Business scene identification method, electronic equipment and storage medium
Scene recognition is performed through base station information, replacing cloud query, solving the problems of high power consumption and poor real-time performance in electronic device scene recognition, and realizing low power consumption and high real-time service scenario recognition.
Patent Information
- Application Number
- CN202411180585.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2022-10-26
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2042-10-26
AI Technical Summary
In the prior art, electronic devices need to frequently query location information from cloud service platforms when performing scene recognition, resulting in high power consumption and poor real-time performance.
By obtaining the base station information currently accessed by the electronic device, scene identification is performed based on the scene feature data and base station information, determining whether the device is located in the target scenario, using base station positioning, reducing data comparison with cloud service platform, reducing power consumption and Improve real-time.
It realizes low-power business scenario recognition, improves real-time recognition, saves power consumption of electronic devices, and improves user experience.
Smart Images

Figure CN118945815A_ABST
Abstract
Description
[0001] This application is a divisional application of the Chinese patent application submitted to the State Intellectual Property Office on October 26, 2022, with application number 202211320411.X and application name "Business Scenario Identification Method, Electronic Device and Storage Medium". Technical Field
[0002] The present application relates to the field of terminal technology, and in particular to a business scenario recognition method, an electronic device, and a storage medium. Background Art
[0003] In daily life, in some scenes such as companies, canteens, cinemas, shopping malls, railway stations, airports, schools, hospitals, scenic spots, etc., users usually need electronic devices to continuously perform scene recognition to determine the relationship between their location and the scene, so as to facilitate some quick services through electronic devices. For example, when an electronic device (such as a mobile phone) recognizes that a user has entered a canteen, a payment code quick card will automatically pop up on the mobile phone interface, so that when the user buys food in the canteen, he can quickly complete the payment based on the payment code quick card.
[0004] In the related art, when a service triggers an electronic device to perform scene recognition, the electronic device locates the current location information and sends the location information to a cloud service platform. The cloud service platform stores a large number of scene features about different scenes. The cloud service platform queries whether the corresponding location is in the target scene based on the received location information and feeds back the result to the electronic device.
[0005] However, since electronic devices need to query their location from the cloud service platform every time, power consumption is high and real-time performance is poor. Summary of the invention
[0006] The present application provides a business scene recognition method, an electronic device and a storage medium. The business scene recognition method can realize low-power business scene recognition and can effectively improve the real-time performance of business scene recognition.
[0007] In a first aspect, the present application provides a service scene identification method, which is executed by an electronic device, and the method includes: when a scene identification request for a target service is monitored, obtaining base station information of a base station to which the electronic device is currently connected, the base station information including a target operator identifier, a target cell number, and a target base station number, the scene identification request is used to request identification of whether the electronic device is located in a target scene associated with the target service; performing scene identification based on scene feature data and base station information to determine whether the electronic device is located in the target scene, the scene feature data including at least one base station fence snapshot, the base station fence snapshot including an operator identifier, a cell number, and a base station number with an associated relationship.
[0008] When the scene recognition accuracy includes high accuracy, it is detected that the base station information matches the operator identifier, cell number and base station number in a base station fence snapshot, and the base station fence snapshot includes a scene fence identifier; the target scene fence snapshot is determined according to the scene fence identifier in the base station fence snapshot that matches the base station information; the target scene fence snapshot includes a WiFi feature; the fence area corresponding to the target scene fence snapshot is determined; the current position of the electronic device is obtained; if the current position is detected to be within the fence area, the WiFi list of the electronic device is obtained; if it is detected that the WiFi list matches the WiFi feature, it is determined that the electronic device is located in the target scene.
[0009] Optionally, the target scene fence snapshot includes latitude and longitude information of the center point of the scene fence and a radius of the scene fence, and the fence area is determined according to the latitude and longitude information of the center point of the scene fence and the radius of the scene fence in the target scene fence snapshot.
[0010] Optionally, the base station information of the base station currently accessed by the electronic device may be obtained by Cell-ID positioning.
[0011] Optionally, the target business may be a regular payment business, a ticket collection business, a QR code business, a ticket purchase business, etc.
[0012] Optionally, an operator identifier, a cell number, and a base station number that are associated with each other are used to uniquely identify a base station.
[0013] Optionally, the base station fence snapshot may also include latitude and longitude information of a center point of the base station fence and a radius of the base station fence.
[0014] The business scene identification method provided in the first aspect, when monitoring the scene identification request of the target business, obtains the base station information of the base station currently connected to the electronic device, and performs scene identification based on the scene feature data and the base station information to determine whether the electronic device is located in the target scene. Among them, the scene feature data includes at least one base station fence snapshot, the base station fence snapshot includes an operator identifier, a cell number and a base station number with an associated relationship, and the base station information includes a target operator identifier, a target cell number and a target base station number. Obviously, scene identification based on scene feature data and base station information is to compare the operator identifier, cell number, base station number in the base station fence snapshot with the target operator identifier, target cell number and target base station number in the base station information. That is to say, this method determines whether the electronic device is located in the target scene by comparing the base station information with the base station fence snapshot. In the process of business scene identification, the base station information is used, and there is no need to request the cloud service platform to obtain the location, and compared with the use of GPS positioning in the relevant technology, the power consumption of base station positioning is less than that of GPS positioning. In this method, there is no need to compare with the data in the cloud service platform, thereby reducing the power consumption of the electronic device and improving the real-time performance.
[0015] For services with high scene recognition accuracy, when the base station information of the electronic device matches a base station fence snapshot in the base station fence snapshot set, and the current location of the electronic device is within the fence area corresponding to a scene fence snapshot (a scene fence snapshot determined by the scene fence identifier in the base station fence snapshot), and the WiFi list matches the WiFi feature in the scene fence snapshot, it can be identified that the electronic device has entered a service scene with high scene recognition accuracy, with high real-time performance. Based on this, quick cards can be recommended to users immediately, which improves the intelligence of electronic devices, meets the user's usage needs, and improves user experience.
[0016] In the process of high-precision business scene recognition, on the one hand, Cell-ID positioning is used in the early stage (that is, Cell-ID positioning is used before matching with the scene fence snapshot), and GPS positioning and WiFi scanning are used in the later stage, which saves power consumption while maintaining recognition accuracy. On the other hand, there is no need to request the cloud service platform during the business scene recognition process, which also saves power consumption.
[0017] Optionally, the scene feature data may be data sent to the electronic device based on a feature acquisition request sent by the electronic device to the cloud service platform. The electronic device caches the scene feature data in a local database in advance.
[0018] In one possible implementation, when it is detected that the scene recognition accuracy of the target service is low, scene recognition is performed based on scene feature data and base station information to determine whether the electronic device is located in the target scene, including: if the base station information matches the operator identifier, cell number and base station number in a base station fence snapshot, it is determined that the electronic device is located in the target scene.
[0019] In this implementation, for services with low scene recognition accuracy, as long as the base station information of the electronic device matches a base station fence snapshot in the base station fence snapshot set, it can be identified that the electronic device has entered a service scene with low scene recognition accuracy, with high real-time performance. Based on this, quick cards can be immediately recommended to users, which improves the intelligence of electronic devices, meets the user's usage needs, and improves user experience.
[0020] In the process of low-precision business scene recognition, on the one hand, the power consumption of electronic devices using Cell-ID positioning is less than that of using GPS positioning. Therefore, the base station information of the electronic device is matched with the base station fence snapshot to identify whether the electronic device has entered a business scene with low scene recognition accuracy, saving power consumption. On the other hand, there is no need to request the cloud service platform during the business scene recognition process, which also saves power consumption.
[0021] Optionally, if a base station fence snapshot matching the base station information is not found in the scene feature data, it is determined that the electronic device is not currently located in the target scene associated with the target service. For example, if the operator identifier, cell number, and base station number in a base station fence snapshot are not found in the scene feature data, and are the same as the target operator identifier, target cell number, and target base station number in the base station information, it is determined that the electronic device is not currently located in the target scene associated with the target service.
[0022] In one possible implementation, when it is detected that the scene recognition accuracy of the target service is low, scene recognition is performed based on scene feature data and base station information to determine whether the electronic device is located in the target scene. It may also include: if the base station information does not match the operator identification, cell number and base station number in any base station fence snapshot, then determining the target area according to the target service, the target area is the area corresponding to the destination, and the destination is the location where the target service is implemented; obtaining the current location of the electronic device; if it is detected that the current location of the electronic device is within the target area, determining that the electronic device is located in the target scene.
[0023] In this implementation method, before the base station information of the electronic device matches any base station fence snapshot, it is possible to determine whether the current location of the electronic device is within the target area through the current location information of the electronic device and the target area, thereby identifying whether the electronic device has entered a business scene with low scene recognition accuracy, providing support for cold start of low-precision business scene recognition.
[0024] Optionally, the base station fence snapshot may further include a scene fence identifier. The scene feature data may further include at least one scene fence snapshot, the scene fence snapshot including the latitude and longitude information of the scene fence center point with an associated relationship and the scene fence radius.
[0025] In one possible implementation, when it is detected that the scene recognition accuracy of the target service is medium accuracy, scene recognition is performed based on scene feature data and base station information to determine whether the electronic device is located in the target scene, including: if the base station information matches the operator identifier, cell number and base station number in a base station fence snapshot, then the target scene fence snapshot is determined according to the scene fence identifier in the base station fence snapshot that matches the base station information; the fence area is determined according to the latitude and longitude information of the scene fence center point and the scene fence radius in the target scene fence snapshot; the current position of the electronic device is obtained; if it is detected that the current position of the electronic device is within the fence area, it is determined that the electronic device is located in the target scene.
[0026] In this implementation, for services with medium scene recognition accuracy, when the base station information of the electronic device matches a base station fence snapshot, and the current position of the electronic device is within the fence area corresponding to a scene fence snapshot (a scene fence snapshot determined by the scene fence identifier in the base station fence snapshot), it can be identified that the electronic device has entered a service scene with medium scene recognition accuracy, with high real-time performance. Based on this, shortcut cards can be immediately recommended to users, which improves the intelligence of electronic devices, meets user usage needs, and improves user experience. And when the base station information of the electronic device matches a base station fence snapshot in a base station fence snapshot set, it detects whether the current position of the electronic device is within the fence area corresponding to a scene fence snapshot, and then starts medium-precision service scene recognition, effectively avoiding the waste of power consumption of medium-precision service scene recognition.
[0027] In the process of medium-precision business scene recognition, on the one hand, Cell-ID positioning is used in the early stage (that is, Cell-ID positioning is used before matching with the scene fence snapshot), and there is no need to use GPS positioning throughout the process, which saves power consumption. On the other hand, there is no need to request the cloud service platform during the business scene recognition process, which also saves power consumption.
[0028] Optionally, obtaining the current position of the electronic device may include: obtaining the current position of the electronic device through a global satellite positioning system, which can ensure the accuracy of the current position of the electronic device, thereby improving the accuracy of business scenario recognition.
[0029] Optionally, the WiFi list includes at least one WiFi identification information and the WiFi strength corresponding to each WiFi identification information.
[0030] In one possible implementation, if it is detected that the WiFi list matches the WiFi feature of the target scene fence snapshot, it is determined that the electronic device is located in the target scene, including: determining a matching threshold corresponding to the WiFi list; if it is detected that the WiFi identification information in the WiFi list matches the WiFi identification information list in the WiFi feature, and the matching threshold is greater than or equal to the target matching threshold, it is determined that the electronic device is located in the target scene.
[0031] Optionally, if it is detected that the WiFi list matches the WiFi feature of the target scene fence snapshot, then it is determined that the electronic device is located in the target scene. It may also include: if the WiFi identification information in the WiFi list and the WiFi strength corresponding to each WiFi identification information match each WiFi identification information in the WiFi identification information list in the WiFi feature and the WiFi strength corresponding to each WiFi identification information, then it is determined that the electronic device is located in the target scene.
[0032] In this implementation, the accuracy of the results of matching the WiFi list with the WiFi features is improved, which is conducive to improving the accuracy of business scenario recognition.
[0033] Optionally, the WiFi list may be obtained by using WiFi hitchhiking technology, where the WiFi hitchhiking technology refers to obtaining WiFi scanning results generated by the system or a third-party application, and the WiFi scanning results may include a WiFi list.
[0034] In one possible implementation, the business scenario identification method provided by the present application may also include: if it is detected that the WiFi list does not match the WiFi features of the target scene fence snapshot, obtaining a WiFi list generated by a third-party application; if it is detected that the WiFi list generated by the third-party application matches the WiFi features of the target scene fence snapshot, determining that the electronic device is located within the target scene.
[0035] In this implementation, when the WiFi list does not match the WiFi characteristics, WiFi-related data is obtained using WiFi hitchhiking technology without performing a separate WiFi scan, which effectively saves power consumption.
[0036] In one possible implementation, when the scene recognition accuracy of the target service is detected to be high, scene recognition is performed based on scene feature data and base station information to determine whether the electronic device is located in the target scene. It may also include: if it is detected that the WiFi list of the electronic device matches the WiFi feature in any scene fence snapshot, it is determined that the electronic device is located in the target scene.
[0037] In this implementation, when the scene recognition accuracy of the target business is high, if the WiFi list is detected to match a WiFi feature, the electronic device is immediately identified as being in the target scene, which improves the real-time performance of business scene recognition and saves the power consumption required for early positioning.
[0038] In one possible implementation, the business scenario identification method provided by the present application may also include: obtaining the motion state of a user carrying an electronic device; predicting the user's first motion speed based on the motion state; determining a destination for implementing the target business based on the target business, and determining a first distance between the user's current position and the destination; and predicting the time of the next positioning based on the first motion speed and the first distance.
[0039] Optionally, the user's current motion state may include a walking state, a running state, a fast walking state, a driving state, etc.
[0040] In this implementation, the movement speed is evaluated according to the user's current movement status, and then the time for the next positioning is predicted based on the movement speed and the distance to the destination. During the entire process, there is no need to use GPS positioning all the time, which greatly reduces the number of positioning times and reduces power consumption.
[0041] In one possible implementation, the business scenario identification method provided by the present application may also include: if during the movement of the electronic device, it is detected that the base station information of the base station to which the electronic device is currently connected matches the target base station fence snapshot, then the user's position is determined based on the longitude and latitude information of the center point of the base station fence of the target base station fence snapshot; the second distance is determined based on the user's position and destination; the user's second movement speed is determined, and the time for the next positioning is updated based on the second movement speed and the second distance.
[0042] In this implementation, the next positioning time is constantly refreshed according to the snapshot of the base station fence matched during the user's movement. During the whole process, there is no need to use GPS positioning all the time. While maintaining the accuracy of business scene recognition, the number of positioning times and power consumption are greatly reduced. And as the learning of scene features increases, the scene feature data is constantly improved. In the later stage, no matter where the user wants to go, the number of times GPS positioning is used is getting less and less. For the realization of business scene recognition, the overall power consumption that can be saved is increasing.
[0043] In a possible implementation, the business scene recognition method provided by the present application may also include: when the electronic device is in the target scene, obtaining the latest position of the electronic device; and determining whether the electronic device has left the target scene through the latest position. This implementation can effectively avoid misidentification and improve the accuracy of business scene recognition, that is, accurately determine whether the electronic device has actually left the target scene associated with the target business through the latest position, thereby bringing a better experience to the user.
[0044] In a possible implementation, the service scenario identification method provided in the present application may further include: when it is detected that the electronic device is stationary, the electronic device stops positioning and / or stops scanning WiFi, which can effectively save power consumption.
[0045] In a possible implementation, the business scenario identification method provided in the present application may also include: when it is detected that the movement range of the electronic device is less than or equal to a preset range, the electronic device stops positioning and / or stops scanning WiFi, which can effectively save power consumption.
[0046] Optionally, the present application also provides a WIFI chip, which can be installed in an electronic device. The method used by the WIFI chip when scanning WIFI is different from the method used for scanning WIFI in the related art, so that the scanning power consumption of the WIFI chip is much lower than that of the existing WIFI chip. Business scenario recognition is performed based on the WIFI chip, which greatly reduces the scanning power consumption.
[0047] Optionally, the present application also provides a method for collecting scene crowdsourcing data, including: a first application in an electronic device executes a first business; a perception module in the electronic device obtains business data of the first business; the perception module in the electronic device collects current environmental data of the electronic device; the perception module reports a collected data set to a cloud service platform, the collected data set includes environmental data and business data, so that the cloud service platform can perform cloud computing, thereby learning scene features based on these data.
