Resource utilization rate evaluation method and device, storage medium and electronic device

Abstract

The application discloses a resource utilization evaluation method and device, a storage medium and an electronic device. It relates to the field of artificial intelligence, and the method comprises the following steps: obtaining first parameter data associated with a communication site to be evaluated by a large language model, wherein the first parameter data is parameter data related to resource utilization evaluation in a current evaluation period; determining target parameter data according to the first parameter data and second parameter data, wherein the second parameter data is parameter data used for resource utilization evaluation in a previous evaluation period; adjusting a current evaluation model according to the target parameter data to obtain a target evaluation model; and evaluating the resource utilization of the communication site to be evaluated according to the target parameter data and the target evaluation model to obtain an evaluation result. The method solves the problem of low evaluation efficiency of the resource utilization of the communication site in the related art, which relies on manual identification of parameter changes and manual adjustment of evaluation algorithms.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence, and more specifically, to a method and apparatus for evaluating resource utilization, a storage medium, and an electronic device. Background Technology

[0002] Assessment of communication site resource utilization is a core aspect of communication site operation optimization. Accurate assessment results provide reliable support for resource scheduling, capacity expansion and upgrades, and layout optimization. The number of parameters related to resource utilization assessment (such as lease order parameters, regional demand parameters, and equipment status parameters) is constantly changing, and the mechanisms influencing them are becoming increasingly complex. Currently, related technologies rely on manual identification of parameter changes and manual adjustment of the assessment algorithm accordingly. This results in low parameter adaptation efficiency and delayed algorithm adjustments, leading to low efficiency in assessing communication site resource utilization.

[0003] There is currently no effective solution to the problem that relying on manual identification of parameter changes and manual adjustment of evaluation algorithms in related technologies leads to low efficiency in evaluating the utilization of communication site resources. Summary of the Invention

[0004] The main objective of this application is to provide a method, apparatus, storage medium, and electronic device for evaluating resource utilization, in order to solve the problem that the evaluation efficiency of communication site resource utilization is low due to reliance on manual identification of parameter changes and manual adjustment of evaluation algorithms in related technologies.

[0005] To achieve the above objectives, according to one aspect of this application, a method for assessing resource utilization is provided. The method includes: obtaining first parameter data associated with a communication site to be assessed through a large language model, wherein the first parameter data is parameter data related to resource utilization assessment in the current assessment period; determining target parameter data based on the first parameter data and second parameter data, wherein the second parameter data is parameter data used for resource utilization assessment in the previous assessment period, and the target parameter data is: parameter data existing in the current assessment period with a correlation value greater than a first threshold for resource utilization, excluding parameter data existing in the previous assessment period, not existing in the current assessment period, and with a historical correlation value less than a second threshold; adjusting the current assessment model based on the target parameter data to obtain a target assessment model; and assessing the resource utilization of the communication site to be assessed based on the target parameter data and the target assessment model to obtain an assessment result.

[0006] Further, determining the target parameter data based on the first parameter data and the second parameter data includes: comparing the first parameter data and the second parameter data to determine the newly added parameter data, the deleted parameter data, and the common parameter data; calculating the correlation between the newly added parameter data and the resource utilization rate to obtain a first value, and comparing the first value with a first threshold, using the newly added parameter data whose first value is greater than the first threshold as the initial target parameter data; calculating the correlation between the deleted parameter data and the resource utilization rate to obtain a second value, and comparing the second value with a second threshold, using the deleted parameter data whose second value is less than the second threshold as the deletable parameter data; and determining the target parameter data based on the common parameter data and the initial target parameter data.

[0007] Furthermore, after comparing the second value with the second threshold, the method further includes: taking the deletion parameter data whose second value is greater than or equal to the second threshold as the erroneously deleted parameter data, generating early warning information, and sending the early warning information to the target object.

[0008] Further, adjusting the current evaluation model based on the target parameter data to obtain the target evaluation model includes: obtaining the input nodes and parameter weights of the current evaluation model, wherein each input node corresponds one-to-one with the second parameter data, and the parameter weight is the correlation coefficient of each input node with resource utilization; determining the first input node, the second input node, and the third input node based on the target parameter data and the input nodes, wherein the first input node corresponds to the common parameter data in the target parameter data, the second input node corresponds to the initial target parameter data in the target parameter data, and the third input node is the input node other than the first input node; adjusting the input nodes and parameter weights of the current evaluation model based on the parameter weights, the first input node, the second input node, and the third input node to obtain the initial target evaluation model; validating the initial target evaluation model based on the validation dataset, and if the validation passes, the initial target evaluation model is used as the target evaluation model.

[0009] Furthermore, based on the target parameter data and the target evaluation model, the resource utilization rate of the communication site to be evaluated is evaluated, and the evaluation results include: obtaining an intermediate feature vector by performing feature mapping on the target parameter data through the input node of the target evaluation model; obtaining a resource utilization rate score by performing weighted aggregation and nonlinear transformation on the intermediate feature vector through the calculation node of the target evaluation model; and determining the evaluation result based on the resource utilization rate score through the output node of the target evaluation model.

[0010] Furthermore, before obtaining the first parameter data associated with the communication site to be evaluated through the large language model, the method also includes: obtaining multi-source heterogeneous data from multiple business systems in real time, and cleaning and standardizing the multi-source heterogeneous data to obtain an initial parameter dataset; performing semantic analysis and parameter extraction on the initial parameter dataset through the large language model to obtain the first parameter data.

[0011] Furthermore, after obtaining the evaluation results, the method also includes: comparing the evaluation results with a preset utilization threshold to obtain a comparison result; and determining resource optimization suggestions corresponding to the communication site to be evaluated based on the comparison result.

[0012] To achieve the above objectives, according to another aspect of this application, a resource utilization assessment apparatus is provided. The apparatus includes: a first processing unit, configured to acquire first parameter data associated with a communication site to be assessed through a large language model, wherein the first parameter data is parameter data related to resource utilization assessment in the current assessment period; a first determining unit, configured to determine target parameter data based on the first parameter data and second parameter data, wherein the second parameter data is parameter data used for resource utilization assessment in the previous assessment period, and the target parameter data is: parameter data existing in the current assessment period and having a correlation value greater than a first threshold with resource utilization, excluding parameter data existing in the previous assessment period, not existing in the current assessment period, and having a historical correlation value less than a second threshold; a second processing unit, configured to adjust the current assessment model based on the target parameter data to obtain a target assessment model; and a third processing unit, configured to perform resource utilization assessment on the communication site to be assessed based on the target parameter data and the target assessment model to obtain an assessment result.

