Ris codebook determination method, apparatus and device

Abstract

The application discloses a RIS codebook determination method, device and equipment, the method comprises: obtaining the initial fingerprint database corresponding to the initial RIS codebook set;Based on the RSS information entropy of the non-uniform quantization of the RSS data of each reference node, determine the candidate RIS codebook set in the initial RIS codebook set;Based on genetic simulated annealing algorithm, determine the target RIS codebook set from the candidate RIS codebook set, each RIS codebook in the target RIS codebook set is used to determine the position information of the user equipment in the positioning area. The application determines the final target RIS codebook set by introducing a two-stage RIS codebook selection, and effectively avoids introducing RIS configuration with small RSS difference, so that when positioning is carried out by using the target RIS codebook set, multiple information interaction and RSS measurement of AP and UE are not required, and the positioning accuracy and positioning time can be effectively improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of wireless communication, in particular to a RIS codebook determination method, device and equipment. BACKGROUND

[0002] Wireless fingerprint positioning technology is an effective positioning technology. In order to improve the positioning accuracy of fingerprint positioning technology in complex scenes, the emerging technology of being able to control the propagation path of radio waves, i.e. reconfigurable intelligent surface (RIS), is used to enhance the strength and stability of the received signal through directional control of the reflected signal.

[0003] At present, in the RIS-assisted fingerprint positioning technology, there are mainly two methods to improve the positioning accuracy. One is to optimize the RIS reflection coefficient to make the RSS values in different areas more different. In addition, some RIS codebook configurations are generated in advance during the offline fingerprint data collection stage, and after the fingerprint data collection is completed, some search methods are applied to filter out the RIS codebooks with better positioning effect from the fixed multiple RIS codebook configurations, and only the measurement of these better RIS codebooks is needed to complete the positioning in the online positioning process.

[0004] However, the first method described above often needs multiple information interactions and RSS measurements of AP and UE to obtain better positioning effect, and the positioning time is longer. For the second method, the codebook generated in advance is not specially designed for the environment, which will inevitably introduce some RIS configurations with small RSS difference, so that when they are included in the search range, the cost is large, which reduces the positioning efficiency and affects the accuracy in actual positioning. SUMMARY

[0005] The problem solved by the present application is how to determine an effective RIS codebook set to improve the positioning accuracy and efficiency.

[0006] To solve the above problems, in a first aspect, the present application provides a RIS codebook determination method, which comprises:

[0007] obtaining an initial fingerprint database corresponding to an initial RIS codebook set, wherein the initial fingerprint database includes RSS data corresponding to each RIS codebook in the initial RIS codebook set on each reference node in the positioning area;

[0008] determining a candidate RIS codebook set from the initial RIS codebook set based on the non-uniform quantization RSS information entropy of the RSS data of each reference node, wherein the difference between the RSS information entropy corresponding to the RIS codebooks in the candidate RIS codebook set satisfies a set threshold;

[0009] determine a target RIS codebook set from the candidate RIS codebook set based on a genetic simulated annealing algorithm, each RIS codebook in the target RIS codebook set being used to determine location information of a user equipment in the positioning area.

[0010] Optionally, the RIS codebook determination method provided in the present application further comprises, after the target RIS codebook configuration set is determined:

[0011] acquiring target RSS data corresponding to each RIS codebook in the target RIS codebook set of the user equipment to be positioned in the positioning area;

[0012] comparing the target RSS data with RSS data in the initial fingerprint database to determine location information of the user equipment.

[0013] Optionally, the RIS codebook determination method provided in the present application, the non-uniform quantization RSS information entropy based on the RSS data of each reference node, comprises:

[0014] determining non-uniform quantization RSS information entropy of each RIS codebook in the initial RIS codebook set at each reference node to obtain a corresponding information entropy vector;

[0015] sorting the information entropy vector to determine an RIS codebook corresponding to a set threshold value of RSS information entropy, to obtain the candidate RIS codebook set.

[0016] Optionally, the RIS codebook determination method provided in the present application, the determination of the non-uniform quantization RSS information entropy of each RIS codebook in the initial RIS codebook set at each reference node comprises:

[0017] normalizing each RSS data in the initial fingerprint database based on a maximum RSS data value and a minimum RSS data value in the initial fingerprint database to obtain a normalization result of each RSS data;

[0018] standardizing each normalization result based on a non-uniform quantization function to obtain standardized RSS data;

[0019] calculating a frequency value of each interval in a frequency range of the standardized RSS data;

[0020] calculating the non-uniform quantization RSS information entropy of each reference node according to the frequency value through a set function.

[0021] Optionally, the RIS codebook determination method provided in the present application, the non-uniform quantization function is as follows:

[0022]

[0023] wherein, denotes the normalized result of each RSS data, denotes the RSS data of the i-th RIS codebook after standardization processing, and the variable μ denotes the compression constant in the μ-law compression.

[0024] Optionally, the RIS codebook determination method provided in the present application, the function formula is:

[0025]

[0026] wherein, is the frequency value of the RSS data corresponding to the i-th codebook belonging to the t-th interval.