[0048] Optionally, the present application also provides a method for learning scene features, which is usually performed by a cloud service platform, and includes: constructing a grid map based on the spatial data of the earth's surface; mapping the scene crowdsourcing data into the grid map; determining the scene fence snapshot corresponding to each business; and determining the base station fence snapshot of each base station. This method provides a basis for subsequent business scene recognition.
[0049] Optionally, the scene crowdsourcing data may include multiple scene collection data sets, each scene collection data set may include business data and environmental data collected by the electronic device when implementing the corresponding business, each scene collection data set corresponds to a business type, and each scene collection data set includes longitude and latitude information.
[0050] Optionally, determining the scene fence snapshot corresponding to each business may include: determining points with the same attribute in the grid map; clustering the points with the same attribute to obtain a first clustering result, wherein the first clustering result includes at least one cluster; determining the longitude and latitude information of the center point of the scene fence according to the first clustering result; determining the radius of the scene fence according to the first clustering result; generating a scene fence snapshot based on the longitude and latitude information of the center point of the scene fence, the radius of the scene fence, the business type information, and the city code corresponding to the business type information. This method provides a basis for subsequent business scene identification.
[0051] Optionally, the points belonging to the same attribute are points corresponding to a scene acquisition data set belonging to the same attribute, and the same attribute means that the business type information is the same and the city code is the same.
[0052] Optionally, determining the base station fence snapshot of each base station may include: determining points belonging to the same base station in the grid map; clustering the points of the same base station to obtain a second clustering result, the second clustering result including at least one cluster; determining the longitude and latitude information of the center point of the base station fence according to the second clustering result; determining the radius of the base station fence according to the second clustering result; generating the base station fence snapshot based on the longitude and latitude information of the center point of the base station fence, the radius of the base station fence, the base station indication information, and the city code corresponding to the base station. This method provides a basis for subsequent business scenario identification.
[0053] Optionally, the points belonging to the same base station are points corresponding to a scene acquisition data set belonging to the same base station, and the same base station means that the base station indication information is the same, that is, the operator identifier, cell number and base station number are the same.
[0054] In a second aspect, the present application provides a device, which is included in an electronic device, and has the function of implementing the electronic device behavior in the above-mentioned first aspect and the possible implementation of the above-mentioned first aspect. The function can be implemented by hardware, or it can be implemented by hardware executing corresponding software. The hardware or software includes one or more modules or units corresponding to the above-mentioned functions. For example, a monitoring module or unit, a processing module or unit, etc.
[0055] In a third aspect, the present application provides an electronic device, comprising: a processor, a memory, and an interface; the processor, the memory, and the interface cooperate with each other so that the electronic device executes any one of the methods in the technical solution provided in the first aspect.
[0056] In a fourth aspect, the present application provides a chip, including a processor. The processor is used to read and execute a computer program stored in a memory to perform the method in the first aspect and any possible implementation thereof.
[0057] Optionally, the chip also includes a memory, and the memory is connected to the processor via a circuit or wire.
[0058] Optionally, the chip also includes a communication interface.
[0059] Optionally, the WIFI chip provided in this application may also be integrated into the chip.
[0060] In a fifth aspect, the present application provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the processor executes any one of the methods in the technical solution of the first aspect.
[0061] In a sixth aspect, the present application provides a computer program product, the computer program product comprising: a computer program code, when the computer program code runs on an electronic device, the electronic device executes any one of the methods in the technical solution of the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS
[0062] Figure 1 A schematic diagram of an application scenario shown as an exemplary embodiment of the present application;
[0063] Figure 2 A schematic diagram of a process of opening a payment code is shown as an exemplary embodiment of the present application;
[0064] Figure 3 A schematic diagram of an application scenario shown in another exemplary embodiment of the present application;
[0065] Figure 4 A schematic diagram of a process of opening a QR code is shown as an exemplary embodiment of the present application;
[0066] Figure 5 A schematic diagram of an application scenario shown as another exemplary embodiment of the present application;
[0067] Figure 6 is a schematic diagram of a system architecture shown in an exemplary embodiment of the present application;
[0068] Figure 7 is a schematic diagram of the structure of an electronic device shown in an exemplary embodiment of the present application;
[0069] Figure 8 is a software structure block diagram of an electronic device shown in an exemplary embodiment of the present application;
[0070] Fig. 9 is a flow chart of an electronic device collecting scene crowdsourcing data shown in an exemplary embodiment of the present application;
[0071] Fig.10 is a flow chart of a method for learning scene features shown in an exemplary embodiment of the present application;
[0072] Fig.11 is a schematic diagram of a grid diagram shown in an exemplary embodiment of the present application;
[0073] Fig.12 is a schematic diagram of another grid diagram shown in an exemplary embodiment of the present application;
[0074] Fig.13 is a schematic diagram of data distribution shown in an exemplary embodiment of the present application;
[0075] Fig.14 is a schematic diagram of cache scene features shown in an exemplary embodiment of the present application;
[0076] Fig.15 is a flow chart of a business scenario identification method shown in an exemplary embodiment of the present application;
[0077] Fig.16 is a flow chart of a method for predicting the time of the next positioning shown in an exemplary embodiment of the present application;
[0078] Fig.17 is a schematic diagram of an application scenario of predicting time shown in an exemplary embodiment of the present application;
[0079] Fig.18 is a schematic diagram of another application scenario of predicting time shown in an exemplary embodiment of the present application;
[0080] Fig.19 is a schematic diagram of switching positioning modes shown in an exemplary embodiment of the present application;
[0081] Fig. 20 It is a schematic diagram showing power consumption and real-time changes according to an exemplary embodiment of the present application. DETAILED DESCRIPTION
[0082] The technical solution in this application will be described below in conjunction with the accompanying drawings.
[0083] In the description of the embodiments of the present application, unless otherwise specified, " / " means or, for example, A / B can mean A or B; "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present application, "multiple" means two or more than two.
[0084] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this embodiment, unless otherwise specified, "plurality" means two or more.
[0085] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.
[0086] First, some terms in the embodiments of the present application are explained to facilitate understanding by those skilled in the art.
[0087] 1. Coarse positioning service, also known as Cell-ID positioning or base station positioning. Cell-ID positioning is to determine the location of a mobile phone based on the location of the cellular base station to which the electronic device (such as a mobile phone) is currently connected. When a user moves with a mobile phone, the user's location is almost the same as the location of the mobile phone, so the location of the mobile phone is usually determined as the user's location.
[0088] 2. Point of Interest (POI), each POI contains at least four basic information: name, address, category, latitude and longitude coordinates. For example, a POI can represent a house, a shop, a community entrance, a mailbox, a bus stop, etc.
[0089] 3. Area of Interest (AOI), also known as information surface, is mainly used to represent regional geographical entities in map data. For example, an AOI can represent a residential area, a university, an office building, a comprehensive shopping mall, a scenic spot, a railway station, etc.
[0090] 4. Spatial clustering algorithm (DBSCAN) is an unsupervised clustering algorithm. This algorithm divides areas with sufficient density into clusters, and defines a cluster as the largest set of density-connected points.
[0091] 5. Morton coding is an algorithm for encoding rasters.
[0092] 6. Global Positioning System (GPS) is a high-precision radio navigation positioning system based on artificial satellites. It can provide accurate geographic location, vehicle speed and precise time information anywhere in the world and in near-Earth space.
[0093] The above is a brief introduction to the terms involved in the embodiments of the present application, which will not be repeated below.
[0094] With the rapid development of electronic devices, users have more and more demands on electronic devices. In some scenarios, users hope that electronic devices can automatically realize certain quick services through scene recognition. For example, taking the electronic device as a mobile phone, when the user enters the airport, the user hopes that the mobile phone can automatically pop up a reminder card with information such as the waiting hall, flight number, airline, etc. in the interface. When the user enters the hospital, the user usually hopes that the mobile phone can automatically display the QR code in the interface. When the user enters the company cafeteria, the user hopes that the mobile phone can automatically pop up the payment code in the interface.
[0095] In order to achieve scene recognition, the electronic device is usually required to determine the associated service and its own location. For example, when a service pre-associated in the electronic device triggers the electronic device to perform scene recognition, the electronic device locates the current location information and then sends the location information to the cloud service platform. The cloud service platform stores a large number of scene features about different scenes. The cloud service platform queries whether the corresponding location is in the target scene based on the received location information and feeds the result back to the electronic device.
[0096] In this implementation, the electronic device needs to request the cloud service platform every time, resulting in high power consumption and poor real-time performance. To this end, an embodiment of the present application provides a business scene recognition method, which can realize low-power business scene recognition and effectively improve the real-time performance of business scene recognition.
[0097] Before introducing the business scenario identification method provided by the embodiment of the present application in detail, several possible application scenarios (such as companies, canteens, cinemas, shopping malls, railway stations, airports, schools, hospitals, scenic spots, etc.) involved in the embodiment of the present application are introduced. The embodiment of the present application takes the electronic device as an example, and describes several possible application scenarios.
[0098] In an example, see Figure 1 , Figure 1 This is a schematic diagram of an application scenario shown in an exemplary embodiment of the present application. For example, the mobile phone used by user A supports regular payment services, and user A eats in the company cafeteria between 11:45 and 12:10 every weekday. Figure 1 As shown in the figure, user A carries a mobile phone and moves from position S1 to the company cafeteria at 11:40 am on a certain weekday. While user A is moving with the mobile phone, the mobile phone starts scene recognition with the screen on to determine whether user A has entered the company cafeteria. Afterwards, when user A enters the area where the company cafeteria is located, for example, user A moves to position S1. Figure 1 At the S2 position shown (such as the entrance to the company cafeteria), the mobile phone displays a card with a payment code in the main interface, so that user A can use the payment code to quickly pay when buying food.
[0099] For ease of understanding, the process of displaying the payment code is described in conjunction with the main interface of the mobile phone. Figure 2 , Figure 2 This is a schematic diagram of a process of opening a payment code according to an exemplary embodiment of the present application. For example, when user A is at his workstation or on the way to the company cafeteria, the main interface of the mobile phone is as follows Figure 2 As shown in (a), the file management icon 102 is displayed in the YOYO suggestion card 101 displayed on the main interface of the mobile phone. When user A enters the area where the company cafeteria is located, for example, when user A moves to the entrance of the company cafeteria, the mobile phone recommends the payment code quick card to the user. At this time, the main interface of the mobile phone is as follows Figure 2 As shown in (b), the payment code icon 103 is displayed in the YOYO suggestion card 101 displayed on the main interface of the mobile phone. The payment code icon 103 is a shortcut. When the user buys food, he can quickly jump to the payment code interface of the third party by clicking the payment code icon 103, as shown in FIG. Figure 2 As shown in (c) in the figure, quick payment can be achieved based on the payment code interface. After the payment is completed, the payment code quick card disappears automatically, and the main interface of the mobile phone is as follows: Figure 2 As shown in (d) in the figure, the file management icon 102 is displayed in the YOYO suggestion card 101 displayed on the main interface of the mobile phone.
[0100] Optionally, the payment code quick card can also be displayed above the main interface of the mobile phone. Figure 2 The payment code quick card is displayed in the place where the current time, date and day of the week are displayed as shown in (b).
[0101] In another example, see Figure 3 , Figure 3 This is a schematic diagram of an application scenario shown in another exemplary embodiment of the present application. During the epidemic, QR codes are required to enter public places and take public transportation. For example, the mobile phone used by user A supports the quick display of QR code services, and user A needs to take a bus from bus station BS1 to bus station BS2 between 7:25 and 7:35 on every weekday, and then walk from bus station BS2 to work. Figure 3 As shown, at 7:20 on weekdays, the mobile phone starts scene recognition. When the mobile phone determines that user A has moved to position S3, which is one hundred meters away from bus stop BS1, the mobile phone displays a card with a QR code in the main interface. In this way, the user can quickly display the QR code before getting on the bus.
[0102] For ease of understanding, the process of displaying a QR code is described in conjunction with the main interface of a mobile phone. Figure 4 , Figure 4 This is a schematic diagram of a process of opening a QR code according to an exemplary embodiment of the present application. For example, when user A is on the way to bus station BS1, the main interface of the mobile phone is as follows Figure 4 As shown in (a), the file management icon 202 is displayed in the YOYO suggestion card 201 displayed on the main interface of the mobile phone. The mobile phone starts scene recognition at 7:20 on weekdays. When the mobile phone determines that user A has moved to the S3 position 100 meters away from the bus stop BS1, it recommends the QR code shortcut card to the user. At this time, the main interface of the mobile phone is as follows Figure 4 As shown in (b), a QR code icon 203 is displayed in the YOYO suggestion card 201 displayed on the main interface of the mobile phone. The QR code icon 203 is a shortcut. The user clicks the QR code icon 203 to quickly jump to the QR code interface of the third party. Figure 4 In the interface shown in (c) of FIG. 1 , the user clicks the “My Electronic Code” control in the interface to jump to the following Figure 4 The QR code interface shown in (d) in the figure can be used to quickly display the QR code to the driver. After the display is completed, the QR code interface can be exited, and the QR code shortcut card will automatically disappear. The main interface of the mobile phone is as follows: Figure 4 As shown in (e) in FIG. 1 , a file management icon 202 is displayed in a YOYO suggestion card 201 displayed on the main interface of the mobile phone.
[0103] Optionally, the QR code may be a boarding code. For example, the boarding code icon is displayed at the location where the QR code icon 203 was originally displayed on the main interface of the mobile phone. The boarding code icon is a shortcut, and the user can quickly go to the boarding code interface of the third party by clicking the boarding code icon. In this way, the user can directly swipe the card through the boarding code on the boarding code interface after getting on the bus.
[0104] In another example, see Figure 5 , Figure 5 This is a schematic diagram of an application scenario for another exemplary embodiment of the present application. For example, the mobile phone used by user A supports quick display of ticket purchase services, and user A often watches movies at cinema B. Suppose the user goes to cinema B to watch a movie one day. Figure 5 As shown, when the user moves to the entrance of Cinema B with a mobile phone, the mobile phone automatically displays a movie ticket purchase icon 302 in the recommendation card 301 on the negative one screen. The movie ticket purchase icon 302 is a shortcut. The user clicks on the movie ticket purchase icon 302, and the mobile phone responds to the user's click operation and jumps to the ticket purchase page, so that the user can purchase movie tickets based on the ticket purchase page.
[0105] For ease of understanding, the following briefly introduces the system architecture involved in the embodiments of the present application. Figure 6 , Figure 6 1 is a schematic diagram of a system architecture shown in an exemplary embodiment of the present application, wherein the system architecture includes an electronic device 400 and a cloud service platform 500. A communication connection is established between the electronic device 400 and the cloud service platform 500.
[0106] The electronic device 400 can perform scene recognition for some businesses so as to automatically implement some quick functions when it determines that it has entered certain specific scenes, such as automatically displaying a QR code card, automatically displaying a boarding code card, automatically displaying a payment code card, etc.
[0107] As an example of the present application, the electronic device 400 has the ability to access a mobile communication network and can support at least one network type. Exemplarily, the electronic device 400 can support a third generation (3G network), a fourth generation (4G) network, a fifth generation (5G) network, etc. The electronic device 400 provided in the embodiment of the present application can be a mobile phone, a tablet computer, a wearable device, a laptop computer, a netbook, a portable terminal, etc. The embodiment of the present application does not impose any restrictions on the specific type of the electronic device 400.
[0108] The cloud service platform 500 is used to collect data based on scene crowdsourcing, that is, to collect scene crowdsourcing data and learn scene features corresponding to different businesses. In this way, the electronic device 400 can pull / acquire some scene features from the cloud service platform 500 according to needs, so as to be able to perform scene recognition for a certain business based on the pulled / acquired part of the scene features.
[0109] The cloud service platform 500 provided in the embodiment of the present application may include a server, such as a cloud server.
[0110] Optionally, the system structure may further include a map service cloud platform based on the electronic device 400 and the cloud service platform 500. The map service cloud platform can provide positioning services for the electronic device 400, and can also provide scene crowdsourcing data, etc. to the cloud service platform 500 according to the positioning results. In addition, the cloud service platform 500 can also order / acquire POI data, AOI data, etc. from the map service cloud platform.