[0013] Further, the first determining unit includes: a first processing subunit, used to compare the first parameter data and the second parameter data to determine the newly added parameter data, the deleted parameter data, and the common parameter data; a second processing subunit, used to perform correlation calculation between the newly added parameter data and the resource utilization rate to obtain a first value, and compare the first value with a first threshold, taking the newly added parameter data whose first value is greater than the first threshold as the initial target parameter data; a third processing subunit, used to perform correlation calculation between the deleted parameter data and the resource utilization rate to obtain a second value, and compare the second value with a second threshold, taking the deleted parameter data whose second value is less than the second threshold as the deletable parameter data; and a first determining subunit, used to determine the target parameter data based on the common parameter data and the initial target parameter data.

[0014] Furthermore, the device also includes a second determining unit, which, after comparing the second value with the second threshold, takes the deletion parameter data where the second value is greater than or equal to the second threshold as the erroneous deletion parameter data, generates a warning message, and sends the warning message to the target object.

[0015] Further, the second processing unit includes: an acquisition subunit, used to acquire the input nodes and parameter weights of the current evaluation model, wherein the input nodes correspond one-to-one with the second parameter data, and the parameter weights are the correlation coefficients of each input node with the resource utilization rate; a second determination subunit, used to determine the first input node, the second input node, and the third input node based on the target parameter data and the input nodes, wherein the first input node corresponds to the common parameter data in the target parameter data, the second input node corresponds to the initial target parameter data in the target parameter data, and the third input node is the input node other than the first input node; a fourth processing subunit, used to adjust the input nodes and parameter weights of the current evaluation model based on the parameter weights, the first input node, the second input node, and the third input node to obtain the initial target evaluation model; and a third determination subunit, used to verify the initial target evaluation model based on the verification dataset, and if the verification is successful, the initial target evaluation model is used as the target evaluation model.

[0016] Furthermore, the third processing unit includes: a fifth processing subunit, used to perform feature mapping based on target parameter data through the input nodes of the target evaluation model to obtain an intermediate feature vector; a sixth processing subunit, used to perform weighted aggregation and nonlinear transformation based on the intermediate feature vector through the calculation nodes of the target evaluation model to obtain a resource utilization score; and a fourth determination subunit, used to determine the evaluation result based on the resource utilization score through the output nodes of the target evaluation model.

[0017] Furthermore, the device also includes: a first acquisition unit, used to acquire multi-source heterogeneous data from multiple business systems in real time before acquiring the first parameter data associated with the communication site to be evaluated through a large language model, and to perform data cleaning and standardization on the multi-source heterogeneous data to obtain an initial parameter dataset; and a second acquisition unit, used to perform semantic analysis and parameter extraction on the initial parameter dataset through a large language model to obtain the first parameter data.

[0018] Furthermore, the device also includes: a comparison unit, used to compare the evaluation results with a preset utilization threshold after obtaining the evaluation results, and obtain a comparison result; and a third determination unit, used to determine resource optimization suggestions corresponding to the communication site to be evaluated based on the comparison result.

[0019] According to another aspect of the present invention, an electronic device is also provided, comprising: a memory storing an executable program; and a processor for running the program, wherein the program executes the resource utilization evaluation method of any one of the above-mentioned methods during runtime.

[0020] According to another aspect of the present invention, a computer-readable storage medium is also provided, wherein the storage medium stores a program, wherein the program controls the device where the storage medium is located to perform the resource utilization evaluation method of any of the above-mentioned methods when the program is running.

[0021] In this embodiment, the following steps are employed: First parameter data associated with the communication site to be evaluated is obtained through a large language model, wherein the first parameter data is parameter data related to resource utilization evaluation in the current evaluation period; Target parameter data is determined based on the first parameter data and second parameter data, wherein the second parameter data is parameter data used for resource utilization evaluation in the previous evaluation period, and the target parameter data is: parameter data that exists in the current evaluation period and whose correlation value with resource utilization is greater than a first threshold, excluding parameter data that existed in the previous evaluation period, does not exist in the current evaluation period, and whose historical correlation value is less than a second threshold; The current evaluation model is adjusted based on the target parameter data to obtain a target evaluation model; Resource utilization evaluation of the communication site to be evaluated is performed based on the target parameter data and the target evaluation model to obtain the evaluation result. This solves the technical problem in related technologies where reliance on manual identification of parameter changes and manual adjustment of the evaluation algorithm leads to low efficiency in evaluating the resource utilization of communication sites.

[0022] In this scheme, the first parameter data of the communication site to be evaluated in the current evaluation period is obtained through a large language model. Combined with the second parameter data used for resource utilization evaluation in the previous evaluation period, correlation analysis is used to determine that only parameter data existing in the current evaluation period and whose correlation with resource utilization is greater than the first threshold is retained, while parameter data existing in the previous evaluation period but disappearing in the current evaluation period and whose historical correlation value is lower than the second threshold is removed, thus forming the target parameter data. Based on the target parameter data, the structure and weights of the current evaluation model are adaptively adjusted to obtain the target evaluation model. Then, the resource utilization of the communication site to be evaluated is evaluated using the target parameter data and the target evaluation model, and high-precision evaluation results are output. This realizes dynamic screening of evaluation parameters and adaptive adjustment of model structure, improving the accuracy and efficiency of resource utilization evaluation. Attached Figure Description

[0023] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:

[0024] Figure 1 A hardware block diagram of a computer terminal for implementing a method for evaluating resource utilization is shown.

[0025] Figure 2 This is a flowchart of a resource utilization assessment method provided according to an embodiment of this application;

[0026] Figure 3 This is a schematic diagram of the workflow of a resource utilization assessment system provided according to an embodiment of this application;

[0027] Figure 4 This is a schematic diagram of the resource utilization assessment process provided in the embodiments of this application;

[0028] Figure 5 This is a schematic diagram of a resource utilization evaluation device provided according to an embodiment of this application;

[0029] Figure 6 This is a structural block diagram of an electronic device according to an embodiment of this application. Detailed Implementation

[0030] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present application.