[0027] Optionally, the RIS codebook determination method provided in the present application, each RSS data set corresponding to the RIS codebook in the candidate RIS codebook set is a new fingerprint database, and the target RIS codebook set is determined from the candidate RIS codebook set based on the genetic simulated annealing algorithm, comprising:

[0028] performing genetic algorithm chromosome coding processing on each RSS data in the new fingerprint database to obtain an initialization population;

[0029] performing intermediate processing on the initialization population data to obtain intermediate processed population data;

[0030] performing simulated annealing processing on the intermediate processed population data to obtain a target RSS database, and the RIS codebook corresponding to each RSS data in the RSS database is used as the target RIS codebook.

[0031] Optionally, the RIS codebook determination method provided in the present application, the simulated annealing processing on the intermediate processed population data comprises:

[0032] based on the initial temperature and the annealing rate, randomly flipping the intermediate processed population data to generate a flipped RSS database;

[0033] calculating the acceptance probability of each RSS data in the flipped RSS database;

[0034] based on the annealing relationship, performing iterative annealing processing on the flipped RSS database until the set iteration number or temperature threshold value.

[0035] In a second aspect, the present application provides a RIS codebook determination device, the device comprising:

[0036] The acquisition module is configured to acquire an initial fingerprint database corresponding to an initial RIS codebook set, wherein the initial fingerprint database includes RSS data corresponding to each RIS codebook in the initial RIS codebook set on each reference node in a positioning area.

[0037] The first selection module is configured to determine a candidate RIS codebook set from the initial RIS codebook set based on non-uniformly quantized RSS information entropy of the RSS data of each reference node, wherein a difference between the RSS information entropy corresponding to each RIS codebook in the candidate RIS codebook set satisfies a set threshold.

[0038] The second selection module is configured to determine a target RIS codebook set from the candidate RIS codebook set based on a genetic simulated annealing algorithm, wherein each RIS codebook in the target RIS codebook set is used to determine location information of a user equipment in the positioning area.

[0039] In a third aspect, a computer device is provided, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor executes the computer program to implement the RIS codebook determination method according to the first aspect.

[0040] According to the embodiments provided in the present application, the following technical effects are disclosed.

[0041] The RIS codebook determination method, device and equipment provided in the present application introduce a two-stage RIS codebook selection method, that is, first, based on the non-uniformly quantized RSS information entropy, the RIS codebooks corresponding to the RSS data with sufficient differences in information entropy are selected from the initial fingerprint database corresponding to the initial RIS codebook set to construct a new initial fingerprint database, and then in the second stage, a supervised learning feature selection method is used to search for the RSS data in the initial fingerprint database to simulate processing, and finally the best RIS codebook configuration subset, that is, the target RIS codebook set, is selected. Therefore, in the RIS codebook set determination process of the present application, the RIS codebook set determined through the two-stage selection can effectively avoid introducing some RIS configurations with very small RSS differences, thereby narrowing the search range and ultimately improving the positioning accuracy. That is, when the target RIS codebook set is used to position the user equipment in the positioning area, since the selection of the RIS codebook is in the offline fingerprint data acquisition stage, only the RSS data corresponding to the target RIS codebook set needs to be collected in the positioning stage, thereby reducing the positioning delay and eliminating the need for multiple information interactions and RSS measurements between the AP and the UE, and ultimately improving the positioning efficiency and the positioning accuracy. BRIEF DESCRIPTION OF DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed in the embodiments. Obviously, the drawings described below only illustrate some of the embodiments of the present application, and for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0043] Figure 1 Flowchart of a method for determining an RIS codebook according to some embodiments of the present application;

[0044] Figure 2 Flowchart of a method for determining an RIS codebook according to some other embodiments of the present application;

[0045] Figure 3 Flowchart of a method for determining an RIS codebook according to some other embodiments of the present application;

[0046] Figure 4 Structure diagram of an apparatus for determining an RIS codebook according to some embodiments of the present application;

[0047] Figure 5 Structure diagram of a computer device according to some embodiments of the present application. DETAILED DESCRIPTION

[0048] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present application.

[0049] The above purposes, features and advantages of the present application can be more obvious and easy to understand. The present application will be described in further detail below with reference to the drawings and specific embodiments.

[0050] It can be understood that for a positioning system based on cellular network technology, received signal strength (RSS), time of arrival, angle of arrival, etc. can be used to realize user positioning. Among them, the RSS fingerprint positioning technology is widely used due to the easy acquisition of RSS information.

[0051] RSS fingerprint positioning is a positioning technology based on wireless signal characteristics, which is widely used in indoor environments. The main idea is to measure the wireless signal characteristics (such as received signal strength RSS, channel state information CSI, etc.) at a specific location, and construct a fingerprint database. When the position of a device needs to be determined, the real-time measured signal characteristics are matched with the fingerprints in the database, so as to estimate the actual position of the device.

