Method and device for improving recognition accuracy of object attributes

Abstract

The present application discloses a method and device for improving recognition accuracy of object attributes. The method comprises: obtaining first attribute data of a target object in a sensing area; in response to the first attribute data not satisfying a predetermined sensing condition, querying nodes by means of a target node to determine N target auxiliary nodes matched with the first attribute data, wherein N is a positive integer greater than or equal to 1; and obtaining data from the target auxiliary nodes, wherein the data comprises second attribute data of the target object in the sensing area, and the accuracy of the second attribute data is higher than that of the first attribute data.

Description

Method and device for improving recognition accuracy of object attributes

[0001] This application claims priority to the Chinese patent application filed with the China Patent Office on September 25, 2023, with application number 202311243683.9 and invention name “Method and device for improving the recognition accuracy of object attributes”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the field of data processing, and in particular to a method and device for improving the recognition accuracy of object attributes. Background Art

[0003] If an object, such as a person or object, appears within the sensing area, wireless sensing technology can be used to obtain parameters such as the object's distance and direction within the sensing area. Currently, the acquisition of these object parameters may be inaccurate. Improving this accuracy has become a pressing technical challenge.

[0004] Summary of the Invention

[0005] According to a first aspect of the present application, a method for improving the recognition accuracy of object attributes is provided, the method comprising:

[0006] Obtaining first attribute data of the target object within the perception area;

[0007] In response to the first attribute data not satisfying a predetermined perception condition, querying the node using the target node to determine N target auxiliary nodes that match the first attribute data, where N is a positive integer greater than or equal to 1;

[0008] Data from the target auxiliary node is obtained, where the data includes second attribute data of the target object within the perception area, and the accuracy of the second attribute data is better than that of the first attribute data.

[0009] In one possible implementation, the target node includes a first role node;

[0010] The querying of the node using the target node to determine N target auxiliary nodes matching the first attribute data includes:

[0011] Obtaining pre-configuration information of a second role node located in the sensing area, the pre-configuration information including fixed location information of the second role node;

[0012] Based on the pre-configured information, N nodes matching the first attribute data are determined from the second role nodes located in the perception area as target auxiliary nodes.

[0013] In one possible implementation, the target node includes a first role node;

[0014] The querying of the node using the target node to determine N target auxiliary nodes matching the first attribute data includes:

[0015] Initiate a query request to the second role node located in the sensing area;

[0016] Based on the feedback information, N nodes matching the first attribute data are determined from the second character nodes located in the sensing area as target auxiliary nodes;

[0017] The feedback information is the real-time location information of the node fed back by the second role node in response to the query request.

[0018] In one possible implementation manner, the target node includes a second role node; the first attribute data is used to represent the position of the target object in the perception area;

[0019] The querying of the node using the target node to determine N target auxiliary nodes matching the first attribute data includes:

[0020] Determining a target management node of the target node based on the first attribute data, where the target management node is a node that manages the target node, and a perception area of ​​the target management node at least covers a position of the target object within the perception area;

[0021] When the target node accesses the communication domain where the target management node is located, sending a request to the target management node;

[0022] When the information received as feedback from the target management node in response to the request in the communication domain is predetermined information, the target management node is used as a target auxiliary node.

[0023] In one possible implementation, the target node includes a first role node and at least one second role node;

[0024] The querying of the node using the target node to determine N target auxiliary nodes matching the first attribute data includes:

[0025] Obtaining pre-configuration information of M second role nodes located in the sensing area, excluding the at least one second role node, wherein the pre-configuration information includes fixed position information of the M second role nodes; M is a positive integer greater than or equal to 1;

[0026] Based on the pre-configuration information of the M second role nodes, N nodes matching the first attribute data are determined from the M second role nodes as target auxiliary nodes.

[0027] In one possible implementation, the target node includes a first role node and at least one second role node;

[0028] The querying of the node using the target node to determine N target auxiliary nodes matching the first attribute data includes:

[0029] Initiate a query request to L second role nodes located in the perception area, excluding the at least one second role node, where L is a positive integer greater than or equal to 1;

[0030] Based on the feedback information of the L second role nodes, determining N nodes matching the first attribute data from the L second role nodes as target auxiliary nodes;

[0031] The feedback information is the real-time location information of the node fed back by the second role node in response to the query request.

[0032] In one embodiment, obtaining data from the target auxiliary node, wherein the data includes second attribute data of the target object within the sensing area, includes:

[0033] Obtaining second attribute data of the target object within the perception area;

[0034] Based on the first attribute data and the second attribute data, third attribute data is obtained, wherein the accuracy of the third attribute data is better than that of the first attribute data.

[0035] In one possible implementation manner, obtaining first attribute data of the target object within the perception area includes:

[0036] In response to a target object appearing within a perception area of ​​the target node, first attribute data of the target object within the perception area is obtained based on a perception signal sent and a received perception signal by the target node.

[0037] In one embodiment, the method further comprises:

[0038] outputting the second attribute data;

[0039] Alternatively, in response to the first attribute data satisfying a preset perception condition, the first attribute data is output.

[0040] According to a second aspect of the present application, there is provided a device for improving the recognition accuracy of object attributes, comprising:

[0041] a processor configured to obtain first attribute data of a target object within a sensing area; and in response to the first attribute data not satisfying a predetermined sensing condition, querying nodes to determine N target auxiliary nodes that match the first attribute data, where N is a positive integer greater than or equal to 1;

[0042] The transceiver is used to obtain data from the target auxiliary node, where the data includes second attribute data of the target object within the sensing area, and the accuracy of the second attribute data is better than that of the first attribute data.

[0043] According to a third aspect of the present application, an electronic device is provided, including:

[0044] at least one processor; and

[0045] a memory communicatively connected to the at least one processor; wherein,

[0046] The memory stores instructions that can be executed by the at least one processor. The instructions are executed by the at least one processor to enable the at least one processor to perform the method described in this application.

[0047] According to a fourth aspect of the present application, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute the method described in the present application.

[0048] The present application provides a method and device for improving the recognition accuracy of object attributes, obtaining first attribute data of a target object within a perception area, and in response to the first attribute data not meeting a predetermined perception condition, querying N target auxiliary nodes that match the first attribute data, obtaining second attribute data from the target auxiliary nodes that is more accurate than the first attribute data, thereby achieving accurate acquisition of attribute data such as location.

[0049] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] The above and other objects, features and advantages of the exemplary embodiments of the present application will become readily understood by reading the detailed description below with reference to the accompanying drawings. In the accompanying drawings, several embodiments of the present application are shown in an illustrative and non-limiting manner, in which:

[0051] In the drawings, the same or corresponding reference numerals denote the same or corresponding parts.

[0052] Figures 1(a) to 1(d) show schematic diagrams of coverage of the sensing areas of nodes of two roles in an embodiment of the present application;

[0053] FIG2 is a schematic diagram showing a flow chart of a method for improving the recognition accuracy of object attributes according to an embodiment of the present application;

[0054] FIG3 is a schematic diagram showing a flow chart of a method for improving the recognition accuracy of object attributes in the following application scenario according to an embodiment of the present application;

[0055] FIG4 is a schematic diagram showing a flow chart of a method for improving the recognition accuracy of object attributes under application scenario 2 in an embodiment of the present application;

[0056] FIG5 is a schematic diagram showing a flow chart of a method for improving the recognition accuracy of object attributes in application scenario three according to an embodiment of the present application;

[0057] FIG6 shows a first schematic diagram of the structure of a device for improving the recognition accuracy of object attributes according to an embodiment of the present application;

[0058] FIG7 shows a second schematic diagram of the structure of a device for improving the recognition accuracy of object attributes according to an embodiment of the present application;

[0059] FIG8 shows a schematic diagram of the structure of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION

[0060] In order to make the purpose, features, and advantages of this application more obvious and easy to understand, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without making creative efforts shall fall within the scope of protection of this application.