[0031] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0032] It should be noted that the information collected in this application (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for display, data used for analysis, etc.) are information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, storage, use, processing, transmission, provision, disclosure, and application of this data all comply with relevant laws, regulations, and standards, and necessary measures have been taken to ensure compliance with public order and good morals. Corresponding access points are provided for users to choose whether to authorize or refuse. For example, interfaces are established between this system and relevant users or organizations, providing users with corresponding access points to choose whether to agree to or refuse automated decision-making results; if the user chooses to refuse, the process proceeds to the expert decision-making stage.

[0033] Example 1

[0034] According to an embodiment of this application, a method embodiment for evaluating resource utilization is also provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0035] The method embodiment provided in Embodiment 1 of this application can be executed on a mobile terminal, computer terminal, or similar computing device. Figure 1 A hardware block diagram of a computer terminal (or mobile device) for implementing a method for evaluating resource utilization is shown. Figure 1 As shown, the computer terminal 10 (or mobile device) may include one or more processors 102 (shown as 102a, 102b, ..., 102n in the figure) 102 (processor 102 may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.), a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of a BUS bus), a network interface, a power supply, and / or a camera. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, computer terminal 10 may also include... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0036] It should be noted that the aforementioned one or more processors 102 and / or other data processing circuits are generally referred to herein as "data processing circuits". These data processing circuits may be embodied, in whole or in part, in software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuits may be a single, independent processing module, or may be integrated, in whole or in part, into any other element within the computer terminal 10 (or mobile device). As involved in the embodiments of this application, the data processing circuits serve as a processor control mechanism (e.g., selection of a variable resistor termination path connected to an interface).

[0037] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the resource utilization evaluation method in this embodiment. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, thereby realizing the aforementioned resource utilization evaluation method. The memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the computer terminal 10 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0038] The transmission device 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of the computer terminal 10. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 may be a Radio Frequency (RF) module, used for wireless communication with the Internet.

[0039] The display may be a touchscreen liquid crystal display (LCD) that allows the user to interact with the user interface of the computer terminal 10 (or mobile device).

[0040] Under the aforementioned operating environment, this application provides the following: Figure 2 The resource utilization rate assessment method is shown. Figure 2 This is a flowchart of a resource utilization rate assessment method according to Embodiment 1 of this application. The resource utilization rate assessment method includes:

[0041] Step S201: Obtain the first parameter data associated with the communication site to be evaluated through the large language model, wherein the first parameter data is the parameter data related to resource utilization evaluation in the current evaluation period;

[0042] Step S202: Determine target parameter data based on the first parameter data and the second parameter data. The second parameter data is the parameter data used for resource utilization assessment in the previous assessment period. The target parameter data is: parameter data that exists in the current assessment period and whose correlation value with resource utilization is greater than the first threshold, but does not include parameter data that existed in the previous assessment period, does not exist in the current assessment period, and whose historical correlation value is less than the second threshold.

[0043] Step S203: Adjust the current evaluation model based on the target parameter data to obtain the target evaluation model;

[0044] Step S204: Based on the target parameter data and the target evaluation model, evaluate the resource utilization rate of the communication site to be evaluated, and obtain the evaluation results.

[0045] Optionally, the evaluation system, based on preset time intervals or when detecting parameter data changes, uses a large language model to collect multi-source heterogeneous data related to the communication site to be evaluated in real time from multiple business systems (such as leasing management systems, equipment monitoring systems, regional planning systems, and operator docking platforms). This data is then cleaned and standardized to obtain an initial parameter dataset. The large language model is fine-tuned and trained based on parameter data such as historical resource utilization rate data, long-term lease order data, equipment operating status data, and regional business demand data for the communication site, along with labeled parameter importance tags. Then, based on the semantic understanding capabilities of the pre-trained large language model, it automatically identifies semantic entities and numerical features related to resource utilization rate evaluation, i.e., performs semantic analysis and parameter extraction on the initial parameter dataset to obtain the parameter data related to resource utilization rate evaluation in the current evaluation period (i.e., the first parameter data).

[0046] Optionally, the large language model retrieves parameter data (i.e., second parameter data) used in the previous evaluation period for resource utilization assessment. Through correlation analysis, it determines to retain only parameter data that exists in the current evaluation period and whose correlation with resource utilization is greater than a first threshold, and removes parameter data that existed in the previous evaluation period but has disappeared in the current evaluation period and whose historical correlation is lower than the second threshold, thus forming the target parameter data. For example, the first parameter data is the number of lease orders, communication site type, and base station density, and the second parameter data is the number of lease orders, the number of tenants leaving the premises, and the type of communication site. The large language model analyzes: "Number of tenants leaving the premises" existed in the previous evaluation period but disappeared in the current evaluation period, and its historical correlation is 0.11, which is less than the second threshold (e.g., 0.2), so it is determined to be an invalid disappeared parameter and is excluded; "Base station density" appears for the first time in the current evaluation period, and its correlation is 0.67, which is greater than the first threshold (e.g., 0.5), so it is included in the target parameters; "Number of lease orders" and "Communication site type" continue to exist, so these parameters are retained. That is, the target parameter data are the number of lease orders, the type of communication site, and the base station density.

[0047] Optionally, the large language model adaptively adjusts the structure and weights of the current evaluation model (such as a machine learning model) based on the target parameter data. For example, the model automatically removes the "number of tenants leaving" input channel and adds a "base station density" channel, keeping the input dimensions stable but updating the content to improve evaluation accuracy and obtain the target evaluation model. Then, the target parameter data and the target evaluation model are used to evaluate the resource utilization of the communication site to be evaluated, and output high-precision evaluation results.

[0048] In summary, by using a large language model to obtain the first parameter data of the communication site to be evaluated in the current evaluation period, and combining it with the second parameter data used for resource utilization evaluation in the previous evaluation period, correlation analysis is conducted to determine that only parameter data existing in the current evaluation period with a correlation value greater than the first threshold for resource utilization is retained, while parameter data existing in the previous evaluation period but no longer existing in the current evaluation period and whose historical correlation value is lower than the second threshold is removed, thus forming the target parameter data. Based on this target parameter data, the structure and weights of the current evaluation model are adaptively adjusted to obtain the target evaluation model. Then, the target parameter data and the target evaluation model are used to evaluate the resource utilization of the communication site to be evaluated, outputting high-precision evaluation results. This achieves dynamic screening of evaluation parameters and adaptive adjustment of model structure, improving the accuracy and efficiency of resource utilization evaluation.