[0111] The above briefly introduces the system architecture involved in the embodiment of the present application. The following briefly introduces the structure of the electronic device 400 involved in the embodiment of the present application. Figure 7 , Figure 7 4 is a schematic diagram of the structure of an electronic device shown in an exemplary embodiment of the present application. The electronic device 400 may include a processor 410, an external memory interface 420, an internal memory 421, a universal serial bus (USB) interface 430, a charging management module 440, a power management module 441, a battery 442, an antenna 1, an antenna 2, a mobile communication module 450, a wireless communication module 460, an audio module 470, a speaker 470A, a receiver 470B, a microphone 470C, an earphone interface 470D, a sensor module 480, a button 490, a motor 491, an indicator 492, a camera 493, a display screen 494, and a subscriber identification module (SIM) card interface 495, etc. The sensor module 480 may include a pressure sensor 480A, a gyroscope sensor 480B, an air pressure sensor 480C, a magnetic sensor 480D, an acceleration sensor 480E, a distance sensor 480F, a proximity light sensor 480G, a fingerprint sensor 480H, a temperature sensor 480J, a touch sensor 480K, an ambient light sensor 480L, a bone conduction sensor 480M, etc.
[0112] It is understood that the structure illustrated in the embodiment of the present application does not constitute a specific limitation on the electronic device 400. In other embodiments of the present application, the electronic device 400 may include more or fewer components than shown in the figure, or combine some components, or split some components, or arrange the components differently. The components shown in the figure may be implemented in hardware, software, or a combination of software and hardware.
[0113] The processor 410 may include one or more processing units, for example, the processor 410 may include an application processor (AP), a modem processor, a graphics processor (GPU), an image signal processor (ISP), a controller, a memory, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural-network processing unit (NPU), etc. Different processing units may be independent devices or integrated into one or more processors.
[0114] The controller may be the nerve center and command center of the electronic device 400. The controller may generate an operation control signal according to the instruction operation code and the timing signal to complete the control of fetching and executing instructions.
[0115] The processor 410 may also be provided with a memory for storing instructions and data. In some embodiments, the memory in the processor 410 is a cache memory. The memory may store instructions or data that the processor 410 has just used or cyclically used. If the processor 410 needs to use the instruction or data again, it may be directly called from the memory. This avoids repeated access, reduces the waiting time of the processor 410, and thus improves the efficiency of the system.
[0116] The wireless communication function of the electronic device 400 can be implemented through the antenna 1, the antenna 2, the mobile communication module 450, the wireless communication module 460, the modem processor and the baseband processor.
[0117] Antenna 1 and antenna 2 are used to transmit and receive electromagnetic wave signals. Figure 4 The structures of antenna 1 and antenna 2 in the electronic device 400 are only examples. Each antenna in the electronic device 400 can be used to cover a single or multiple communication frequency bands. Different antennas can also be reused to improve the utilization of the antennas. For example, antenna 1 can be reused as a diversity antenna for a wireless local area network. In some other embodiments, the antenna can be used in combination with a tuning switch.
[0118] The mobile communication module 450 can provide solutions for wireless communications including 2G / 3G / 4G / 5G, etc., applied to the electronic device 400. The mobile communication module 450 may include at least one filter, a switch, a power amplifier, a low noise amplifier (LNA), etc. The mobile communication module 450 can receive electromagnetic waves from the antenna 1, and filter, amplify, and process the received electromagnetic waves, and transmit them to the modulation and demodulation processor for demodulation. The mobile communication module 450 can also amplify the signal modulated by the modulation and demodulation processor, and convert it into electromagnetic waves for radiation through the antenna 1. In some embodiments, at least some of the functional modules of the mobile communication module 450 can be set in the processor 410. In some embodiments, at least some of the functional modules of the mobile communication module 450 can be set in the same device as at least some of the modules of the processor 410.
[0119] The modem processor may include a modulator and a demodulator. Among them, the modulator is used to modulate the low-frequency baseband signal to be sent into a medium-high frequency signal. The demodulator is used to demodulate the received electromagnetic wave signal into a low-frequency baseband signal. The demodulator then transmits the demodulated low-frequency baseband signal to the baseband processor for processing. After the low-frequency baseband signal is processed by the baseband processor, it is passed to the application processor. The application processor outputs a sound signal through an audio device (not limited to a speaker 470A, a receiver 470B, etc.), or displays an image or video through a display screen 494. In some embodiments, the modem processor may be an independent device. In other embodiments, the modem processor may be independent of the processor 410 and be set in the same device as the mobile communication module 450 or other functional modules.
[0120] The wireless communication module 460 can provide wireless communication solutions including wireless local area networks (WLAN) (such as wireless fidelity (Wi-Fi) networks), bluetooth (BT), global navigation satellite system (GNSS), frequency modulation (FM), near field communication (NFC), infrared (IR), etc., which are applied to the electronic device 400. The wireless communication module 460 can be one or more devices integrating at least one communication processing module. The wireless communication module 460 receives electromagnetic waves via the antenna 2, modulates the frequency of the electromagnetic wave signal and performs filtering, and sends the processed signal to the processor 410. The wireless communication module 460 can also receive the signal to be sent from the processor 410, modulate the frequency of it, amplify it, and convert it into electromagnetic waves for radiation through the antenna 2.
[0121] In some embodiments, the antenna 1 of the electronic device 400 is coupled to the mobile communication module 450, and the antenna 2 is coupled to the wireless communication module 460, so that the electronic device 400 can communicate with the network and other devices through wireless communication technology. The wireless communication technology may include global system for mobile communications (GSM), general packet radio service (GPRS), code division multiple access (CDMA), wideband code division multiple access (WCDMA), time-division code division multiple access (TD-SCDMA), long term evolution (LTE), BT, GNSS, WLAN, NFC, FM, and / or IR technology, etc. GNSS may include global positioning system (GPS), global navigation satellite system (GLONASS), Beidou navigation satellite system (BDS), quasi-zenith satellite system (QZSS) and / or satellite based augmentation system (SBAS). It is understood that in the embodiments of the present application, the hardware module in the positioning or navigation system may be referred to as a positioning sensor.
[0122] The electronic device 400 implements the display function through a GPU, a display screen 494, and an application processor. The GPU is a microprocessor for image processing, which connects the display screen 494 and the application processor. The GPU is used to perform mathematical and geometric calculations for graphics rendering. The processor 410 may include one or more GPUs, which execute program instructions to generate or change display information.
[0123] The display screen 494 is used to display images, videos, etc. The display screen 494 includes a display panel. The display panel can be a liquid crystal display (LCD), an organic light-emitting diode (OLED), an active-matrix organic light-emitting diode or an active-matrix organic light-emitting diode (AMOLED), a flexible light-emitting diode (FLED), Miniled, MicroLed, Micro-oLed, a quantum dot light-emitting diode (QLED), etc. In some embodiments, the electronic device 400 may include 1 or N display screens 494, where N is a positive integer greater than 1.
[0124] The external memory interface 420 can be used to connect an external memory card, such as a Micro SD card, to expand the storage capacity of the electronic device 400. The external memory card communicates with the processor 410 through the external memory interface 420 to implement a data storage function, such as storing music, video and other files in the external memory card.
[0125] The internal memory 421 can be used to store computer executable program codes, and the executable program codes include instructions. The processor 410 executes various functional applications and data processing of the electronic device 400 by running the instructions stored in the internal memory 421. The internal memory 421 may include a program storage area and a data storage area. Among them, the program storage area may store an operating system, an APP required for at least one function (such as a sound playback function, an image playback function, etc.), etc. The data storage area may store data created during the use of the electronic device 400 (such as audio data, a phone book, etc.), etc. In addition, the internal memory 421 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, a universal flash storage (UFS), etc.
[0126] The pressure sensor 480A is used to sense the pressure signal and can convert the pressure signal into an electrical signal. In some embodiments, the pressure sensor 480A can be set on the display screen 494. There are many types of pressure sensors 480A, such as resistive pressure sensors, inductive pressure sensors, capacitive pressure sensors, etc. The capacitive pressure sensor can be a parallel plate including at least two conductive materials. When a force acts on the pressure sensor 480A, the capacitance between the electrodes changes. The electronic device 400 determines the intensity of the pressure according to the change in capacitance. When a touch operation acts on the display screen 494, the electronic device 400 detects the touch operation intensity according to the pressure sensor 480A. The electronic device 400 can also calculate the touch position according to the detection signal of the pressure sensor 480A. In some embodiments, touch operations acting on the same touch position but with different touch operation intensities can correspond to different operation instructions. For example: when a touch operation with a touch operation intensity less than the first pressure threshold acts on the short message application icon, an instruction to view the short message is executed. When a touch operation with a touch operation intensity greater than or equal to the first pressure threshold acts on the short message application icon, an instruction to create a new short message is executed.
[0127] The acceleration sensor 480E can detect the magnitude of the acceleration of the electronic device 400 in all directions (generally three axes). When the electronic device 400 is stationary, the magnitude and direction of gravity can be detected. It can also be used to identify the posture of the electronic device and is applied to applications such as horizontal and vertical screen switching and pedometers.
[0128] It is understandable that the electronic device may further include a speed sensor. The speed sensor is used to obtain the moving speed of the electronic device.
[0129] The ambient light sensor 480L is used to sense the ambient light brightness. The electronic device 400 can adaptively adjust the brightness of the display screen 494 according to the perceived ambient light brightness. The ambient light sensor 480L can also be used to automatically adjust the white balance when taking pictures. The ambient light sensor 480L can also cooperate with the proximity light sensor 480G to detect whether the electronic device 400 is in a pocket to prevent accidental touch. Specifically in the method of the embodiment of the present application, the electronic device 400 can perform scene recognition based on the ambient light brightness sensed by the ambient light sensor 480L to determine whether the environmental scene (indoor scene or outdoor scene) where the electronic device 400 is located has changed.
[0130] The touch sensor 480K is also called a "touch panel". The touch sensor 480K can be set on the display screen 494, and the touch sensor 480K and the display screen 494 form a touch screen, also called a "touch screen". The touch sensor 480K is used to detect touch operations acting on or near it. The touch sensor can pass the detected touch operation to the application processor to determine the type of touch event. Visual output related to the touch operation can be provided through the display screen 494. In other embodiments, the touch sensor 480K can also be set on the surface of the electronic device 400, which is different from the position of the display screen 494.
[0131] The above briefly introduces the structure of the electronic device 400 involved in the embodiment of the present application. The following briefly introduces the software structure involved in the embodiment of the present application. Figure 8 , Figure 8 4 is a software structure diagram of an electronic device shown in an exemplary embodiment of the present application. The layered architecture divides the software into several layers, each layer has a clear role and division of labor. The layers communicate with each other through software interfaces. In some embodiments, the electronic device 400 is an Android system as an example for explanation. The Android system is divided into four layers, which are the application layer, the application framework layer, the Android runtime (Android runtime) and the system library, and the kernel layer from top to bottom.
[0132] The application layer can include a series of application packages. Figure 8 As shown, the application package may include applications such as camera, calendar, instant messaging, payment, ticket purchase, map, navigation, wireless local area networks (WLAN), music, and short message.
[0133] In addition to instant messaging services, instant messaging applications can also be used to implement QR code services, ride code services, etc. For example, instant messaging applications can be but are not limited to The payment application can be used to implement online payment services. For example, the payment application can be but is not limited to UnionPay, etc. The ticket purchase application can be used to implement the ticket purchase business, for example, it can include but is not limited to an application for purchasing movie tickets, an application for purchasing bus tickets or air tickets, etc.
[0134] The application framework layer provides an application programming interface (API) and a programming framework for the applications in the application layer. The application framework layer includes some predefined functions.
[0135] As an example of the present application, the application framework layer may include a business program module (also referred to as YOYO suggestion) for displaying a card on the screen of the electronic device 400 or controlling the disappearance of a card.
[0136] Optionally, the application framework layer may also include a decision module and a perception module. The perception module is used to send the generated business data to the notification decision module when it perceives that other applications and systems are performing a certain business. In addition, the perception module can also be used to perform scene recognition for a certain business. The decision module is used to manage business events based on business data, for example, requesting scene recognition from the perception module based on business data.
[0137] Optionally, the application framework layer may further include a general collection module, and the general collection module is used to collect environmental data.
[0138] Optionally, the application framework layer may also include a window manager, a content provider, a view system, a phone manager, a resource manager, a notification manager, etc. The window manager is used to manage window programs. The window manager can obtain the display screen size, determine whether there is a status bar, lock the screen, capture the screen, etc.
[0139] Content providers are used to store and retrieve data and make it accessible to applications. These data may include videos, images, audio, calls made and received, browsing history and bookmarks, phone books, etc.
[0140] The view system may include visual controls, such as controls for displaying text, controls for displaying images, etc. The view system may be used to construct the display interface of an application, and the display interface may be composed of one or more views, for example, a view for displaying a text message notification icon, a view for displaying text, and a view for displaying images.
[0141] The phone manager is used to provide communication functions for the electronic device 400, such as management of call status (including answering, hanging up, etc.).
[0142] The resource manager provides various resources for applications, such as localized strings, icons, images, layout files, video files, etc.
[0143] The notification manager enables applications to display notification information in the status bar. It can be used to convey notification-type messages and can disappear automatically after a short stay without user interaction. For example, the notification manager is used to notify the completion of downloads, message reminders, etc. The notification manager can also be a notification that appears in the system top status bar in the form of an icon or scroll bar text, such as notifications from applications running in the background. The notification manager can also be a notification that appears on the screen in the form of a dialog window, such as a text message prompt in the status bar, a beep, an electronic device vibrates, an indicator light flashes, etc.
[0144] Android Runtime includes core libraries and virtual machines. Android runtime is responsible for scheduling and management of the Android system. The core library consists of two parts: one is the function that the Java language needs to call, and the other is the Android core library. The application layer and the application framework layer run in the virtual machine. The virtual machine executes the Java files of the application layer and the application framework layer as binary files. The virtual machine is used to perform object life cycle management, stack management, thread management, security and exception management, and garbage collection.
[0145] The system library can include multiple functional modules, such as: surface manager, media library, 3D graphics processing library (such as OpenGL ES), 2D graphics engine (such as SGL), etc.
[0146] The surface manager is used to manage the display subsystem and provide the fusion of 2D and 3D layers for multiple applications.
[0147] The media library supports playback and recording of a variety of commonly used audio and video formats, as well as static image files, etc. The media library can support a variety of audio and video encoding formats, such as: MPEG4, H.264, MP3, AAC, AMR, JPG, PNG, etc.
[0148] The 3D graphics processing library is used to implement 3D graphics drawing, image rendering, compositing, and layer processing.
[0149] A 2D graphics engine is a drawing engine for 2D drawings.
[0150] The kernel layer is the layer between hardware and software. The kernel layer contains at least display driver, camera driver, audio driver, and sensor driver.
[0151] In addition, the electronic device 400 provided in the embodiment of the present application may also include but is not limited to a wireless fidelity (WiFi) chip, etc. The WiFi chip may be used to display a WiFi scanning function.
[0152] The above briefly introduces the software structure involved in the embodiment of the present application. The following introduces the process of collecting crowdsourced scene data involved in the embodiment of the present application. For example, during the implementation process, the electronic device 400 will collect environmental data of the surrounding environment when implementing the business, and report the collected environmental data and business data related to the business to the cloud service platform 500. The cloud service platform 500 collects the environmental data collected by crowdsourcing, as well as the business data related to the business, and performs cloud computing based on the collected data to determine the scene features corresponding to different businesses. In this way, the electronic device 400 can pull some scene features from the cloud service platform 500 according to actual needs to perform scene recognition for a certain business.
[0153] As an example of this application, please refer to Fig. 9 , Fig. 9 This is a flow chart of an electronic device collecting scene crowdsourcing data according to an exemplary embodiment of the present application. The process of an electronic device collecting scene crowdsourcing data may include: S601 to S604.
[0154] S601: A first application in an electronic device executes a first service.
[0155] The first service is any one of the multiple services supported by the electronic device for scene recognition, and the first application is an application that can implement the first service. For example, the first service may be a QR code service, a payment code service, a ride code service, etc., and the first application may be a WeChat application, an Alipay application, etc.
[0156] S602: The perception module obtains business data of the first business.
[0157] Exemplarily, the service data may include service type information. For example, the service type information is pay, which means that the first service currently being performed is a payment service.
[0158] Optionally, in a possible implementation manner, the service data may further include, but is not limited to, one or more of a service package name of the first service, service additional description information, and scene recognition accuracy.
[0159] The service package name is used to identify which application program implements the currently performed first service. For example, a payment service may be implemented by a WeChat application program, an Alipay application program, or a UnionPay application program.