[0061] In order to make the purpose, technical solutions and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be regarded as limiting this application. All other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0062] In the following description, reference is made to “some embodiments”, which describes a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0063] In the following description, the terms "first\second" involved are merely used to distinguish similar objects and do not represent a specific ordering of the objects. It is understandable that "first\second" can be interchanged with a specific order or sequence where permitted, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.

[0064] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application pertains. The terms used herein are for the purpose of describing the embodiments of this application only and are not intended to limit this application.

[0065] It should be understood that in the various embodiments of the present application, the size of the serial number of each implementation process does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0066] Wireless sensing technology, as a communications technology, uses wireless signals to perceive the surrounding environment. By detecting changes in certain characteristics of wireless signals (such as phase, power, and eigenvalues), it can extract specific information or events that represent the occurrence of certain behaviors, thereby satisfying desired services or facilitating more efficient communication transmission. Wireless sensing technology can be used to detect the presence of objects such as people and objects within the sensing area, monitor the health of objects within the sensing area (such as heartbeat and breathing), and detect unexpected events within the sensing area (such as falls).

[0067] In wireless sensing technology, there are two types of nodes: one is the management node (management node, referred to as G node), and the other is the node managed by the G node (managed node, T node). Both types of nodes have their own sensing area. As shown in Figure 1(a), the G node perceives the environment within its sensing area by sending and receiving sensing signals. This information includes determining whether an object has entered the sensing area and, if so, the distance and direction of the object. As shown in Figure 1(b), the T node can also send and receive sensing signals. By doing so, it can determine whether an object has appeared within the T node's sensing area and, if so, the distance and direction of the object within the sensing area.

[0068] In practical applications, the sensing range (sensing area range) of nodes (G nodes and T nodes) in wireless sensing technology depends to a certain extent on the transmission power of the sensing signal.

[0069] As shown in Figure 1(c) and Figure 1(d), in actual applications, objects that appear in the G node perception area and the T node perception area may be located in the intersection area of ​​the two node perception areas. Because the intersection area is located both in the perception area of ​​the G node and in the perception area of ​​the T node, the intersection area can be regarded as the perception enhancement coverage area of ​​the GT node group (referred to as the enhanced perception area for short). In this application, for objects that appear in this area, the two nodes can be used to perceive the distance, orientation and other parameters of the object separately to achieve accurate perception of the distance, orientation and other parameters of the object.

[0070] FIG2 shows a schematic diagram of a first implementation flow of a method for improving the recognition accuracy of object attributes in an embodiment of the present application. The method is applied to a target node. The target node can be a G node or a T node.

[0071] As shown in FIG2 , the method includes:

[0072] S(step) 201: Obtain first attribute data of the target object within the perception area.

[0073] The target node realizes the perception of the environment in the perception area by sending and receiving sensing signals. When it senses that a target object such as a person or object has entered the perception area, it uses the sensing signal to obtain the location of the target object in the perception area.

[0074] During implementation, in response to the target object appearing within the target node's perception area, first attribute data of the target object within the perception area is obtained based on the perception signals transmitted and received by the target node. Specifically, in wireless sensing technology, the target node calculates the autocorrelation between the two perception signals transmitted and received, and analyzes the location of the target object within the perception area based on the autocorrelation result. For details on this process, please refer to Wireless Sensing Technology and will not be elaborated on here.

[0075] The first attribute data at least includes the position (distance and orientation) of the target object within the perception area of ​​the target node. In addition, the first attribute data may also include the motion trajectory and / or speed of the target object within the perception area.

[0076] S202: In response to the first attribute data not meeting the predetermined perception condition, query the node using the target node to determine N target auxiliary nodes that match the first attribute data, where N is a positive integer greater than or equal to 1.

[0077] Determine whether the first attribute data satisfies a predetermined perception condition. If the first attribute data does not satisfy the predetermined perception condition, then utilize S202 and S203 to accurately acquire the attribute data of the target object. If the first attribute data satisfies the predetermined perception condition, then output the first attribute data of the target object.

[0078] In practical applications, wireless sensing services have certain requirements, such as location information accuracy. These requirements can be considered as predetermined sensing conditions. If the first attribute data meets these requirements, the predetermined sensing conditions are considered met; otherwise, the predetermined sensing conditions are considered not met.

[0079] In this step, when the first attribute data cannot meet the wireless sensing service requirement, the target node queries a node that can assist it in sensing the location of the target object.

[0080] For example, if the first attribute data is the location of the target object, the target auxiliary node that matches the first attribute data can be: a node in the target node query whose location is close to the target object; or a node in the query whose sensing area includes the target object's location. The number of target auxiliary nodes found can be one, two, or more, depending on the specific situation.

[0081] In the case where the target node is a G-node in a management role, the target auxiliary node may be a T-node. In the case where the target node is a T-node, the target auxiliary node may be a G-node.

[0082] S203: Obtain data from the target auxiliary node, where the data includes second attribute data of the target object within the perception area, and the second attribute data is more accurate than the first attribute data.

[0083] The target node configures a sensing signal for the target auxiliary node, such as the type of sensing signal (G node or T node), the transmission power of the sensing signal, the signal bandwidth, etc. It can be understood that because the target object is located within the enhanced sensing area of ​​the target node and the target auxiliary node, the accuracy of the calculation of the target object's position is directly proportional to the magnitude of the transmission power of the sensing signal. Therefore, compared with the transmission power of the sensing signal transmitted and received by the target node, the transmission power of the sensing signal configured by the target node for the target auxiliary node is greater. Compared with the position of the target object obtained by the target node using the sensing signal with relatively low transmission power transmitted and received by the target node, the position of the target object obtained by the target auxiliary node using the sensing signal with high transmission power transmitted and received by the target node is more accurate, thereby achieving precise positioning of the target object.

[0084] In S201 to S203, the target node obtains the first attribute data of the target object within the perception area, and in response to the first attribute data not meeting the predetermined perception condition, queries N target auxiliary nodes that match the first attribute data, and obtains second attribute data from the target auxiliary nodes that is more accurate than the first attribute data, thereby realizing accurate acquisition of attribute data such as location.

[0085] In some embodiments, the aforementioned scheme for obtaining data from the target auxiliary node, wherein the data includes second attribute data of the target object within the perception area, includes: obtaining second attribute data of the target object within the perception area; and obtaining third attribute data based on the first attribute data and the second attribute data, wherein the accuracy of the third attribute data is better than that of the first attribute data.

[0086] During implementation, a mean or weighted average calculation can be performed on the first and second attribute data to obtain the third attribute data. Because the second attribute data is obtained based on a sensing signal with high transmit power, the second attribute data is more accurate. Therefore, the third attribute data obtained based on the highly accurate second attribute data will also be more accurate than the first attribute data. This allows the use of target nodes and target auxiliary nodes to accurately obtain attribute data such as location.

[0087] In some embodiments, the second attribute data may be output after S203. Alternatively, the first attribute data may be output in response to the first attribute data satisfying a preset perception condition. Outputting the first or second attribute data for subsequent use is easy to apply.

[0088] In some embodiments, the target node includes a first role node (G node). The second role node is a T node. The aforementioned solution of using the target node to query the node to determine N target auxiliary nodes that match the first attribute data may include the following two scenarios:

[0089] Scenario 1: Obtain pre-configuration information of a second role node located within the perception area, the pre-configuration information including fixed location information of the second role node; based on the pre-configuration information, determine N nodes that match the first attribute data from the second role nodes located within the perception area as target auxiliary nodes.

[0090] Scenario 1 is when the T-node queried by the target node is a fixed-position node. In this case, the target node obtains the position information of each T-node at a fixed position within the perception area, and queries from such nodes the T-node that can assist the target node in perception, which is feasible and practical.

[0091] Scenario 2: A query request is initiated to a second role node located in the perception area; based on the feedback information, N nodes matching the first attribute data are determined from the second role nodes located in the perception area as target auxiliary nodes; wherein the feedback information includes the real-time location information of the nodes fed back by the second role node in response to the query request.