[0049] Optionally, in the resource utilization evaluation method provided in this application embodiment, determining the target parameter data based on the first parameter data and the second parameter data includes: comparing the first parameter data and the second parameter data to determine the newly added parameter data, the deleted parameter data, and the common parameter data; performing a correlation calculation between the newly added parameter data and the resource utilization rate to obtain a first value, and comparing the first value with a first threshold, taking the newly added parameter data whose first value is greater than the first threshold as the initial target parameter data; performing a correlation calculation between the deleted parameter data and the resource utilization rate to obtain a second value, and comparing the second value with a second threshold, taking the deleted parameter data whose second value is less than the second threshold as the deletable parameter data; and determining the target parameter data based on the common parameter data and the initial target parameter data.

[0050] Optionally, in the resource utilization evaluation method provided in the embodiments of this application, after comparing the second value with the second threshold, the method further includes: taking the deletion parameter data whose second value is greater than or equal to the second threshold as the erroneous deletion parameter data, generating early warning information, and sending the early warning information to the target object.

[0051] In an optional embodiment, the large language model compares the first parameter data and the second parameter data, automatically identifying the increase or decrease of parameters, marking the name, type, and data characteristics of newly added parameters, and marking the name and corresponding deletion identifier of deleting parameters. This identifies newly added parameter data in the current evaluation period, parameter data that existed in the previous evaluation period but has been deleted in the current period, and common parameter data that exists in both periods. Then, through a preset correlation analysis logic, the correlation between newly added parameters and resource utilization is determined, filtering out valid newly added parameters (correlation values ​​greater than a first threshold), eliminating invalid newly added parameters (correlation values ​​less than or equal to the first threshold), and verifying the deleting parameters to confirm whether they are obsolete or invalid parameters (correlation values ​​less than a second threshold), avoiding the accidental deletion of valid parameters (correlation values ​​greater than or equal to the second threshold). The valid newly added parameters and common parameters are then used as target parameters. If any parameter data is accidentally deleted, an early warning message is generated and sent to the target object (such as operations management personnel).

[0052] By using a large language model, the real-time automatic monitoring and identification of relevant parameters is achieved, which solves the problems of low efficiency, easy omission, and large error in manual identification of parameter additions and subtractions. This improves the accuracy and real-time performance of parameter identification and can quickly adapt to scenarios with dynamic parameter changes.

[0053] Optionally, in the resource utilization evaluation method provided in this application embodiment, adjusting the current evaluation model based on the target parameter data to obtain the target evaluation model includes: obtaining the input nodes and parameter weights of the current evaluation model, wherein the input nodes correspond one-to-one with the second parameter data, and the parameter weights are the correlation coefficients of each input node with the resource utilization rate; determining the first input node, the second input node, and the third input node based on the target parameter data and the input nodes, wherein the first input node corresponds to the common parameter data in the target parameter data, the second input node corresponds to the initial target parameter data in the target parameter data, and the third input node is the input node other than the first input node; adjusting the input nodes and parameter weights of the current evaluation model based on the parameter weights, the first input node, the second input node, and the third input node to obtain the initial target evaluation model; and validating the initial target evaluation model based on the validation dataset. If the validation passes, the initial target evaluation model is used as the target evaluation model.

[0054] In an optional embodiment, the input nodes and parameter weights of the current evaluation model (i.e., the model used in the previous evaluation cycle) are obtained. Based on the target parameter data and input nodes, the input nodes to be retained (i.e., the first input node), the input nodes to be added (i.e., the second input node), and the input nodes to be removed (i.e., the third input node) are determined. Then, the input nodes and parameter weights of the current evaluation model are adjusted according to the parameter weights, the first input node, the second input node, and the third input node. For example, in the input layer of the current evaluation model, the first input node and its original parameter weights are retained, and the parameter weights are fine-tuned based on the current data distribution; in the input layer of the current evaluation model, a second input node is added, and its corresponding parameter weights are initialized to zero or based on the migration value of historical similar parameters; in the input layer of the current evaluation model, the third input node and all its connection paths are removed, and the corresponding computing resources are released to obtain the initial target evaluation model. Then, the accuracy of the adjusted model (i.e. the initial target evaluation model) is evaluated using a validation dataset (such as the latest dataset containing target parameter data). If the accuracy improvement relative to the original model is not less than a preset threshold, the adjusted model is determined as the target evaluation model. If the preset threshold is not reached, the parameter optimization process is automatically started, the learning rate and regularization strength are adjusted, and the fine-tuning is repeated until the accuracy requirement is met.

[0055] In an optional embodiment, the large language model determines the adjustment type (e.g., parameter increase adjustment or parameter decrease adjustment) based on the identified parameter increase / decrease results, and invokes the algorithm's adaptive adjustment logic: if it is a parameter increase adjustment, the large language model automatically expands the input dimensions of the evaluation model, incorporates the selected effective new parameters into the model input system, extracts the feature information of the new parameters, adjusts the model's weight parameters, strengthens the impact of the new parameters on utilization evaluation, and ensures that the model can fully integrate the information of the new parameters; if it is a parameter decrease adjustment, the large language model automatically identifies the input dimensions and redundant modules of the evaluation model related to parameter decrease, deletes the corresponding input dimensions, eliminates redundant modules, optimizes the model structure, and adjusts the model weights to ensure that the model can still maintain high evaluation accuracy after eliminating the reduced parameters, avoiding resource waste.

[0056] The large language model enables automatic adjustment of the evaluation model. When parameters are added or removed, the model structure and parameters can be automatically adjusted without manual re-tuning and retraining. This solves the problems of lag and high cost in parameter adaptation, improves model adaptation efficiency, and reduces operating costs.

[0057] Optionally, in the resource utilization evaluation method provided in this application embodiment, the resource utilization of the communication site to be evaluated is evaluated based on the target parameter data and the target evaluation model, and the evaluation result is obtained by: performing feature mapping on the target parameter data through the input node of the target evaluation model to obtain an intermediate feature vector; performing weighted aggregation and nonlinear transformation on the intermediate feature vector through the calculation node of the target evaluation model to obtain a resource utilization score; and determining the evaluation result based on the resource utilization score through the output node of the target evaluation model.

