Communication site planning method, apparatus, and electronic device

Abstract

This invention provides a communication site planning method, apparatus, and electronic device. The method includes: acquiring demand data for multiple target sites to be planned, determining multiple candidate envelopes, and acquiring basic data for the multiple candidate envelopes; classifying the multiple candidate envelopes based on the demand data for the multiple target sites and the basic data for the multiple candidate envelopes to obtain multiple types of envelopes; performing dynamic spatial matching between the multiple target sites and the multiple types of envelopes based on the demand data to obtain matching results; and generating planning schemes for the multiple target sites based on the matching results. The communication site planning method provided by this invention, by classifying multiple candidate envelopes, can perform fine-grained dynamic spatial matching between multiple target sites and multiple types of envelopes, thereby improving the efficiency and accuracy of site planning and increasing resource utilization.

Description

Technical Field

[0001] This invention relates to the field of communication technology, and in particular to a communication site planning method, apparatus, and electronic device. Background Technology

[0002] With the development of mobile communication technology, users have increasingly higher demands for network performance. Operators need to plan and construct sites in areas with weak network coverage or coverage blind spots. How to rationally plan communication sites is a key issue that urgently needs to be addressed. Currently, existing communication site planning methods rely on manual methods, which are inefficient and inaccurate, and easily lead to resource waste. Summary of the Invention

[0003] This invention provides a communication site planning method, apparatus, and electronic device to address the shortcomings of existing communication site planning methods, which rely on manual labor, have low efficiency and accuracy, and are prone to resource waste.

[0004] This invention provides a communication site planning method, comprising:

[0005] Obtain demand data for multiple target sites to be planned, determine multiple candidate envelopes, and obtain basic data for the multiple candidate envelopes;

[0006] Based on the demand data of the multiple target sites and the basic data of the multiple candidate envelopes, the multiple candidate envelopes are classified to obtain multiple types of envelopes;

[0007] Based on the demand data, the multiple target sites are dynamically spatially matched with the multiple types of envelopes to obtain matching results;

[0008] Based on the matching results, a planning scheme for the multiple target sites is generated.

[0009] In some embodiments, the multiple candidate envelopes are classified based on the demand data of the multiple target sites and the basic data of the multiple candidate envelopes to obtain multiple types of envelopes, including:

[0010] The demand data of the multiple target sites is preprocessed to obtain preprocessed demand data;

[0011] The basic data of the multiple candidate envelopes are preprocessed to obtain preprocessed basic data;

[0012] Based on the preprocessed demand data and the preprocessed basic data, the multiple candidate envelopes are classified to obtain multiple types of envelopes; the multiple types of envelopes include: authentication envelopes, potential envelopes, and discarded envelopes.

[0013] In some embodiments, the classification of the plurality of candidate envelopes based on the preprocessed demand data and the preprocessed basic data yields multiple types of envelopes, including:

[0014] Feature extraction is performed on the preprocessed demand data to obtain the demand feature vectors of the multiple target sites;

[0015] Feature extraction is performed on the preprocessed basic data to obtain the basic feature vectors of the multiple candidate envelopes;

[0016] The demand feature vectors of the multiple target sites and the basic feature vectors of the multiple candidate envelopes are input into a pre-built envelope classification model to obtain the types of the multiple candidate envelopes output by the envelope classification model.

[0017] The envelope classification model is trained based on the sample demand feature vectors of multiple sample sites, the sample basic feature vectors of multiple sample candidate envelopes, and the type labels of the multiple sample candidate envelopes.

[0018] In some embodiments, classifying the plurality of candidate envelopes based on the preprocessed demand data and the preprocessed basic data includes:

[0019] Based on the preprocessed demand data and the preprocessed basic data, the ratio of the envelope area of ​​each candidate envelope to the corresponding single-station coverage area is calculated.

[0020] If the ratio of the envelope area of ​​each candidate envelope to the coverage area of ​​the corresponding single station is less than or equal to a preset threshold, the type of each candidate envelope is determined to be a discarded envelope.