[0092] The second scenario involves the target node querying a mobile T-node. In this scenario, the target node obtains the real-time location information of all mobile T-nodes within its sensing area and, from these nodes, searches for T-nodes that can assist the target node in sensing. If the target auxiliary node is considered an auxiliary sensing node, the aforementioned solution allows for flexible selection of auxiliary sensing nodes, making it suitable for this application.

[0093] If the target node is regarded as the initial perception node and the target auxiliary node is the auxiliary perception node, then the initial perception node's perception of the target object's position can be regarded as the first layer of perception, and the auxiliary perception node's perception of the target object's position can be regarded as the second layer of perception. In this way, the technical solution of the present application can be regarded as a layered perception solution, which can enhance the accuracy of obtaining attribute data.

[0094] 3 , taking the G node as the initial perception node and the T node as the auxiliary perception node (application scenario one) as an example, the technical solution of this application is described in detail.

[0095] In application scenario 1, the target node is a G node and the target auxiliary node is a T node. The G node initial perception scenario is suitable for wireless perception environments where T nodes need to save energy and are mostly silent.

[0096] In application scenario 1, the specific process and signaling interaction between GT nodes include the following steps and content:

[0097] S301: Node G serves as a management node and periodically sends and receives sensing signals to sense the surrounding environment.

[0098] In this step, the G node periodically senses the surrounding environment within the sensing area by periodically sending and receiving sensing signals.

[0099] The perception signal can be a physical layer reference signal from an existing wireless perception system, or it can be an enhanced physical layer reference signal. For example, based on the existing reference signal, an enhanced signal type can be designed to provide a larger bandwidth or more transmission cycles. Alternatively, a reference signal specifically optimized for perception, such as a sequence signal with superior autocorrelation characteristics, can be designed as the perception signal.

[0100] S302: Based on the self-transmitted and self-received sensing signals, the G node detects whether a target object enters the sensing area.

[0101] Node G performs autocorrelation on the self-transmitted and self-received sensing signals and extracts changes in channel state information from the autocorrelation results. If there is a significant change, it indicates that a target object, such as a person or object, has entered the sensing area. Node G then performs a rough sensing of the target object and executes S303. If there is no change or a small change, it indicates that no target object has entered the sensing area and the sensing of the surrounding environment continues.

[0102] S303: Based on the self-transmitted and self-received sensing signals, the G node roughly senses the distance and direction of the target object.

[0103] The process of the G node obtaining the rough location information of the target object through the self-transmitted and self-received sensing signals can be found in the relevant description and will not be repeated here.

[0104] Node G is a single node. Given the limitations of single-node perception, its perception results may have a large error range. The target object's probable location is represented by its approximate location and the radius of a circle centered at that location, for example, R = (pest, rest). Pest is the coordinate of the location perceived by node G. R is the radius of the circle centered at that coordinate. R represents the target object's probable location within the perception area.

[0105] Alternatively, the possible location of the target object within the perception area is represented by a closed polygon consisting of a series of coordinate points. For example, R = (pest, p1, p2, …, pk), where pest is the coordinate of the location perceived by node G. pk is the coordinate value of the kth node within the perception area that surrounds pest and forms a closed polygon with pest.

[0106] The range of possible locations of the target object within the sensing area depends on the transmission configuration of the self-transmitted and self-received signals and the quality of the received signals, such as the transmission signal bandwidth, signal transmission power, and the signal-to-noise ratio of the received signal.

[0107] S304: Node G determines whether the perception accuracy needs to be increased.

[0108] The wireless sensing service requires sensing accuracy. A determination is made as to whether the target object's rough location meets the sensing accuracy requirements of the wireless sensing service. If not, a determination is made that there is a need to increase sensing accuracy, and the process proceeds to S305. If so, a determination is made that there is no need to increase sensing accuracy, and the process proceeds to S310 to output a rough sensing result. No auxiliary sensing node is required to assist in sensing.

[0109] Among them, if the wireless sensing service requirements cannot be met, for example, the wireless sensing service requires higher location accuracy, or, in addition to higher location accuracy, also requires the moving trajectory and / or speed of the target object, then auxiliary sensing node-T node collaborative perception is required.

[0110] S305: Node G queries node T.

[0111] The G node needs to query whether there are any T nodes nearby that can assist the G node in completing perception. The nodes that assist the G node in completing perception must have certain perception capabilities, such as the ability to transmit, receive, and process perception signals, air interface capabilities, and potential perception and resolution capabilities.

[0112] The T-nodes near the target object include two types: nodes with fixed positions and mobile nodes. Different query schemes are used for these two types of nodes.

[0113] Query solution 1: Applicable to T nodes with fixed positions within the perception area of ​​G nodes.

[0114] T-nodes with sensing capabilities within the sensing area must register with the G-node. The G-node records the pre-configuration information of these T-nodes. This pre-configuration information represents the T-node's sensing capabilities and its fixed location within the G-node's sensing area. Sensing capabilities include the sensing signal types supported by the T-node, the sensing signal transceiver mode, the supported sensing signal bandwidth, the maximum supported transmit power, the received signal sensitivity, and / or the number of antenna ports. Table 1 illustrates some of the pre-configuration information for T-nodes within the sensing area.

[0115] Table 1

[0116] The G node selects the T node within the sensing area that is close to the rough location of the target object as the target auxiliary node. Alternatively, the G node selects the T node that is close to the rough location of the target object, has a strong signal-to-noise ratio (SNR) of the sensing signal, and has a small channel state change as the target auxiliary node.

[0117] Alternatively, the G node initiates an assisted sensing request to a T node within the sensing area that is close to the approximate location of the target object. Alternatively, the G node initiates an assisted sensing request to a T node within the sensing area that is close to the approximate location of the target object, has a strong SNR for the sensing signal, and has minimal channel state variation. The T node then responds based on its actual situation to determine whether it is willing to serve as an assisted sensing node for collaborative sensing.

[0118] Query method 2: Applicable to mobile T nodes within the perception area of ​​G nodes.

[0119] This approach is suitable for mobile T-nodes within the G-node's sensing area. The G-node sends a sensing service query request to the mobile T-node. Upon receiving the sensing service query request, the mobile T-node feeds back its sensing capability information and real-time location.

[0120] Based on the feedback information from the mobile T-nodes, the G-node selects the mobile T-nodes whose real-time locations are close to the target object as target auxiliary nodes. Alternatively, the G-node selects the mobile T-nodes whose real-time locations are close to the target object, whose perceived signal SNR is strong, and whose channel state changes little as target auxiliary nodes.

[0121] Alternatively, a G node can initiate an assisted sensing request to a mobile T node whose real-time location is close to the target object. Alternatively, a G node can initiate an assisted sensing request to a mobile T node whose real-time location is close to the target object, whose perceived signal has a strong SNR, and whose channel state changes are minimal. The mobile T node then responds based on its actual situation, indicating whether it is willing to serve as an assisted sensing node for collaborative sensing.

[0122] Taking initiating an auxiliary perception request to the node as an example, continue to execute S306.

[0123] S306: The G node determines whether any T node responds to the auxiliary perception request initiated by it.

[0124] The T node that receives the auxiliary perception request can provide feedback on the auxiliary perception request based on its own actual situation to indicate that it is willing to serve as an auxiliary perception node of the G node for collaborative perception.

[0125] The feedback received from the auxiliary perception request can determine whether the node can participate in the auxiliary perception, which provides a certain degree of flexibility for whether the T node participates in the auxiliary perception.

[0126] It should be noted that the auxiliary perception request initiated by the G node to the T node can be sent to only one T node at a time, and the auxiliary perception request can be sent to different T nodes one by one. The auxiliary perception request can also be sent to multiple T nodes at the same time, and there is no specific limitation on this.

[0127] If no T node feeds back to the G node that it can participate in the auxiliary perception, the G node may directly output the rough position obtained in S303 as a result.

[0128] S307: The G node configures a perception signal for the auxiliary perception node - the T node.

