CN102573053B - System and method for realizing hybrid positioning on cloud server - Google Patents

Abstract

The invention discloses a system and method for realizing hybrid positioning on a cloud server. The positioning system mainly includes a database, a data computing server and a positioning computing server. The database records training data, which is obtained using a mobile training device. The data calculation server is configured to use the training data to calculate the position of the detected access point, and the calculated position is recorded in the database. The positioning calculation server is configured to use data from the database to calculate the position of the mobile device. The step of the positioning method is to first select a position information from a plurality of position information through the position selection unit in the positioning calculation server and send it back to the mobile device. The plurality of position information includes cellular and WiFi solutions. Then, through the location selection unit in the mobile device, a location information is selected from a plurality of location information to determine a location of the device. The plurality of location information includes GPS and cellular/WiFi solutions.

Description

System and method for realizing hybrid positioning on cloud server

technical field

The present invention relates to a system and method for determining the location of a mobile device, and more particularly, to a hybrid positioning system and method using a global positioning system, a cellular network system, and a WiFi network system.

Background technique

In recent years, with the rapid development of various types of location-based services (Location-based services, LBS), wireless positioning technology has attracted attention and attention from related fields. The signal to be measured by the positioning technology may be a Global Positioning System (GPS) signal, a reference signal of a wireless network system, or an auxiliary positioning signal of other systems. Due to the different content of signal measurement, there are different positioning methods. At present, various positioning technologies in related fields have been widely proposed.

Among satellite-based positioning systems, GPS is the most well-known positioning system widely used in various fields. GPS transmits positioning signals to the ground through 24 satellites deployed in space around the clock. Mobile devices only need to be equipped with appropriate receiving equipment to receive positioning signals and perform three-dimensional spatial position calculations at any time anywhere in the world. GPS mainly provides longitude and latitude coordinate positioning services for outdoor environments, and its positioning accuracy is high, and its position information has an error of only about ten meters. However, this technology cannot be used indoors because the positioning signals emitted by GPS satellites are blocked by buildings. In addition, in narrow urban streets or poor weather conditions in urban areas, the accuracy of GPS positioning will be reduced to a considerable extent.

Among terrestrial radio-based positioning systems, representative positioning systems are cellular network and wireless local area network positioning systems. The most basic positioning technology of the cellular network positioning system is to use the cell tower of the cellular network, that is, the cell global identity (CGI) code of the base station, to realize the two-dimensional spatial position calculation. The advantage is that it does not require complex calculations, and this technology can be used indoors. The disadvantage is that the positioning accuracy directly depends on the range covered by the cell base station. From urban areas to suburban areas, the location information ranges from about several hundred meters. to tens of kilometers of error. Another simple and practical positioning technology of the cellular network positioning system is to use the mobile device to receive the signal power strength from the base station, that is, Received Signal Strength (RSS), to realize two-dimensional spatial position calculation. The positioning method is to use three or more received RSS values to calculate the position of the mobile device with a triangular positioning algorithm. The disadvantage is that due to the non-line of sight effect and shadow fading Due to the influence of the RSS value measurement error, the triangulation positioning algorithm cannot solve or calculate a huge positioning error value. In addition, in the suburban or hilly environment, the deployment of cellular base stations is less, and the ability to listen to three or more base stations is also a major bottleneck.

WLAN positioning systems are actually mostly used to provide location information in indoor environments. However, with the rapid popularization of wireless access points (APs) and the increasing proportion of mobile handheld devices such as smart phones with built-in WiFi functions, the positioning system has been developed from indoor to outdoor applications. In other words, the positioning system can also provide location information in an outdoor environment at a considerable distance. The most widely used positioning technology in the wireless local area network positioning system is to use the mobile device to receive the signal power strength from the wireless AP, that is, RSS, to realize the two-dimensional spatial position calculation. Different from the above-mentioned honeycomb network positioning system, its positioning method is to use the database association positioning method. In the offline (off-line) stage, first collect the RSS value for the positioning environment training point, and then associate the RSS value with the position to establish a signal fingerprint database. In the online (on-line) stage, the mobile device that requires positioning first reports the measured RSS value, and then compares the RSS value with the database established in the off-line stage to find the most likely location , which is the location of the mobile device. The advantage is that the positioning accuracy is high, and the disadvantage is that the RSS value must be collected repeatedly in the offline stage to conform to the correlation between the RSS value and the location.

In the terrestrial radio-based positioning system, in addition to the above-mentioned positioning technologies, positioning technologies based on measuring time signals such as Time of Arrive (ToA) and Time Difference of Arrive (TDoA) are also widely used. usage instructions. Although it has better positioning accuracy, its main disadvantages are the need for complex position calculations, high signal measurement complexity, high additional hardware cost, and the need to change the hardware architecture of mobile devices. In addition, in suburban or hilly environments, the ability to hear three or more base stations is a major issue in order to enable position resolution.

Contents of the invention

In order to enable mobile devices to seamlessly acquire location-based services in different environments, the present invention proposes a hybrid positioning system and method applied to mobile devices.