[0160] The service additional description information can be used to identify some additional service information. Exemplarily, the service additional description information can be the store name associated with the first service. For example, in the case where the first service is a payment service, the service additional description information is used to identify the store name paid by the first service. In one example, the service additional description information can be a JSON-formatted string, such as {"payType":"qrcode","payee":"milk tea shop"}.
[0161] As an example of the present application, the scene recognition accuracy of services includes three levels: low, medium, and high. The scene recognition accuracy of different services is usually determined by the services themselves. For example, different scene recognition accuracies can be preset for different services according to different user requirements. Exemplarily, the scene recognition accuracy of the regular payment service can be low, the scene recognition accuracy of the QR code service can be medium, and the scene recognition accuracy of the ticket collection service can be high. This is only for illustrative purposes and is not limited thereto.
[0162] In one example, the perception module may include service collection plugins for multiple services, and each service collection plugin can be used to perceive a service and collect the service data generated by the service. For example, the perception module includes, but is not limited to, service collection plugins for QR code services, bus code services, regular payment services, ticket collection services, ticket purchase services, etc. When a certain application or system in the electronic device implements a service, the corresponding service collection plugin can perceive and obtain the service data of the service. In addition, the service collection plugin notifies the general collection module to collect environmental data.
[0163] For example, when the WeChat application in the electronic device presents a QR code, the service collection plugin corresponding to the QR code service can perceive this operation. At this time, the service collection plugin corresponding to the QR code obtains the relevant service data and notifies the general collection module to collect environmental data.
[0164] S603: The perception module collects the current environmental data of the electronic device.
[0165] The perception module collects environmental data through the general collection module. In one example, the environmental data can include base station indication information, longitude and latitude information, and city code.
[0166] Among them, the base station indication information is used to uniquely identify a base station, and the base station indication information can include an operator identifier (operator), a location area code (lac), and a cell identifier (cellid).
[0167] The longitude and latitude information may include longitude and latitude, and the longitude and latitude information may be determined by global positioning system (GPS) positioning or network positioning. The network positioning may be based on base station positioning to determine the longitude and latitude information, or may be based on base station and wireless network (Wireless Fidelity, WiFi) to determine the longitude and latitude information.
[0168] The city code is used to uniquely identify a city. For example, if the city code is 0755, the city code is used to identify Shenzhen. Another example is that the city code is 029, and the city code is used to identify Xi'an. The city code can be obtained by calling the geo interface based on the location based service (LBS).
[0169] In an example, the environmental data may also include at least one of positioning accuracy, data collection time, connected base station strength, positioning type, coordinate system type, device type, and base station type.
[0170] In one example, when the scene recognition of a business involves multiple different regions (for example, different countries), the environmental data may also include a region name, which is used to distinguish different regions.
[0171] In one example, the environmental data may further include the number of satellite searches, where the number of satellite searches is used to analyze whether the electronic device is currently indoors or outdoors.
[0172] In one example, for a service with medium precision requirement for scene recognition, the environment data may also include information of neighboring base stations. A neighboring base station is a base station adjacent to the currently connected base station, and the information of the neighboring base station may include the base station number, base station strength, etc. of the neighboring base station.
[0173] As an example of the present application, for a business with high precision requirements for scene recognition, the environmental data may also include WiFi data, where the WiFi data includes at least one WiFi identification information and the WiFi strength corresponding to each WiFi identification information. The WiFi identification information may be used to uniquely identify a WiFi hotspot. In one example, the WiFi identification information may include WiFi physical address information and WiFi name.
[0174] S604: The perception module reports the collected data set to the cloud service platform, where the collected data set includes environmental data and business data.
[0175] Exemplarily, after acquiring the business data and environmental data, the perception module can generate scene crowdsourcing data based on the business data and environmental data, and the scene crowdsourcing data includes multiple scene collection data sets, each of which can include latitude and longitude information, base station information, WiFi data, and business type information, etc. The perception module sends the generated scene crowdsourcing data to the cloud service platform so that the cloud service platform can perform cloud computing.
[0176] As an example of the present application, for each element in each scene collection data set, different field types can be set according to requirements. For example, the elements and field types of the elements included in each scene collection data set are shown in Table 1.
[0177] Table 1
[0178]
[0179] It should be noted that the above is an example of electronic devices collecting data in a default manner. In another example, the cloud service platform can also send different collection configuration information to electronic devices according to the scene recognition accuracy required by different businesses to instruct the electronic devices how to collect data for different businesses. In one example, please refer to Table 2, the collection configuration information may include business type, collection level, maximum number of collections per day, etc.
[0180] Table 2
[0181]
[0182]
[0183] The collection level is also the scene recognition level of the service, that is, the scene recognition accuracy of the service. After the cloud service platform configures the collection level for the electronic device, the electronic device is informed whether it needs to collect WiFi data. For example, if the collection level is low (for example, 0), WiFi data does not need to be collected, but if the collection level is high (for example, 2), WiFi data needs to be collected.
[0184] The maximum number of data collections per day indicates the maximum number of data collections performed by the electronic device for the configured service per day. In this way, the power consumption of the electronic device during data collection can be controlled, thereby saving the collection power consumption of the electronic device.
[0185] Further, please refer to Table 2, the collection configuration information may also include service description information. The service description information is used to explain the service so that the user can view it intuitively. For example, the service description information may be location-based ride-hailing, regular payment, QR code, etc. It is worth noting that when an electronic device runs a third-party application (an application that requires positioning operations), it will also generate base station indication information, longitude and latitude information, positioning accuracy, WiFi scan results (such as WiFi lists), etc. Obtaining the base station indication information, longitude and latitude information, positioning accuracy, WiFi scan results (such as WiFi lists), etc. generated by these applications is called location-based ride-hailing.
[0186] For similar electronic devices, while implementing the business, the scene crowdsourcing data related to the business can be determined according to the above process, and the scene crowdsourcing data can be reported to the cloud service platform. In this way, the cloud service platform can obtain a large amount of scene crowdsourcing data through the crowdsourcing collection mode. On this basis, the cloud service platform can use these scene crowdsourcing data to learn the scene characteristics corresponding to different businesses.
[0187] The following describes how to use the collected scene collection data sets to learn the scene features corresponding to different services. As an example of this application, please refer to Fig.10 , Fig.10 This is a flow chart of a method for learning scene features shown in an exemplary embodiment of the present application. The method is usually executed by a cloud service platform. In a possible implementation, the method can also be executed by an electronic device. The method may include S701 to S704:
[0188] S701: Construct a raster map based on the spatial data of the earth's surface.
[0189] In one example, the spatial data on the earth's surface may include longitude and latitude information, and a grid map may be constructed by Morton coding based on the longitude and latitude information in the spatial data on the earth's surface. It can be generally understood that the earth's surface is divided into a grid map. The grid map may include multiple levels of grids, and each level of grid corresponds to a Morton code. For example, the grid map may include a kilometer-level group granularity grid and a hundred-meter-level fine-grained grid. Exemplarily, the longitude and latitude information of a location point in the physical space is Morton-coded, so that the location point is mapped to the grid of the grid map.
[0190] For easier understanding, please refer to Fig.11 , Fig.11 is a schematic diagram of a grid map shown in an exemplary embodiment of the present application. Here, it is assumed that the data in the base station and the data within the WiFi coverage area are mapped into the grid map, as shown in FIG. Fig.11As shown in (a), the dashed line is the data within the base station coverage area, and the solid line is the data within the WiFi coverage area. Fig.11 After the local area in (a) is enlarged, it is as follows Fig.11 As shown in (b), it can be seen that some grids only include base station data. At this time, it can be understood that the electronic device is only connected to the base station covering this grid at the location points included in these grids; some grids include both base station data and WiFi data. At this time, it can be understood that the electronic device is not only connected to the base station covering this grid, but also connected to the WiFi covering this grid at the location points included in these grids.
[0191] S702: Map the scene crowdsourcing data into a grid map.
[0192] The scene crowdsourcing data may include multiple scene collection data sets, each of which may be obtained through the above Fig. 9 The corresponding embodiment obtains that, according to the previous records, each scene collection data set may include business data and environmental data collected by the electronic device when implementing the corresponding business, each scene collection data set corresponds to a business type, and each scene collection data set includes longitude and latitude information.
[0193] As an example of the present application, the cloud service platform can perform Morton encoding on the longitude and latitude information in each scene collection data set to obtain the Morton code corresponding to the longitude and latitude information in each scene collection data set, and then map each scene collection data set into a grid map based on the Morton code.
[0194] As an example of the present application, the cloud service platform may also include POI data and AOI data, and both POI data and AOI data may include longitude and latitude information. The cloud service platform may map POI data to a grid map based on the longitude and latitude information in the POI data, and may also map AOI data to a grid map based on the longitude and latitude information in the AOI data.
[0195] For example, a POI data contains "_point": "POINT(114.064829 22.572986)". A AOI data contains POLYGON data: "_polygon": "MULTIPOLYGON(((114.064063
[0196] 22.573102,114.063954 22.572744,114.063946 22.572678,114.063946 22.572652,114.063954 22.572625,114.063964 22.572609,114.064751 22.572433,114.064795
[0197] 22.572432,114.064893……114.064063 22.573102)))”.
[0198] Map AOI data and POI data to the grid map respectively. For easy understanding, please refer to Fig.12 , Fig.12 FIG. 1 is a schematic diagram of another grid diagram shown in an exemplary embodiment of the present application. Fig.12 As shown, the grid set composed of the grids passed by each side of the irregular area and the grids covered in the irregular area is the expression of AOI data mapping in the grid map. It can be understood that AOI data corresponds to a grid set in the grid map. Fig.11 The independent circles in the figure are the expressions of multiple POI data mapped in the grid map respectively. It can be understood that one POI data corresponds to one grid in the grid map.
[0199] As an example of the present application, when the scene collection data set includes the data collection time, the cloud service platform can filter out the scene collection data set within the recent period, that is, filter out the scene collection data set that is far from the current time. Afterwards, the filtered scene collection data set is mapped to the grid map in the above manner, so that the scene features learned subsequently can be real-time and effective.
[0200] As an example of the present application, when the scene acquisition data set includes a coordinate system type, if the scene acquisition data set collected by crowdsourcing involves different coordinate system types (for example, the GCJ02 Mars coordinate system, the BD09 Baidu coordinate system, and the WGS84 Earth coordinate system), the cloud service platform may first unify the scene acquisition data sets under different types of coordinate systems into the same type of coordinate system before mapping the scene acquisition data set, for example, unify them all into the WGS84 Earth coordinate system, and then map the scene acquisition data set with the unified coordinate system type into a raster map, so that the mapping result can be more accurate.
[0201] As an example of the present application, when the scene acquisition data set includes a scene recognition level, the crowdsourced scene acquisition data set can also be screened based on the scene recognition level. Specifically, since the scene recognition accuracy of a certain business may change, for example, the scene recognition accuracy of a certain business is improved from low precision to high precision, in this case, if the scene feature learning is still based on the low-level scene acquisition data set, it is easy to cause inaccurate subsequent scene recognition. Therefore, the cloud service platform can filter out the scene acquisition data set with the same scene recognition level as the current scene recognition level of the business from the crowdsourced scene acquisition data set according to the scene recognition level, and then map the screened scene acquisition data set to the grid map in the above manner. This implementation method can enable the subsequent learned scene features to ensure the effectiveness and accuracy of scene recognition.
[0202] As an example of the present application, when the scene acquisition data set also includes the positioning type and the accuracy of the longitude and latitude information, some scene acquisition data sets can also be screened according to the positioning type and the accuracy of the longitude and latitude information. For example, the scene acquisition data sets with an accuracy lower than the accuracy threshold are filtered out, thereby filtering out some scene acquisition data sets with low confidence, to ensure the effectiveness and accuracy of subsequent scene feature learning. Among them, the accuracy threshold can be set according to actual needs, and there is no limitation on this.
[0203] As an example of the present application, when the scene collection data set also includes region names, the crowdsourced scene collection data set can be grouped according to the region names, with each group of scene collection data sets corresponding to a region name. Scene feature learning is then performed based on the groups as dimensions, that is, learning is performed by region, thereby improving the efficiency of subsequent scene feature learning.
[0204] S703: Determine the scene fence snapshot corresponding to each business.
[0205] Exemplarily, the scene fence snapshot of any business may include the scene features of this business in its corresponding scene, such as business type information, longitude and latitude information of the scene fence center point (i.e., the center point of the scene fence), scene fence radius (i.e., the radius of the scene fence), etc.
[0206] As an example of the present application, the specific implementation of the above S703 may include S7031 to S7035:
[0207] S7031: Determine points with the same attributes in the grid map.
[0208] Points with the same attribute are points corresponding to the scene collection data set with the same attribute, and the same attribute means the same business type information and the same city code. It can be understood that points with the same attribute are points corresponding to the scene collection data set with the same business type information and the same city code.
[0209] Exemplarily, using the business type information as an index, points corresponding to scene acquisition data sets having the same business type information and including the same city code are determined in the grid map.
[0210] As an example of the present application, since the same type of business may involve different cities, the cloud service platform can first use the city code as a dimension to bucket the data corresponding to the same type of business information, so as to divide the data of the same type of business in the same city into the same bucket. According to the previous records, each scene collection data set includes a business type information (ie, a tag) and a city code. Therefore, the cloud service platform can use the business type information as an index to query the points corresponding to the scene collection data set with the same business type information and the same city code in the raster map to bucket the data of these points and obtain at least one bucket, each bucket corresponding to a business type information and a city code. Feature learning can then be performed based on the data in each bucket to determine the scene fence snapshot of each business in a city.
[0211] To facilitate understanding and description, the following will take feature learning based on data in a bucket corresponding to any business type information as an example.
[0212] S7032: Clustering points with the same attribute to obtain a first clustering result, where the first clustering result includes at least one cluster.
[0213] Each point with the same attribute has longitude and latitude information, and the points with the same attribute are clustered by a clustering algorithm to obtain at least one cluster. It can also be understood that the longitude and latitude information corresponding to a business type information is clustered by a clustering algorithm to obtain at least one cluster.
[0214] For example, please refer to Fig.13 , Fig.13 is a schematic diagram of data distribution shown in an exemplary embodiment of the present application. Specifically, Fig.13 FIG. 1 is a schematic diagram showing the distribution of data in a grid map corresponding to a bucket of business type information according to an exemplary embodiment. The cloud service platform can cluster the longitude and latitude information of the points in the bucket using a clustering algorithm to obtain at least one cluster, such as Fig.13 As shown, three clusters are obtained. The clustering algorithm may be a spatial clustering algorithm (DBSCAN).
[0215] It is worth noting that the data outside the cluster can be considered as noise points and no calculation is required for these data. That is, the DBSCAN clustering algorithm can filter out the dirty data outside the cluster.
[0216] It should be noted that, in the process of using the DBSCAN clustering algorithm, the neighborhood radius can be set to a first preset distance, and the first preset distance can be set according to actual needs. For example, the first preset distance can be set to 50 meters, which means that for any two clusters, when the distance between the two closest points is greater than 50 meters, the DBSCAN clustering algorithm will determine that the two points are not related.
[0217] The scene fence center point and scene fence radius of a business type information can determine the scene fence corresponding to the business type information, that is, determine the scene fence corresponding to a business. It can be understood that a cluster corresponds to a scene fence. The following describes how to determine the scene fence center point and the latitude and longitude information of the scene fence center point.
[0218] S7033: Determine the longitude and latitude information of the center point of the scene fence based on the first clustering result.
[0219] Exemplarily, the center point of the scene fence of each cluster can be determined first. For example, for any one of the multiple clusters, the cloud service platform can determine the average value of all longitude and latitude information included in the cluster, and then calculate the longitude and latitude information of the center point of the cluster (i.e., the center point of the scene fence) based on the average value of all longitude and latitude information. In this way, the longitude and latitude information of the center point of each cluster in the multiple clusters (i.e., the center point of the scene fence) can be determined. That is, the longitude and latitude information of the center point of the scene fence of each business type information is obtained.
[0220] S7034: Determine the scene fence radius based on the first clustering result.
[0221] As an example of the present application, when the number of at least one cluster is one, the radius of the cluster is determined as the scene fence radius of the scene fence of the business type information. That is, when the number of clusters is one, the radius of the cluster is determined as the scene fence radius of the scene fence of the business type information.