[0129] The G node configures the corresponding sensing signals for the T nodes participating in the collaborative sensing, such as the sensing signal type, signal bandwidth, and transmit power, to ensure that the configured sensing signals can adapt to the capabilities of the T nodes and meet the requirements of wireless sensing services.

[0130] Here, compared with the transmission power of the perception signal sent and received by the target node, the G node will try to configure a larger transmission power for the T node within the capability of the T node so that the T node can detect the target object with a more accurate location.

[0131] S308: GT nodes send and receive perception signals to enhance perception of the target object.

[0132] Based on the configuration of the G node, the T node transmits a sensing signal. The sensing signal of the T node can be received by the G node as a self-received sensing signal. Based on the received sensing signal, the G node again determines the position of the target object within the sensing area of ​​the G node. It can be understood that, compared to the transmit power of the sensing signal used by the G node in S301, the transmit power of the sensing signal configured by the G node for the T node is greater, and the power of the sensing signal of the T node received by the G node is greater. Utilizing the sensing signal with greater power, the position of the target object within the sensing area of ​​the G node can be accurately calculated.

[0133] Alternatively, the G node transmits a sensing signal, which the T node receives based on its configuration, calculates the target object's location within the G node's sensing area, and feeds back to the G node. The G node configures a higher-power sensing signal for the T node, and using this higher-power sensing signal allows for accurate calculation of the target object's location within the G node's sensing area.

[0134] In the aforementioned solution, the second attribute data includes a position obtained using a sensing signal with greater power.

[0135] Using the sensing signal with greater power, the moving trajectory and / or moving speed of the moving object within the sensing area can also be calculated. The calculation process is described in the relevant instructions and will not be repeated here.

[0136] It can be understood that the auxiliary perception T-node is the node closest to the target object. From another perspective, the target object is within the perception area of ​​the auxiliary perception T-node, and naturally, it is within the intersection area of ​​the auxiliary perception T-node and the G-node. The intersection area is the perception enhancement area. Using the G-node and the auxiliary perception T-node to jointly perceive the target object within the perception enhancement area will inevitably obtain more accurate location information of the target object compared to the single-node perception of the G-node.

[0137] S309: Node G obtains more accurate (second) attribute data of the target object within the perception area.

[0138] As shown in S308, the G node may resolve or calculate the sensing signal with greater power to obtain a more accurate position. Alternatively, the G node receives a more accurate position calculated by the auxiliary sensing node based on the sensing signal with greater power.

[0139] In addition, the G node can perform an averaging operation or a weighted averaging operation on the rough position calculated in S303 and the position obtained using the sensing signal with greater power, thereby obtaining location information that is more accurate than the aforementioned rough position (the more accurate location information can be used as third attribute data).

[0140] The more accurate (secondary or tertiary) attribute data of the target object within the perception area can be used as the final perception result obtained through collaborative perception between GT nodes or assisted perception by the target auxiliary node. If necessary, the G node can output the final perception result for use by the perception service requester who requests the final perception result from the G node.

[0141] Application scenario one: Based on relevant protocols of wireless sensing technology such as the Star Flash Protocol, the Star Flash Protocol can be updated. For example, a report on the node perception capability is added to the protocol air interface (S305), a step is added to the protocol to query whether the T node is willing to participate in auxiliary perception (S306), and two expressions of the possible location of the target object in the perception area are defined in the protocol (S303).

[0142] In simple terms, in application scenario 1, the G node achieves preliminary perception of the target object within the perception area by sending and receiving sensing signals, obtaining a relatively rough perception result. By querying auxiliary nodes (T nodes) with sensing capabilities near the target object and scheduling auxiliary T nodes willing to participate in auxiliary perception, they can participate in enhanced perception of the target object, thereby obtaining a more accurate perception result of the target object.

[0143] Application scenario one uses G nodes and T nodes to achieve hierarchical perception. This hierarchical perception solution can enhance the accuracy of attribute data acquisition.

[0144] In some embodiments, the target node includes a second role node; the first attribute data is used to characterize the location of the target object within the perception area. Based on this, the aforementioned solution of using the target node to query the node to determine N target auxiliary nodes that match the first attribute data includes: determining the target management node of the target node based on the first attribute data, the target management node is a node that manages the target node, and the perception area of ​​the target management node must at least cover the location of the target object within the perception area; when the target node accesses the communication domain where the target management node is located, sending a request to the target management node; when the information received from the target management node in response to the request in the communication domain is predetermined information, using the target management node as the target auxiliary node.

[0145] The above solution is an application scenario where the T node is the initial perception node and the G node is the auxiliary perception node (Application Scenario 2). In Application Scenario 2, the T node queries the G node to achieve enhanced perception of the target object through collaboration between the T node and the G node, thereby obtaining more accurate attribute data. The following is a detailed description of the technical solution of this application in conjunction with Figure 4.

[0146] Application scenario 2 is suitable for situations where G nodes need to save energy in the perception environment, while T nodes can autonomously send and receive perception signals. In this scenario, after completing initial perception, T nodes need to request access from G nodes, and achieve enhanced perception through the combination of GT nodes.

[0147] In the second application scenario, the specific process and signaling interaction between the GT nodes include the following steps and contents.

[0148] S401: The T node periodically sends and receives sensing signals to sense the surrounding environment.

[0149] In this step, the T node periodically senses the surrounding environment within the sensing area by periodically sending and receiving sensing signals.

[0150] The perception signal can be a physical layer reference signal from an existing wireless perception system, or it can be an enhanced physical layer reference signal. For example, based on the existing reference signal, an enhanced signal type can be designed to provide a larger bandwidth or more transmission cycles. Alternatively, a reference signal specifically optimized for perception, such as a sequence signal with superior autocorrelation characteristics, can be designed as the perception signal.

[0151] S302: Based on the self-transmitted and self-received sensing signals, the T node detects whether a target object enters the sensing area.

[0152] The T node performs autocorrelation on the self-transmitted and self-received sensing signals and extracts changes in the channel state information from the autocorrelation results. If there is a large change, it indicates that a target object, such as a person or object, has entered the sensing area. The T node then performs a rough sensing of the target object and executes S403. If there is no change or a small change, it indicates that no target object has entered the sensing area and the sensing of the surrounding environment continues.

[0153] S403: Based on the self-transmitted and self-received sensing signals, the T node roughly senses the distance and direction of the target object.

[0154] The process of the T node obtaining the rough location information of the target object through the self-transmitted and self-received sensing signals can be found in the relevant description and will not be repeated here.

[0155] As a single node, the T-node's perception results may have a large margin of error, given the limitations of single-node perception. The target object's probable location is represented by its approximate location and the radius of a circle centered at that location, for example, R = (pest, rest). Pest is the coordinate of the location perceived by the T-node, and r is the radius of the circle centered at that coordinate. R represents the target object's probable location within the perception area.

[0156] Alternatively, the possible location of the target object within the perception area is represented by a closed polygon consisting of a series of coordinate points. For example, R = (pest, p1, p2, …, pk), where pest is the coordinate of the location perceived by the T node. pk is the coordinate value of the kth node within the perception area that surrounds pest and forms a closed polygon with pest.

[0157] The range of possible locations of the target object within the sensing area depends on the transmission configuration of the self-transmitted and self-received signals and the quality of the received signals, such as the transmission signal bandwidth, signal transmission power, and the signal-to-noise ratio of the received signal.

[0158] S404: The T node determines whether the perception accuracy needs to be increased.

[0159] The wireless sensing service requires sensing accuracy. A determination is made as to whether the target object's rough location meets the sensing accuracy requirements of the wireless sensing service. If not, a determination is made that there is a need to increase sensing accuracy, and the process proceeds to S405. If so, a determination is made that there is no need to increase sensing accuracy, and the process proceeds to S410 to output a rough sensing result. No auxiliary sensing node is required to assist in sensing.

[0160] Among them, if the wireless sensing service requirements cannot be met, for example, the wireless sensing service requires higher location accuracy, or, in addition to higher location accuracy, also requires the moving trajectory and / or speed of the target object, then auxiliary sensing node-G node collaborative perception is required.