In order to achieve the above object, the technical scheme adopted in the present invention is as follows:

In the present invention, the hybrid positioning system implemented on the cloud server is a positioning system based on satellite and terrestrial radio. The positioning system is deployed on a hybrid wireless network with multiple GPS satellites, multiple cellular base stations, and multiple WiFi APs. The positioning system includes a data training subsystem, a position solving subsystem, and a main database.

The data training subsystem includes a mobile training device and a cloud data computing server. The mobile training device is used to acquire training data and transmit the training data to the cloud data computing server. The data computing server calculates the training data based on the training data. detecting a location of the access point;

The positioning calculation subsystem includes a mobile device and a cloud positioning computing server. The mobile device is used to obtain positioning data and transmit the positioning data to the cloud positioning computing server. The positioning computing server calculates the device based on the positioning data. a position of

The main database is used to store training data, record the location information and status of the calculated detection access points. The primary database includes a hive secondary database and a hybrid secondary database.

In the example of the present invention, the data training subsystem is set up with at least one mobile training device and a cloud data computing server. The training device is used to obtain training data, the training data includes a GPS position coordinates, CGI code parameters and signal strength values of multiple cell base stations, and Medium Access Control (MAC) address parameters and Signal strength value. Based on the acquired training data, the training device performs data staging, classification and encryption. The encrypted training data is sent to the cloud data computing server through an application programming interface (API). After receiving the encrypted training data, the cloud server performs data decryption, search and fusion, and location estimation. The location refers to the location of the cell base station and the WiFi AP. According to the fusion data of the cloud server, the master database updates or stores the data, and records the status of the location information. If the location information is in an unknown state, the cloud server immediately obtains the training data of the master database to perform location calculation. If the location information is in an updated state, the cloud server regularly obtains the training data of the master database to perform location calculation. According to the position calculation result of the cloud server, the master database updates or stores the position information, and records the position information as a known state.

In the example of the present invention, the positioning calculation subsystem is set up with at least one mobile device and a cloud positioning calculation server. The mobile device is used to obtain positioning data, and the positioning data may include a GPS position coordinate, a CGI code parameter and a signal strength value of a serving cell base station, and/or a MAC address parameter and a signal strength value of a WiFi link AP. If the GPS location coordinate is in an existing state, then the location coordinate is stored in the location selection unit of the mobile device. The mobile device can perform positioning data type differentiation according to the detected cell base stations and WiFi AP signals. If no WiFiAP signal is detected, the type is the cellular positioning data type. If no cell base station signal is detected, this type is the type of WiFi positioning data. Otherwise, the location data type is a mixed type. After the location data is encrypted, it is sent to the cloud location computing server through the API. After receiving the encrypted positioning data, the cloud server performs data decryption and searching and estimation of a plurality of positions. The location refers to the location of the mobile device. The obtained location information is stored in the location selection unit of the cloud server.

In the present invention, the method for realizing hybrid positioning on the cloud server can be based on the cell base station and WiFi AP signals detected by the above-mentioned mobile device, and the cloud positioning computing server provides multiple positioning methods, including a base station (CGI) positioning method, a Base station assisted RSS (CGI-RSS) positioning method, one AP (MAC) positioning method and one AP assisted RSS (MAC-RSS) positioning method. Each positioning method is assigned a priority and provides a location information. According to the positioning data type defined by the mobile device, the cloud positioning calculation server selects the corresponding positioning method, and stores the position information to the position selection unit. The location selection unit can select a high-weight location information from the plurality of location information, and send it back to the mobile device.

The positioning method in the implementation of the present invention can provide a plurality of position information for the mobile device according to the presence status of the GPS signal detected by the mobile device. The location selection unit of the mobile device stores the location information, and can select a location information from the location information to determine a location of the device.

The above-mentioned method of the present invention is a pure software architecture, which can be deployed in a physical machine through program codes. When the machine is loaded with the program code and executed, the machine becomes a device for implementing the present invention.

Description of drawings

The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

FIG. 1 is a schematic diagram of a simplified mode of a hybrid positioning system in an embodiment of the present invention.

FIG. 2 is a schematic diagram of a data training subsystem of the hybrid positioning system in an embodiment of the present invention.

FIG. 3 is a flowchart showing database search, data fusion, and position estimation according to the honeycomb pattern training data framework according to an embodiment of the present invention.

FIG. 4 is a flow chart showing database search, data fusion, and position estimation according to the mixed-type training data architecture according to an embodiment of the present invention.

FIG. 5 is a schematic diagram of a positioning solution subsystem of the hybrid positioning system in an embodiment of the present invention.

FIG. 6 is a flow chart showing database search and position estimation according to the cellular positioning data type framework according to an embodiment of the present invention.

FIG. 7 is a flow chart showing database search and location estimation according to the WiFi positioning data type framework according to an embodiment of the present invention.

FIG. 8 is a flow chart showing database search and position estimation according to the hybrid positioning data type framework in an embodiment of the present invention.

FIG. 9 is a flowchart showing a positioning method according to an embodiment of the present invention.