[0021] In some embodiments, classifying the plurality of candidate envelopes based on the preprocessed demand data and the preprocessed basic data includes:

[0022] Based on the preprocessed demand data, determine the total number of target problem grids to be covered for each target site;

[0023] Based on the preprocessed basic data, determine the number of target problem grids covered by each candidate envelope;

[0024] Based on the total number of target problem grids to be covered at each target site and the number of target problem grids to be covered by each candidate envelope, at least one authentication envelope is determined from the plurality of candidate envelopes.

[0025] In some embodiments, generating a planning scheme for the plurality of target sites based on the matching results includes:

[0026] If the target site is found to be successfully matched with the authentication envelope, a planning scheme for the target site is directly generated.

[0027] If the target site is successfully matched with the potential envelope, the corresponding potential envelope is verified. If the verification is successful, a planning scheme for the target site is generated.

[0028] If the target site is successfully matched with the dropped envelope, the demand data of the target site is intercepted and a prompt message is generated.

[0029] In some embodiments, after performing dynamic spatial matching between the plurality of target sites and the plurality of types of envelopes to obtain the matching results, the method further includes:

[0030] Based on the matching results, multiple target envelopes that match the multiple target sites are determined;

[0031] For each target envelope, site conflict is predicted. If site conflict is predicted, the site conflict is processed, and the matching result is optimized.

[0032] In some embodiments, the training process of the envelope classification model includes:

[0033] Obtain sample requirement data from multiple sample sites and sample basic data from multiple sample candidate envelopes, and determine the type labels of the multiple sample candidate envelopes;

[0034] The sample demand data of the multiple sample sites are preprocessed to obtain preprocessed sample demand data, and the sample basic data of the multiple sample candidate envelopes are preprocessed to obtain preprocessed sample basic data.

[0035] Feature extraction is performed on the preprocessed sample demand data to obtain the sample demand feature vectors of the multiple sample sites; feature extraction is performed on the preprocessed sample basic data to obtain the sample basic feature vectors of the multiple sample candidate envelopes.

[0036] Using the sample requirement feature vector and the sample basic feature vector as training samples, and the type labels of the multiple sample candidate envelopes as sample labels, an initial envelope classification model is trained. After training, the envelope classification model is obtained.

[0037] The present invention also provides a communication site planning device, comprising:

[0038] The acquisition unit is used to acquire demand data for multiple target sites to be planned, determine multiple candidate envelopes, and acquire basic data of the multiple candidate envelopes;

[0039] A classification unit is used to classify the multiple candidate envelopes based on the demand data of the multiple target sites and the basic data of the multiple candidate envelopes, so as to obtain multiple types of envelopes;

[0040] The matching unit is used to perform dynamic spatial matching between the multiple target sites and the multiple types of envelopes based on the demand data, and obtain the matching result;

[0041] A planning unit is used to generate a planning scheme for the multiple target sites based on the matching results.

[0042] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the communication site planning method as described above.

[0043] The communication site planning method, apparatus, and electronic device provided by this invention obtain demand data of multiple target sites to be planned, determine multiple candidate envelopes, and obtain basic data of multiple candidate envelopes; based on the demand data of multiple target sites and the basic data of multiple candidate envelopes, classify the multiple candidate envelopes to obtain multiple types of envelopes; then, based on the demand data, perform fine-grained dynamic spatial matching between multiple target sites and multiple types of envelopes to obtain matching results; and based on the matching results, generate planning schemes for multiple target sites, thereby improving the efficiency and accuracy of site planning and increasing resource utilization. Attached Figure Description

[0044] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0045] Figure 1 This is a flowchart illustrating the communication site planning method provided in an embodiment of the present invention.

[0046] Figure 2 This is a schematic diagram of the process for classifying multiple candidate envelopes provided in an embodiment of the present invention.