[0052] In practice, wireless fingerprinting generally consists of two stages:

[0053] Offline stage (fingerprint construction stage): In this stage, a plurality of reference points are first divided in a predetermined area, and the signal characteristics of each wireless access point (such as Wi-Fi hotspots or base stations) are measured at each reference point to generate a fingerprint library. The position of each reference point and the corresponding signal characteristics form a pair of data. Since RSS signals are greatly affected by environmental changes (such as obstructions, reflections, etc.), the fingerprint library needs sufficient density and coverage to ensure positioning accuracy.

[0054] Online stage (position estimation stage): During positioning, the device measures the received wireless signal characteristics and matches these characteristics with the data in the fingerprint library. Common matching methods include the nearest neighbor method (K-Nearest Neighbor, KNN) and weighted KNN, which determine the reference point or area where the device is most likely located based on similarity.

[0055] It can also be understood that a smart metasurface (RIS) is an emerging electromagnetic wave control technology, which is a two-dimensional structure composed of a large number of small, adjustable units. These units can dynamically control the reflection, transmission, and absorption behavior of incident electromagnetic waves by changing their electromagnetic properties. It can achieve functions such as beamforming, beam deflection, and suppression of multipath effects.

[0056] Moreover, unlike traditional super-large MIMO wireless communication systems, RIS can not rely on the surrounding environment and can actively change the wireless channel by controlling the reflection coefficients of each unit in real time to directionally reflect, refract, or transmit incident electromagnetic waves, thereby achieving strong coverage capabilities. RIS also has the advantages of passivity, extremely low thermal noise, software self-definability and simplicity, unique nanosecond-level low latency, full-band response, etc. Compared with current technologies used in wireless networks, the remarkable feature of RIS is that the wireless transmission environment can be artificially controlled, and the electromagnetic response in the entire network can be fully controlled, bringing revolutionary impact to 6G wireless networks. Therefore, as a possible key technology for 6G, RIS provides new degrees of freedom to further enhance performance due to its low power consumption, low cost, wide coverage, wide access, and fast response.

[0057] It can be understood that, in the present application, in order to solve the problem of the need for multiple groups of UE measurement and RIS optimization in the related art, which increases the positioning delay, a two-stage RIS codebook determination method is introduced, an initial fingerprint database is constructed by selecting RIS codebook configurations that show sufficient differences, and a supervised learning feature selection method is used to search for the best RIS codebook configuration subset to improve positioning accuracy, and in the scenario where only a single base station exists, the introduction of RIS makes it possible to perform fingerprint positioning in this scenario.

[0058] The method can be executed by a processing device with data processing function, and the user equipment can be a computer, a mobile phone, a tablet computer or other electronic equipment in a positioning area.

[0059] In order to better understand the RIS codebook determination method provided by the embodiments of the present application, the following will be described in detail with reference to the drawings.

[0060] Figure 1 As shown in the flowchart of the RIS codebook determination method in some embodiments, as shown in the flowchart, the method specifically includes: Figure 1

[0061] S110, obtaining an initial fingerprint database corresponding to an initial RIS codebook set, the initial fingerprint database including RSS data corresponding to each RIS codebook in the initial RIS codebook set on each reference node in the positioning area.

[0062] S120, determining a candidate RIS codebook set in the initial RIS codebook set based on the non-uniform quantization RSS information entropy of the RSS data of each reference node, the difference between the RSS information entropy corresponding to the RIS codebooks in the candidate RIS codebook set satisfying a set threshold.

[0063] S130, determining a target RIS codebook set from the candidate RIS codebook set based on a genetic simulated annealing algorithm, each RIS codebook in the target RIS codebook set being used to determine the position information of a user equipment in the positioning area.

[0064] Specifically, in the embodiments of the present application, first, offline initial fingerprint data corresponding to the initial RIS codebook set can be collected, that is, a reference node (Reference Point, RP) with known position can be set in a positioning area, such as an indoor positioning area, and then the RSS data corresponding to each different RIS codebook in the initial RIS codebook set can be measured and obtained, to obtain an initial fingerprint database corresponding to the initial RIS codebook set.

[0065] ​For example, first, an initial RIS codebook set including q different RIS codebooks can be constructed, and then the RIS codebooks are switched at L different points in the positioning area, i.e., the reference nodes, and RSS data is collected and stored in an Lxq database.

[0066] wherein the RSS of the i-th RIS codebook collected at the grid point l can be defined as

[0067] Further, the non-uniform quantized RSS information entropy can be introduced, and through the non-uniform quantized RSS information entropy of the RSS data of each reference node, a candidate RIS codebook set is determined in the initial RIS codebook set, so that the difference between the RSS information entropies corresponding to the RIS codebooks in the candidate RIS codebook set satisfies a set threshold.

[0068] That is, by differentiating the RSS information entropy, the RIS codebook configuration with sufficient difference in signal is selected from the initial fingerprint database, so as to obtain the RIS codebook configuration with greater contribution to positioning ability from the initial RIS codebook set, and realize the first-stage selection of the RIS codebook in the initial RIS codebook set.

[0069] wherein the RSS data set corresponding to each RIS codebook in the candidate RIS codebook set is a new fingerprint database; and the set threshold represents a limit on the difference of the RSS information entropies corresponding to each RIS codebook in the screening process, so that when the difference is large enough, the RIS codebook configuration with greater contribution to positioning ability can be obtained.