[Description of main component symbols]

101, 102, 103: GPS satellites

104, 105, 106: honeycomb cell base station

107, 108, 109, 110: WiFi APs

111: Mobile Training Device

112: Mobile device

113: Data computing server

114: Positioning computing server

115: Hive Secondary Database

116: Hybrid Secondary Database

201, 501: receiving unit

202: data cache unit

203: Data Taxonomy Units

204, 503: data encryption unit

205: Backup database

206, 505: cellular or WiFi wireless network

207, 506: data decryption unit

208: Data fusion unit

209, 210, 507, 508: position calculation unit

210: Master database

502: Positioning Taxa

504, 509: location selection unit

301～312, 401～412, 601～609, 701～709, 801～803, 901～913: steps

detailed description

In order to make the technical means, creative features, goals and effects achieved by the present invention easy to understand, the present invention will be further described below in conjunction with specific illustrations.

FIG. 1 is a schematic diagram of a simplified mode of a positioning system based on satellite and terrestrial radio according to an embodiment of the present invention. The positioning system includes a plurality of GPS satellites (101, 102, 103), a plurality of cell base stations (104, 105, 106), a plurality of WiFi APs (107, 108, 109, 110), a mobile training device 111 such as a smart A mobile phone or personal digital assistant (PDA), a mobile device 112 such as a mobile phone, a smart phone, a PDA, a notebook computer or a tablet computer, a data computing server 113, a location computing server 114, a cellular secondary database 115, and a Hybrid secondary database 116 .

Among them, GPS satellites transmit positioning signals to the ground around the clock. Each cell base station has a common control channel (CCH), which can continuously broadcast its signal in the cellular network to provide unique CGI code parameters. Each WiFi AP has a CCH, which can continuously broadcast its signal in the WiFi network to provide unique MAC address parameters. It should be noted that the number of GPS satellites, cell base stations and WiFi APs is not limited to the number shown in FIG. 1 , and the number can vary in different embodiments without departing from the spirit of the present invention.

FIG. 2 is a schematic diagram of the data training subsystem in the embodiment of the present invention. The mobile training device 111 is equipped with a receiving unit 201 , a data cache unit 202 , a data classification unit 203 , a data encryption unit 204 and a backup database 205 . When the training device 111 enters the outdoor target area of the hybrid network, training data can be obtained through the receiving unit 201 . The training data includes the following:

GPS location coordinates. The GPS location coordinates of the device are acquired through a GPS receiver (not shown) in the receiving unit 201 . Its working principle is roughly as follows: a presence state of at least 4 GPS satellite signals is detected, and the position coordinates are calculated by measuring the ToA value based on the signals from the satellites.

CGI code parameters and signal strength values for cell-based stations. The receiving unit 201 detects the existence status of the signals of a plurality of cell base stations (such as 104 and 105 in FIG. 1 ), and can extract the CGI code parameters and measure the signal strength value according to the signals of the cell base stations.

MAC address parameter and signal strength value of WiFi AP. The receiving unit 201 detects the existence status of the signals of multiple WiFi APs (such as 107 and 108 in FIG. 1 ), and the MAC address parameters and the measured signal strength values can be extracted according to the signals of the APs.

As is known to those familiar with GPS technology, typically GPS location coordinates are updated every second. Therefore, the time stamp of the signal detection is set to one second. In a time stamp, the receiving unit 201 can acquire GPS position coordinates once, extract CGI code parameters and measure signal strength values twice, and extract MAC address parameters and measure signal strength values four times. The data cache unit 202 stores the training data acquired, extracted and measured by the receiving unit 201 , and transmits the stored training data to the data classification unit 203 in batches. The interval time stamp for transmitting a batch of data is set to thirty seconds. It should be noted that, in the embodiment of the present invention, the time stamp and the number of times set are not limited to the above-mentioned numbers, and the number may vary in different embodiments without departing from the spirit of the present invention. Variety.

After receiving the training data, the data classification unit 203 performs data type and class distinction. In terms of data types, the training data can be divided into honeycomb type and mixed type. The honeycomb type training data mainly records GPS position coordinates, CGI code parameters and signal strength values, and the mixed type training data mainly records GPS position coordinates, CGI code parameters, MAC address parameters and signal strength values. For data types, the cellular type training data for the same CGI code parameter can be divided into service type and neighbor type, and the mixed type training data for the same MAC address parameter can be divided into link type and unlink type. Before connecting the cellular or WiFi wireless network 206 (such as 104 or 108 in Figure 1) to transmit the training data to the cloud data computing server 113 through the API, the data encryption unit 204 is used to compress and encrypt the data , and send the encrypted training data to the backup database 205 for storage. Based on the transmission characteristics of the wireless network, once the transmission of the encrypted training data fails, the encrypted training data can be obtained from the backup database 205 for retransmission. After the cloud data computing server 113 receives the encrypted training data, the data decryption unit 207 is used to decompress and decrypt the data. According to the decrypted training data, the data fusion unit 208 checks the type of the data, and then obtains the training data of the corresponding database by searching the master database 211 to perform data fusion. 3 to 4 below are mainly used to describe the steps of database search, data fusion, and location estimation.

FIG. 3 shows the structure of a hive pattern training data. In this mode, the cell sub-database 115 is searched using the extracted CGI code parameter as a key (step 302). The results are described below:

1. If the CGI code parameter is an existing state (step 303). The data fusion unit 208 acquires the training data of the secondary database 115 (step 304), performs fusion of the secondary database training data and the hive pattern training data, and returns the fused data to the secondary database 115 (step 305). After receiving the fusion data, the sub-database 115 performs update storage, and records the location information of the cell base station as an update status (step 306);

2. If the CGI code parameter is a non-existing state (step 303). The data fusion unit 208 directly transmits the hive pattern training data to the secondary database 115 (step 307 ). After receiving the training data, the sub-database 115 stores and records the location information of the cell base station as an unknown state (step 308 ).