[0058] In an optional embodiment, target parameter data is input into a target evaluation model. The input nodes of the target evaluation model perform feature mapping based on the target parameter data to obtain an intermediate feature vector. The calculation nodes of the target evaluation model perform weighted aggregation and nonlinear transformation based on the intermediate feature vector to obtain a resource utilization score. The output nodes of the target evaluation model determine the evaluation result based on the resource utilization score, including single communication site utilization, regional cluster utilization, and utilization of different resource types (such as towers, equipment rooms, power supplies, etc.). At the same time, the evaluation accuracy and parameter influence weights are marked to clarify the degree of influence of newly added parameters on the evaluation result.

[0059] Optionally, in the resource utilization evaluation method provided in this application embodiment, before obtaining the first parameter data associated with the communication site to be evaluated through a large language model, the method further includes: obtaining multi-source heterogeneous data from multiple business systems in real time, and cleaning and standardizing the multi-source heterogeneous data to obtain an initial parameter dataset; and performing semantic analysis and parameter extraction on the initial parameter dataset through a large language model to obtain the first parameter data.

[0060] In an optional embodiment, the evaluation system, based on preset time intervals or when a parameter data change event is detected, uses a large language model to collect multi-source heterogeneous data related to the communication site to be evaluated in real time from multiple business systems (such as a leasing management system, equipment monitoring system, regional planning system, and operator docking platform). The data is then cleaned and standardized to obtain an initial parameter dataset. The large language model is fine-tuned and trained based on parameter data such as historical resource utilization rate data, long-term lease order data, equipment operating status data, and regional business demand data of the communication site, along with labeled parameter importance tags. Then, based on the semantic understanding capabilities of the pre-trained large language model, it automatically identifies semantic entities and numerical features related to resource utilization rate evaluation, i.e., performs semantic analysis and parameter extraction on the initial parameter dataset to obtain the parameter data related to resource utilization rate evaluation in the current evaluation period (i.e., the first parameter data).

[0061] Optionally, in the resource utilization evaluation method provided in the embodiments of this application, after obtaining the evaluation result, the method further includes: comparing the evaluation result with a preset utilization threshold to obtain a comparison result; and determining resource optimization suggestions corresponding to the communication site to be evaluated based on the comparison result.

[0062] In an optional embodiment, the resource utilization assessment value output by the target assessment model is compared with a preset utilization threshold. For communication sites with assessment values ​​greater than the preset utilization threshold, expansion and upgrade suggestions are output (such as increasing data center capacity, upgrading power supply, etc.). For communication sites with assessment values ​​less than or equal to the preset utilization threshold, idle resource adjustment suggestions are output (such as connecting to other operators' needs, etc.). In the case of unbalanced regional cluster utilization, layout optimization suggestions are output (such as adding new communication site locations, adjusting resource allocation, etc.), providing a reliable basis for reasonable resource scheduling.

[0063] In an alternative embodiment, Figure 3 This is a schematic diagram of the workflow of the resource utilization assessment system provided in the embodiments of this application, as shown below. Figure 3As shown, the initial parameter dataset is first collected and a large-scale model is trained. This large-scale model automates the monitoring and identification of parameters for assessing the utilization rate of communication site resources. It automatically determines the increase, decrease, type, and importance of parameters, identifies newly added and removed parameters, filters effective parameters, and eliminates invalid and redundant parameters, providing a foundation for subsequent model adjustments. For example, all initial parameter data related to the assessment of communication site resource utilization rate are collected, including time parameters (e.g., quarterly, monthly), lease order parameters (e.g., number of new tenants, number of vacated tenants, number of existing tenants), resource configuration parameters (e.g., communication site type, equipment room capacity, power supply), and regional demand parameters (e.g., city level, regional business density, operator layout planning), etc. An initial parameter dataset is constructed and input into the large-scale model for training, enabling the model to identify, classify, and determine the importance of parameters.

[0064] Optionally, the large-scale model monitors parameter data in real time, compares the initial parameter dataset with the real-time parameter dataset, automatically identifies parameter increases and decreases, and marks newly added parameters by name, type, and data characteristics, as well as deleting parameters by name and corresponding deletion flags. The large-scale model uses pre-defined correlation analysis logic to determine the correlation between newly added parameters and resource utilization data, filtering out valid newly added parameters (correlation higher than a set threshold) and removing invalid newly added parameters (correlation lower than a set threshold). It also verifies deleting parameters to confirm whether they are obsolete or invalid, avoiding the accidental deletion of valid parameters. A parameter change log is constructed to record the time, type, and importance score of parameter increases and decreases, providing a basis for subsequent model adjustments, evaluation, and tracing.

[0065] Optionally, when the large model detects increases or decreases in evaluation parameters, it automatically adjusts the structure and parameters of the evaluation model to achieve real-time adaptation to parameter changes. For example, based on the identified parameter increases or decreases, the large model determines the type of adjustment (parameter increase or parameter decrease). If it is a parameter increase adjustment, it automatically expands the input dimensions of the evaluation model, incorporates the selected effective new parameters into the model's input system, extracts the feature information of the new parameters, adjusts the model's weight parameters, strengthens the impact of the new parameters on utilization evaluation, and ensures that the model can fully integrate the information of the new parameters. If it is a parameter decrease adjustment, it automatically identifies the input dimensions and redundant modules related to the parameter decrease, deletes the corresponding input dimensions, eliminates redundant modules, optimizes the model structure, and adjusts the model weights to ensure that the evaluation model can still maintain high evaluation accuracy after removing the reduced parameters, avoiding resource waste. After the evaluation model adjustment is completed, the large model quickly verifies the adjusted evaluation model, compares the model fit and evaluation accuracy before and after the adjustment, and if it does not meet the set standards, it automatically readjusts the parameters until the fit requirements are met.

[0066] In an alternative embodiment, Figure 4This is a schematic diagram of the resource utilization assessment process provided in the embodiments of this application. After the assessment model is adjusted, the large model merges the adjusted assessment model and uses the complete dataset containing newly added effective parameters or removed parameters to assess resource utilization. Based on the self-learning capability of the large model, the assessment accuracy is continuously optimized to adapt to different parameter combinations and changing scenarios, such as... Figure 4 As shown, the updated parameter dataset is first constructed by integrating the selected new parameters into the initial dataset, or by removing datasets corresponding to reduced parameters, forming a complete dataset adapted to the current parameter combination. The updated dataset is then input into the adjusted evaluation model. Based on the model's self-learning capability, the impact of parameter changes on resource utilization is analyzed, the model's evaluation parameters are optimized, and evaluation biases are corrected. The adjusted evaluation model outputs resource utilization evaluation results, including single communication site utilization, regional cluster utilization, and utilization of different resource types (such as towers, equipment rooms, and power supplies). Simultaneously, the evaluation accuracy and parameter influence weights are labeled to clarify the degree of impact of new parameters on the evaluation results. Then, based on the evaluation results, the large model automatically generates resource utilization optimization suggestions, providing targeted recommendations for communication site resource expansion, idle resource adjustment, and regional layout optimization, taking into account the actual business situation after parameter changes.