[0161] S405: The T node requests access to the domain management G node.

[0162] Query for management nodes whose perception areas cover the perception area of ​​the T-node and the rough location of the target object. The management node found should geographically have a perception area covering the perception area of ​​the T-node and the rough location of the target object. It should also be the node responsible for managing the T-node.

[0163] The T node, as a node of the communication domain where the management node is located, accesses the communication domain and, based on the communication domain, initiates an (assisted perception) request to the G node to request the G node to implement assisted perception.

[0164] During the access process, indications of relevant information related to participation in perception can be added at the signaling level of the communication domain, such as the perception capability of the node and whether it participates in perception.

[0165] S406: Determine whether the G node responds to the auxiliary perception request (determine whether the G node is successfully accessed).

[0166] When G receives a (assisted sensing) request from a T-node, it decides whether to accept it based on its own circumstances. If G's traffic load is heavy and the required sensing resources cannot meet the assisted sensing requirements, it may reject the request. If G's traffic load is light, it may return a signaling indication of successful access and acceptance of assisted sensing.

[0167] If the G node responds with a signaling indication that it agrees to the assisted sensing request, it is considered to have responded to the assisted sensing request and the G node has successfully accessed. If the G node responds with a signaling indication that it rejects the request, it is considered to have responded to the assisted sensing request and the G node has not successfully accessed. If the G node does not respond to the (assisted sensing) request within a preset time, it is considered to have not responded to the assisted sensing request and the G node has not successfully accessed.

[0168] S407: Node G configures a perception signal for the initial perception node, node T.

[0169] Based on the wireless sensing service requirements and the sensing capabilities of the initial sensing T-node, the G-node configures the corresponding sensing signals for the initial sensing node, such as the sensing signal type, signal bandwidth, and transmit power. This ensures that the configured sensing signals are both adapted to the capabilities of the T-node and meet the wireless sensing service requirements.

[0170] Here, compared with the transmission power of the initial perception signal sent and received by the T node, the G node will try to configure a larger transmission power for the T node within the capability of the T node so that the T node can detect the target object with a more accurate location.

[0171] S408: GT nodes send and receive perception signals to enhance perception of the target object.

[0172] Based on the configuration of the G node, the T node transmits a sensing signal. The sensing signal of the T node can be received by the G node as a self-received sensing signal. Based on the received sensing signal, the G node again determines the position of the target object within the sensing area of ​​the G node. It can be understood that, compared to the transmit power of the sensing signal used by the G node in S401, the transmit power of the sensing signal configured by the G node for the T node is greater, and the power of the sensing signal of the T node received by the G node is greater. Utilizing the sensing signal with greater power, the position of the target object within the sensing area of ​​the G node can be accurately calculated.

[0173] Alternatively, the G node transmits a sensing signal, which the T node receives based on its configuration, calculates the target object's location within the G node's sensing area, and feeds back to the G node. The G node configures a higher-power sensing signal for the T node, and using this higher-power sensing signal allows for accurate calculation of the target object's location within the G node's sensing area.

[0174] In the aforementioned solution, the second attribute data includes a position obtained using a sensing signal with greater power.

[0175] By utilizing the sensing signal with greater power, the moving trajectory and / or moving speed of the moving object within the sensing area can also be calculated.

[0176] It can be understood that the G node's perception area covers the target object's location, as well as the T node's perception area. From another perspective, the target object is located in the intersection of the initial perception T node and the G node. This intersection area is the perception enhancement area. Using the initial auxiliary T node and the G node to jointly perceive the target object within the perception enhancement area will inevitably provide more accurate location information of the target object compared to single-node perception by the T node.

[0177] S409: Node G obtains more accurate (second) attribute data of the target object within the perception area.

[0178] As shown in S408, the G node may resolve or calculate the sensing signal with greater power to obtain a more accurate position. Alternatively, the G node receives a more accurate position calculated by the auxiliary sensing node based on the sensing signal with greater power.

[0179] In addition, the G node can perform an averaging operation or a weighted averaging operation on the rough position calculated in S403 and the position obtained using the sensing signal with greater power, thereby obtaining location information that is more accurate than the aforementioned rough position (the more accurate location information can be used as third attribute data).

[0180] The more accurate (secondary or tertiary) attribute data of the target object within the perception area can be used as the final perception result obtained through collaborative perception between GT nodes or assisted perception by the target auxiliary node. If necessary, the G node can output the final perception result for use by the perception service requester who requests the final perception result from the G node.

[0181] Application scenario two: Based on the relevant protocols of wireless sensing technology such as the Star Flash Protocol, the Star Flash Protocol can be updated. For example, an auxiliary sensing request for access to the sensing node can be added at the air interface (S405), and a protocol for whether the G node responds to the auxiliary sensing request (S406) can be added.

[0182] In simple terms, in application scenario 2, the T-node achieves preliminary perception of the target object within the perception area by automatically transmitting and receiving sensing signals, obtaining a relatively rough perception result. By querying the auxiliary node (G-node) and combining the T-node and G-node, enhanced perception of the target object is achieved, obtaining a more accurate perception result of the target object.

[0183] Application scenario two uses G nodes and T nodes to achieve hierarchical perception. This hierarchical perception solution can enhance the accuracy of attribute data acquisition.

[0184] In some embodiments, the target node includes a first role node (G node) and at least one second role node (T node). That is, the initial perception node includes a G node and a T node. Based on this, the aforementioned solution of using the target node to query the node to determine N target auxiliary nodes that match the first attribute data can be implemented in the following two ways.

[0185] Method 1: Obtain pre-configuration information of M second role nodes located in the perception area, excluding the at least one second role node, where the pre-configuration information includes fixed position information of the M second role nodes; M is a positive integer greater than or equal to 1; based on the pre-configuration information of the M second role nodes, determine N nodes that match the first attribute data from the M second role nodes as target auxiliary nodes.

[0186] Method 1 is for the case where the T-node queried by the target node is a fixed-position node. In this case, the target node obtains the location information of each T-node at a fixed position within the perception area, and queries from such nodes the T-node that can assist the target node in perception, which is highly feasible and practical.

[0187] Method 2: Initiate a query request to L second role nodes located in the perception area, excluding the at least one second role node, where L is a positive integer greater than or equal to 1; based on the feedback information of the L second role nodes, determine N nodes that match the first attribute data from the L second role nodes as target auxiliary nodes; wherein the feedback information includes the real-time location information of the node fed back by the second role node in response to the query request.

[0188] Method 2 addresses the situation where the target node queries a mobile T-node. In this case, the target node obtains the real-time location information of each mobile T-node within its sensing area and, from these nodes, searches for T-nodes that can assist the target node in sensing. This approach enables flexible selection of auxiliary sensing nodes, enabling accurate acquisition of the target object's attribute data.

[0189] The above solution is an application scenario where the G node and the T node are the initial perception nodes and the T node is the auxiliary perception node (application scenario three). In application scenario three, the G node queries the T node to achieve enhanced perception of the target object through collaboration between the T node and the initial perception node (GT node), so as to obtain more accurate attribute data. The technical solution of this application is described in detail below in conjunction with Figure 5.

[0190] In application scenario 3, the initial sensing nodes include G nodes and T nodes. The number of T nodes in the initial sensing nodes can be one, two, or more.

[0191] In application scenario three, that is, the scenario where the initial perception node is a GT node (a combination of a G node and a T node), one or at least two T nodes have been configured for the G node in the perception environment, and the surrounding environment is perceived through the transmission and reception of perception signals by the G node and the T node. However, it is necessary to request more T nodes to access and assist in achieving enhanced perception to improve perception performance. Unlike the aforementioned application scenario one in which the initial perception node is a G node and the application scenario two in which the initial perception node is a T node, the initial perception node in application scenario three is a GT node, and it is necessary to request more T nodes to achieve collaborative perception.

[0192] In application scenario three, the specific process and interactive signaling content include the following steps and corresponding content.

[0193] S501: The GT node group periodically sends and receives sensing signals to sense the surrounding environment.