[0047] Figure 3 This is a flowchart illustrating the training process of the envelope classification model provided in this embodiment of the invention.

[0048] Figure 4 This is a schematic diagram of the communication site planning device provided in an embodiment of the present invention.

[0049] Figure 5 This is a schematic diagram of the structure of the electronic device provided in an embodiment of the present invention. Detailed Implementation

[0050] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0051] Figure 1 This is a flowchart illustrating the communication site planning method provided in an embodiment of the present invention. Figure 1 As shown, a communication site planning method is provided, including the following steps: step 110, step 120, step 130, and step 140. These method steps are merely one possible implementation of the present invention.

[0052] Step 110: Obtain the demand data of multiple target sites to be planned, determine multiple candidate envelopes, and obtain the basic data of multiple candidate envelopes.

[0053] The demand data should include at least the site's latitude and longitude, coverage type, demand network, demand ID, and issue grid ID.

[0054] Among them, the candidate envelope is a closed polygon formed by covering holes or weakly covered areas.

[0055] The basic data includes at least the envelope area, problem raster ID, and envelope ID.

[0056] Optionally, multiple candidate envelopes can be selected from a geographic envelope library based on the demand data of multiple target sites.

[0057] Optionally, based on drive test data or measurement report data, continuous regions within the target area with signal strength less than a threshold are merged into polygons to obtain candidate envelopes.

[0058] Step 120: Based on the demand data of multiple target sites and the basic data of multiple candidate envelopes, classify the multiple candidate envelopes to obtain multiple types of envelopes.

[0059] Optionally, multiple types of envelopes include: authentication envelopes, potential envelopes, and discard envelopes.

[0060] In some embodiments, step 120 classifies multiple candidate envelopes based on demand data from multiple target sites and basic data from multiple candidate envelopes to obtain multiple types of envelopes, including:

[0061] Step 121: Preprocess the demand data from multiple target sites to obtain preprocessed demand data;

[0062] Step 122: Preprocess the basic data of multiple candidate envelopes to obtain preprocessed basic data;

[0063] Step 123: Based on the preprocessed demand data and preprocessed basic data, classify multiple candidate envelopes to obtain multiple types of envelopes.

[0064] Optionally, data cleaning, standardization, normalization, and other preprocessing can be performed on the demand data from multiple target sites.

[0065] Optionally, preprocessing such as data cleaning, missing value imputation, and standardization can be performed on the basic data of multiple candidate envelopes.

[0066] Step 130: Based on the demand data, perform dynamic spatial matching between multiple target sites and multiple types of envelopes to obtain the matching results.

[0067] Optionally, the demand data can be updated, and the matching results can be updated based on the updated demand data.

[0068] Optionally, the matching results can be checked to determine if there is a case where one envelope corresponds to multiple sites. If so, the conflict situation can be handled.

[0069] Step 140: Based on the matching results, generate planning schemes for multiple target sites.

[0070] Optionally, a planning scheme for the target site can be directly generated based on the type of envelope matched by the target site, or the envelope can be verified, and a planning scheme for the target site can be generated after the verification is successful.

[0071] In this embodiment of the invention, by acquiring demand data for multiple target sites to be planned, multiple candidate envelopes are determined, and basic data for the multiple candidate envelopes is obtained. Based on the demand data for multiple target sites and the basic data for multiple candidate envelopes, the multiple candidate envelopes are classified to obtain multiple types of envelopes. Then, based on the demand data, fine-grained dynamic spatial matching can be performed between the multiple target sites and the multiple types of envelopes to obtain matching results. Based on the matching results, planning schemes for multiple target sites are generated, which improves the efficiency and accuracy of site planning and increases resource utilization.