[0070] The set threshold can be flexibly set according to actual conditions, and the present application does not limit this.

[0071] Finally, a genetic simulated annealing algorithm is used to further enhance the selection process using a data-driven training scheme. Specifically, by using the simulated annealing algorithm to anneal the new fingerprint database, the candidate RIS codebook set is further screened. That is, the main goal of this method is to determine a set of optimal RIS configurations, and to obtain high positioning accuracy using fewer RIS codebook configurations. Finally, a set of optimal RIS codebook configurations, i.e., a target RIS codebook set, can be obtained.

[0072] It can be understood that the RIS codebook determination method provided by the embodiments of the present application can effectively avoid introducing some RIS configurations with very small RSS difference, and finally improve the positioning efficiency and positioning accuracy.

[0073] And the RIS codebook set determined by the two-stage selection can effectively avoid introducing some RIS configurations with very small RSS difference, and finally improve the positioning efficiency and positioning accuracy.

[0074] In addition, in the scenario where only a single base station exists, the introduction of RIS makes it possible to perform fingerprint positioning in this scenario.

[0075] In addition, in terms of positioning delay, some researches in the related art need the UE to perform multiple sets of RSS measurements, and perform phase shift optimization of the RIS to obtain improved positioning accuracy, which increases the positioning delay. The present application selects the RIS codebook in the offline fingerprint data collection stage, and the user equipment position estimation stage only needs to collect one set of RSS data of the screened RIS codebook, and also considers minimizing the measured RSS quantity in the fitness function design, that is, reduces the positioning delay. Finally, a search algorithm with more robust local search capability is used to reduce the risk of the genetic algorithm falling into local optimum in the optimization process and improve the fingerprint positioning accuracy.

[0076] Optionally, in some embodiments of the present application, after the target RIS codebook configuration set is determined through the above steps, the target RIS codebook configuration set can be used for actual positioning, that is, the method can further include the following steps:

[0077] S140, acquiring target RSS data corresponding to each RIS codebook in the target RIS codebook set of the user equipment to be positioned in the positioning area.

[0078] S150, comparing the target RSS data with the RSS data in the initial fingerprint database to determine the position information of the user equipment.

[0079] Specifically, after the selection of the best RIS codebook configuration subset, that is, the target RIS codebook set, is completed through the above steps, the target RIS codebook set can be used for accurate positioning of the user equipment.

[0080] That is, in practice, first, the RIS codebook set can be switched, that is, the selected target RIS codebook set is executed, and then the target RSS data corresponding to the target RIS codebook set in the positioning area of the user equipment to be positioned is measured and obtained.

[0081] Further, the obtained target RSS data is compared with the RSS data in the above-mentioned offline fingerprint library, that is, the initial fingerprint database, and then the weighted K nearest neighbor method can be used to estimate and determine the accurate position of the user equipment, thereby realizing the positioning of the user equipment.

[0082] It can be understood that, in the embodiments of the present application, the method for positioning the user equipment by measuring the RSS data corresponding to the RIS codebook in the selected target RIS codebook set and then comparing it with the original offline RSS, effectively reduces the positioning delay due to the selection of the target RIS codebook set to collect the corresponding RSS data; and in the above-mentioned user equipment positioning process, multiple information interactions and RSS measurements of AP and UE are not required, thereby greatly reducing the positioning time.

[0083] Optionally, in S120, RSS data corresponding to RSS information entropy with sufficient difference in signal is selected from the initial fingerprint database to obtain RIS codebook configurations with greater contribution to positioning ability from the initial RIS codebook set.

[0084] Specifically, the following steps can be adopted:

[0085] S121, determining the non-uniform quantization RSS information entropy of each RIS codebook in the initial RIS codebook set at each reference node to obtain the corresponding information entropy vector.

[0086] S122, sorting the information entropy vector to determine the RIS codebook corresponding to the RSS information entropy exceeding the set threshold to obtain the candidate RIS codebook set.

[0087] Specifically, after obtaining the RSS data of each codebook in the initial RIS codebook set at each node, the information entropy value of each codebook at each node can be calculated.

[0088] The corresponding calculation process is shown in Figure 2 and can include the following steps:

[0089] S01, based on the maximum RSS data value and the minimum RSS data value in the initial fingerprint database, normalizing each RSS data in the initial fingerprint database to obtain the normalization result of each RSS data.

[0090] S02, based on the non-uniform quantization function, standardizing each normalized result to obtain the standardized RSS data.

[0091] S03, calculating the frequency value of each interval of the RSS data in the frequency range after the standardization processing.

[0092] S04, calculating the information entropy of the non-uniform quantized RSS of each reference node according to the frequency value through the set function formula.

[0093] Specifically, first, the initial fingerprint database can be normalized by the maximum and minimum values of the RSS in the initial fingerprint database, and then the normalized result is processed by using the non-uniform quantization function, and then the frequency value of each RSS data in the set frequency range is determined. Finally, according to the frequency value, the information entropy of the non-uniform quantized RSS of each reference node is calculated through the set function formula.