[0194] The G node periodically transmits and receives sensing signals within its sensing area, and the T node periodically transmits and receives sensing signals within its sensing area to sense the environment within the sensing area. Alternatively, the G node periodically transmits signals in the intersection area between the G node and the T node, and the T node periodically receives the signals as its own signals, thereby enabling the GT node to periodically sense the environment within its sensing area. Alternatively, the T node periodically transmits signals in the intersection area between the G node and the T node, and the G node receives the signals, thereby enabling the GT node to periodically sense the environment within its sensing area.

[0195] The sensing signal may be a physical layer reference signal in an existing wireless sensing system, or an enhanced physical layer reference signal. For details, please refer to the above related descriptions and will not be repeated here.

[0196] S502: At least one of the nodes in the GT node group detects whether a target object enters its perception area.

[0197] This step can be performed by either a G node or a T node. Its purpose is to determine whether a target object has entered the sensing coverage area. Taking the G node as an example, this step is performed by the G node. The G node performs autocorrelation on the sensing signals it transmits and receives, extracting changes in channel state information from the autocorrelation results. If the change is significant, it indicates that a target object, such as a person or object, has entered the sensing area. This allows for rough sensing of the target object and execution of S503. If the change is small or absent, it indicates that no target object has entered the sensing area, and the sensing of the surrounding environment continues.

[0198] S503: At least one of the nodes in the GT node group senses the distance and orientation of the target object.

[0199] This step is completed by the G node, T node or GT node group. The process of obtaining the rough location information of the target object through the self-transmitted and self-received sensing signals of the G node, T node or GT node group can be found in the relevant description and will not be repeated here.

[0200] S504: At least one of the nodes in the GT node group determines whether the perception accuracy needs to be increased or improved.

[0201] Taking node G as the node performing this step, a determination is made as to whether the rough location meets the sensing accuracy required by the wireless sensing service. If not, a determination is made that there is a need to increase sensing accuracy, and the process proceeds to S505. If not, a determination is made that there is no need to increase sensing accuracy, and the process proceeds to S510 to output a rough sensing result (rough location), eliminating the need for auxiliary sensing nodes to participate in sensing assistance.

[0202] S505: The G node queries other T nodes in the perception area except the initial perception T node.

[0203] The T-nodes near the target object include two types: nodes with fixed positions and mobile nodes. Different query schemes are used for these two types of nodes.

[0204] Query solution 1: Applicable to T nodes with fixed positions within the perception area of ​​G nodes.

[0205] T-nodes with sensing capabilities within the sensing area need to register with the G-node. The G-node records the pre-configured information of these T-nodes, which includes the sensing capability of the T-node and its fixed position within the sensing area of ​​the G-node.

[0206] The G node selects other T nodes within the sensing area that are close to the rough location of the target object, except for the initial sensing T node, as target auxiliary nodes. Alternatively, it selects other T nodes within the sensing area that are close to the rough location of the target object, have a strong signal-to-noise ratio (SNR) of the sensing signal, and have small channel state changes, except for the initial sensing T node.

[0207] Alternatively, the G node initiates an auxiliary sensing request to other T nodes within the sensing area that are close to the target object's rough location, excluding the initial sensing T node. Alternatively, the G node initiates an auxiliary sensing request to other T nodes within the sensing area that are close to the target object's rough location, have a strong SNR for the sensing signal, and have minimal channel state variation. Based on their actual conditions, the other T nodes provide feedback on whether they are willing to serve as auxiliary sensing nodes for collaborative sensing.

[0208] Query method 2: Applicable to mobile T nodes within the perception area of ​​G nodes.

[0209] This approach is suitable for mobile T-nodes within the G-node's sensing area. The G-node sends a (sensing service) query request to all mobile T-nodes within the sensing area, excluding the initial sensing T-node. Upon receiving the sensing service query request, the mobile T-node returns its sensing capability information and real-time location.

[0210] Based on the feedback information from the mobile T-nodes, the G-node selects the mobile T-nodes whose real-time locations are close to the target object as target auxiliary nodes. Alternatively, the G-node selects the mobile T-nodes whose real-time locations are close to the target object, whose perceived signal SNR is strong, and whose channel state changes little as target auxiliary nodes.

[0211] Alternatively, a G node can initiate an assisted sensing request to a mobile T node whose real-time location is close to the target object. Alternatively, a G node can initiate an assisted sensing request to a mobile T node whose real-time location is close to the target object, whose perceived signal has a strong SNR, and whose channel state changes are minimal. The mobile T node then responds based on its actual situation, indicating whether it is willing to serve as an assisted sensing node for collaborative sensing.

[0212] Taking initiating an auxiliary perception request to a node as an example, continue to execute S506.

[0213] S506: The G node determines whether any T node responds to the auxiliary perception request.

[0214] The T node that receives the auxiliary perception request can provide feedback on the auxiliary perception request based on its own actual situation to indicate that it is willing to serve as an auxiliary perception node of the G node for collaborative perception.

[0215] The feedback received from the auxiliary perception request can determine whether the node can participate in the auxiliary perception, which provides a certain degree of flexibility for whether the T node participates in the auxiliary perception.

[0216] It should be noted that the auxiliary perception request initiated by the G node to the T node can be sent to only one T node at a time, and the auxiliary perception request can be sent to different T nodes one by one. The auxiliary perception request can also be sent to multiple T nodes at the same time, and there is no specific limitation on this.

[0217] If no T node feeds back to the G node that it can participate in the auxiliary perception, the G node may directly output the rough position obtained in S503 as a result.

[0218] S507: The G node configures a perception signal for the auxiliary perception node - the T node.

[0219] Here, the G node configures corresponding sensing signals for the T nodes participating in collaborative sensing, including sensing signal type, signal bandwidth, and transmit power, in addition to the initial sensing T node. This ensures that the configured sensing signals are both adapted to the capabilities of the T nodes and meet the requirements of wireless sensing services.

[0220] Here, compared with the transmission power of the perception signal sent and received by the target node, the G node will try to configure a larger transmission power for the T node within the capability of the T node participating in the collaborative perception, so that the T node can detect the target object with a more accurate location.

[0221] S508: GT node groups send and receive perception signals to enhance perception of the target object.

[0222] In this step, the node group consisting of the G node and the T node in the initial perception node, and another GT group consisting of the G node and the auxiliary perception node, send and receive perception signals to achieve enhanced perception of the target object.

[0223] The T node, a node participating in collaborative sensing, transmits a sensing signal based on the configuration of the G node. The sensing signal of the T node can be received by the G node as a self-received sensing signal. Based on the received sensing signal, the G node again obtains the position of the target object within the sensing area of ​​the G node. It can be understood that, compared with the transmission power of the sensing signal used by the G node in S501 and the transmission power of the initial sensing T node, the transmission power of the sensing signal configured by the G node for the T node participating in collaborative sensing is greater, and the power of the sensing signal of the T node received by the G node is greater. Using the sensing signal with greater power, the position of the target object within the sensing area of ​​the G node can be accurately calculated.

[0224] Alternatively, the G node transmits a sensing signal, which the T nodes participating in collaborative sensing receive according to their configuration, calculate the target object's location within the G node's sensing area, and feed it back to the G node. The G node configures a higher-power sensing signal for the T nodes participating in collaborative sensing. This higher-power sensing signal allows for accurate calculation of the target object's location within the G node's sensing area.

[0225] In the aforementioned solution, the second attribute data includes a position obtained using a sensing signal with greater power.

[0226] Using the sensing signal with greater power, the moving trajectory and / or moving speed of the moving object within the sensing area can also be calculated. The calculation process is described in the relevant instructions and will not be repeated here.

[0227] It can be understood that the auxiliary perception T-node is the node closest to the target object. From another perspective, the target object is within the perception area of ​​the auxiliary perception T-node, and naturally, it is within the intersection area of ​​the auxiliary perception T-node and the G-node. The intersection area is the perception enhancement area. Using a node group consisting of the G-node and the auxiliary perception T-nodes participating in collaborative perception, and another node group consisting of the G-node and the initial perception T-node, that is, the two node groups jointly perceive the target object in the perception enhancement area, compared with single-node group perception, it is bound to obtain more accurate location information of the target object.

