least one of: shared bicycles, shared gas vehicles, shared electric vehicles, etc.

In an embodiment, the apparatus may further include a recall module, configured to perform recall processing on the shared device in the target cluster that is idle for a long time and has abnormal GPS positioning according to the corrected location information.

It should be noted that, the units, devices, modules, etc. illustrated in the above embodiments may be implemented by a computer chip or an entity, or implemented by a product with certain functions. For convenience of description, the above devices are described as being divided into various modules by functions, and are described separately. It is to be understood that, in implementing the present specification, functions of each module may be implemented in one or more pieces of software and/or hardware, or a module that implements the same function may be implemented by a combination of a plurality of sub-modules or sub-units, or the like. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.

As can be seen from the above, the positioning apparatus for sharing devices provided in the embodiments of the present specification can effectively correct, by using group data of the sharing devices in a cluster, location information of the sharing devices with GPS positioning abnormality, such as GPS signal blocking or GPS positioning drift, due to the gathering and stacking of the sharing devices in the cluster, and can relatively efficiently and accurately determine location information of a whole amount of sharing devices, so that a sharing device maintainer can accurately find the sharing devices with GPS positioning abnormality in a gathering area and in an idle state, and perform corresponding recall processing in time.

In a specific scenario example, the released vehicle (for example, a shared bicycle) may be identified and located by applying the method for locating a shared device provided in this specification with reference to the following contents, so as to avoid the phenomenon that the vehicle is left unused for a long time and is not maintained by people or is occupied by people.

In this scenario example, according to the above method, based on the multidimensional information features of group vehicles, such as historical order information of a single vehicle, original positioning signal information (e.g., GPS positioning data) of the single vehicle, base station signal Wi-Fi signal information (e.g., base station sequence information), bluetooth scanning signal information (e.g., bluetooth scanning information), and the like, vehicles gathered in the same area are mined (a second cluster is obtained), and then the positions of the vehicles with GPS positioning abnormality, such as positioning drift, in the above gathering area are corrected, so as to improve the positioning accuracy.

In the example of the scenario, the vehicle is pre-installed with a module (for example, a GPS positioning module) containing a GPS chip capable of performing satellite positioning, and is installed with a Wi-Fi scanning module (for example, a Wi-Fi scanner) capable of scanning Wi-Fi list information near the vehicle, including mac address and signal strength of the Wi-Fi device. In addition, the vehicle can be further provided with a low-power-consumption Bluetooth chip, and the vehicle can continuously broadcast signals to external low-power-consumption Bluetooth in the operation process. Wherein, the bluetooth broadcast signal may include id number information of the vehicle. The vehicle can also be provided with an SIM card which can collect the signal intensity information of surrounding base stations.

The bicycle satellite positioning module can utilize satellite positioning. Specifically, when the bicycle is unlocked by the scanning code, the positioning module can be opened to perform satellite positioning. After the scanned code unlocking service is carried out, the single vehicle can carry out timed satellite positioning according to a set positioning frequency threshold value. And integrating and reporting the satellite positioning longitude and latitude information and the positioning timestamp information to a server at a preset reporting frequency.

During the concrete implementation, the bicycle when carrying out satellite positioning, the Wi-Fi scanning module of bicycle can scan according to preset scanning frequency, scans the peripheral Wi-Fi information of bicycle vehicle, includes: the mac address number of each Wi-Fi device, the ssid of each Wi-Fi device, signal strength information corresponding to each Wi-Fi device, and scanning time point information. The information scanned by the Wi-Fi module can be contained in the reported satellite positioning information of the bicycle.

Further, the bicycle can report the base station information searched by the SIM card according to a preset reporting frequency, and the reporting content comprises: base station number information, base station sector information, base station signal strength information.

The low-power consumption Bluetooth chip installed in the bicycle starts the Bluetooth broadcast all the time. And the vehicle can start the Bluetooth scanning function according to the set scanning frequency every day, scan the Bluetooth broadcasting equipment around the vehicle and report the Bluetooth information to the server.

Before implementation, a suspected vehicle gathering area may be excavated. And performing density clustering on the longitude and latitude information of the global vehicle which is newly reported to be positioned by the GPS according to a preset density threshold value to obtain a plurality of clusters. (finding a plurality of second clusters)

Further, according to each cluster, the vehicle proportion information of the time difference between the latest order and the current time and the vehicle proportion information exceeding the threshold is calculated according to the latest historical order information of the vehicles in the cluster. The area where the cluster exceeds the idle ratio threshold is labeled with label information of a suspected vehicle idle aggregation area (e.g., idle aggregation group), and the vehicle to which the cluster belongs is labeled with aggregated vehicle label information (e.g., preset idle aggregation label).