[0094] In order to better understand the calculation process, the calculation of the information entropy of the non-uniform quantized RSS will be described in detail below by taking a certain RIS codebook as an example, such as taking the i-th RIS codebook configuration as an example.

[0095] Suppose Max i is the maximum RSS value in all grid points, i.e., the initial fingerprint database l∈[1,L], and Min i is the minimum RSS value, i.e.

[0096]

[0097] Based on the above assumptions, first, the RSS signal can be normalized by using the maximum-minimum normalization method, i.e.:

[0098]

[0099] Next, substitute into the non-uniform quantization function to get:

[0100]

[0101] where the variable μ represents the compression constant in the μ-law compression, represents the RSS data of the i-th RIS codebook after standardization and compression. Its range is 0-1, i.e., as a frequency range. Subsequently, we divide the frequency range into W uniform intervals, i.e., form multiple intervals, and calculate the frequency of each RSS data value in each interval, where the signal belongs to the t-th interval can be represented as

[0102]

[0103] where let is the number of grid points corresponding to the i-th RIS codebook belonging to the t-th interval, then it can be represented as represents that in the i-th RIS codebook case, the signal belongs to the t-th interval, i.e. the frequency value of the interval, and L is the number of reference nodes in the positioning area.

[0104] After the above process, according to the concept of information entropy, the non-uniform quantization RSS information entropy of the i-th RIS codebook configuration is given by the following formula:

[0105]

[0106] wherein, is the frequency value, W is the total number of intervals in the frequency interval, and t is the number of the interval.

[0107] Through the above formula, we can obtain the non-uniform quantization RSS information entropy vector of all RIS codebook sets, denoted as:

[0108] H = [H 1 , H 2 , ..., H q ].

[0109] Further, through the above steps, the non-uniform quantization RSS information entropy vector of all RIS codebook sets is calculated, and the information entropy vector can be sorted to determine the codebook whose information entropy exceeds the set threshold to obtain a candidate codebook set.

[0110] For example, H can be sorted in descending order, the largest s RIS codebook configurations are selected, and the RSS data corresponding to the selected RIS codebook is used to construct a new RSS fingerprint database with a size of Lxs.

[0111] It can be understood that through the above process, the first stage of screening of the initial codebook is completed, and a candidate RIS codebook set is obtained, and the RSS data corresponding to each RIS codebook in the candidate RIS codebook set reconstitutes a new offline fingerprint data, i.e. a new fingerprint database, so that in the second stage, further selection is made based on the new fingerprint database.

[0112] Optionally, in S130, a genetic simulated annealing algorithm is used to enhance the selection process using a data-driven training scheme, and the main goal of this method is to determine a set of optimal RIS configurations using fewer RIS codebook configurations to obtain a high enough positioning accuracy.

[0113] As shown in Figure 3 , it can specifically include the following steps:

[0114] S131, genetic algorithm chromosome coding processing is performed on each RSS data in the new fingerprint database to obtain an initialization population.

[0115] S132, intermediate processing is performed on the initialization population data to obtain intermediate processed population data.

[0116] S132, simulated annealing processing is performed on the intermediate processed population data to obtain a target RSS database, and the RIS codebook corresponding to each RSS data in the RSS database is taken as the target RIS codebook.

[0117] Specifically, first, for the new fingerprint database obtained in the above step, i.e., the fingerprint database corresponding to the candidate RIS codebook set, a data set of M data points is divided into two parts, i.e., a training set with M data points and a verification set with M data points. u v

[0118] Further, a s-bit binary vector is used to perform genetic algorithm chromosome coding on each individual, i.e., the RSS data of each candidate codebook at each node, where 1 represents using the RIS codebook, and 0 represents not using. In order to minimize the positioning error under the configuration of as few RIS codebooks as possible, the fitness function is designed as:

[0119] F(Ind) = E(Ind) + b x max(0, |Ind|1-M),

[0120] where M is the maximum number of available RIS codebooks, |Ind|1 is the number of RIS codebooks used by the current individual, b is a penalty value as large as possible, which is used to limit the number of RIS codebooks, and E(Ind) is the root mean square error of the positioning result under the current RIS configuration.

[0121] Further, selection, crossover, mutation and simulated annealing operations are performed on the initialized population, and the detailed process is as follows:

[0122] Selection operation: In order to ensure the positioning accuracy of the result, we use an elite selection mechanism to select a group of individuals with the lowest fitness function from the population of the last generation, and take them as the next generation.

[0123] Crossover operation: Each bit of the child individual is inherited from the bit of the last generation with equal probability.

[0124] Mutation operation: Each bit in each individual may be inverted, and the probability value is set to 1 / s.

[0125] It can be understood that although the genetic algorithm has strong control over the search process, it has problems such as low local search capability. The simulated annealing algorithm shows robust local search capability and can reduce the risk of the genetic algorithm falling into local optimization during optimization. Therefore, simulated annealing operation is performed thereafter.

[0126] ​​Specifically comprising the following steps:

[0127] S001, based on the initial temperature and the annealing rate, randomly flipping the population data after the intermediate processing to generate a flipped RSS database.