[0067] The resource utilization assessment method provided in this application includes the following steps: obtaining first parameter data associated with the communication site to be assessed through a large language model, wherein the first parameter data is parameter data related to resource utilization assessment in the current assessment period; determining target parameter data based on the first parameter data and second parameter data, wherein the second parameter data is parameter data used for resource utilization assessment in the previous assessment period, and the target parameter data is: parameter data that exists in the current assessment period and whose correlation value with resource utilization is greater than a first threshold, excluding parameter data that existed in the previous assessment period, does not exist in the current assessment period, and whose historical correlation value is less than a second threshold; adjusting the current assessment model based on the target parameter data to obtain a target assessment model; and assessing the resource utilization of the communication site to be assessed based on the target parameter data and the target assessment model to obtain the assessment result. This solves the technical problem in related technologies where reliance on manual identification of parameter changes and manual adjustment of the assessment algorithm leads to low efficiency in assessing the resource utilization of communication sites.

[0068] In this scheme, the first parameter data of the communication site to be evaluated in the current evaluation period is obtained through a large language model. Combined with the second parameter data used for resource utilization evaluation in the previous evaluation period, correlation analysis is used to determine that only parameter data existing in the current evaluation period and whose correlation with resource utilization is greater than the first threshold is retained, while parameter data existing in the previous evaluation period but disappearing in the current evaluation period and whose historical correlation value is lower than the second threshold is removed, thus forming the target parameter data. Based on the target parameter data, the structure and weights of the current evaluation model are adaptively adjusted to obtain the target evaluation model. Then, the resource utilization of the communication site to be evaluated is evaluated using the target parameter data and the target evaluation model, and high-precision evaluation results are output. This realizes dynamic screening of evaluation parameters and adaptive adjustment of model structure, improving the accuracy and efficiency of resource utilization evaluation.

[0069] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0070] Example 2

[0071] This application also provides a resource utilization evaluation apparatus. It should be noted that the resource utilization evaluation apparatus of this application can be used to execute the resource utilization evaluation method provided in this application. The resource utilization evaluation apparatus provided in this application will be described below.

[0072] According to an embodiment of this application, a resource utilization rate assessment apparatus for implementing the above-described resource utilization rate assessment method is also provided, such as... Figure 5 As shown, the device includes: a first processing unit 501, a first determining unit 502, a second processing unit 503, and a third processing unit 504.

[0073] The first processing unit 501 is used to obtain the first parameter data associated with the communication site to be evaluated through a large language model, wherein the first parameter data is the parameter data related to resource utilization evaluation in the current evaluation period;

[0074] The first determining unit 502 is used to determine target parameter data based on the first parameter data and the second parameter data. The second parameter data is the parameter data used for resource utilization rate assessment in the previous assessment period. The target parameter data is: parameter data that exists in the current assessment period and whose correlation value with resource utilization rate is greater than the first threshold, but does not include parameter data that existed in the previous assessment period, does not exist in the current assessment period, and whose historical correlation value is less than the second threshold.

[0075] The second processing unit 503 is used to adjust the current evaluation model based on the target parameter data to obtain the target evaluation model;

[0076] The third processing unit 504 is used to evaluate the resource utilization rate of the communication site to be evaluated based on the target parameter data and the target evaluation model, and obtain the evaluation results.

[0077] The resource utilization assessment apparatus provided in this application embodiment obtains first parameter data associated with the communication site to be assessed through a large language model by a first processing unit 501. The first parameter data is parameter data related to resource utilization assessment in the current assessment period. A first determining unit 502 determines target parameter data based on the first parameter data and the second parameter data. The second parameter data is parameter data used for resource utilization assessment in the previous assessment period. The target parameter data is parameter data that exists in the current assessment period and whose correlation value with resource utilization is greater than a first threshold, excluding parameter data that existed in the previous assessment period, does not exist in the current assessment period, and whose historical correlation value is less than a second threshold. A second processing unit 503 adjusts the current assessment model based on the target parameter data to obtain a target assessment model. A third processing unit 504 performs resource utilization assessment on the communication site to be assessed based on the target parameter data and the target assessment model to obtain the assessment result.

[0078] Optionally, in the resource utilization evaluation apparatus provided in this application embodiment, the first determining unit includes: a first processing subunit, used to compare the first parameter data and the second parameter data to determine the newly added parameter data, the deleted parameter data, and the common parameter data; a second processing subunit, used to perform correlation calculation between the newly added parameter data and the resource utilization rate to obtain a first value, and compare the first value with a first threshold, and take the newly added parameter data whose first value is greater than the first threshold as the initial target parameter data; a third processing subunit, used to perform correlation calculation between the deleted parameter data and the resource utilization rate to obtain a second value, and compare the second value with a second threshold, and take the deleted parameter data whose second value is less than the second threshold as the deletable parameter data; and a first determining subunit, used to determine the target parameter data based on the common parameter data and the initial target parameter data.

[0079] Optionally, in the resource utilization evaluation device provided in the embodiments of this application, the device further includes: a second determining unit, used to, after comparing the second value with the second threshold, take the deletion parameter data where the second value is greater than or equal to the second threshold as the erroneous deletion parameter data, generate early warning information, and send the early warning information to the target object.

[0080] Optionally, in the resource utilization evaluation apparatus provided in this application embodiment, the second processing unit includes: an acquisition subunit, used to acquire the input nodes and parameter weights of the current evaluation model, wherein the input nodes correspond one-to-one with the second parameter data, and the parameter weights are the correlation coefficients of each input node with the resource utilization rate; a second determination subunit, used to determine a first input node, a second input node, and a third input node based on the target parameter data and the input nodes, wherein the first input node corresponds to the common parameter data in the target parameter data, the second input node corresponds to the initial target parameter data in the target parameter data, and the third input node is the input node other than the first input node; a fourth processing subunit, used to adjust the input nodes and parameter weights of the current evaluation model based on the parameter weights, the first input node, the second input node, and the third input node to obtain an initial target evaluation model; and a third determination subunit, used to verify the initial target evaluation model based on the verification dataset, and if the verification is successful, the initial target evaluation model is used as the target evaluation model.