3. The sub-database 115 checks the location information status of the cell base station. If the record of the location information is in an updated state, the secondary database 115 regularly sends the training data of the cell base station to the location calculation unit 209 (step 310 ). If the record of the location information is in an unknown state, the secondary database 115 immediately sends the training data of the cell base station to the location calculation unit 209 (step 309 ). The position solving unit 209 can establish clusters according to the received training data, and use an RF signal clustering algorithm to perform position estimation (step 311 ). The RF signal refers to the received signal strength value. The position calculating unit 209 returns the estimated cell base station position to the secondary database 115 . After receiving the location information, the secondary database 115 performs storage and records the status of the location information as a known state (step 312 ).

Figure 4 shows the architecture of a mixed-type training data. In this mode, the extracted CGI code parameter of the cell base station is used as the first key value, and the MAC address parameter of the WiFi AP is used as the second key value to search the hybrid secondary database 116 (step 402 ). The results are described below:

1. If both the CGI code parameter and the MAC address parameter are in an existing state (step 403). The data fusion unit 208 obtains the training data of the secondary database 116 (step 404 ), performs fusion of the secondary database training data and the hybrid training data, and returns the fused data to the secondary database 116 (step 405 ). After receiving the fusion data, the secondary database 116 executes update storage, and records the location information of the WiFi AP as an update status (step 406);

2. If both the CGI code parameter and the MAC address parameter are in a non-existing state (step 403). The data fusion unit 208 directly transmits the mixed-type training data to the secondary database 116 (step 407 ). After receiving the training data, the secondary database 116 stores and records the location information of the WiFi AP as an unknown state (step 408 ).

3. The secondary database 116 checks the location information status of the WiFi AP. The steps of obtaining the location estimate of the WiFi AP location calculation unit 210 are as described above (steps 409 , 410 , 411 ). The location calculation unit 210 returns the estimated WiFi AP location to the secondary database 116 . After receiving the location information, the secondary database 116 performs storage and records the status of the location information as a known state (step 412 ).

It should be noted that, in the embodiment of the present invention, in the training data stored in the hybrid secondary database 116 , one MAC address parameter key may correspond to multiple CGI code parameter keys. The cloud data computing server 113 is equipped with a data decryption unit 207 , a data fusion unit 208 , a cell base station position calculation unit 209 and a WiFi AP position calculation unit 210 .

FIG. 5 is a schematic diagram of a positioning solution subsystem in an embodiment of the present invention. A mobile device 112 is equipped with a receiving unit 501 , a location classification unit 502 , a data encryption unit 503 and a first location selection unit 504 . When the device exists in the outdoor target area of the hybrid wireless network, location information is required at any time, and at this time, positioning data is obtained through the receiving unit 501 . This location data may include the following:

1. GPS location coordinates. The GPS location coordinates of the device are acquired through a GPS receiver (not shown) in the receiving unit 501 . If the GPS location coordinates exist, the location coordinates are stored in the first location selection unit 504 .

2. CGI code parameters and signal strength values of the cell base station. A presence state of a cell base station signal is detected by the receiving unit 501, and the CGI code parameter and the measured signal strength value can be extracted according to the cell base station signal. The cell base station is a service type cell base station (106 in FIG. 1).

3. MAC address parameter and signal strength value of WiFi AP. A presence state of a WiFi AP signal is detected by the receiving unit 501 , and MAC address parameters and a measured signal strength value can be extracted according to the signal of the AP. The AP is a link type AP (such as 109 in FIG. 1 ).

According to the cell base station and WiFi AP signals detected by the receiving unit 501, the positioning classification unit 502 performs the classification of positioning data types. For example, if no WiFi AP signal is detected, the positioning data type is a cellular positioning type. . If no cell base station signal is detected, the positioning data type is WiFi positioning type. Otherwise, the positioning data type is a mixed positioning type, that is, the signals of the cell base station and the WiFi AP are detected at the same time. Before connecting the cellular or WiFi wireless network 505 (such as 106 or 109 in FIG. 1 ) to transmit the positioning data to the cloud positioning computing server 114 through the API, the data encryption unit 503 is used to perform compression and encryption on the data . After the cloud location computing server 114 receives the encrypted location data, the data decryption unit 506 is used to perform decompression and decryption on the data, and check the location data type of the decrypted location data, according to the defined type The state transmits the decrypted positioning data to the position solving units. Then, the training data of the corresponding database is obtained by searching the main database 211 , and the training data of the database are sent to the position calculation units to perform position estimation. The following FIGS. 6 to 8 are mainly used to describe the steps of database search and location estimation.