[0128] S002, calculating the acceptance probability of each RSS data in the flipped RSS database.

[0129] S003, based on the annealing relationship, iteratively annealing the flipped RSS database until the set number of iterations or the temperature threshold.

[0130] Specifically, first set the initial temperature t0 and the annealing rate a, then generate a new individual by randomly flipping one bit value of each individual, the new individual is denoted as Ind', and calculate the difference between the fitness function of the new individual and the original individual:

[0131] ΔC = F(Ind') - F(Ind).

[0132] Then, calculate the acceptance probability of the new individual:

[0133] P r = min[exp(-ΔC / t k ), 1],

[0134] Where t k is the current temperature, if the fitness function of the new individual is lower than that of the original individual, the new individual is accepted with a probability of 1, if not, it is accepted with a probability of exp(-ΔC / t k ), where t k is the current temperature.

[0135] Then, use t k+1 = at k to perform annealing, where the annealing rate a is in the interval [0, 1]. When the predefined number of iterations is reached or the temperature drops below the specified threshold, the annealing operation is stopped.

[0136] When the predetermined number of iterations is reached or when the fitness value does not improve within a given number of consecutive iterations, the entire genetic simulated annealing process ends, obtaining a set of optimal RIS codebook configurations and corresponding RSS values.

[0137] It can be understood that in the embodiments of the present application, by introducing a two-stage RIS codebook selection method, the RIS codebook configuration that selects the signal to show sufficient difference is used to construct the initial fingerprint database, and the supervised learning feature selection method is used to search for the best RIS codebook configuration subset, so as to improve the positioning accuracy.

[0138] That is, in the positioning system, there are multiple dimensions of commonly used performance indicators, such as positioning accuracy, coverage range, positioning delay, robustness, etc. In terms of coverage range, traditional multi-base station positioning often requires more than three base stations to proceed, which limits the coverage range of positioning, making it impossible for fingerprint positioning to proceed in some extreme scenarios. Therefore, the present application makes it possible to perform fingerprint positioning in the scenario of only a single base station by introducing RIS.

[0139] In addition, in terms of positioning delay, some existing researches require the UE to perform multiple sets of RSS measurements and perform phase shift optimization of RIS to improve positioning accuracy, which increases the positioning delay. The present application selects the RIS codebook in the offline fingerprint data collection stage, and only needs to collect one set of RSS data of the screened RIS codebook in the user position estimation stage, and also considers minimizing the number of measured RSS in the fitness function design, that is, reduces the positioning delay. Finally, a search algorithm with more robust local search capability is used to reduce the risk of genetic algorithm falling into local optimum in the optimization process and improve the fingerprint positioning accuracy.

[0140] On the other hand, as Figure 4 shown, the present application also provides an RIS codebook determination device, which comprises:

[0141] The first acquisition module 210 is configured to acquire an initial fingerprint database corresponding to an initial RIS codebook set, wherein the initial fingerprint database includes RSS data corresponding to each RIS codebook in the initial RIS codebook set on each reference node in a positioning area;

[0142] The first selection module 220 is configured to determine a candidate RIS codebook set from the initial RIS codebook set based on the RSS information entropy of the non-uniform quantization of the RSS data of each reference node, and the difference between the RSS information entropy corresponding to the RIS codebooks in the candidate RIS codebook set satisfies a set threshold value;

[0143] The second selection module 230 is configured to determine a target RIS codebook set from the candidate RIS codebook set based on a genetic simulated annealing algorithm, and each RIS codebook in the target RIS codebook set is used to determine the position information of a user equipment in the positioning area.

[0144] Optionally, the RIS codebook determination device provided by the embodiment of the present application further comprises:

[0145] The second acquisition module 240 is configured to acquire target RSS data corresponding to each RIS codebook in the target RIS codebook set in the positioning area of the user equipment to be positioned;

[0146] The positioning module 250 is configured to compare the target RSS data with RSS data in the initial fingerprint database to determine position information of the user equipment.

[0147] Optionally, the RIS codebook determination apparatus provided in the embodiments of the present application, the first selection module is specifically configured to:

[0148] determine RSS information entropy of non-uniform quantization of each RIS codebook in the initial RIS codebook set at each reference node, to obtain a corresponding information entropy vector;

[0149] perform sorting processing on the information entropy vector to determine an RIS codebook corresponding to RSS information entropy exceeding a set threshold, to obtain the candidate RIS codebook set.

[0150] Optionally, the RIS codebook determination apparatus provided in the embodiments of the present application, the first selection module is specifically configured to:

[0151] normalize each RSS data in the initial fingerprint database based on a maximum RSS data value and a minimum RSS data value in the initial fingerprint database, to obtain a normalization result of each RSS data;

[0152] perform standardization processing on each normalization result based on a non-uniform quantization function, to obtain RSS data after standardization processing;

[0153] calculate a frequency value of each interval in a frequency range in which the RSS data after standardization processing appears;

[0154] calculate information entropy of non-uniform quantization RSS of each reference node according to the frequency value through a set function formula.