[0081] Optionally, in the resource utilization evaluation apparatus provided in this application embodiment, the third processing unit includes: a fifth processing subunit, used to perform feature mapping based on target parameter data through the input node of the target evaluation model to obtain an intermediate feature vector; a sixth processing subunit, used to perform weighted aggregation and nonlinear transformation based on the intermediate feature vector through the calculation node of the target evaluation model to obtain a resource utilization score; and a fourth determining subunit, used to determine the evaluation result based on the resource utilization score through the output node of the target evaluation model.

[0082] Optionally, in the resource utilization evaluation device provided in the embodiments of this application, the device further includes: a first acquisition unit, used to acquire multi-source heterogeneous data from multiple business systems in real time before acquiring the first parameter data associated with the communication site to be evaluated through a large language model, and to perform data cleaning and standardization on the multi-source heterogeneous data to obtain an initial parameter dataset; and a second acquisition unit, used to perform semantic analysis and parameter extraction on the initial parameter dataset through a large language model to obtain the first parameter data.

[0083] Optionally, in the resource utilization evaluation device provided in the embodiments of this application, the device further includes: a comparison unit, used to compare the evaluation result with a preset utilization threshold after obtaining the evaluation result, and obtain a comparison result; and a third determination unit, used to determine resource optimization suggestions corresponding to the communication site to be evaluated based on the comparison result.

[0084] It should be noted that the first processing unit 501, the first determining unit 502, the second processing unit 503, and the third processing unit 504 mentioned above correspond to steps S201 to S204 in Embodiment 1. The four units and the corresponding steps implement the same instances and application scenarios, but are not limited to the content disclosed in Embodiment 1. It should be noted that the above modules or units can be hardware or software components stored in memory (e.g., memory 104) and processed by one or more processors (e.g., processors 102a, 102b, ..., 102n). The above units can also be part of a device and run in the computer terminal 10 provided in Embodiment 1.

[0085] Example 3

[0086] Embodiments of this application may provide an electronic device. Figure 6 This is a structural block diagram of an electronic device according to an embodiment of this application. Figure 6 As shown, the electronic device may include: one or more ( Figure 6 (Only one is shown) Processor 602, memory 604, memory controller, and peripheral interface, wherein the peripheral interface is connected to the radio frequency module, audio module and display.

[0087] The memory can be used to store software programs and modules, such as the program instructions / modules corresponding to the methods and apparatus in the embodiments of this application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, thereby implementing the above-described methods. The memory may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include memory remotely located relative to the processor, and these remote memories can be connected to the terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0088] The processor can access information and applications stored in the memory via a transmission device to execute the following steps: First parameter data associated with the communication site to be evaluated is obtained through a large language model, wherein the first parameter data is parameter data related to resource utilization assessment in the current assessment period; Target parameter data is determined based on the first parameter data and the second parameter data, wherein the second parameter data is parameter data used for resource utilization assessment in the previous assessment period, and the target parameter data consists of parameter data that exists in the current assessment period and whose correlation with resource utilization is greater than a first threshold, excluding parameter data that existed in the previous assessment period, does not exist in the current assessment period, and whose historical correlation value is less than a second threshold; The current assessment model is adjusted based on the target parameter data to obtain a target assessment model; Resource utilization assessment is performed on the communication site to be evaluated based on the target parameter data and the target assessment model to obtain the assessment result.

[0089] The processor can access information and applications stored in memory via a transmission device to perform the following steps: comparing first parameter data and second parameter data to determine new parameter data, deleted parameter data, and common parameter data; performing correlation calculations between new parameter data and resource utilization to obtain a first value, comparing the first value with a first threshold, and using new parameter data whose first value is greater than the first threshold as initial target parameter data; performing correlation calculations between deleted parameter data and resource utilization to obtain a second value, comparing the second value with a second threshold, and using deleted parameter data whose second value is less than the second threshold as deletable parameter data; and determining target parameter data based on common parameter data and initial target parameter data.

[0090] The processor can call the information and application stored in the memory through the transmission device to perform the following steps: after comparing the second value with the second threshold, the deletion parameter data that is greater than or equal to the second threshold is taken as the erroneous deletion parameter data, and a warning message is generated and sent to the target object.

[0091] The processor can access information and applications stored in memory via a transmission device to execute the following steps: Obtain the input nodes and parameter weights of the current evaluation model, where each input node corresponds one-to-one with the second parameter data, and the parameter weights are the correlation coefficients between each input node and resource utilization; Based on the target parameter data and input nodes, determine the first, second, and third input nodes, where the first input node corresponds to the common parameter data in the target parameter data, the second input node corresponds to the initial target parameter data in the target parameter data, and the third input node is the input node other than the first input node; Adjust the input nodes and parameter weights of the current evaluation model according to the parameter weights, the first, second, and third input nodes to obtain the initial target evaluation model; Validate the initial target evaluation model using the validation dataset. If the validation passes, the initial target evaluation model is used as the target evaluation model.

[0092] The processor can access the information and application programs stored in the memory via the transmission device to perform the following steps: First, the input nodes of the target evaluation model perform feature mapping based on the target parameter data to obtain an intermediate feature vector. Second, the computation nodes of the target evaluation model perform weighted aggregation and nonlinear transformation based on the intermediate feature vector to obtain a resource utilization score. Third, the output nodes of the target evaluation model determine the evaluation result based on the resource utilization score.

[0093] The processor can call the information and application stored in the memory through the transmission device to perform the following steps: before obtaining the first parameter data associated with the communication site to be evaluated through the large language model, multi-source heterogeneous data is obtained in real time from multiple business systems, and the multi-source heterogeneous data is cleaned and standardized to obtain the initial parameter dataset; the initial parameter dataset is semantically analyzed and parameters are extracted through the large language model to obtain the first parameter data.

[0094] The processor can call the information and application stored in the memory through the transmission device to perform the following steps: after obtaining the evaluation results, compare the evaluation results with the preset utilization threshold to obtain the comparison results; based on the comparison results, determine the resource optimization suggestions corresponding to the communication site to be evaluated.