[0222] As an example of the present application, when the number of at least one cluster is multiple, the radius of each cluster is determined as the scene fence radius of the scene fence corresponding to the business type information of each cluster.
[0223] S7035: Generate a scene fence snapshot based on the latitude and longitude information of the center point of the scene fence, the radius of the scene fence, the business type information, and the city code corresponding to the business type information.
[0224] Exemplarily, the city code corresponding to the business type information is obtained, and based on the latitude and longitude information of the center point of the scene fence corresponding to the business type information, the scene fence radius, the business type information and its corresponding city code, a scene fence snapshot of the scene fence of this business type information is generated.
[0225] During implementation, the scene fence can be determined in the grid map according to the latitude and longitude information of the center point of the scene fence and the radius of the scene fence, and then a scene fence snapshot is generated based on the data within the scene fence. As an example of the present application, the scene fence snapshot may include the scene fence identification, city code, latitude and longitude information (longitude information and latitude information) of the center point of the scene fence, fence radius, business type information, and Morton code within the scene fence.
[0226] Optionally, when the scene collection data set also includes the service package name and service additional description information, it can also be divided into buckets according to the city code, service package name and service additional description information. For example, for the same service, data occurring in the same city with the same service package name and service additional description information are divided into the same bucket. Afterwards, clustering is performed based on the data in each bucket.
[0227] In an example, if the scene fence in the grid image also includes a POI and / or an AOI, the scene fence snapshot may also include the POI and / or the AOI.
[0228] Optionally, the scene fence snapshot may also include WiFi features based on the fence identification, city code, longitude and latitude information of the scene fence center point (longitude information and latitude information), scene fence radius, business type information, Morton code within the scene fence, POI and / or AOI.
[0229] Exemplarily, if the bucket also includes WiFi data, the WiFi features in the scene fence can also be determined based on the WiFi data in the bucket. According to the previous records, the WiFi data can include multiple WiFi identification information and the WiFi strength corresponding to each WiFi identification information. In one example, the cloud service platform can determine the frequency of each WiFi identification information appearing in the bucket and obtain the frequency corresponding to each WiFi identification information. For WiFi identification information with a frequency lower than the frequency threshold, it may be a WiFi hotspot outside the scene and can be considered as dirty data. Therefore, the cloud service platform can delete the WiFi identification information with a frequency lower than the frequency threshold and its WiFi strength. Among them, the frequency threshold can be set according to demand and is not limited to this. Afterwards, the cloud service platform learns the WiFi features in the scene fence based on the remaining WiFi identification information in the bucket and the WiFi strength corresponding to each WiFi identification information in the remaining WiFi identification information.
[0230] In one example, the cloud service platform learns the WiFi features in the scene fence based on the remaining WiFi identification information list in the bucket and the WiFi strength corresponding to each WiFi identification information in the remaining WiFi identification information list. The specific implementation method may include: for each WiFi identification information in the remaining WiFi identification information list, the cloud service platform determines the average strength of the WiFi strength corresponding to each WiFi identification information, determines the strength matching degree of each WiFi strength corresponding to each WiFi identification information and the average strength corresponding to each WiFi identification information, obtains multiple strength matching degrees, sorts them in order from small to large in strength matching degrees, and obtains the nth strength matching degree from the sorted strength matching degrees as the target matching degree threshold of the remaining WiFi identification information list. The remaining WiFi identification information list, the average strength and frequency corresponding to each WiFi identification information in the remaining WiFi identification information list, and the target matching degree threshold corresponding to the remaining WiFi identification information list are used as the WiFi features in the scene fence.
[0231] In one example, when determining the intensity matching degree between each WiFi strength and the average intensity corresponding to each WiFi identification information, the cloud service platform can determine the Hellinger Distance between each WiFi strength and the average intensity corresponding to each WiFi identification information, and then use the obtained data as the intensity matching degree between each WiFi strength and the average intensity corresponding to each WiFi identification information.
[0232] Optionally, before learning the WiFi features within the scene fence, the cloud service platform can also filter some WiFi data in the bucket according to WiFi similarity. For example, the cloud service platform can determine the similarity of the longitude and latitude information of every two WiFi identification information, and then filter out the WiFi identification information whose similarity is lower than the similarity threshold. After that, the scene feature learning is performed based on the filtered WiFi data, which can improve the effectiveness and accuracy of the scene feature learning.
[0233] As an example of the present application, when the electronic device model is included in the collection data set, since the WiFi scanning stability of electronic devices of different models is different, if the scene fence includes WiFi data scanned by electronic devices of different models, in order not to lower the target matching threshold of WiFi data with stronger WiFi scanning stability, the cloud service platform can bucket the WiFi data according to the electronic device model, and then determine the target matching threshold corresponding to the WiFi identification information list in each bucket in the above manner based on the WiFi data in each bucket. It is not difficult to understand that at this time, the WiFi features in the scene fence include multiple WiFi identification information lists, and each WiFi identification information list corresponds to a target matching threshold.
[0234] Exemplarily, the scene fence snapshots may be as shown in Table 3, where each row represents a scene fence snapshot.
[0235] Table 3
[0236]
[0237] S704: Determine a base station fence snapshot of each base station.
[0238] Exemplarily, the base station snapshot of any base station may include the city code (citycode), operator identifier (operator), cell number (lac), base station number (cellID), longitude (longitude), latitude (latitude), radius (radius), service list (taglist), etc. of this base station.
[0239] As an example of the present application, the specific implementation of the above S704 may include S7041 to S7045:
[0240] S7041: Determine points belonging to the same base station in the grid map.
[0241] The points belonging to the same base station are points corresponding to the scene collection data set belonging to the same base station. The same base station means that the base station indication information is the same, that is, the operator identification, cell number and base station number are the same.
[0242] Exemplarily, the base station indication information is used as an index to determine the point corresponding to the scene acquisition data set belonging to the same base station in the grid map.
[0243] As an example of the present application, according to the previous records, each scene acquisition data set includes base station indication information. Therefore, the cloud service platform can use the base station indication information as an index to query the points corresponding to the scene acquisition data set belonging to the same base station in the raster map, and perform feature learning based on these points to determine the base station snapshot corresponding to each base station.
[0244] For ease of understanding and description, feature learning of points corresponding to a scene collection data set belonging to the same base station is taken as an example for explanation.
[0245] S7042: Cluster the points of the same base station to obtain a second clustering result, where the second clustering result includes at least one cluster.
[0246] Each point corresponding to the scene collection data set of the same base station has longitude and latitude information, and the points corresponding to the scene collection data set of the same base station are clustered by a clustering algorithm to obtain at least one cluster. That is, the longitude and latitude information of the points corresponding to the scene collection data set of the same base station are clustered by a clustering algorithm to obtain at least one cluster. The clustering algorithm may be a spatial clustering algorithm (DBSCAN).
[0247] It is worth noting that the data outside the cluster can be considered as noise points and no calculation is required for these data. That is, the DBSCAN clustering algorithm can filter out the dirty data outside the cluster.
[0248] It should be noted that, in the process of using the DBSCAN clustering algorithm, the neighborhood radius can be set to a second preset distance, and the second preset distance can be set according to actual needs. For example, the second preset distance can be set to 50 meters, which means that for any two clusters, when the distance between the two closest points is greater than 50 meters, the DBSCAN clustering algorithm will determine that the two points are not related.
[0249] The base station fence center point and base station fence radius corresponding to a base station can determine the base station fence corresponding to the base station. The following describes how to determine the base station fence center point and the latitude and longitude information of the base station fence center point.
[0250] S7043: Determine the longitude and latitude information of the center point of the base station fence according to the second clustering result.
[0251] Exemplarily, the center point of each cluster can be first determined, and then the longitude and latitude information of the center point of each cluster can be determined. The average value of the longitude and latitude information of the center points of multiple clusters is calculated, and the center point of the base station fence of the base station is determined based on the average value, and the longitude and latitude information of the center point of the base station fence is determined at the same time. Exemplarily, for any cluster among the multiple clusters, the cloud service platform can determine the average value of all the longitude and latitude information included in the cluster, so as to calculate the longitude and latitude information of the center point of the cluster based on the average value of all the longitude and latitude information. In this way, the longitude and latitude information of the center point of each cluster among the multiple clusters can be determined.
[0252] Afterwards, the cloud service platform can calculate the average latitude and longitude information of the center points of multiple clusters based on the latitude and longitude information of the center point of each cluster, and use the average latitude and longitude information of the center points of multiple clusters as the latitude and longitude information of the center point of the base station fence of this base station.
[0253] S7044: Determine the base station fence radius according to the second clustering result.
[0254] As an example of the present application, when the number of at least one cluster is one, the radius of the cluster is determined as the base station fence radius of the base station fence. That is, when the number of clusters is one, the radius of the cluster is determined as the base station fence radius of the base station fence of the one base station.
[0255] As an example of the present application, when the number of at least one cluster is multiple, the distance between the center point of the base station fence and the center point of each of the multiple clusters is determined to obtain multiple distances, and the base station fence radius of the base station fence is determined based on the multiple distances.
[0256] Exemplarily, the cloud service platform can calculate the distance between the center point of the base station fence of this base station and the center point of each cluster based on the longitude and latitude information of the center point of the base station fence of this base station and the longitude and latitude information of the center point of each cluster, so as to obtain multiple distances. The maximum distance among the multiple distances can be used as the base station fence radius of this base station. In a possible implementation, the average value of the multiple distances can also be calculated, and the calculated average value is used as the base station fence radius of this base station.
[0257] S7045: Generate a base station fence snapshot based on the latitude and longitude information of the base station fence center point, the base station fence radius, the base station indication information, and the city code corresponding to the base station.
[0258] As can be seen from the above, the base station indication information is used to uniquely identify a base station, and the base station indication information may include an operator identifier, a cell number, and a base station number.
[0259] Exemplarily, the base station fence can be determined in the grid map according to the base station fence radius and the latitude and longitude information of the center point of the base station fence, and then the base station fence snapshot is generated based on the data within the base station fence. As an example of the present application, the base station fence snapshot may include the city code (citycode), operator identifier (operator), cell number (lac), base station number (cellID), longitude (longitude), latitude (latitude), radius (radius), service list (taglist), etc. of the base station.
[0260] Exemplarily, the base station snapshot generated by the cloud service platform is shown in Table 4, where each row represents a base station fence snapshot:
[0261] Table 4
[0262]
[0263] In the above Table 4, taglist represents the service list, which is the service type information included in the base station fence in the grid map and the scene fence identifier corresponding to the service type information. That is, you can first determine what service type information is included in the base station fence in the grid map, and then query the scene fence identifier corresponding to these service type information from the scene fence snapshot, so as to establish the taglist and add the taglist to the base station snapshot.
[0264] Optionally, when the scene acquisition data set also includes base station strength, the base station strength distribution information in the base station fence can also be determined, and the base station strength distribution information can be carried in the base station snapshot, so that in the subsequent scene recognition, the location of the electronic device can be determined based on the base station strength distribution information and the base station strength of the base station to which the electronic device is currently connected, thereby improving the positioning accuracy and thus improving the accuracy of scene recognition.
[0265] As an example of the present application, after learning the scene features, the cloud service platform can display the data distribution in the grid map in the form of a visual graph, and can identify the base station type for each base station during the display, such as 4G or 5G type, etc., so that technicians can intuitively view the distribution of different types of networks in the visual graph.
[0266] As an example of the present application, the cloud service platform can periodically perform scene feature learning and updating, and the cycle duration can be set according to actual needs. For example, the cycle duration can be one day, one week, or one month, etc., and the embodiments of the present application are not limited to this.
[0267] The above describes the process of how to use the collected scene collection data set to learn the scene features corresponding to different services. The following describes the process of caching scene features involved in the embodiment of the present application.
[0268] On the basis of scene features stored in the cloud service platform, electronic devices can download scene features from the cloud service platform. Since the data volume of the full scene features is large, in order to improve the timeliness of downloading scene features, reduce traffic, reduce the operating power consumption of electronic devices, and reduce the storage space occupied, electronic devices can obtain partial scene features according to business needs.
[0269] As an example of the present application, for each service that supports scene recognition, the cloud service platform can configure the feature update configuration information of each service, and then send the feature update configuration information of each service to the electronic device, so that the electronic device determines the scene feature update method for each service according to the feature update configuration information of each service, that is, the electronic device obtains part of the scene features from the cloud service platform according to the business needs, thereby reducing the amount of downloaded data.
[0270] In one example, an electronic device sends a feature acquisition request to a cloud service platform, and the feature acquisition request may include a city code. Accordingly, the cloud service platform obtains a base station fence snapshot set including the city code from the full set of scene features. The base station fence snapshot set includes scene fence identifiers corresponding to each business type information. Afterwards, based on the scene fence identifiers corresponding to each business type information in each base station fence snapshot set obtained, the scene fence snapshots corresponding to each scene fence identifier are obtained to obtain a scene fence snapshot set. The cloud service platform sends the obtained data (i.e., the base station fence snapshot set and the scene fence snapshot set) to the electronic device. For the electronic device, after receiving the data sent by the cloud service platform, it stores it in a database, such as a local database.
[0271] In one example, the feature acquisition request may include a city code and business type information of the target business. Accordingly, the cloud service platform obtains a base station fence snapshot set including the city code and the business type information from the full set of scene features. The base station fence snapshot set includes scene fence identifiers corresponding to each business type information. Afterwards, based on the scene fence identifiers corresponding to each business type information in each base station fence snapshot set obtained, the scene fence snapshots corresponding to each scene fence identifier are obtained to obtain a scene fence snapshot set. The cloud service platform sends the obtained data (i.e., the base station fence snapshot set and the scene fence snapshot set) to the electronic device. After receiving the data sent by the cloud service platform, the electronic device stores it in a database.
[0272] In one example, the feature acquisition request may carry the base station indication information of the base station to which the electronic device has been connected, in addition to the city code and the service type information of the target service. In this way, after the cloud service platform obtains the base station fence snapshot set including the city code and the service type information from the full amount of scene features, the cloud service platform filters out the base station fence snapshot set including the base station indication information from the obtained base station fence snapshot set. The filtered base station fence snapshot set including the base station indication information includes the scene fence identifier corresponding to each service type information. According to the scene fence identifier corresponding to each service type information in each filtered base station fence snapshot set, the scene fence snapshot corresponding to each scene fence identifier is obtained to obtain the scene fence snapshot set. The cloud service platform sends the filtered base station fence snapshot set and the scene fence snapshot set to the electronic device. After receiving the base station fence snapshot set and the scene fence snapshot set sent by the cloud service platform, the electronic device stores them in the database.
[0273] For easier understanding, please refer to Fig.14 , Fig.14 This is a schematic diagram of a cached scene feature shown in an exemplary embodiment of the present application. If the current location of the electronic device reaches a new city, that is, the scene features of the new city are not stored in the electronic device, the scene features of the area near the current location can be obtained from the cloud service platform in real time based on the current location of the electronic device.
[0274] like Fig.14 In the area (a) shown in the grid diagram, the current position of the electronic device is taken as the center, and several (e.g., 2048*2048) grids are extended to the periphery as the range to be downloaded. In one implementation, the data covered in these grids (i.e., the base station fence snapshot set and the scene fence snapshot set) are all downloaded to the electronic device. In another implementation, Fig.14 In the area (b) shown, dark gray grids are filtered out in the range to be downloaded based on business needs (such as base station indication information of base stations to which the electronic device has been connected), and the data covered in these dark gray grids (i.e., the base station fence snapshot set and the scene fence snapshot set) are taken as the data in the actual download range and downloaded to the electronic device.
[0275] In one example, every time the electronic device reaches a new location, if the location is more than a preset distance from the original location, then in order to ensure the recall rate of the service on the electronic device side, the electronic device can send the current longitude and latitude information and the longitude and latitude information of the last positioning to the cloud service platform. The preset distance can be set according to actual needs. For example, the preset distance can be 1000 meters. Correspondingly, the cloud service platform removes the intersection data of the scene features based on the last longitude and latitude information and the current longitude and latitude information, and sends the scene features within the range to the electronic device side. For the electronic device side, the intersection data is retained, and the new scene features sent by the electronic device side are written into the database. In this way, download traffic can be saved, that is, the power consumption of online real-time downloading is saved, and the electronic device side can also reduce the erasure of the database.