Vehicles that fail to be GPS located for aggregation (e.g., vehicles with GSP location anomalies) may then be identified for recall identification using the vehicle information in the aggregation area. Because in the area where vehicles gather, there are often vehicle heaps, which results in the vehicle GPS signal being blocked, and further results in the vehicle having GPS positioning drift, even GPS cannot be positioned, which is an important reason why the vehicle is not recalled and identified.

Further, in order to recall more vehicles, feature vectors (e.g., environmental feature vectors) may be constructed for the environments where the entire number of vehicles are located, and then the environment feature vectors are used for clustering to identify vehicles with similar signals (e.g., similar environmental features) in the physical space.

The environment feature vector of the vehicle may include several kinds of feature information (e.g., environment parameters): the latest updated time of the vehicle, the latest updated Wi-Fi fingerprint of the vehicle, the latest base station sequence (such as the base station number of the latest 50 scans and the base station signal strength information) of the vehicle, the latest bluetooth scan list information of the vehicle, and the like. Further, an environmental feature vector corresponding to each vehicle may be established.

Further, similar vectors need to be clustered. Specifically, for example, the logic of the calculation of any 2 environment feature vectors is as follows. The calculating of the feature similarity with respect to the latitude and longitude includes: and carrying out geocoding on the GPS positioning longitude and latitude of the 2 devices, and then calculating the character similarity of the encoding result. The similarity calculation of the Wi-Fi fingerprint partial characteristics comprises the following steps: and calculating the ratio of the number of the mac addresses of the 2 sections of Wi-Fi fingerprints which appear together to the number of all the mac addresses of the 2 sections of Wi-Fi fingerprints. The similarity calculation for the characteristic part of the base station sequence comprises the following steps: and calculating the ratio of the number of the base station numbers id of the 2 segments of base station sequences appearing together to the threshold value of the base station sequences. The similarity calculation of the Bluetooth scanning part comprises the step of calculating the ratio of the co-occurrence number of mac addresses scanned by the Bluetooth of 2 pieces of equipment to the total number of the mac addresses scanned by all Bluetooth.

And further, the 4 parts of similarity values can be subjected to linear weighted fusion according to preset weights to obtain a comprehensive similarity value. And clustering according to a calculation formula of the comprehensive similarity value and the environment feature vector similarity to obtain a multi-cluster environment feature vector set.

Then, the vehicle belonging to each cluster can be checked, the proportion of the aggregation area vehicle labels marked in the first step of each cluster is calculated, and the vehicle positioning information of the cluster belonging to the cluster with the proportion exceeding a threshold value is corrected.

When the position is corrected specifically, the vehicle position information of the cluster needing to be corrected can be subjected to linear weighting through the GPS positioning information of the vehicles which are originally marked with the aggregation area vehicle labels in the cluster to obtain a new position, and the position information of other vehicles in the cluster can be corrected.

Through the above scenario example, it is verified that the positioning method of the sharing device provided by the present specification can utilize a multi-dimensional information feature based on group vehicles, such as historical order information of a vehicle, original positioning signal information of the vehicle, a base station signal, a Wi-Fi signal, a bluetooth scanning signal, etc., to dig out vehicle accesses aggregated in the same area, for the problem of positioning drift in a vehicle aggregation area. And the vehicle multi-dimensional information of the group can be utilized to correct the positioning drift or the vehicle positioning which can not be positioned by the GPS, so that the positioning precision is obviously improved, and the safety of the vehicle assets is ensured.

Although the present specification provides method steps as described in the examples or flowcharts, additional or fewer steps may be included based on conventional or non-inventive approaches. The order of steps recited in the embodiments is merely one manner of performing the steps in a multitude of sequences, and does not represent a unique order of performance. When an apparatus or client product in practice executes, it may execute sequentially or in parallel (e.g., in a parallel processor or multithreaded processing environment, or even in a distributed data processing environment) according to the embodiments or methods shown in the figures. The terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, the presence of additional identical or equivalent elements in processes, methods, articles, or apparatus that include the recited elements is not excluded. The terms first, second, etc. are used to denote names, but not any particular order.

Those skilled in the art will also appreciate that, in addition to implementing the controller as pure computer readable program code, the same functionality can be implemented by logically programming method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Such a controller may therefore be considered as a hardware component, and the means included therein for performing the various functions may also be considered as a structure within the hardware component. Or even means for performing the functions may be regarded as being both a software module for performing the method and a structure within a hardware component.

This description may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, classes, etc. that perform particular tasks or implement particular abstract data types. The specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.