FIG. 6 shows a cellular positioning data type structure. In this mode, the CGI code parameter of the cell base station of the service category extracted by the receiving unit 501 is used as a key value, and the search of the cellular secondary database 115 is performed to obtain the corresponding location information and location information of the cell base station. Training data (step 602). The position information of the cell base station is sent to the second position selection unit 509 of the cloud positioning calculation server 114 for storage (step 603), and the training data of the cell base station is sent to the first position calculation unit of the cloud positioning calculation server 114 507 (step 604). The training data includes two classes: service class and neighbor class. If the training data of the service category exists, a cluster of the training data is established (steps 605, 607). If the training data of the service category does not exist, a cluster of the training data of the neighbor category is established (steps 605, 606). The first position calculating unit 507 uses the RF signal clustering algorithm according to the established cluster to estimate the position of the mobile device 112 (step 608 ). The RF signal refers to a received signal strength value. The estimated location information is sent to the second location selection unit 509 of the cloud location computing server 114 for storage (step 609 ).

FIG. 7 shows a structure of a WiFi positioning data type. In this mode, the MAC address parameter of the linked AP extracted by the receiving unit 501 is used as a key value, and the search of the hybrid secondary database 116 is performed to obtain the location information and training data of the corresponding WiFi AP (step 702 ). The location information of the WiFi AP is sent to the second location selection unit 509 of the cloud positioning computing server 114 for storage (step 703), and the training data of the WiFi AP is sent to the second location computing unit 508 of the cloud positioning computing server 114 ( Step 704). The training data includes two classes: linked and unlinked. Based on the training data of the linked and unlinked categories, the estimated location of the mobile device 112 is obtained by the second location calculating unit 508 , and the steps are as described above (steps 705 to 708 ). The estimated location information is sent to the second location selection unit 509 of the cloud location computing server 114 for storage (step 709 ).

FIG. 8 shows a hybrid location data type architecture. In this pattern, the database search and position estimation are described as follows:

1. Use the CGI code parameter of the service type cell base station extracted by the receiving unit 501 as a key value, and execute the search of the cellular secondary database 115 (step 802). The steps of obtaining the location of the cell base station and estimating the location of the mobile device 112 are as described above. The location information is sent to the second location selection unit 509 of the cloud location computing server 114 for storage (steps 603 to 609).

2. Use the CGI code parameter of the service type cell base station extracted by the receiving unit 501 as a first key value, and the MAC address parameter of a WiFi link AP as a second key value, and perform the search of the mixed secondary database 116 (step 803). The steps of obtaining the location of the WiFi AP and estimating the location of the mobile device 112 are as described above. The location information is sent to the second location selection unit 509 of the cloud location computing server 114 for storage (steps 703 to 709).

The cloud location calculation server 114 is equipped with a data decryption unit 506 , a first location calculation unit 507 , a second location calculation unit 508 and a second location selection unit 509 .

FIG. 9 is a flow chart of an embodiment of a positioning method according to the present invention. According to the existence state of the cell base station (106 in FIG. 1 ) and the WiFi AP signal (109 in FIG. 1 ) detected by the receiving unit 501, a plurality of positioning methods are provided by the cloud positioning calculation server 114, including the base station (CGI) positioning method, base station assisted RSS (CGI-RSS) positioning method, AP (MAC) positioning method and AP assisted RSS (MAC-RSS) positioning method. In operation, the cloud positioning calculation server 114 can select a corresponding positioning method according to the result of the positioning data type defined by the mobile device 112 . Under the honeycomb positioning data type (step 901), based on the extracted CGI code parameters, use the CGI positioning method (step 902), based on the extracted CGI code parameters and the measured signal strength value, use CGI-RSS Positioning method (step 903). Under the WiFi positioning data type (step 904), based on the extracted MAC address parameters, use the MAC positioning method (step 905), based on the extracted MAC address parameters and the measured signal strength value, use MAC-RSS Positioning method (step 906). Under the hybrid positioning data type (step 907), use the CGI-RSS positioning method (step 908) based on the extracted CGI code parameters and the measured signal strength value, based on the extracted CGI code parameters and MAC address parameters , and the measured signal strength value, using the MAC-RSS positioning method (step 909). Each positioning method is assigned a priority and provides location information, and the weights of the CGI-RSS and MAC-RSS positioning methods are generally higher. The second location selection unit 509 of the cloud location calculation server 114 stores the location information provided by each location method, and can select a high-weight location information from the location information and send it back to the mobile device 112 . After the mobile device receives the location information, the first location selection unit stores the location information.

A plurality of location information is provided for the mobile device 112 according to the presence status of the GPS signal detected by the receiving unit 501 . The first location selection unit 304 stores the location information. If the receiving unit 501 does not detect a presence state of the GPS signal (step 910), the first location selection unit 304 selects a location information sent back by the cloud positioning computing server 114 to determine a location of the device (step 911 ). If the receiving unit 501 detects that the GPS signal is present, before obtaining the GPS position coordinates (step 912), the first position selection unit 504 selects a position information returned by the cloud positioning calculation server 114 to determine the device of a location. Once the GPS location coordinates are obtained (step 912), the first location selecting unit 504 selects GPS location information to determine a location of the device (step 913).