[0072] Figure 2 This is a schematic diagram illustrating the process of classifying multiple candidate envelopes according to an embodiment of the present invention. Figure 2As shown, in some embodiments, step 123 classifies multiple candidate envelopes based on preprocessed demand data and preprocessed basic data to obtain multiple types of envelopes, including:

[0073] Step 1231: Extract features from the preprocessed demand data to obtain demand feature vectors for multiple target sites;

[0074] Step 1232: Extract features from the preprocessed basic data to obtain basic feature vectors of multiple candidate envelopes;

[0075] Step 1233: Input the demand feature vectors of multiple target sites and the basic feature vectors of multiple candidate envelopes into the pre-built envelope classification model to obtain the types of multiple candidate envelopes output by the envelope classification model;

[0076] The envelope classification model is trained based on the sample demand feature vectors of multiple sample sites, the sample basic feature vectors of multiple sample candidate envelopes, and the type labels of multiple sample candidate envelopes.

[0077] The demand feature vector includes at least demand location features, demand network features, and demand coverage type features.

[0078] The basic feature vector includes at least envelope attribute features, network features, and problem grid features.

[0079] In this embodiment of the invention, by inputting the demand feature vectors of multiple target sites and the basic feature vectors of multiple candidate envelopes into a pre-built envelope classification model, the types of multiple candidate envelopes output by the envelope classification model are obtained, thereby improving the efficiency of envelope classification and the real-time performance of site planning.

[0080] In some embodiments, multiple candidate envelopes are classified based on preprocessed demand data and preprocessed basic data, including:

[0081] Based on the preprocessed demand data and preprocessed basic data, the ratio of the envelope area of ​​each candidate envelope to the corresponding single-station coverage area is calculated.

[0082] If the ratio of the envelope area of ​​each candidate envelope to the coverage area of ​​the corresponding single station is less than or equal to a preset threshold, the type of each candidate envelope is determined to be a discard envelope.

[0083] Optionally, the average coverage area of ​​a single target site corresponding to each candidate envelope is calculated to obtain the single-site coverage area corresponding to each candidate envelope.

[0084] Optionally, a preset threshold, such as 0.2, can be determined based on user input or empirical data.

[0085] Understandably, if the ratio of the envelope area of ​​each candidate envelope to the coverage area of ​​the corresponding single station is less than or equal to a preset threshold, the candidate envelope is determined to be a discard envelope. This can achieve automated filtering of invalid envelopes and avoid resource waste.

[0086] In some embodiments, multiple candidate envelopes are classified based on preprocessed demand data and preprocessed basic data, including:

[0087] Based on the preprocessed demand data, determine the total number of target problem grids to be covered for each target site;

[0088] Based on the preprocessed basic data, determine the number of target problem grids covered by each candidate envelope;

[0089] Based on the total number of target issue rasters to be covered at each target site and the number of target issue rasters to be covered by each candidate envelope, at least one authentication envelope is determined from multiple candidate envelopes.

[0090] Optionally, discard envelopes from multiple candidate envelopes to obtain multiple filtered candidate envelopes.

[0091] Optionally, the multiple candidate envelopes after screening are sorted, and based on the sorting results, multiple authentication envelopes and multiple potential envelopes are determined from the multiple candidate envelopes after screening.

[0092] In some embodiments, based on the matching results, a planning scheme for multiple target sites is generated, including:

[0093] If the target site and the authentication envelope are successfully matched, a planning scheme for the target site is generated directly.

[0094] If the target site and the potential envelope are successfully matched, the corresponding potential envelope is verified. If the verification is successful, a planning scheme for the target site is generated.

[0095] If the target site and the dropped envelope are successfully matched, the required data of the target site is intercepted and a prompt message is generated.

[0096] Specifically, if the target site falls within the authentication envelope, pre-planned site generation is allowed directly. If the target site falls within the potential envelope, a mandatory verification mechanism is triggered: if the target site coordinates are within the potential envelope, the user is prompted to add drive test DT sampling points, re-upload the test data, and trigger a data filtering mechanism. This mechanism selects only DT test data whose latitude and longitude fall within this envelope, verifying whether the coverage rate is greater than or equal to a preset coverage threshold (e.g., 80%). If the coverage rate is less than the preset coverage threshold, pre-planned site generation is allowed, and the envelope attribute is changed from potential envelope to authentication envelope; otherwise, no site is generated. If the target site falls within the discard envelope, the data is intercepted, and a message is displayed: "Target site falls within discard envelope; please modify latitude and longitude and re-upload."