From the above description of the embodiments, it is clear to those skilled in the art that the present specification can be implemented by software plus necessary general hardware platform. Based on such understanding, the technical solutions in this specification may be essentially embodied in the form of a software product, which may be stored in a storage medium, such as a ROM/RAM, a magnetic disk, an optical disk, etc., and includes several instructions for enabling a computer device (which may be a personal computer, a mobile terminal, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments in this specification.

The embodiments in the present specification are described in a progressive manner, and the same or similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. The description is operational with numerous general purpose or special purpose computing system environments or configurations. For example: personal computers, server computers, hand-held or portable devices, tablet-type devices, multiprocessor systems, microprocessor-based systems, set top boxes, programmable electronic devices, network PCs, minicomputers, mainframe computers, distributed computing environments that include any of the above systems or devices, and the like.

While the specification has been described with examples, those skilled in the art will appreciate that there are numerous variations and permutations of the specification that do not depart from the spirit of the specification, and it is intended that the appended claims include such variations and modifications that do not depart from the spirit of the specification.

Claims

1. A method for positioning a shared device comprises the following steps:

performing preset first clustering processing on the plurality of sharing devices according to the environment feature vector to obtain a plurality of first clusters; the similarity between the environment features represented by the environment feature vectors of different sharing devices in the same first cluster is greater than a preset similarity threshold;

determining a first cluster of which the proportion of the target equipment is greater than a preset first proportion threshold value as a target cluster; the target cluster is a shared equipment cluster with an idle aggregation condition;

2. The method of claim 1, the obtaining the environmental feature vector for each of the plurality of shared devices, comprising:

and determining corresponding vector elements according to the environment parameters to establish and obtain environment characteristic vectors corresponding to the sharing equipment.

3. The method of claim 2, the environmental parameters further comprising at least one of: wi-Fi fingerprint information, bluetooth scanning information and GPS positioning data.

4. The method according to claim 3, wherein performing a preset first clustering process on the plurality of sharing devices according to the environment feature vector to obtain a plurality of first clusters includes:

5. The method of claim 4, wherein in the case that the vector elements include base station sequence information, counting similarities between the same vector elements in different environment feature vectors comprises:

6. The method of claim 4, where the vector elements comprise GPS positioning data, counting similarities between the same vector elements in different environmental feature vectors, comprising:

respectively carrying out geocoding according to the GPS positioning data in different environment characteristic vectors to obtain corresponding geocode characters;

7. The method of claim 4, where the vector elements comprise Wi-Fi fingerprint information, counting similarities between the same vector elements in different environmental feature vectors, comprising:

and determining the similarity between the Wi-Fi fingerprint information in different environment characteristic vectors according to the address number of the same mac address in the Wi-Fi fingerprint information.

8. The method of claim 1, prior to counting the proportion of target devices in each first cluster, the method further comprising:

acquiring GPS positioning data sent by sharing equipment;

according to the GPS positioning data, performing preset second clustering processing on the shared equipment which sends the GPS positioning data to obtain a plurality of second clusters; the second cluster comprises sharing equipment for sending GPS positioning data, and the difference value of the GPS positioning data of different sharing equipment in the same second cluster is smaller than a preset difference threshold value;

and determining idle aggregation clusters from the plurality of second clusters, and setting preset idle aggregation labels for shared devices in the idle aggregation clusters.

9. The method of claim 8, determining an idle aggregated cluster from the plurality of second clusters, comprising:

acquiring historical order information of shared equipment in a second cluster;

10. The method of claim 9, wherein determining idle shared devices in the second cluster according to historical order information of shared devices in the second cluster comprises:

calculating the time difference between the last time of use and the current time of the shared equipment as the idle time of the shared equipment;

11. The method of claim 8, wherein the correcting the position information of the shared device in the target cluster according to the acquired GPS positioning data sent by the shared device in the target cluster comprises:

obtaining an average value of the position information by weighting and averaging according to the acquired GPS positioning data of the shared equipment in the target cluster; the number of the shared devices in the target cluster for sending the GPS positioning data is less than or equal to the number of the shared devices in the target cluster;

12. The method of claim 1, the sharing device comprising at least one of: shared bicycles, shared gas vehicles and shared electric vehicles.

13. The method of claim 1, after correcting location information of shared devices in the target cluster, further comprising:

14. A server comprising a processor and a memory for storing processor-executable instructions which, when executed by the processor, implement the steps of the method of any one of claims 1 to 13.

15. A computer readable storage medium having stored thereon computer instructions which, when executed, implement the steps of the method of any one of claims 1 to 13.