The above-mentioned method of the present invention, or a specific system unit or part thereof, is a pure software architecture, and can be deployed on a physical medium through program code, such as a hard disk, a floppy disk, a CD, or any machine-readable (such as a smart phone, computer-readable) storage medium, when the machine loads and executes the program code, such as a smart phone loads and executes, the machine becomes a device for implementing the present invention. The above-mentioned method and device of the present invention can also be transmitted in the form of program code through some transmission media, such as cables, optical fibers, or any transmission mode. When the program code is received, loaded and executed by a machine, such as a smart phone, the machine Become a device for implementing the present invention.

The basic principles, main features and advantages of the present invention have been shown and described above. Those skilled in the industry should understand that the present invention is not limited by the above-mentioned embodiments. What are described in the above-mentioned embodiments and the description only illustrate the principle of the present invention. Without departing from the spirit and scope of the present invention, the present invention will also have Variations and improvements are possible, which fall within the scope of the claimed invention. The protection scope of the present invention is defined by the appended claims and their equivalents.

Claims (37)

1. The system for realizing hybrid positioning in cloud server is characterized in that, said system is based on GPS satellite and terrestrial radio system, including A data training subsystem, including a mobile training device and a cloud data computing server, the mobile training device is used to acquire training data, and transmit the training data to the cloud data computing server, and the data computing server calculates based on the training data a location of the detected access point; A positioning calculation subsystem, including a mobile device and a cloud positioning computing server, the mobile device is used to obtain positioning data, and transmit the positioning data to the cloud positioning computing server, and the cloud positioning computing server transmits the positioning data based on the positioning data Obtaining training data of the corresponding database by searching the main database, and the cloud location computing server calculates a position of the mobile device based on the training data of the database; A master database is used to store training data, record location information and status of calculated detection access points. 2. The system for realizing hybrid positioning on a cloud server according to claim 1, wherein the terrestrial radio system is a cellular network system and a WiFi network system. 3. The system for implementing hybrid positioning on a cloud server according to claim 1, wherein the mobile training device is a smart phone or a personal digital assistant. 4. The system for realizing hybrid positioning on a cloud server according to claim 3, wherein the mobile training device further comprises: a receiving unit for measuring training data; a data buffer unit for storing the training data; a data classification unit for classifying the types and categories of the training data; a data encryption unit for compressing and encrypting the training data; a backup database for storing the encrypted training data. 5 . The system for implementing hybrid positioning on a cloud server according to claim 4 , wherein the training data are a GPS position coordinate and a plurality of detected access point signals. 6 . 6. The system for realizing hybrid positioning on a cloud server according to claim 5, wherein the plurality of detected access points at least include a plurality of detected cell base stations and a plurality of detected WiFi APs , wherein each cell base station signal includes a CGI code parameter and a signal strength value, and each WiFi AP signal includes a MAC address parameter and a signal strength value. 7. The system for realizing hybrid positioning on a cloud server according to claim 1, wherein the types of the training data are divided into a honeycomb type and a mixed type, and the honeycomb type training data mainly Record GPS position coordinates, CGI code parameters and signal strength values; the mixed type training data mainly records GPS position coordinates, CGI code parameters, MAC address parameters and signal strength values. 8. The system according to claim 7 in which a cloud server realizes hybrid positioning, wherein the class distinction of the training data type comprises: the training data of the same CGI code parameter is divided into The service category and the neighbor category, the hybrid type is divided into the link category and the unlink category for the training data of the same MAC address parameter. 9. The system for implementing hybrid positioning on a cloud server according to claim 7, wherein the primary database includes a cellular secondary database and a hybrid secondary database. 10. The system for realizing hybrid positioning on a cloud server according to claim 9, wherein the data computing server includes: a data decryption unit for decompressing and decrypting the training data; a data fusion A unit for performing main database search and data fusion according to the data type of the decrypted training data; a cell base station position calculation unit for calculating the position of the detected cell base station based on the training data of the main database; a WiFi The AP location calculation unit calculates the location of the detected WiFi AP based on the training data of the master database. 11. The system according to claim 10 in which hybrid positioning is realized on a cloud server, wherein the searching and fusion of the honeycomb pattern training data comprises the following steps: Use the CGI code parameter as a key value to execute the search of the hive secondary database; If the CGI code parameter is an existing state, execute the fusion of the database training data and the honeycomb pattern training data, and return the fusion data to the database for update and storage, and record the location information of the cell base station as a update status; If the CGI code parameter is in a non-existing state, directly transmit the hive pattern training data to the secondary database for storage, and record the location information of the cell base station as an unknown state. 12. The system for realizing hybrid positioning on a cloud server according to claim 10, wherein the search and fusion of the hybrid training data comprises the following steps: Using the CGI code parameter as a first key value and the MAC address parameter as a second key value, perform the search of the hybrid secondary database; If both the CGI code and the MAC address parameters are in an existing state, perform the fusion of the database training data and the mixed type training data, and return the fusion data to the database for update and storage, and record the location of the WiFi AP The information is an update status; If both the CGI code and the MAC address parameters are in a non-existing state, the mixed type training data is directly sent to the secondary database for storage, and the location information of the WiFi AP is recorded as an unknown state. 