[0097] In some embodiments, after dynamically spatially matching multiple target sites with multiple types of envelopes to obtain the matching results, the method further includes:

[0098] Based on the matching results, multiple target envelopes that match multiple target sites are determined;

[0099] For each target envelope, site conflict is predicted. If site conflicts are predicted, they are handled, and the matching results are optimized.

[0100] Optionally, if there are no other sites within the target envelope, site planning is carried out according to the normal process, and the corresponding sites are marked as newly created - self-pickup.

[0101] Optionally, if only a new self-pickup site exists within the target envelope, a new site is generated and tagged as a new co-pickup site, while the existing new self-pickup sites within the target envelope are tagged as new co-pickup sites.

[0102] Optionally, if a new-co-extraction site already exists within the target envelope, a new site is generated and marked as a new-co-extraction site.

[0103] Optionally, if multiple target sites imported in the same batch fall within the same envelope, only one site will be selected, and the rest will be rejected, with a prompt: "Multiple submissions of pre-planned sites within one envelope area."

[0104] Figure 3 This is a flowchart illustrating the training process of the envelope classification model provided in an embodiment of the present invention. Figure 3 As shown, in some embodiments, the training process of the envelope classification model includes:

[0105] Step 310: Obtain sample requirement data from multiple sample sites and sample basic data from multiple sample candidate envelopes, and determine the type labels of multiple sample candidate envelopes.

[0106] Step 320: Preprocess the sample demand data of multiple sample sites to obtain preprocessed sample demand data; preprocess the sample basic data of multiple sample candidate envelopes to obtain preprocessed sample basic data.

[0107] Step 330: Extract features from the preprocessed sample demand data to obtain sample demand feature vectors for multiple sample sites; extract features from the preprocessed sample basic data to obtain sample basic feature vectors for multiple sample candidate envelopes.

[0108] Step 340: Using the sample requirement feature vector and the sample basic feature vector as training samples, and the type labels of multiple sample candidate envelopes as sample labels, train the initial envelope classification model. After training, the envelope classification model is obtained.

[0109] Optionally, the type labels for multiple sample candidate envelopes include certified envelope, potential envelope, and discarded envelope.

[0110] Optionally, demand data from multiple historical sites (or similar scenarios) that have been successfully deployed can be collected, which constitutes sample demand data for multiple sample sites.

[0111] Optionally, preprocessing such as data cleaning, missing value imputation, data transformation, and data integration can be performed on the sample requirement data and sample basic data.

[0112] Optionally, the initial envelope classification model can be of the type logistic regression, support vector machine, random forest, neural network, etc.

[0113] In this embodiment of the invention, an initial envelope classification model is trained using sample requirement feature vectors and sample basic feature vectors as training samples and type labels of multiple sample candidate envelopes as sample labels. After training, an envelope classification model is obtained, which improves the robustness of the envelope classification model. In turn, different envelopes can be classified through the envelope classification model, thereby improving the efficiency and accuracy of envelope classification.

[0114] The communication site planning apparatus provided in the embodiments of the present invention will be described below. The communication site planning apparatus described below can be referred to in correspondence with the communication site planning method described above.

[0115] Figure 4 This is a schematic diagram of the communication site planning device provided in an embodiment of the present invention, as shown below. Figure 4 As shown, the communication site planning device 400 includes:

[0116] The acquisition unit 410 is used to acquire the demand data of multiple target sites to be planned, determine multiple candidate envelopes, and acquire the basic data of multiple candidate envelopes;

[0117] Classification unit 420 is used to classify multiple candidate envelopes based on demand data from multiple target sites and basic data from multiple candidate envelopes, thereby obtaining multiple types of envelopes;

[0118] Matching unit 430 is used to perform dynamic spatial matching of multiple target sites with multiple types of envelopes based on demand data to obtain matching results;

[0119] Planning unit 440 is used to generate planning schemes for multiple target sites based on the matching results.