[0276] like Fig.14 In the area (c) shown, the electronic device side moves from the original position to the current position (the current position here refers to the new position). In the grid map, the current position of the electronic device is taken as the center, and several (such as 2048*2048) grids are extended to the periphery as the new range to be downloaded. Fig.14 In the area (d) shown in the figure, according to the business requirements (such as the base station indication information of the base stations that the electronic device has connected to), the gray grids are selected in the new download range, and the data covered by these gray grids (i.e., the base station fence snapshot set and the scene fence snapshot set) are regarded as the data in the range that should be downloaded. Fig.14 In the area (e) shown, the download range corresponding to the original position and the download range corresponding to the current position have an intersection (the hit cache part). After removing the intersection data, the data covered in the remaining gray grids (i.e., the base station fence snapshot set and the scene fence snapshot set) are taken as the data in the actual download range and downloaded to the electronic device.
[0277] The above describes the process of caching scene features involved in the embodiment of the present application. The following describes the business scene identification method involved in the embodiment of the present application. Fig.15 , Fig.15 is a flowchart of a business scenario identification method shown in an exemplary embodiment of the present application, and the method may include:
[0278] S801: When a scene recognition request of a target service is monitored, base station information of a base station to which the electronic device is currently connected is obtained.
[0279] S802: Perform scene recognition based on scene feature data and base station information to determine whether the electronic device is located in the target scene.
[0280] The base station information includes a target operator identifier, a target cell number, and a target base station number, and the scene identification request is used to request identification of whether the electronic device is located in a target scene associated with a target service. The scene feature data includes at least one base station fence snapshot, and the base station fence snapshot includes an operator identifier, a cell number, and a base station number that have an associated relationship.
[0281] Exemplarily, when a scene recognition request of a target service is monitored, the base station information of the base station currently accessed by the electronic device is obtained, and based on the base station information of the base station currently accessed by the electronic device and one or more base station fence snapshots in the scene feature data, it is determined whether the electronic device is located in the target scene. For example, when the target operator identifier, target cell number, and target base station number in the base station information are the same as the operator identifier, cell number, and base station number in a certain base station fence snapshot, it is determined that the electronic device is located in the target scene.
[0282] In the business scene identification method, when the scene identification request of the target business is monitored, the base station information of the base station currently connected to the electronic device is obtained, and the scene identification is performed based on the scene feature data and the base station information to determine whether the electronic device is located in the target scene. Among them, the scene feature data includes at least one base station fence snapshot, the base station fence snapshot includes an operator identifier, a cell number and a base station number with an associated relationship, and the base station information includes a target operator identifier, a target cell number and a target base station number. Obviously, scene identification based on scene feature data and base station information is to compare the operator identifier, cell number, base station number in the base station fence snapshot with the target operator identifier, target cell number and target base station number in the base station information. That is to say, this method determines whether the electronic device is located in the target scene by comparing the base station information with the base station fence snapshot. In the process of business scene identification, the base station information is used, and there is no need to request the cloud service platform to obtain the location, and compared with the use of GPS positioning in the relevant technology, the power consumption of base station positioning is less than that of GPS positioning. In this method, there is no need to compare with the data in the cloud service platform, thereby reducing the power consumption of the electronic device and improving the real-time performance.
[0283] As an example of the present application, the scene recognition accuracy of a business may include low, medium, and high. The scene recognition accuracy of different businesses is usually determined by the business itself. For example, different scene recognition accuracies can be set in advance for different businesses according to different user needs. Exemplarily, the scene recognition accuracy of the regular payment business may be low precision, the scene recognition accuracy of the QR code business may be medium precision, and the scene recognition accuracy of the ticket collection business may be high precision. This is only an exemplary description and is not limited to this.
[0284] In one example, the scene recognition accuracy of the service is low-precision. When the scene recognition request of the target service is monitored, the base station information of the base station currently connected to the electronic device is obtained, and based on the base station information of the base station currently connected to the electronic device and the base station fence snapshot set, it is determined whether the electronic device is located in the target scene associated with the target service. Among them, the base station information currently connected to the electronic device may include the target operator identifier, the target cell number, and the target base station number, and the target service is a service with low scene recognition accuracy. And from the above description, it can be seen that the electronic device stores a base station fence snapshot set, and the base station fence snapshot set includes multiple base station fence snapshots.
[0285] The electronic device will always perform Cell-ID positioning. When the electronic device is an Android phone, the switching of the base station can be sensed / monitored through the telephonyManager that comes with the Android phone. Exemplarily, the base station information of the base station to which the electronic device is currently connected can be obtained through Cell-ID positioning. Search the base station fence snapshot collection to see if there is a base station fence snapshot that matches the base station information. If a base station fence snapshot that matches the base station information is found in the base station fence snapshot collection, it is determined that the electronic device is currently located in the target scene associated with the target service. If a base station fence snapshot that matches the base station information is not found in the base station fence snapshot collection, it is determined that the electronic device is not currently located in the target scene associated with the target service.
[0286] For example, the scene recognition accuracy of the regular payment service is low precision, that is to say, the target service in this embodiment is the regular payment service. The current target operator identification, target cell number and target base station number of the electronic device are obtained through Cell-ID positioning, and the operator, lac and cellID in a certain base station fence snapshot are found in the base station fence snapshot set. If they are the same as the current target operator identification, target cell number and target base station number of the electronic device, it is determined that the electronic device is currently located in the target scene associated with the regular payment service. At this time, the payment code quick card is displayed in the display interface of the electronic device, so that the user can use the payment code quick card to realize quick payment.
[0287] For another example, if the operator, lac, and cellID in a certain base station fence snapshot are not found in the base station fence snapshot set, and are the same as the current target operator identifier, target cell number, and target base station number of the electronic device, it is determined that the electronic device is not currently located in the target scene associated with the regular payment service. At this time, the payment code shortcut card will not be displayed in the display interface of the electronic device. The electronic device will continue to perform Cell-ID positioning and repeat the above process to determine whether the electronic device is located in the target scene associated with the regular payment service.
[0288] In this implementation, for services with low scene recognition accuracy, as long as the base station information of the electronic device matches a base station fence snapshot in the base station fence snapshot set, or as long as the base station information of the electronic device intersects with the base station fence snapshot set within the low-precision feature, it can be identified that the electronic device has entered a service scene with low scene recognition accuracy, with low latency, that is, high real-time performance. Based on this, shortcut cards can be immediately recommended to users, which improves the intelligence of electronic devices, meets user usage needs, and improves user experience. Among them, if the scene recognition accuracy of the service represented by the service type information included in the base station fence snapshot is low, then the base station fence snapshot can be said to meet the low-precision feature.
[0289] In the process of low-precision business scene recognition, on the one hand, the power consumption of electronic devices using Cell-ID positioning is less than that of using GPS positioning. Therefore, the base station information of the electronic device is matched with the base station fence snapshot set to identify whether the electronic device has entered a business scene with low scene recognition accuracy, saving power consumption. On the other hand, there is no need to request the cloud service platform during the business scene recognition process, which also saves power consumption.
[0290] In one example, when the scene recognition accuracy of the service is low, in addition to determining whether the electronic device is located in the target scene associated with the target service based on the base station information of the base station currently connected to the electronic device and the base station fence snapshot set, it is also possible to determine whether the electronic device is located in the target scene associated with the target service based on the current location information and target area of the electronic device. Among them, the current location information of the electronic device is used to characterize the current location of the electronic device, and the current location information of the electronic device may include longitude information and latitude information. The target area is the area corresponding to the destination for realizing the target service, and the target area is determined by the center point of the destination and the radius corresponding to the destination. It can be understood that the destination is usually manifested as an area in the real environment, so it has a corresponding center point and radius.
[0291] Exemplarily, a target area is obtained. For example, a scene fence snapshot set is stored in the electronic device, and the scene fence snapshot set includes multiple scene fence snapshots. The scene recognition request of the monitored target service can carry service type information, and one or more scene fence snapshots matching the service type information can be determined in the scene fence snapshot set. Each scene fence snapshot includes longitude information, latitude information, and a scene fence radius, and the target area corresponding to each scene fence snapshot is determined based on the longitude information, latitude information, and scene fence radius.
[0292] Optionally, in a possible implementation, each scene fence snapshot may also include a POI, and the scene recognition request may also carry POI data. If multiple scene fence snapshots matching the business type information are determined in the scene fence snapshot set, then based on the POI data and the POI included in the scene fence snapshot, a scene fence snapshot is again determined from the multiple scene fence snapshots initially determined. Thereafter, based on the longitude information, latitude information, and scene fence radius included in the finally determined scene fence snapshot, the target area corresponding to the scene fence snapshot is determined.
[0293] Exemplarily, the current location information of the electronic device can be obtained by GPS, or by positioning the ride. According to the current location information of the electronic device and the target area, it is determined whether the current location of the electronic device is within the target area. In layman's terms, a point is determined by the longitude and latitude information of the electronic device, and it is determined whether the point is within the target area. If the current location of the electronic device is within the target area, it is determined that the electronic device is currently located within the target scene associated with the target business. If the current location of the electronic device is not within the target area, it is determined that the electronic device is not currently located within the target scene associated with the target business.
[0294] In this implementation, before the base station information of the electronic device matches any base station fence snapshot in the base station fence snapshot set, it is possible to determine whether the current location of the electronic device is within the target area through the current location information of the electronic device and the target area, thereby identifying whether the electronic device has entered a business scene with low-precision scene recognition accuracy, providing support for the cold start of low-precision business scene recognition.
[0295] In one example, the scene recognition accuracy of the service is medium precision. When the scene recognition request of the target service is monitored, the base station information of the base station currently connected to the electronic device is obtained, and based on the base station information of the base station currently connected to the electronic device, the current location information of the electronic device obtained, the base station fence snapshot set and the scene fence snapshot set, it is determined whether the electronic device is located in the target scene associated with the target service. It is worth noting that the target service here refers to the service with medium scene recognition accuracy. The electronic device stores a base station fence snapshot set and a scene fence snapshot set, the base station fence snapshot set includes multiple base station fence snapshots, and the scene fence snapshot set includes multiple scene fence snapshots.
[0296] Exemplarily, the base station information of the electronic device is obtained through Cell-ID positioning, and a base station fence snapshot set is searched to see whether there is a base station fence snapshot matching the base station information. If a base station fence snapshot matching the base station information is found in the base station fence snapshot set, a service list included in the base station fence snapshot is obtained. The service list includes service type information and a scene fence identifier corresponding to the service type information. One or more scene fence snapshots can be found in the scene fence snapshot set according to the scene fence identifier. According to the longitude information and latitude information contained in the scene fence snapshot, a center point can be determined, and then the fence area corresponding to the scene fence snapshot can be determined according to the center point and the scene fence radius contained in the scene fence snapshot. The current location information of the electronic device is obtained by GPS, and according to the current location information of the electronic device and the fence area corresponding to the scene fence snapshot, it is determined whether the current location of the electronic device is within the fence area, thereby determining whether the electronic device is located in the target scene associated with the target service.
[0297] When a scene fence snapshot is found in the scene fence snapshot set according to the scene fence identifier, the fence area corresponding to the scene fence snapshot is determined according to the longitude information, latitude information and scene fence radius contained in the scene fence snapshot. The location information of the electronic device is obtained, the location of the electronic device is determined based on the location information, and it is determined whether the current location of the electronic device is within the fence area. If the current location of the electronic device is within the fence area, it is determined that the electronic device is located in the target scene associated with the target business. If the current location of the electronic device is not within the fence area, it is determined that the electronic device is not located in the target scene associated with the target business.
[0298] Optionally, in one possible implementation, when it is determined that the electronic device is located in a target scene associated with a target business, a shortcut card related to the target business (a business with medium scene recognition accuracy) is displayed in the display interface of the electronic device, so that the user can use the shortcut card to implement the target business. When it is determined that the electronic device is not located in the target scene associated with the target business, the shortcut card will not be displayed in the display interface of the electronic device. The electronic device will repeat the judgment process to determine whether the electronic device is located in the target scene associated with the target business.
[0299] In the case where multiple scene fence snapshots are found in the scene fence snapshot set according to the scene fence identifier, if POI data is detected, then according to the POI data, a scene fence snapshot matching the POI data is searched in the multiple scene fence snapshots. For example, a scene fence snapshot that contains the same POI as the POI data is searched in multiple scene fence snapshots. The fence area corresponding to the found scene fence snapshot is determined, and based on the acquired location information of the electronic device, it is determined whether the current location of the electronic device is within the fence area. In this way, the fence area of the scene fence snapshot related to the target business can be quickly determined without comparing the current location of the electronic device with each fence area, thereby improving the speed of business scene recognition.
[0300] In the case where multiple scene fence snapshots are found in the scene fence snapshot set according to the scene fence identifier, if no POI data is detected, the fence area corresponding to each scene fence snapshot is determined according to the longitude information, latitude information and scene fence radius contained in each scene fence snapshot. According to the acquired location information of the electronic device, if it is determined that the current location of the electronic device is within any fence area, that is, it is determined that the electronic device is located in the target scene associated with the target business, the applicability is wider.
[0301] In this implementation, for a service with medium scene recognition accuracy, when the base station information of the electronic device matches a base station fence snapshot in the base station fence snapshot set, and the current position of the electronic device is within the fence area corresponding to a scene fence snapshot (a scene fence snapshot determined by a scene fence identifier in the base station fence snapshot), it can be identified that the electronic device has entered a service scene with medium scene recognition accuracy, with high real-time performance. Based on this, quick cards can be immediately recommended to users, which improves the intelligence of electronic devices, meets the user's usage needs, and improves user experience. When the base station information of the electronic device matches a base station fence snapshot in the base station fence snapshot set, it is detected whether the current position of the electronic device is within the fence area corresponding to a scene fence snapshot (a scene fence snapshot determined by a scene fence identifier in the base station fence snapshot), or as long as the base station information of the electronic device has an intersection with the base station fence snapshot set in the medium-precision feature, medium-precision service scene recognition is started, effectively avoiding the waste of power consumption of medium-precision service scene recognition. Among them, if the scene recognition accuracy of the service represented by the service type information included in the base station fence snapshot is medium precision, the base station fence snapshot can be said to meet the medium-precision feature.
[0302] In the process of medium-precision business scene recognition, on the one hand, Cell-ID positioning is used in the early stage (that is, Cell-ID positioning is used before matching with the scene fence snapshot), and there is no need to use GPS positioning throughout the process, which saves power consumption. On the other hand, there is no need to request the cloud service platform during the business scene recognition process, which also saves power consumption.
[0303] In one example, the scene recognition accuracy of the service is high-precision. When the scene recognition request of the target service is monitored, the base station information of the base station currently accessed by the electronic device is obtained, and the electronic device is determined whether it is located in the target scene associated with the target service according to the base station information of the base station currently accessed by the electronic device, the current location information of the electronic device obtained, the WiFi list currently corresponding to the electronic device, the base station fence snapshot set, and the scene fence snapshot set. Among them, the WiFi list may include at least one WiFi identification information and the WiFi strength corresponding to each WiFi identification information, wherein the WiFi identification information may include WiFi physical address information and WiFi name. It is worth noting that the target service here refers to the service with high-precision scene recognition accuracy. The electronic device stores a base station fence snapshot set and a scene fence snapshot set, the base station fence snapshot set includes multiple base station fence snapshots, the scene fence snapshot set includes multiple scene fence snapshots, and the scene fence snapshot includes WiFi features.
[0304] Exemplarily, the base station information of the electronic device is obtained through Cell-ID positioning, and a base station fence snapshot set is searched for a base station fence snapshot that matches the base station information. If a base station fence snapshot that matches the base station information is found in the base station fence snapshot set, the base station fence snapshot is determined by the scene fence identifier in the base station fence snapshot. The fence area corresponding to the scene fence snapshot is determined according to the longitude information, latitude information and scene fence radius contained in the scene fence snapshot. The current location information of the electronic device is obtained by GPS, and according to the current location information of the electronic device and the fence area corresponding to the scene fence snapshot, it is determined whether the current location of the electronic device is within the fence area. If the current location of the electronic device is within the fence area, the current WiFi list of the electronic device is obtained. It is determined whether the WiFi list matches the WiFi features in the scene fence snapshot. If the WiFi list matches the WiFi features in the scene fence snapshot, it is determined that the electronic device is located in the target scene associated with the target service. If the WiFi list does not match the WiFi features in the scene fence snapshot, it is determined that the electronic device is not located in the target scene associated with the target service.