13. The system according to claim 10 in which hybrid positioning is implemented on a cloud server, wherein the calculation of the position of the detected cell base comprises the following steps: The cell sub-database checks the location information status of the cell base station; If the record of the position information is in an updated state, the database periodically transmits the training data of the cell base station to the cell base station position calculation unit to perform position estimation, and records the state of the position information as a known state; If the record of the position information is in an unknown state, the sub-database immediately transmits the training data of the cell base station to the cell base station position calculation unit to perform position estimation, and records the state of the position information as a known state. 14. The system for implementing hybrid positioning on a cloud server according to claim 13, wherein the location calculation method is an RF signal clustering algorithm, wherein the RF signal is a received signal strength value. 15. The system according to claim 10, wherein the cloud server realizes hybrid positioning, wherein the calculation of the detected WiFi AP position comprises the following steps: The hybrid secondary database checks the location information status of the WiFi AP; If the record of the location information is in an updated state, the database periodically transmits the training data of the WiFi AP to the WiFi AP location calculation unit to perform location estimation, and records that the location information state is a known state; If the record of the location information is in an unknown state, the secondary database immediately sends the training data of the WiFi AP to the WiFi AP location calculation unit to perform location estimation, and records the state of the location information as a known state. 16 . The system for implementing hybrid positioning on a cloud server according to claim 15 , wherein the location calculation method is an RF signal clustering algorithm, wherein the RF signal is a received signal strength value. 17. The system for implementing hybrid positioning on a cloud server according to claim 1, wherein the mobile device is one of a mobile phone, a smart phone, a PDA, a notebook computer, and a tablet computer. 18. The system for implementing hybrid positioning on a cloud server according to claim 17, wherein the mobile device further comprises: a receiving unit for measuring positioning data; a positioning classification unit for performing the positioning Distinguishing data types; a data encryption unit for performing compression and encryption of the positioning data; a first location selection unit, which can select one of the location information from a plurality of location information to determine a location of the device Location. 19. The system for implementing hybrid positioning on a cloud server according to claim 18, wherein the positioning data at least includes a GPS position coordinate, a specific cell base station signal and a specific WiFi AP signal. 20 . The system for implementing hybrid positioning on a cloud server according to claim 19 , wherein if the GPS location coordinates are in an existing state, the location coordinates are stored in the first location selection unit. 21 . 21. The system for realizing hybrid positioning on a cloud server according to claim 19, wherein the specific cell base station is a serving base station of the mobile device, wherein the serving base station signal is a CGI code parameter and A signal strength value. 22. The system for implementing hybrid positioning on a cloud server according to claim 19, wherein the specific WiFi AP is a link AP of the mobile device, wherein the link AP signal is a MAC address parameter and a signal strength value. 23. The system for realizing hybrid positioning on a cloud server according to claim 18, wherein the positioning data types are a cellular type, a WiFi type, and a hybrid type, wherein The honeycomb positioning data mainly records the CGI code parameters and signal strength values of a serving cell base station; Described WiFi positioning data mainly records the MAC address parameter and the signal strength value of a WiFi link AP; The mixed positioning data mainly records the CGI code parameter and signal strength value of a serving cell base station and the MAC address parameter and signal strength value of a WiFi link AP. 24. The system for implementing hybrid positioning on a cloud server according to claim 9, wherein the positioning calculation server further comprises: a data decryption unit for decompressing and decrypting the positioning data; a first A location calculation unit, used to estimate the location information of the mobile device; a second location calculation unit, used to estimate the location information of the mobile device; a second location selection unit, which can select the location information from a plurality of location information Wait for one of the location information, and return the location information to the first location selection unit of the mobile device. 25. The system for implementing hybrid positioning on a cloud server according to claim 24, wherein the first position calculating unit estimates the position information of the mobile device based on cellular positioning data, comprising the following steps: Use the CGI code parameter as a key value to execute the search of the hive secondary database; Obtain the location information and training data of the corresponding cell base station, wherein the location information is sent to the second location selection unit for storage, and the training data is sent to the first location calculation unit; The training data includes a service category and a neighbor category, wherein if the training data of the service category is in an existing state, a cluster of the training data is established; otherwise, a cluster of the training data of the neighbor category is established; Using an RF signal clustering algorithm based on the established cluster to estimate the location of the mobile device, wherein the RF signal refers to a received signal strength value; The estimated location information is sent to the second location selection unit for storage. 26. The system for implementing hybrid positioning on a cloud server according to claim 24, wherein the second position calculating unit estimates the position information of the mobile device based on WiFi positioning data, comprising the following steps: Use the MAC address parameter as a key value to perform a search of the hybrid secondary database; Obtaining corresponding location information and training data of the WiFi AP, wherein the location information is sent to the second location selection unit for storage, and the training data is sent to the second location calculation unit; The training data includes a linked category and an unlinked category, wherein if the training data of the linked category is in an existing state, a cluster of the training data is established, otherwise, a cluster of the unlinked category of training data is established; Using an RF signal clustering algorithm based on the established cluster to estimate the location of the mobile device, wherein the RF signal refers to a received signal strength value; The estimated location information is sent to the second location selection unit for storage. 27. The system for implementing hybrid positioning on a cloud server according to claim 24, wherein the first position calculating unit estimates the location information of the mobile device based on hybrid positioning data, comprising the following steps: Use the CGI code parameter as a key value to search the hive secondary database; Obtain the location information and training data of the corresponding cell base station, wherein the location information is sent to the second location selection unit for storage, and the training data is sent to the first location calculation unit; The training data includes a service category and a neighbor category, wherein if the training data of the service category is in an existing state, a cluster of the training data is established; otherwise, a cluster of the training data of the neighbor category is established; Using an RF signal clustering algorithm based on the established cluster to estimate the location of the mobile device, wherein the RF signal refers to a received signal strength value; The estimated location information is sent to the second location selection unit for storage. 