[0120] Optionally, based on demand data from multiple target sites and basic data from multiple candidate envelopes, the multiple candidate envelopes are classified to obtain multiple types of envelopes, including:

[0121] The demand data from multiple target sites is preprocessed to obtain preprocessed demand data.

[0122] The basic data of multiple candidate envelopes are preprocessed to obtain preprocessed basic data.

[0123] Based on the preprocessed demand data and preprocessed basic data, multiple candidate envelopes are classified to obtain multiple types of envelopes; the multiple types of envelopes include: authentication envelopes, potential envelopes, and discarded envelopes.

[0124] Optionally, based on the preprocessed demand data and preprocessed basic data, multiple candidate envelopes are classified to obtain multiple types of envelopes, including:

[0125] Feature extraction is performed on the preprocessed demand data to obtain demand feature vectors for multiple target sites;

[0126] Feature extraction is performed on the preprocessed basic data to obtain basic feature vectors of multiple candidate envelopes;

[0127] Input the demand feature vectors of multiple target sites and the basic feature vectors of multiple candidate envelopes into a pre-built envelope classification model to obtain the types of multiple candidate envelopes output by the envelope classification model;

[0128] The envelope classification model is trained based on the sample demand feature vectors of multiple sample sites, the sample basic feature vectors of multiple sample candidate envelopes, and the type labels of multiple sample candidate envelopes.

[0129] Optionally, based on the preprocessed demand data and preprocessed basic data, multiple candidate envelopes are classified, including:

[0130] Based on the preprocessed demand data and preprocessed basic data, the ratio of the envelope area of ​​each candidate envelope to the corresponding single-station coverage area is calculated.

[0131] If the ratio of the envelope area of ​​each candidate envelope to the coverage area of ​​the corresponding single station is less than or equal to a preset threshold, the type of each candidate envelope is determined to be a discard envelope.

[0132] Optionally, based on the preprocessed demand data and preprocessed basic data, multiple candidate envelopes are classified, including:

[0133] Based on the preprocessed demand data, determine the total number of target problem grids to be covered for each target site;

[0134] Based on the preprocessed basic data, determine the number of target problem grids covered by each candidate envelope;

[0135] Based on the total number of target issue rasters to be covered at each target site and the number of target issue rasters to be covered by each candidate envelope, at least one authentication envelope is determined from multiple candidate envelopes.

[0136] Optionally, based on the matching results, planning schemes for multiple target sites are generated, including:

[0137] If the target site and the authentication envelope are successfully matched, a planning scheme for the target site is generated directly.

[0138] If the target site and the potential envelope are successfully matched, the corresponding potential envelope is verified. If the verification is successful, a planning scheme for the target site is generated.

[0139] If the target site and the dropped envelope are successfully matched, the required data of the target site is intercepted and a prompt message is generated.

[0140] Optionally, the communication site planning device also includes:

[0141] The determining unit is used to determine multiple target envelopes that match multiple target sites based on the matching results;

[0142] The site conflict handling unit is used to predict site conflicts for each target envelope, process site conflicts when they are predicted to exist, and optimize the matching results.

[0143] Optionally, the training process of the envelope classification model includes:

[0144] Obtain sample requirement data from multiple sample sites, as well as sample basic data from multiple candidate envelopes, and determine the type labels of multiple candidate envelopes.

[0145] Preprocess the sample requirement data of multiple sample sites to obtain preprocessed sample requirement data, and preprocess the sample basic data of multiple sample candidate envelopes to obtain preprocessed sample basic data.