[0305] Determining whether the WiFi list matches the WiFi feature in the scene fence snapshot may include: the WiFi identification information in the WiFi list and the WiFi strength corresponding to each WiFi identification information are the same as each WiFi identification information in the WiFi identification information list in the WiFi feature and the WiFi strength corresponding to each WiFi identification information, determining that the WiFi list matches the WiFi feature in the scene fence snapshot.
[0306] Determining whether the WiFi list matches the WiFi feature in the scene fence snapshot may also include: determining a matching threshold corresponding to the current WiFi list of the electronic device, when the similarity between the WiFi identification information in the WiFi list and the WiFi identification information in the WiFi identification information list in the WiFi feature is greater than or equal to a preset similarity threshold, and the matching threshold corresponding to the WiFi list is greater than or equal to a target matching threshold in the WiFi feature, then determining that the WiFi list matches the WiFi feature in the scene fence snapshot. The preset similarity threshold may be set to 50%, 60%, 70%, etc. The process of determining the matching threshold corresponding to the current WiFi list may refer to the relevant description in the aforementioned process of determining the WiFi feature, which will not be repeated here.
[0307] Determining whether the WiFi list matches the WiFi features in the scene fence snapshot may also include: determining the intensity matching degree corresponding to each WiFi strength in the WiFi list. When the similarity between the WiFi identification information in the WiFi list and the WiFi identification information in the WiFi identification information list in the WiFi feature is greater than or equal to the preset similarity threshold, and the intensity matching degree corresponding to each WiFi strength in the WiFi list is greater than or equal to the intensity matching degree corresponding to each WiFi strength in the WiFi feature, it is determined that the WiFi list matches the WiFi features in the scene fence snapshot. Among them, the process of determining the intensity matching degree corresponding to each WiFi strength in the WiFi list can refer to the relevant description in the aforementioned process of determining the WiFi features, which will not be repeated here. These three methods of determining whether the WiFi list matches the WiFi features in the scene fence snapshot improve the accuracy of the matching results, which is conducive to improving the accuracy of business scene recognition.
[0308] In this implementation, for services with high scene recognition accuracy, when the base station information of the electronic device matches a base station fence snapshot in the base station fence snapshot set, and the current position of the electronic device is within the fence area corresponding to a scene fence snapshot (a scene fence snapshot determined by the scene fence identifier in the base station fence snapshot), and the WiFi list matches the WiFi feature in the scene fence snapshot, it can be identified that the electronic device has entered a service scene with high scene recognition accuracy, with high real-time performance. Based on this, quick cards can be immediately recommended to users, which improves the intelligence of electronic devices, meets the user's usage needs, and improves user experience. As long as the base station information of the electronic device has an intersection with the base station fence snapshot set in the high-precision feature, high-precision business scene recognition begins, effectively avoiding the waste of power consumption of high-precision business scene recognition. Among them, if the scene recognition accuracy of the service represented by the service type information included in the base station fence snapshot is high-precision, then the base station fence snapshot can be said to meet the high-precision feature.
[0309] In the process of high-precision business scene recognition, on the one hand, Cell-ID positioning is used in the early stage (that is, Cell-ID positioning is used before matching with the scene fence snapshot), and GPS positioning and WiFi scanning are used in the later stage, which saves power consumption while maintaining recognition accuracy. On the other hand, there is no need to request the cloud service platform during the business scene recognition process, which also saves power consumption.
[0310] Optionally, in a possible implementation, when the scene recognition accuracy of the service is high, if the WiFi list is detected to match the WiFi features in a scene fence snapshot, the electronic device can be directly identified to enter the service scene with high scene recognition accuracy, without matching the base station fence snapshot and the scene fence snapshot. This implementation improves the real-time performance of service scene recognition and saves the power consumption required for early positioning.
[0311] Optionally, in a possible implementation, when the scene recognition accuracy of the service is high precision, if it is detected that the WiFi list does not match the WiFi features of the target scene fence snapshot (the scene fence snapshot determined by the scene fence identifier in the matched base station fence snapshot), the WiFi hitchhiking technology can be used to obtain the WiFi scan results. Among them, using the WiFi hitchhiking technology to obtain the WiFi scan results refers to obtaining the WiFi scan results generated by the system or a third-party application, and the WiFi scan results may include a WiFi list. If it is detected that the WiFi list generated by the system or a third-party application matches the WiFi features of the target scene fence snapshot, it is determined that the electronic device is located in the target scene. In this implementation, when the WiFi list and the WiFi features do not intersect, the WiFi-related data is obtained using the WiFi hitchhiking technology without performing a separate WiFi scan, which effectively saves power consumption.
[0312] The above describes the identification of whether an electronic device has entered a target scene associated with a target service. The following describes the identification of whether an electronic device has left a target scene associated with a target service.
[0313] In one example, when the scene recognition accuracy of a service is low, the electronic device can be determined to be located in a target scene associated with the target service by matching the base station information of the electronic device with a base station fence snapshot in a base station fence snapshot set. After the electronic device enters the target scene, if the base station information of the electronic device no longer matches the base station fence snapshot, it can be identified that the electronic device has left the target scene. This implementation method has high real-time performance.
[0314] Optionally, in a possible implementation, after the electronic device enters the target scene, if the base station information of the electronic device no longer matches the base station fence snapshot, the location information of the electronic device is obtained. For example, the current location information of the electronic device is obtained by GPS. According to the current location information of the electronic device and the target area, it is determined whether the electronic device has actually left the target scene. If the current location of the electronic device is not within the target area, it is determined that the electronic device has actually left the target scene. If the current location of the electronic device is still within the target area, it is determined that the electronic device has not left the target scene. This implementation method can effectively avoid misidentification and improve the accuracy of business scene recognition, that is, accurately determine whether the electronic device has actually left the target scene associated with the target business, thereby bringing a better experience to the user.
[0315] In one example, when the scene recognition accuracy of a business is medium, the base station information of the electronic device is matched with a base station fence snapshot in a base station fence snapshot set, and the current position of the electronic device is within the fence area corresponding to a scene fence snapshot (a scene fence snapshot determined by a scene fence identifier in the base station fence snapshot), then it is determined that the electronic device has entered a business scene with medium scene recognition accuracy. After the electronic device enters the business scene, if it is detected that the position of the electronic device is not within the fence area, then it is determined that the electronic device has actually left the business scene. This implementation method can effectively avoid misidentification and improve the accuracy of business scene recognition, that is, accurately determine whether the electronic device has actually left the business scene, thereby bringing a better experience to the user.
[0316] In one example, when the scene recognition accuracy of the service is high, the base station information of the electronic device matches a base station fence snapshot in the base station fence snapshot set, and the current position of the electronic device is within the fence area corresponding to a scene fence snapshot (a scene fence snapshot determined by the scene fence identifier in the base station fence snapshot), and the WiFi list matches the WiFi feature in the scene fence snapshot, and the electronic device is identified to have entered the target scene. After the electronic device enters the target scene, if it is detected that the WiFi list does not match the WiFi feature in the scene fence snapshot, it can be identified that the electronic device has left the target scene, and this implementation method has high real-time performance.
[0317] Optionally, in a possible implementation, after the electronic device enters the target scene, if it is detected that the WiFi list does not match the WiFi features in the scene fence snapshot, the location information of the electronic device is obtained. Based on the current location information of the electronic device and the fence area, it is determined whether the electronic device has actually left the target scene. If the current location of the electronic device is not within the fence area, it is determined that the electronic device has actually left the target scene. If the current location of the electronic device is still within the fence area, it is determined that the electronic device has not left the target scene. This implementation can effectively avoid misidentification and improve the accuracy of business scene recognition, that is, accurately determine whether the electronic device has actually left the target scene associated with the target business, thereby bringing a better experience to the user.
[0318] The present application also provides a method for predicting the next positioning time based on the user's current motion state. The method is described below. As an example of the present application, please refer to Fig.16 , Fig.16 This is a flow chart of a method for predicting the time of the next positioning shown in an exemplary embodiment of the present application. The method may include:
[0319] S901: Obtain the user's current exercise status.
[0320] For example, the user's current motion state can be obtained by analyzing the user's current posture through sensors such as acceleration sensors and gyroscope sensors in electronic devices in combination with a network model that can implement posture learning. The user's current motion state may include walking state, running state, fast walking state, driving state, etc.
[0321] S902: Determine the user's current first motion speed according to the motion state.
[0322] The user's current first motion speed is evaluated according to the user's current motion state. A correspondence between different motion states and different motion speeds can be established in advance, and the user's current motion speed is determined based on the correspondence. For example, when the motion state is a walking state, the motion speed can be 1 meter per second, and when the motion state is a driving state, the first motion speed can be 10 meters per second. The user's current first motion speed can also be determined by at least two positionings, for example, obtaining the time interval between the two positionings, obtaining the distance between the two positions of the two positionings, and determining the user's current first motion speed based on the time interval and the distance. This is only an exemplary description and is not limited to this.
[0323] Optionally, in a possible implementation, during the user's movement, the user's current first motion speed can be refreshed according to the historical positioning. For example, the time interval between the historical positioning and the most recent positioning is obtained, the distance between the two positions of the two positionings is obtained, and the user's current first motion speed is refreshed according to the time interval and the distance. This can ensure that the user's current motion speed is determined more accurately, which is conducive to the subsequent accurate determination of the positioning time for the next positioning, reducing the number of positioning times, and thus saving power consumption.
[0324] S903: Determine a destination for implementing the target service according to the target service, and determine a first distance between the user's current location and the destination.
[0325] In one example, determining the destination for implementing the target business based on the target business may include: the scene recognition request of the monitored target business may carry business type information and POI data. The business type information is used to indicate the business type of the target business, and the POI data indicates the destination. Based on the business type information and the POI data carried, a scene fence snapshot may be determined in the scene fence snapshot set. The scene fence snapshot includes longitude information, latitude information, and a scene fence radius. A fence area may be formed by the longitude information, latitude information, and scene fence radius, and the fence area indicates the target area corresponding to the destination. Then, the longitude information and latitude information indicate the center point of the target area corresponding to the destination, and the scene fence radius indicates the radius of the target area corresponding to the destination.
[0326] If the base station information of the current electronic device does not match any base station fence snapshot in the base station fence snapshot set, that is, no base station fence snapshot matching the base station information of the base station currently connected to the electronic device is found in the base station fence snapshot set, then the user's current location is obtained, that is, the user's current location information is obtained. It can be understood that when the user carries the electronic device and moves, the location of the electronic device is almost the same as the user's location, so obtaining the current location of the electronic device is also obtaining the user's current location.
[0327] The distance difference between the user's current location and the destination can be calculated using the latitude and longitude information of the user's current location and the latitude and longitude information of the center point corresponding to the destination. The distance difference is then subtracted from the scene fence radius (i.e., the radius of the target area corresponding to the destination) to obtain the first distance between the user's current location and the destination.
[0328] For easier understanding, please refer to Fig.17 , Fig.17 FIG. 1 is a schematic diagram of an application scenario of predicting time shown in an exemplary embodiment of the present application. Fig.17 As shown in (a), S4 represents the current location of the user, where the base station information of the electronic device does not match any base station fence snapshot in the base station fence snapshot set, and the destination location has a corresponding target area (fence area), where the location information of the electronic device can match a scene fence snapshot. It can be understood that as long as the user moves to the edge of the target area, it can be recognized that the electronic device has entered the target scene. Therefore, when calculating the first distance, the scene fence radius needs to be subtracted.
[0329] Optionally, in a possible implementation, if the base station information of the current electronic device matches a base station fence snapshot in the base station fence snapshot set, the longitude and latitude information of the center point of the base station fence and the radius of the base station fence in the base station fence snapshot are obtained. At this time, the longitude and latitude information of the center point of the base station fence can be used to represent the current position of the user, and the distance difference between the two points is calculated by using the longitude and latitude information of the center point of the base station fence and the longitude and latitude information of the center point corresponding to the destination, and the distance difference is subtracted from the scene fence radius (i.e., the radius of the target area corresponding to the destination) to obtain the result as the first distance between the current position of the user and the destination.
[0330] For easier understanding, please refer to Fig.17In (b), the circular area on the left represents the base station fence corresponding to the base station fence snapshot that matches the base station information of the electronic device, and S5 represents the current location of the user determined based on the base station fence snapshot. The circular area on the right represents the target area (fence area) corresponding to the destination location, where the location information of the electronic device can be matched with a scene fence snapshot. It can be understood that as long as the user moves to the edge of the target area, it can be recognized that the electronic device has entered the target scene. Similarly, when calculating the first distance, the scene fence radius needs to be subtracted.
[0331] S904: Predicting the time of next positioning according to the user's current first movement speed and first distance.
[0332] Calculate the quotient between the first distance and the current first movement speed, and the value obtained is the time for the next positioning. For example, the destination is a company, and the first distance between the user's current location and the company is calculated to be 2000 meters. The user's current first movement speed is 1 meter per second. After 2000 seconds, the user will move to the target area corresponding to the company, so the predicted time for the next positioning is 2000 seconds later. GPS positioning is not required during the user's movement. After 2000 seconds, the user's latest location information is obtained through positioning, and whether the user has entered the target scene can be determined based on the latest location information.
[0333] It is worth noting that the methods in S901 to S904 above can be applied to business scene recognition with different scene recognition accuracies.
[0334] In this implementation, the movement speed is evaluated according to the user's current movement status, and then the time for the next positioning is predicted based on the movement speed and the distance to the destination. During the entire process, there is no need to use GPS positioning all the time, which greatly reduces the number of positioning times and reduces power consumption.
[0335] An embodiment of the present application also provides a method for refreshing the time of the next positioning, which method may include: when the user is moving, the electronic device will always perform Cell-ID positioning, and if the base station information of the base station to which the electronic device is currently connected obtained at a certain time matches a certain base station fence snapshot, the longitude and latitude information of the center point of the base station fence and the radius of the base station fence of the base station fence snapshot are obtained. According to the longitude and latitude information of the center point of the base station fence and the radius of the base station fence, the second distance between the user's current position and the destination is determined, and the second movement speed of the user is predicted according to the user's current motion state. The method of calculating the second distance is the same as the method of calculating the first distance, and the method of predicting the second movement speed is the same as the method of predicting the first movement speed, which will not be repeated here. According to the second movement speed and the second distance, the time for the next positioning is updated.
[0336] For easier understanding, please refer to Fig.18 , Fig.18 This is another application scenario diagram of predicting time shown in an exemplary embodiment of the present application. During the user's travel, he may match several base station fence snapshots, which may be base station fence snapshots that the user has matched before, or may be newly matched base station fence snapshots during this travel. Each base station fence snapshot is Fig.18 It is represented as a base station fence, and the rightmost circular area represents the target area (fence area) corresponding to the destination location, where the location information of the electronic device can be matched with a scene fence snapshot.
[0337] For example, the destination is a company. Fig.18 As shown, the user's starting point is in the first base station fence, that is, the electronic device matches the first base station fence snapshot at the starting point. At this time, the distance between the user's current location and the company is calculated to be 2000 meters, and the user's current movement speed is 1 meter per second. After 2000 seconds, the user will move to the target area corresponding to the company, so the next positioning time will be 2000 seconds later. Afterwards, the user walks into the second base station fence, that is, the electronic device matches the second base station fence snapshot. At this time, the distance between the user's current location and the company is calculated to be 1500 meters, and the user's current movement speed is 1 meter per second. After 1500 seconds, the user will move to the target area corresponding to the company, and the time for the next positioning is refreshed, that is, the time for the next positioning is determined to be 1500 seconds later.
[0338] If the user changes the motion state during the movement, the motion speed will also change. The time for the next positioning is refreshed according to the changed motion speed and the remaining distance. For example, the user walks into the third base station fence, that is, the electronic device matches the third base station fence snapshot. At this time, the distance between the user's current location and the company is calculated to be 1000 meters, and the user's current motion speed is 10 meters per second. After 100 seconds, the user will move to the target area corresponding to the company, and the time for the next positioning will be refreshed, that is, the time for the next positioning will be determined to be 100 seconds later. And so on, until the user moves into the target area and identifies that the electronic device has entered the target scene.
[0339] In this implementation, the next positioning time is constantly refreshed according to the snapshot of the base station fence matched during the user's movement. During the whole process, there is no need to use GPS positioning all the time. While maintaining the accuracy of business scene recognition, the number of positioning times and power consumption are greatly reduced. And as the learning of scene features increases, the scene feature data is constantly improved. In the later stage, no matter where the user wants to go, the number of times GPS positioning is used is getting less and less. For the realization of business scene recognition, the overall power consumption that can be saved is increasing.