[0228] S509: Node G obtains more accurate (second) attribute data of the target object within the perception area.

[0229] As shown in S508, the G node may resolve or calculate the sensing signal with greater power to obtain a more accurate position. Alternatively, the G node receives a more accurate position calculated by the auxiliary sensing node based on the sensing signal with greater power.

[0230] In addition, the G node can perform an averaging operation or a weighted averaging operation on the rough position calculated in S503 and the position obtained using the sensing signal with greater power, thereby obtaining location information that is more accurate than the aforementioned rough position (the more accurate location information can be used as third attribute data).

[0231] The more accurate (secondary or tertiary) attribute data of the target object within the perception area can be used as the final perception result obtained through the collaborative perception between the GT node group. If necessary, the G node can output the final perception result for use by the perception service requester who requests the final perception result from the G node.

[0232] In application scenario three, the Star Flash protocol can be updated based on relevant protocols of wireless sensing technology such as the Star Flash protocol, for example, reporting on node sensing capabilities can be added to the air interface (S505), and inquiring whether other T nodes in the sensing area except the initial sensing T node are willing to participate in auxiliary sensing (S506).

[0233] As can be seen from the above technical solution, the present invention provides a solution for designing interactive signaling between different nodes based on the Star Flash protocol, with the goal of supporting layered perception of target objects within the perception area. This layered perception is manifested in: coarse perception by the initial perception node, and collaborative perception of the target auxiliary node with the initial perception node. Unlike the relatively coarse perception results of the initial perception node, the collaborative perception of the target auxiliary node and the initial perception node can produce more detailed or precise results.

[0234] In summary, in this application, the target node achieves preliminary perception of the target object within the perception area by self-transmitting and self-receiving perception signals to obtain a relatively rough perception result. Based on the rough perception result, the target auxiliary node that can participate in collaborative perception is queried. Based on the coordination between the target node and the target auxiliary node or the coordination between the node groups, the target object is enhanced to obtain a more accurate perception result for the target object, such as improving the perception accuracy.

[0235] The present invention provides a device for improving the recognition accuracy of object attributes, as shown in FIG6 , including:

[0236] Processor 601 is configured to obtain first attribute data of a target object within a sensing area; in response to the first attribute data not satisfying a predetermined sensing condition, query nodes to determine N target auxiliary nodes that match the first attribute data, where N is a positive integer greater than or equal to 1;

[0237] The transceiver 602 is configured to obtain data from the target auxiliary node, where the data includes second attribute data of the target object within the sensing area, and the accuracy of the second attribute data is better than that of the first attribute data.

[0238] In some embodiments, the target node includes a first role node; the processor 601 is configured to:

[0239] Obtaining pre-configuration information of a second role node located in the sensing area, the pre-configuration information including fixed location information of the second role node;

[0240] Based on the pre-configured information, N nodes matching the first attribute data are determined from the second role nodes located in the perception area as target auxiliary nodes.

[0241] In some embodiments, the target node includes a first role node; the processor 601 is configured to:

[0242] Initiate a query request to the second role node located in the sensing area;

[0243] Based on the feedback information, N nodes matching the first attribute data are determined from the second character nodes located in the sensing area as target auxiliary nodes;

[0244] The feedback information includes the real-time location information of the node fed back by the second role node in response to the query request.

[0245] In some embodiments, the target node includes a second role node; the first attribute data is used to represent the position of the target object in the perception area; the processor 601 is used to:

[0246] Determining a target management node of the target node based on the first attribute data, where the target management node is a node that manages the target node, and a perception area of ​​the target management node at least covers a position of the target object within the perception area;

[0247] When the target node accesses the communication domain where the target management node is located, sending a request to the target management node;

[0248] When the information received as feedback from the target management node in response to the request in the communication domain is predetermined information, the target management node is used as a target auxiliary node.

[0249] In some embodiments, the target node includes a first role node and at least one second role node; the processor 601 is configured to:

[0250] Obtaining pre-configuration information of M second role nodes located in the sensing area, excluding the at least one second role node, wherein the pre-configuration information includes fixed position information of the M second role nodes; M is a positive integer greater than or equal to 1;

[0251] Based on the pre-configuration information of the M second role nodes, N nodes matching the first attribute data are determined from the M second role nodes as target auxiliary nodes.

[0252] In some embodiments, the target node includes a first role node and at least one second role node; the processor 601 is configured to:

[0253] Initiate a query request to L second role nodes located in the perception area, excluding the at least one second role node, where L is a positive integer greater than or equal to 1;

[0254] Based on the feedback information of the L second role nodes, determining N nodes matching the first attribute data from the L second role nodes as target auxiliary nodes;

[0255] The feedback information includes the real-time location information of the node fed back by the second role node in response to the query request.

[0256] In some embodiments, the transceiver 602 is configured to:

[0257] Obtaining second attribute data of the target object within the perception area;

[0258] Based on the first attribute data and the second attribute data, third attribute data is obtained, wherein the accuracy of the third attribute data is better than that of the first attribute data.

[0259] In some embodiments, the processor 601 is configured to:

[0260] In response to a target object appearing within a perception area of ​​the target node, first attribute data of the target object within the perception area is obtained based on a perception signal sent and a received perception signal by the target node.

[0261] In some embodiments, the device includes an output device for:

[0262] outputting the second attribute data;

[0263] Alternatively, in response to the first attribute data satisfying a preset perception condition, the first attribute data is output.

[0264] The present invention provides another device for improving the recognition accuracy of object attributes, as shown in FIG7 , including:

[0265] A first obtaining unit 701 is configured to obtain first attribute data of a target object within a sensing area;

[0266] A determining unit 702 is configured to query nodes in response to the first attribute data not satisfying a predetermined perception condition to determine N target auxiliary nodes that match the first attribute data, where N is a positive integer greater than or equal to 1;

[0267] The second obtaining unit 703 is configured to obtain data from the target auxiliary node, where the data includes second attribute data of the target object within the perception area, and the accuracy of the second attribute data is better than that of the first attribute data.

[0268] In some embodiments, the target node includes a first role node; the determining unit 702 is configured to:

[0269] Obtaining pre-configuration information of a second role node located in the sensing area, the pre-configuration information including fixed location information of the second role node;

[0270] Based on the pre-configured information, N nodes matching the first attribute data are determined from the second role nodes located in the perception area as target auxiliary nodes.

[0271] In some embodiments, the target node includes a first role node; the determining unit 702 is configured to:

[0272] Initiate a query request to the second role node located in the sensing area;

[0273] Based on the feedback information, N nodes matching the first attribute data are determined from the second character nodes located in the sensing area as target auxiliary nodes;

[0274] The feedback information is the real-time location information of the node fed back by the second role node in response to the query request.

[0275] In some embodiments, the target node includes a second role node; the first attribute data is used to represent the position of the target object in the perception area; the determination unit 702 is used to:

[0276] Determining a target management node of the target node based on the first attribute data, where the target management node is a node that manages the target node, and a perception area of ​​the target management node at least covers a position of the target object within the perception area;

[0277] When the target node accesses the communication domain where the target management node is located, sending a request to the target management node;

[0278] When the information received as feedback from the target management node in response to the request in the communication domain is predetermined information, the target management node is used as a target auxiliary node.

[0279] In some embodiments, the target node includes a first role node and at least one second role node; the determining unit 702 is configured to:

[0280] Obtaining pre-configuration information of M second role nodes located in the sensing area, excluding the at least one second role node, wherein the pre-configuration information includes fixed position information of the M second role nodes; M is a positive integer greater than or equal to 1;

[0281] Based on the pre-configuration information of the M second role nodes, N nodes matching the first attribute data are determined from the M second role nodes as target auxiliary nodes.