[0146] Feature extraction is performed on the preprocessed sample demand data to obtain sample demand feature vectors for multiple sample sites. Feature extraction is also performed on the preprocessed sample basic data to obtain sample basic feature vectors for multiple sample candidate envelopes.

[0147] Using the sample requirement feature vector and the sample basic feature vector as training samples, and the type labels of multiple sample candidate envelopes as sample labels, an initial envelope classification model is trained. After training, the envelope classification model is obtained.

[0148] It should be noted that the communication site planning device provided in this embodiment of the invention can implement all the method steps implemented in the above-described communication site planning method embodiment, and can achieve the same technical effect. Here, the parts that are the same as those in the method embodiment and the beneficial effects will not be described in detail.

[0149] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention, such as... Figure 5 As shown, the electronic device may include a processor 510, a communications interface 520, a memory 530, and a communication bus 540, wherein the processor 510, communications interface 520, and memory 530 communicate with each other through the communication bus 540. The processor 510 can call logical instructions in the memory 530 to execute a communication site planning method, which includes: acquiring demand data of multiple target sites to be planned, determining multiple candidate envelopes, and acquiring basic data of multiple candidate envelopes; classifying multiple candidate envelopes based on the demand data of multiple target sites and the basic data of multiple candidate envelopes to obtain multiple types of envelopes; performing dynamic spatial matching of multiple target sites with multiple types of envelopes based on the demand data to obtain matching results; and generating planning schemes for multiple target sites based on the matching results.

[0150] Furthermore, the logical instructions in the aforementioned memory 530 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0151] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0152] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0153] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A communication site planning method, characterized in that, include: Obtain demand data for multiple target sites to be planned, determine multiple candidate envelopes, wherein the candidate envelopes are closed polygons formed by coverage holes or weak coverage areas, and obtain basic data for the multiple candidate envelopes; Based on the demand data of the multiple target sites and the basic data of the multiple candidate envelopes, the multiple candidate envelopes are classified to obtain multiple types of envelopes; Based on the demand data, the multiple target sites are dynamically spatially matched with the multiple types of envelopes to obtain matching results; Based on the matching results, a planning scheme for the multiple target sites is generated; Based on the demand data of the multiple target sites and the basic data of the multiple candidate envelopes, the multiple candidate envelopes are classified to obtain multiple types of envelopes, including: The demand data of the multiple target sites is preprocessed to obtain preprocessed demand data; The basic data of the multiple candidate envelopes are preprocessed to obtain preprocessed basic data; Based on the preprocessed demand data and the preprocessed basic data, the multiple candidate envelopes are classified to obtain multiple types of envelopes; the multiple types of envelopes include: authentication envelopes, potential envelopes, and discarded envelopes; The step of generating a planning scheme for the multiple target sites based on the matching results includes: If the target site is found to be successfully matched with the authentication envelope, a planning scheme for the target site is directly generated. If the target site is successfully matched with the potential envelope, the corresponding potential envelope is verified. If the verification is successful, a planning scheme for the target site is generated. If the target site is successfully matched with the dropped envelope, the demand data of the target site is intercepted and a prompt message is generated.

2. The communication site planning method according to claim 1, characterized in that, Based on the preprocessed demand data and the preprocessed basic data, the multiple candidate envelopes are classified to obtain multiple types of envelopes, including: Feature extraction is performed on the preprocessed demand data to obtain the demand feature vectors of the multiple target sites; Feature extraction is performed on the preprocessed basic data to obtain the basic feature vectors of the multiple candidate envelopes; The demand feature vectors of the multiple target sites and the basic feature vectors of the multiple candidate envelopes are input into a pre-built envelope classification model to obtain the types of the multiple candidate envelopes output by the envelope classification model. The envelope classification model is trained based on the sample demand feature vectors of multiple sample sites, the sample basic feature vectors of multiple sample candidate envelopes, and the type labels of the multiple sample candidate envelopes.