[0095] Those skilled in the art will understand that Figure 6 The structure shown is for illustrative purposes only. Electronic devices can also be smartphones, tablets, handheld computers, mobile internet devices (MIDs), PADs, and other terminal devices. Figure 6 This does not limit the structure of the aforementioned electronic device. For example, electronic devices may also include components that are more... Figure 6The more or fewer components shown (such as network interfaces, display devices, etc.), or having the same Figure 6 The different configurations shown.

[0096] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing the hardware related to the terminal device. The program can be stored in a computer-readable storage medium, which may include: flash drive, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0097] Example 4

[0098] Embodiments of this application also provide a computer-readable storage medium. Optionally, in this embodiment, the storage medium can be used to store the program code executed by the resource utilization evaluation method provided in Embodiment 1.

[0099] Optionally, in this embodiment, the storage medium may be located in any computer terminal in a group of computer terminals in a computer network, or in any mobile terminal in a group of mobile terminals.

[0100] This application also provides a computer program product, which, when executed on a data processing device, is suitable for performing steps of a method for evaluating resource utilization.

[0101] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0102] In the above embodiments of this application, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0103] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0104] 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 units can be selected to achieve the purpose of this embodiment according to actual needs.

[0105] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0106] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. 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 this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.

[0107] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method for evaluating resource utilization rate, characterized in that, include: The first parameter data associated with the communication site to be evaluated is obtained through a large language model, wherein the first parameter data is the parameter data related to resource utilization evaluation in the current evaluation period; Target parameter data is determined based on the first parameter data and the second parameter data. The second parameter data is the parameter data used for resource utilization assessment in the previous assessment period. The target parameter data is: parameter data that exists in the current assessment period and whose correlation value with resource utilization is greater than the first threshold, but does not include parameter data that existed in the previous assessment period, does not exist in the current assessment period, and whose historical correlation value is less than the second threshold. The current evaluation model is adjusted based on the target parameter data to obtain the target evaluation model; Based on the target parameter data and the target evaluation model, the resource utilization rate of the communication site to be evaluated is assessed, and the evaluation result is obtained.

2. The method according to claim 1, characterized in that, Determining the target parameter data based on the first parameter data and the second parameter data includes: The first parameter data and the second parameter data are compared to determine the newly added parameter data, the deleted parameter data, and the common parameter data; The correlation between the newly added parameter data and resource utilization rate is calculated to obtain a first value. The first value is then compared with the first threshold, and the newly added parameter data whose first value is greater than the first threshold is taken as the initial target parameter data. The correlation between the deleted parameter data and resource utilization rate is calculated to obtain a second value. The second value is then compared with the second threshold, and the deleted parameter data with the second value being less than the second threshold is taken as the deleteable parameter data. The target parameter data is determined based on the common parameter data and the initial target parameter data.

3. The method according to claim 2, characterized in that, After comparing the second value with the second threshold, the method further includes: The deletion parameter data whose second value is greater than or equal to the second threshold is taken as the erroneous deletion parameter data, and an early warning message is generated and sent to the target object.

4. The method according to claim 1, characterized in that, The current evaluation model is adjusted based on the target parameter data to obtain the target evaluation model, which includes: Obtain the input nodes and parameter weights of the current evaluation model, wherein the input nodes correspond one-to-one with the second parameter data, and the parameter weights are the correlation coefficients of each input node with the resource utilization rate; Based on the target parameter data and the input nodes, a first input node, a second input node, and a third input node are determined, wherein the first input node corresponds to the common parameter data in the target parameter data, the second input node corresponds to the initial target parameter data in the target parameter data, and the third input node is the input node other than the first input node. The input nodes and parameter weights of the current evaluation model are adjusted based on the parameter weights, the first input node, the second input node, and the third input node to obtain the initial target evaluation model; The initial target evaluation model is validated based on the validation dataset. If the validation passes, the initial target evaluation model is adopted as the target evaluation model.

5. The method according to claim 1, characterized in that, Based on the target parameter data and the target evaluation model, the resource utilization rate of the communication site to be evaluated is assessed, and the evaluation results include: The intermediate feature vector is obtained by performing feature mapping on the input nodes of the target evaluation model based on the target parameter data; The resource utilization score is obtained by weighting and nonlinearly transforming the intermediate feature vector through the calculation nodes of the target evaluation model. The evaluation result is determined by the output node of the target evaluation model based on the resource utilization score.

6. The method according to claim 1, characterized in that, Before obtaining the first parameter data associated with the communication site to be evaluated through a large language model, the method further includes: Multi-source heterogeneous data is acquired in real time from multiple business systems, and the multi-source heterogeneous data is cleaned and standardized to obtain an initial parameter dataset; The first parameter data is obtained by performing semantic analysis and parameter extraction on the initial parameter dataset using the large language model.

7. The method according to claim 1, characterized in that, After obtaining the evaluation results, the method further includes: The evaluation results are compared with a preset utilization threshold to obtain a comparison result; Based on the comparison results, resource optimization suggestions are determined for the communication site to be evaluated.

8. A resource utilization rate assessment device, characterized in that, include: The first processing unit is used to obtain the first parameter data associated with the communication site to be evaluated through a large language model, wherein the first parameter data is the parameter data related to resource utilization evaluation in the current evaluation period; The first determining unit is used to determine target parameter data based on the first parameter data and the second parameter data, wherein the second parameter data is the parameter data used for resource utilization assessment in the previous assessment period, and the target parameter data is: parameter data that exists in the current assessment period and whose correlation value with resource utilization is greater than the first threshold, and does not include parameter data that existed in the previous assessment period, does not exist in the current assessment period, and whose historical correlation value is less than the second threshold. The second processing unit is used to adjust the current evaluation model based on the target parameter data to obtain the target evaluation model; The third processing unit is used to evaluate the resource utilization rate of the communication site to be evaluated based on the target parameter data and the target evaluation model, and obtain the evaluation result.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored executable program, wherein, when the executable program is executed, it controls the device on which the computer-readable storage medium is located to perform the resource utilization assessment method according to any one of claims 1 to 7.

10. An electronic device, characterized in that, include: Memory, which stores executable programs; A processor for running the program, wherein the program, when running, executes the resource utilization assessment method according to any one of claims 1 to 7.

Images