28. The system for implementing hybrid positioning on a cloud server according to claim 27, wherein the second location calculating unit estimates the location information of the mobile device based on the hybrid positioning data, further comprising the following steps: Use the CGI code parameter as a first key value and the MAC address parameter of a WiFi link AP as a second key value to perform the search of the mixed secondary database; Obtaining corresponding location information and training data of the WiFi AP, wherein the location information is sent to the second location selection unit for storage, and the training data is sent to the second location calculation unit; The training data includes a linked category and an unlinked category, wherein if the training data of the linked category is in an existing state, a cluster of the training data is established, otherwise, a cluster of the unlinked category of training data is established; Using an RF signal clustering algorithm based on the established cluster to estimate the location of the mobile device, wherein the RF signal refers to a received signal strength value; The estimated location information is sent to the second location selection unit for storage. 29. A method for implementing hybrid positioning on a cloud server, characterized in that the method is implemented based on the system for implementing hybrid positioning on a cloud server according to any one of claims 1-28, and is applied to mobile devices to meet the needs of different locations. The seamless retrieval of location-based services in the environment includes the following steps: Select a piece of location information according to the plurality of location information stored in the second location selection unit, and send it back to the first location selection unit in the mobile device; A piece of location information is selected to determine a location of the mobile device according to a plurality of location information stored by the first location selection unit. 30. The method for realizing hybrid positioning on a cloud server according to claim 29, wherein the plurality of position information stored by the second position selection unit is obtained by corresponding plurality of positioning methods, including a base station positioning When the receiving unit of the mobile device only detects a CGI code parameter of a serving cell base station, the base station positioning method is used, wherein the location information is the position of the serving cell base station. 31. The method for realizing hybrid positioning on a cloud server according to claim 30, wherein the plurality of positioning methods also include a base station-assisted RSS positioning method, when the receiving unit of the mobile device simultaneously detects a The CGI code parameters and signal strength values of the serving cell base station use the base station-assisted RSS positioning method, wherein the first position calculation unit is based on the training data of the cellular secondary database in the main database, using the received signal strength The value determines this location information. 32. The method for implementing hybrid positioning on a cloud server according to claim 30, wherein the plurality of positioning methods also include an AP positioning method, when the receiving unit of the mobile device only detects a link to an AP When the MAC address parameter is used, the AP positioning method is used, wherein the location information is the location of the WiFi AP. 33. The method for realizing hybrid positioning on a cloud server according to claim 30, wherein the plurality of positioning methods also include an AP-assisted RSS positioning method, when the receiving unit of the mobile device simultaneously detects a link The AP's MAC address parameter and signal strength value are used by the AP-assisted RSS positioning method, wherein the second location calculation unit uses the received signal strength value to determine the location information based on the training data of the mixed secondary database. 34. The method for implementing hybrid positioning on a cloud server according to claim 29, wherein the second location selection unit stores a plurality of location information, and selects a location according to the positioning data type defined by the mobile device Information, sent back to the first location selection unit, including: A honeycomb positioning data type, the plurality of position information can be obtained by using the base station positioning method and the base station assisted RSS positioning method, and select a high-weight position information based on the weight value assigned by the positioning method; A WiFi positioning data type, which can use the AP positioning method and the AP-assisted RSS positioning method to obtain the plurality of position information, and select a high-weight position information based on the weight assigned to the positioning method; A mixed positioning data type, the plurality of position information can be obtained by using the base station positioning method, the base station-assisted RSS positioning method, the AP positioning method and the AP-assisted RSS positioning method, and select a high weight based on the weight value assigned to the positioning method Value location information. 35. The method for implementing hybrid positioning on a cloud server according to claim 29, wherein the plurality of location information stored by the first location selection unit includes a GPS location coordinate, wherein the receiving unit of the mobile device detects A presence status of the GPS signal. 36. The method for implementing hybrid positioning on a cloud server according to claim 29, wherein the plurality of location information stored by the first location selection unit further includes a plurality of location information returned by the second location selection unit The location information, wherein the location information is obtained from one of a base station positioning method, a base station-assisted RSS positioning method, an AP positioning method, and an AP-assisted RSS positioning method. 37. The method for implementing hybrid positioning on a cloud server according to claim 29, wherein the first location selection unit stores a plurality of location information, and selects one according to the signal existence status detected by the receiving unit of the mobile device. location information to determine a location of the device, including: If a presence state of the GPS signal is detected and the GPS location coordinates are obtained, the first location selection unit outputs the GPS location coordinates to determine a location of the device; If a presence state of the GPS signal is detected and the GPS position coordinates have not yet been obtained, the first position selection unit outputs a position information returned by the second position selection unit to determine a position of the device; If a non-existing state of the GPS signal is detected, the first position selection unit outputs a position information sent back by the second position selection unit to determine a position of the device.