3. The communication site planning method according to claim 1, characterized in that, The classification of the multiple candidate envelopes based on the preprocessed demand data and the preprocessed basic data includes: Based on the preprocessed demand data and the preprocessed basic data, the ratio of the envelope area of ​​each candidate envelope to the corresponding single-station coverage area is calculated. If the ratio of the envelope area of ​​each candidate envelope to the coverage area of ​​the corresponding single station is less than or equal to a preset threshold, the type of each candidate envelope is determined to be a discarded envelope.

4. The communication site planning method according to claim 1, characterized in that, The classification of the multiple candidate envelopes based on the preprocessed demand data and the preprocessed basic data includes: Based on the preprocessed demand data, determine the total number of target problem grids to be covered for each target site; Based on the preprocessed basic data, determine the number of target problem grids covered by each candidate envelope; Based on the total number of target problem grids to be covered at each target site and the number of target problem grids to be covered by each candidate envelope, at least one authentication envelope is determined from the plurality of candidate envelopes.

5. The communication site planning method according to claim 1, characterized in that, After performing dynamic spatial matching of the multiple target sites with the multiple types of envelopes to obtain the matching results, the process further includes: Based on the matching results, multiple target envelopes that match the multiple target sites are determined; For each target envelope, site conflict is predicted. If site conflict is predicted, the site conflict is processed, and the matching result is optimized.

6. The communication site planning method according to claim 2, characterized in that, The training process of the envelope classification model includes: Obtain sample requirement data from multiple sample sites and sample basic data from multiple sample candidate envelopes, and determine the type labels of the multiple sample candidate envelopes; The sample demand data of the multiple sample sites are preprocessed to obtain preprocessed sample demand data, and the sample basic data of the multiple sample candidate envelopes are preprocessed to obtain preprocessed sample basic data. Feature extraction is performed on the preprocessed sample demand data to obtain the sample demand feature vectors of the multiple sample sites; feature extraction is performed on the preprocessed sample basic data to obtain the sample basic feature vectors of the multiple sample candidate envelopes. Using the sample requirement feature vector and the sample basic feature vector as training samples, and the type labels of the multiple sample candidate envelopes as sample labels, an initial envelope classification model is trained. After training, the envelope classification model is obtained.

7. A communication site planning device, characterized in that, include: The acquisition unit is used to acquire demand data for multiple target sites to be planned, determine multiple candidate envelopes, wherein the candidate envelopes are closed polygons formed by coverage holes or weak coverage areas, and acquire basic data of the multiple candidate envelopes. A classification unit is used to classify the multiple candidate envelopes based on the demand data of the multiple target sites and the basic data of the multiple candidate envelopes, so as to obtain multiple types of envelopes; The matching unit is used to perform dynamic spatial matching between the multiple target sites and the multiple types of envelopes based on the demand data, and obtain the matching result; A planning unit is used to generate a planning scheme for the multiple target sites based on the matching results; Based on the demand data of the multiple target sites and the basic data of the multiple candidate envelopes, the multiple candidate envelopes are classified to obtain multiple types of envelopes, including: The demand data of the multiple target sites is preprocessed to obtain preprocessed demand data; The basic data of the multiple candidate envelopes are preprocessed to obtain preprocessed basic data; Based on the preprocessed demand data and the preprocessed basic data, the multiple candidate envelopes are classified to obtain multiple types of envelopes; the multiple types of envelopes include: authentication envelopes, potential envelopes, and discarded envelopes; The step of generating a planning scheme for the multiple target sites based on the matching results includes: If the target site is found to be successfully matched with the authentication envelope, a planning scheme for the target site is directly generated. If the target site is successfully matched with the potential envelope, the corresponding potential envelope is verified. If the verification is successful, a planning scheme for the target site is generated. If the target site is successfully matched with the dropped envelope, the demand data of the target site is intercepted and a prompt message is generated.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the communication site planning method as described in any one of claims 1 to 6.

Images