[0282] In some embodiments, the target node includes a first role node and at least one second role node;

[0283] Initiate a query request to L second role nodes located in the perception area, excluding the at least one second role node, where L is a positive integer greater than or equal to 1;

[0284] Based on the feedback information of the L second role nodes, determining N nodes matching the first attribute data from the L second role nodes as target auxiliary nodes;

[0285] The feedback information is the real-time location information of the node fed back by the second role node in response to the query request.

[0286] In some embodiments, the second obtaining unit 703 is configured to:

[0287] Obtaining second attribute data of the target object within the perception area;

[0288] Based on the first attribute data and the second attribute data, third attribute data is obtained, wherein the accuracy of the third attribute data is better than that of the first attribute data.

[0289] In some embodiments, the first obtaining unit 701 is configured to:

[0290] In response to a target object appearing within a perception area of ​​the target node, first attribute data of the target object within the perception area is obtained based on a perception signal received by the target node.

[0291] In some embodiments, the device further comprises an output unit for:

[0292] outputting the second attribute data;

[0293] Alternatively, in response to the first attribute data satisfying a preset perception condition, the first attribute data is output.

[0294] It should be noted that the two aforementioned devices for improving the recognition accuracy of object attributes in the embodiments of the present application, since the principles of solving the problems of the devices for improving the recognition accuracy of object attributes are similar to the aforementioned methods for improving the recognition accuracy of object attributes, the implementation process and implementation principles of the devices for improving the recognition accuracy of object attributes can be referred to the description of the implementation process and implementation principles of the aforementioned methods, and the repeated parts will not be repeated.

[0295] According to an embodiment of the present application, the present application also provides an electronic device and a readable storage medium.

[0296] The electronic device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the aforementioned method for improving the recognition accuracy of object attributes.

[0297] With respect to a non-transitory computer-readable storage medium storing computer instructions, the computer instructions are used to enable the computer to execute the aforementioned method for improving the recognition accuracy of object attributes.

[0298] FIG8 shows a schematic block diagram of an example electronic device 800 that can be used to implement an embodiment of the present application. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described and / or required herein.

[0299] As shown in Figure 8, the device 800 includes a computing unit 801, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 802 or a computer program loaded from a storage unit 808 into a random access memory (RAM) 803. Various programs and data required for the operation of the device 800 can also be stored in the RAM 803. The computing unit 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0300] Various components in device 800 are connected to I / O interface 805, including an input unit 806, such as a keyboard, mouse, etc.; an output unit 807, such as various types of displays, speakers, etc.; a storage unit 808, such as a magnetic disk, optical disk, etc.; and a communication unit 809, such as a network card, modem, wireless communication transceiver, etc. The communication unit 809 allows device 800 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0301] The computing unit 801 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various computing units that run machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 801 performs the various methods and processes described above, such as the method for improving the accuracy of object attribute recognition. For example, in some embodiments, the method for improving the accuracy of object attribute recognition can be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 808. In some embodiments, part or all of the computer program can be loaded and / or installed onto the device 800 via the ROM 802 and / or the communication unit 809. When the computer program is loaded into the RAM 803 and executed by the computing unit 801, one or more steps of the method for improving the accuracy of object attribute recognition described above can be performed. Alternatively, in other embodiments, the computing unit 801 may be configured in any other appropriate manner (eg, by means of firmware) to execute the method for improving the recognition accuracy of object attributes.

[0302] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system comprising at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0303] The program code for implementing the methods of the present application can be written in any combination of one or more programming languages. Such program code can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the program code is executed by the processor or controller, the functions / operations specified in the flow charts and / or block diagrams are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0304] In the context of the present application, a machine-readable medium can be a tangible medium that can contain or store a program for use by an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0305] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0306] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0307] A computer system may include a client and a server. The client and server are generally remote from each other and typically interact through a communication network. The client-server relationship arises through computer programs running on the respective computers and having a client-server relationship with each other. The server may be a cloud server, a server in a distributed system, or a server integrated with a blockchain.

[0308] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this application can be achieved. This is not a limitation herein.

[0309] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A method for improving the recognition accuracy of object attributes, the method comprising: Obtaining first attribute data of the target object within the perception area; In response to the first attribute data not satisfying a predetermined perception condition, querying the node using the target node to determine N target auxiliary nodes matching the first attribute data, where N is a positive integer greater than or equal to 1; Data from the target auxiliary node is obtained, wherein the data includes second attribute data of the target object within the perception area, and the accuracy of the second attribute data is better than that of the first attribute data.

2. The method according to claim 1, wherein: The target node includes a first role node; The querying of the node by using the target node to determine N target auxiliary nodes matching the first attribute data includes: Obtaining preconfiguration information of a second role node located in the sensing area, the preconfiguration information including fixed position information of the second role node; Based on the pre-configuration information, N nodes matching the first attribute data are determined from the second role nodes located in the perception area as target auxiliary nodes.

3. The method according to claim 1, wherein: The target node includes a first role node; The querying of the node by using the target node to determine N target auxiliary nodes matching the first attribute data includes: Initiate a query request to a second role node located in the sensing area; Based on the feedback information, N nodes matching the first attribute data are determined from the second role nodes located in the sensing area as target auxiliary nodes; The feedback information includes the real-time location information of the node fed back by the second role node in response to the query request.

4. The method according to claim 1, wherein: The target node includes a second role node; the first attribute data is used to characterize the position of the target object in the perception area; The querying of the node by using the target node to determine N target auxiliary nodes matching the first attribute data includes: Based on the first attribute data, a target management node of the target node is determined, wherein the target management node is a node that manages the target node, and the perception area of ​​the target management node at least covers covering the position of the target object within the sensing area; When the target node accesses the communication domain where the target management node is located, sending a request to the target management node; When the information received from the target management node in response to the request in the communication domain is predetermined information, the target management node is used as a target auxiliary node.

5. The method according to claim 1, wherein: The target node includes a first role node and at least one second role node; The querying of the node by using the target node to determine N target auxiliary nodes matching the first attribute data includes: Obtaining preconfiguration information of M second role nodes located in the sensing area except the at least one second role node, the preconfiguration information including fixed position information of the M second role nodes; M is a positive integer greater than or equal to 1; Based on the pre-configuration information of the M second role nodes, N nodes matching the first attribute data are determined from the M second role nodes as target auxiliary nodes.

6. The method according to claim 1, wherein: The target node includes a first role node and at least one second role node; The querying of the node by using the target node to determine N target auxiliary nodes matching the first attribute data includes: Initiate a query request to L second role nodes located in the perception area, excluding the at least one second role node, where L is a positive integer greater than or equal to 1; Based on the feedback information of the L second role nodes, determining N nodes matching the first attribute data from the L second role nodes as target auxiliary nodes; The feedback information includes the real-time location information of the node fed back by the second role node in response to the query request.

7. The method according to any one of claims 1 to 6, wherein: The obtaining of data from the target auxiliary node, wherein the data includes second attribute data of the target object within the sensing area, comprises: Obtaining second attribute data of the target object within the perception area; Based on the first attribute data and the second attribute data, third attribute data is obtained, wherein The accuracy of the third attribute data is better than that of the first attribute data.

8. The method according to any one of claims 1 to 6, wherein: The obtaining of first attribute data of the target object in the perception area includes: In response to the target object appearing in the perception area of ​​the target node, first attribute data of the target object in the perception area is obtained based on the perception signal sent by the target node and the perception signal received.

9. The method according to any one of claims 1 to 6, further comprising: outputting the second attribute data; Alternatively, in response to the first attribute data satisfying a preset perception condition, the first attribute data is output.

10. A device for improving the recognition accuracy of object attributes, comprising: A processor, configured to obtain first attribute data of a target object within a sensing area; In response to the first attribute data not satisfying a predetermined perception condition, querying the node to determine N target auxiliary nodes matching the first attribute data, where N is a positive integer greater than or equal to 1; The transceiver is used to obtain data from the target auxiliary node, wherein the data includes second attribute data of the target object within the sensing area, and the accuracy of the second attribute data is better than that of the first attribute data.

Images