[0340] The above describes the method for refreshing the time of the next positioning involved in the embodiment of the present application, and the following describes some power saving methods involved in the embodiment of the present application. It is worth noting that the power saving method can be applied to business scene recognition with different scene recognition accuracies.
[0341] In one example, when it is detected that the user stops moving / stationary, the electronic device stops positioning and / or stops scanning WiFi. For example, the user's current posture can be analyzed by sensors such as acceleration sensors and gyroscope sensors in the electronic device, combined with a network model that can implement posture learning, to determine whether the user is currently in a stopped state. When it is determined that the user is currently stopped moving / stationary, there is no need to identify again whether the electronic device is located in the target scene temporarily, and the electronic device can stop positioning and / or stop scanning WiFi operations, which can effectively save power consumption.
[0342] In one example, when it is detected that the user's range of movement is less than or equal to a preset range, the electronic device stops positioning and / or stops scanning WiFi. The range of movement can be represented by the number of steps. For example, the user's range of movement is less than or equal to the preset range, and the number of steps the user is currently walking can be less than or equal to the preset number of steps (such as 40 steps). The number of steps can be counted by a pedometer in the electronic device. When it is determined that the user's range of movement is less than or equal to the preset range, there is no need to identify again whether the electronic device is located in the target scene temporarily, and the electronic device can stop positioning and / or stop scanning WiFi operations, which can effectively save power consumption.
[0343] Optionally, the present application embodiment also provides a method for switching positioning modes, and the process is described in detail below. Fig.19 , Fig.19 It is a schematic diagram of switching positioning modes shown in an exemplary embodiment of the present application.
[0344] In one example, if Fig.18 As shown, the area where the electronic device may be located is divided into an irrelevant area, a low-relevance area, and a high-relevance area. The method of using Cell-ID positioning is called a base station scanning mode. When the electronic device is in an irrelevant area, the base station scanning mode is used. Fig.19 As shown, when the business scene recognition starts, the electronic device uses the base station scanning mode. If the base station signal does not match the low-correlation area at this time, it is determined that the electronic device is currently in an irrelevant area. It can be understood that the base station information of the base station currently connected to the electronic device does not match any base station fence snapshot at this time, and it is determined that the electronic device is currently in an irrelevant area.
[0345] If the base station signal matches the low correlation area, but the WIFI signal does not match the high correlation area, it is determined that the electronic device is currently in the low correlation area. It can be understood that at this time, the base station information of the base station currently accessed by the electronic device matches a base station fence snapshot, but the WIFI list of the electronic device does not match the WIFI feature, and it is determined that the electronic device is currently in the low correlation area. When the electronic device is in a low correlation area, the network scanning mode is adopted. For example, positioning is performed by using GPS. Optionally, when the electronic device is in a low correlation area, if the base station signal does not match the low correlation area, it is determined that the electronic device is currently in an irrelevant area.
[0346] When the electronic device is in a high correlation area, the online positioning mode is adopted. For example, the base station information of the base station currently accessed by the electronic device matches a base station fence snapshot, and the WIFI list of the electronic device also matches the WIFI feature, and it is determined that the electronic device is currently in a high correlation area. Optionally, when the electronic device is in a high correlation area, it can be determined again based on the online positioning result whether the electronic device is currently located in a high correlation area, a low correlation area, or an irrelevant area. For example, according to the online positioning result, it is determined that the base station information of the base station currently accessed by the electronic device matches a base station fence snapshot, and the WIFI list of the electronic device also matches the WIFI feature, and it is determined that the electronic device is still in a high correlation area. For another example, according to the online positioning result, it is determined that the base station signal matches the low correlation area, but the WIFI signal does not match the high correlation area, then it is determined that the electronic device is currently in a low correlation area. For another example, according to the online positioning result, it is determined that the base station signal does not match the low correlation area, then it is determined that the electronic device is currently in an irrelevant area.
[0347] In this implementation, the base station scanning mode, network scanning mode and online positioning mode are flexibly switched to accurately determine whether the electronic device is currently in an irrelevant area, a low-correlation area, or a high-correlation area, thereby improving the flexibility and real-time nature of judging the area where the electronic device is located, and providing a guarantee for the accuracy and real-time nature of business scenario identification.
[0348] Finally, a brief summary is given of the ways to save power consumption in the methods for identifying business scenarios provided in various embodiments of the present application. The details are as follows:
[0349] It has been verified that the power consumption required to achieve indoor and outdoor recognition is 0.1mAh / time, the power consumption required for WIFI feature matching is 0.05mAh / time, the power consumption required for GPS positioning is 0.05mAh / time, the power consumption required for Cell-ID positioning is 0.005mAh / time, and the power consumption required for cellular feature matching (such as base station information matching with base station fence snapshot) is negligible. Correspondingly, there is no error in indoor and outdoor recognition, the error of WIFI feature matching is 5-50 meters, the error of GPS positioning is 10-15 meters, the error of Cell-ID positioning is 100-200 meters, and the error of cellular feature matching is 400-800 meters.
[0350] The method for business scenario identification provided in the embodiment of the present application is mainly implemented by combining cellular feature matching, Cell-ID positioning, GPS positioning and WIFI feature matching. In most cases, cellular feature matching and Cell-ID positioning are mainly used, and GPS positioning and WIFI feature matching are supplementary. The power consumption required by the former is particularly small, and the error of the latter is very small. Therefore, while ensuring the accuracy of business scenario identification, the power consumption required for business scenario identification is greatly reduced.
[0351] The embodiment of the present application collects scene crowdsourcing data to learn the scene features corresponding to different services. With continuous learning, the learned scene features become more and more complete. When business scene identification is performed based on the scene features, it can be achieved in most cases through cellular feature matching and Cell-ID positioning. The number of GPS positioning required will become less and less, and power consumption will continue to decrease. At the same time, as the learned scene features become more and more complete, no matter where the user moves to in the later stage, the scene features can be used to quickly identify whether the user has entered the business scene, thereby improving real-time performance.
[0352] For easier understanding, please refer to Fig. 20 , Fig. 20 FIG. 1 is a schematic diagram showing a power consumption and real-time change of an exemplary embodiment of the present application. Fig. 20 As shown in (a) in Figure 1, during cold start, i.e. before learning scene features, the required power consumption is 2.5 mAh / day. After learning scene features, the power consumption drops to 1.5 mAh / day. Fig. 20 As shown in (b) in the figure, during cold start, that is, before learning the scene features, the real-time performance is 30 seconds. After learning the scene features, the real-time performance is 3 seconds.
[0353] The embodiment of the present application also evaluates the movement speed according to the user's current movement state, and then predicts the time of the next positioning according to the movement speed and the distance to the destination. During the whole process, there is no need to use GPS positioning all the time, which greatly reduces the number of positioning times and reduces power consumption.
[0354] The embodiment of the present application also continuously refreshes the time of the next positioning according to the snapshot of the base station fence matched during the user's travel. During the whole process, there is no need to use GPS positioning all the time. While maintaining the accuracy of business scene recognition, it greatly reduces the number of positioning and WIFI scanning times, and reduces power consumption. And as the learning of scene features increases, the scene feature data is continuously improved. In the later stage, no matter where the user wants to go, the number of times GPS positioning is used is getting less and less. For realizing business scene recognition, the overall power consumption that can be saved is increasing.
[0355] The embodiment of the present application also provides a WIFI chip, which can be installed in an electronic device, and the scanning power consumption of the WIFI chip is much lower than that of the existing WIFI chip. According to the test, the scanning power consumption of the WIFI chip provided by the present application is only one tenth of the scanning power consumption of the existing WIFI chip.
[0356] In one example, when scanning WIFI, the WIFI chip provided by the present application will also parse the data packets discarded in the prior art, thereby scanning more results in one scanning process. The WIFI chip provided by the present application can also perform multi-channel parallel scanning, greatly improving the coverage of WIFI scanning results. When the same number of scanning results are required, the number of scans of the WIFI chip provided by the present application is significantly reduced, thereby reducing scanning power consumption.
[0357] In one example, since the power consumption required for a WIFI chip to scan a 5 GHz frequency band is much greater than the power consumption required for scanning a 2.4 GHz frequency band, the WIFI chip provided in the present application may only scan a 2.4 GHz frequency band, thereby greatly reducing scanning power consumption.
[0358] The above describes in detail the examples of business scenario identification provided by the embodiments of the present application. It is understandable that, in order to implement the above functions, the electronic device includes hardware and / or software modules corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application in combination with the embodiments, but such implementation should not be considered to exceed the scope of the present application.
[0359] The embodiment of the present application can divide the functional modules of the electronic device according to the above method example. For example, each function can be divided into various functional modules, such as a monitoring unit, an acquisition unit, a processing unit, a display unit, etc., or two or more functions can be integrated into one module. The above integrated module can be implemented in the form of hardware or in the form of a software functional module. It should be noted that the division of modules in the embodiment of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation.
[0360] It should be noted that all relevant contents of each step involved in the above method embodiment can be referred to the functional description of the corresponding functional module and will not be repeated here.
[0361] The electronic device provided in this embodiment is used to perform the above-mentioned business scenario recognition, and thus can achieve the same effect as the above-mentioned implementation method.
[0362] In the case of an integrated unit, the electronic device may further include a processing module, a storage module and a communication module. The processing module may be used to control and manage the actions of the electronic device. The storage module may be used to support the electronic device to execute stored program codes and data, etc. The communication module may be used to support the electronic device to communicate with other devices.
[0363] Among them, the processing module can be a processor or a controller. It can implement or execute various exemplary logic boxes, modules and circuits described in conjunction with the disclosure of this application. The processor can also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of digital signal processing (DSP) and a microprocessor, etc. The storage module can be a memory. The communication module can specifically be a device that interacts with other electronic devices, such as a radio frequency circuit, a Bluetooth chip, a WiFi chip, etc.
[0364] In one embodiment, when the processing module is a processor and the storage module is a memory, the electronic device involved in this embodiment may be a Figure 7 Device of the structure shown.
[0365] An embodiment of the present application further provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the processor executes the business scenario recognition method of any of the above embodiments.
[0366] The embodiment of the present application also provides a computer program product. When the computer program product is run on a computer, the computer is enabled to execute the above-mentioned related steps to implement the business scenario identification method in the above-mentioned embodiment.
[0367] In addition, an embodiment of the present application further provides a device, which may be a chip, a component or a module, and the device may include a connected processor and a memory; wherein the memory is used to store computer-executable instructions, and when the device is running, the processor may execute the computer-executable instructions stored in the memory, so that the chip executes the business scenario recognition method in the above-mentioned method embodiments. Optionally, the WIFI chip provided by the present application may also be integrated in the chip.
[0368] Among them, the electronic device, computer-readable storage medium, computer program product or chip provided in this embodiment are all used to execute the corresponding methods provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding methods provided above and will not be repeated here.
[0369] Through the description of the above implementation methods, technical personnel in the relevant field can understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.
[0370] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0371] The units described as separate components may or may not be physically separated, and the components shown as units may be one physical unit or multiple physical units, that is, they may be located in one place or distributed in multiple different places. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.
[0372] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0373] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium, including several instructions to enable a device (which can be a single-chip microcomputer, chip, etc.) or a processor (processor) to perform all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program code.
[0374] The above contents are only specific implementation methods of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
Claims
1. A business scenario identification method, characterized in that: Applied to electronic equipment, the method comprises: When a scene recognition request of a target service is monitored, base station information of a base station currently accessed by the electronic device and scene recognition accuracy of the target service are obtained, the base station information including a target operator identifier, a target cell number, and a target base station number, the scene recognition request is used to request to identify whether the electronic device is located in a target scene associated with the target service; the scene recognition accuracy includes high accuracy; detecting that the base station information matches an operator identifier, a cell ID, and a base station ID in a base station fence snapshot, the base station fence snapshot including a scene fence identifier; Determine a target scene fence snapshot according to a scene fence identifier in a base station fence snapshot that matches the base station information; the target scene fence snapshot includes a WiFi feature; Determine a fence area corresponding to the target scene fence snapshot; Obtaining the current location of the electronic device; If it is detected that the current location is within the fenced area, obtaining a WiFi list of the electronic device; If it is detected that the WiFi list matches the WiFi feature, it is determined that the electronic device is located within the target scene.
2. The method according to claim 1, characterized in that When the scene recognition accuracy includes low accuracy, the method further includes: If the base station information matches the operator identification, cell number and base station number in a base station fence snapshot, it is determined that the electronic device is located in the target scene.
3. The method according to claim 2, characterized in that The method further comprises: If the base station information does not match the operator identifier, cell number, and base station number in any base station fence snapshot, determining a target area according to the target service, the target area being an area corresponding to a destination, and the destination being a location where the target service is implemented; Obtaining the current location of the electronic device; If it is detected that the current position of the electronic device is within the target area, it is determined that the electronic device is located within the target scene.
4. The method according to claim 1, characterized in that When the scene recognition accuracy includes medium accuracy, the method further includes: If the base station information matches the operator identifier, cell number and base station number in a base station fence snapshot, a target scene fence snapshot is determined according to the scene fence identifier in the base station fence snapshot that matches the base station information; the target scene fence snapshot includes the latitude and longitude information of the center point of the scene fence and the radius of the scene fence; Determine a fence area according to the latitude and longitude information of the center point of the scene fence and the radius of the scene fence; Obtaining the current location of the electronic device; If it is detected that the current position of the electronic device is within the fence area, it is determined that the electronic device is located within the target scene.
5. The method according to claim 1, characterized in that The WiFi list includes at least one WiFi identification information and a WiFi strength corresponding to each WiFi identification information, the WiFi feature includes a WiFi identification information list and a target matching threshold corresponding to the WiFi identification information list, and if it is detected that the WiFi list matches the WiFi feature, determining that the electronic device is located in the target scene includes: Determine a matching degree threshold corresponding to the WiFi list; If it is detected that the WiFi identification information in the WiFi list matches the WiFi identification information list in the WiFi feature, and the matching degree threshold is greater than or equal to the target matching degree threshold, it is determined that the electronic device is located in the target scene.
6. The method according to claim 5, characterized in that The method further comprises: If it is detected that the WiFi list does not match the WiFi feature, obtain a WiFi list generated by a third-party application; If it is detected that the WiFi list generated by the third-party application matches the WiFi feature, it is determined that the electronic device is located in the target scene.
7. The method according to any one of claims 1 to 6, characterized in that The method further comprises: If it is detected that the WiFi list of the electronic device matches the WiFi features in any scene fence snapshot, it is determined that the electronic device is located in the target scene.
8. The method according to any one of claims 1 to 7, characterized in that The method further comprises: Acquiring a motion status of a user carrying the electronic device; predicting a first movement speed of the user according to the movement state; Determine a destination for implementing the target service according to the target service, and determine a first distance between the current location of the user and the destination; The time for next positioning is predicted according to the first movement speed and the first distance.
9. The method according to claim 1, characterized in that The obtaining the current position of the electronic device comprises: The current location of the electronic device is obtained through a global satellite positioning system.
10. The method according to claim 8, characterized in that The base station fence snapshot includes the latitude and longitude information of the center point of the base station fence, and the method further includes: If, during the movement of the electronic device, it is detected that the base station information of the base station currently accessed by the electronic device matches the target base station fence snapshot, the location of the user is determined according to the latitude and longitude information of the center point of the base station fence of the target base station fence snapshot; determining a second distance based on the user's location and the destination; A second movement speed of the user is determined, and a time for next positioning is updated according to the second movement speed and the second distance.
11. The method according to any one of claims 1 to 10, characterized in that The method further comprises: When the electronic device is located in the target scene, acquiring the latest position of the electronic device; Through the latest position, it is determined whether the electronic device has left the target scene.
12. An electronic device, characterized in that: include: one or more processors; one or more memories; The memory stores one or more programs, and when the one or more programs are executed by the processor, the electronic device executes the method according to any one of claims 1 to 11.
13. A chip, characterized in that: include: A processor, configured to call and run a computer program from a memory, so that an electronic device equipped with the chip executes a method as claimed in any one of claims 1 to 11.
14. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor is caused to perform the method according to any one of claims 1 to 11.
Citation Information
Patent Citations
Intelligent position monitoring method and device and electronic equipment
CN110267207A
Network positioning method and device, electronic equipment and storage medium
CN111698648A
Express pickup reminding method and device
CN114463898A
Positioning method, system and device based on electronic fence and storage medium
CN114719842A
Network switching method and terminal
CN115002849A