[0155] Optionally, the RIS codebook determination apparatus provided in the embodiments of the present application, the non-uniform quantization function is as follows:

[0156]

[0157] wherein, the normalization result of each RSS data is denoted as, the RSS data after standardization processing of the i th RIS codebook is denoted as, and the variable μ represents a compression constant in μ-law compression.

[0158] Optionally, the RIS codebook determination apparatus provided in the embodiments of the present application, the function formula is as follows:

[0159]

[0160] wherein, The frequency value of the RSS data corresponding to the i-th codebook belonging to the t-th interval, L is the number of reference nodes in the positioning area.

[0161] Optionally, the RIS codebook determination apparatus provided in the embodiments of the present application, the second selection module is specifically configured to:

[0162] The genetic algorithm chromosome coding processing is performed on each RSS data in the new fingerprint database, and an initialization population is obtained.

[0163] The intermediate processing is performed on the initialization population data, and intermediate processed population data is obtained.

[0164] The simulated annealing processing is performed on the intermediate processed population data, and a target RSS database is obtained, and the RIS codebook corresponding to each RSS data in the RSS database is used as the target RIS codebook.

[0165] Optionally, the RIS codebook determination apparatus provided in the embodiments of the present application, the second selection module is specifically configured to:

[0166] Based on the initial temperature and the annealing rate, the intermediate processed population data is randomly flipped to generate a flipped RSS database.

[0167] The acceptance probability of each RSS data in the flipped RSS database is calculated.

[0168] Based on the annealing relationship, the iterative annealing processing is performed on the flipped RSS database until the set iteration number or temperature threshold value.

[0169] In an exemplary embodiment, a computer device can be provided, which can be a server or a terminal, and an internal structure diagram thereof can be as shown in Figure 5 The computer device includes a processor, a memory, an input / output interface (I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium. The database of the computer device is configured to store video tag processing data. The input / output interface of the computer device is configured to exchange information between the processor and external devices. The communication interface of the computer device is configured to communicate with external terminals through a network connection. The computer program is executed by the processor to implement the RIS codebook determination method.

[0170] Those skilled in the art can understand that Figure 5 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0171] In an exemplary embodiment, a computer device is also provided, including a memory and a processor, the memory storing a computer program, and the processor implementing the steps in the above method embodiments when executing the computer program.

[0172] In an exemplary embodiment, a computer readable storage medium is provided, storing a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0173] In an exemplary embodiment, a computer program product is provided, including a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0174] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant regulations.

[0175] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the processes of the above-mentioned embodiments of the methods can be included. Any reference to memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (Read-Only Memory, ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive memory (ReRAM), magnetoresistive random access memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric memory (Ferroelectric Random Access Memory, FRAM), phase change memory (Phase Change Memory, PCM), graphene memory, etc. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, etc. As an illustration but not limitation, RAM can be in various forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), etc.

[0176] The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a blockchain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a computer device, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., without being limited thereto.

[0177] Any combination of the technical features of the above embodiments can be made. In order to make the description simple, all possible combinations of the technical features in the above embodiments are not described, however, as long as the combination of the technical features does not exist contradictory, it should be considered as the scope of the present application.

[0178] The principles and implementation modes of the present application are described by applying specific examples in the present application, and the above-mentioned embodiments are only used to help understand the method and its core idea of the present application; at the same time, for those skilled in the art, according to the idea of the present application, the specific implementation mode and application range will be changed. In conclusion, the content of the present application should not be understood as a limitation.

Claims

1. A method for determining a RIS codebook, characterized in that, The method comprises: obtaining an initial fingerprint database corresponding to an initial RIS codebook set, wherein the initial fingerprint database comprises RSS data corresponding to each RIS codebook in the initial RIS codebook set on each reference node in a positioning area; determining a candidate RIS codebook set in the initial RIS codebook set based on non-uniformly quantized RSS information entropy of RSS data of each reference node, wherein a difference between RSS information entropy corresponding to RIS codebooks in the candidate RIS codebook set satisfies a set threshold, and each RSS data set corresponding to the RIS codebooks in the candidate RIS codebook set is a new fingerprint database; performing genetic algorithm chromosome coding processing on each RSS data in the new fingerprint database using an s-bit binary vector to obtain an initialization population, wherein 1 indicates that the RIS codebook is used, and 0 indicates that the RIS codebook is not used; performing intermediate processing on the initialization population data to obtain intermediate-processed population data, wherein the intermediate processing comprises a selection operation, a crossover operation, and a mutation operation, the selection operation is to select a group of individuals with the lowest fitness function from a population of the previous generation and take the group as the next generation, and the fitness function is: F(Ind)=E(Ind)+b×max(0,|Ind|1-M), wherein M is the maximum number of available RIS codebooks, |Ind|1 is the number of RIS codebooks used by the current individual, b is a penalty value as large as possible and is used to limit the number of RIS codebooks, and E(Ind) is the root mean square error of the positioning result under the current RIS configuration; the crossover operation is that each bit of each individual is inherited from the bits of the previous generation with equal probability, and the mutation operation is that the probability value of each bit in each individual being reversed is set to 1 / s; performing simulated annealing processing on the intermediate-processed population data to obtain a target RSS database, wherein RIS codebooks corresponding to each RSS data in the target RSS database are a target RIS codebook set; wherein the simulated annealing processing on the intermediate-processed population data comprises: performing random flipping on the intermediate-processed population data based on an initial temperature and an annealing rate to generate a flipped RSS database; calculating acceptance probabilities of each RSS data in the flipped RSS database; performing iterative annealing processing on the flipped RSS database based on an annealing relationship until a set number of iterations or a temperature threshold is reached.

2. The RIS codebook determination method of claim 1, wherein, After the target RIS codebook set is determined, the method further comprises: obtaining target RSS data corresponding to each RIS codebook in the target RIS codebook set in the positioning area of a user equipment to be positioned; comparing the target RSS data with RSS data in the initial fingerprint database to determine position information of the user equipment.

3. The RIS codebook determination method of claim 1, wherein, The determination of the candidate RIS codebook set in the initial RIS codebook set based on the non-uniformly quantized RSS information entropy of the RSS data of each reference node comprises: determining non-uniformly quantized RSS information entropy of each RIS codebook in the initial RIS codebook set at each reference node to obtain a corresponding information entropy vector; The information entropy vector is sorted to determine an RIS codebook corresponding to a RSS information entropy exceeding a set threshold, to obtain the candidate RIS codebook set.

4. The RIS codebook determination method of claim 3, wherein, The determining of the non-uniform quantization RSS information entropy of each RIS codebook in the initial RIS codebook set at each reference node includes: Based on the maximum RSS data value and the minimum RSS data value in the initial fingerprint database, each RSS data in the initial fingerprint database is normalized to obtain a normalized result of each RSS data; Based on the non-uniform quantization function, the normalized results are standardized to obtain the standardized RSS data; The frequency value of each interval of the standardized RSS data in the frequency range is calculated; According to the frequency value, the non-uniform quantization RSS information entropy of each reference node is calculated through a set function.

5. The RIS codebook determination method of claim 4, wherein, The non-uniform quantization function is as follows: wherein, denotes the normalized result of each RSS data, denotes the RSS data of the i-th RIS codebook after standardization, and the variable μ denotes the compression constant in μ-law compression.

6. The RIS codebook determination method of claim 4, wherein, The function is as follows: wherein t is the number of the interval, is the frequency value of the RSS data corresponding to the i th codebook belonging to the t th interval, is the number of grid points corresponding to the i th RIS codebook belonging to the t th interval, W is the total number of intervals in the frequency interval, and L is the number of reference nodes in the positioning area. 7.A RIS codebook determination apparatus characterized in that, The device includes: An acquisition module is configured to acquire an initial fingerprint database corresponding to an initial RIS codebook set, the initial fingerprint database including RSS data corresponding to each RIS codebook in the initial RIS codebook set at each reference node in a positioning area; A first selection module is configured to determine a candidate RIS codebook set in the initial RIS codebook set based on the non-uniform quantization RSS information entropy of each reference node, the difference between the RSS information entropies of the RIS codebooks in the candidate RIS codebook set satisfying a set threshold, and each RSS data set corresponding to the RIS codebooks in the candidate RIS codebook set being a new fingerprint database; A second selection module is configured to use an s-bit binary vector to perform genetic algorithm chromosome coding processing on each RSS data in the new fingerprint database to obtain an initialization population, wherein 1 indicates that the RIS codebook is used, and 0 indicates that the RIS codebook is not used; Intermediate processing is performed on the initialization population data to obtain intermediate population data, the intermediate processing including selection operation, crossover operation and mutation operation, the selection operation being to select a group of individuals with the lowest fitness function from the population of the previous generation and to use the individuals as the next generation; wherein the fitness function is as follows: F(Ind)=E(Ind)+b×max(0,|Ind|1-M), wherein M is the maximum number of available RIS codebooks, |Ind|1 is the number of RIS codebooks used by the current individual, b is a maximum penalty value used to limit the number of RIS codebooks, E(Ind) is the root mean square error of the positioning result under the current RIS configuration; The crossover operation is that each bit of each individual is inherited from the bits of the previous generation with equal probability, and the mutation operation is that each bit in each individual has a possibility of being reversed, and the probability value is set to 1 / s; based on an initial temperature and an annealing rate, the population data after intermediate processing is randomly flipped to generate a flipped RSS database; the acceptance probability of each RSS data in the flipped RSS database is calculated; based on an annealing relationship, the flipped RSS database is iteratively annealed until a set iteration number or a temperature threshold value, and a target RSS database is obtained, and each RIS codebook corresponding to each RSS data in the target RSS database is a target RIS codebook set, and each RIS codebook in the target RIS codebook set is used to determine the position information of a user equipment in the positioning area.

8. A computer device, comprising: The computer device comprises a memory, a processor, and a computer program stored on the memory and executable on the processor, and the processor executes the computer program to implement the RIS codebook determination method according to any one of claims 1-6.

Images