A building value assessment method and system

Abstract

This invention discloses a building value assessment method and system. Based on pre-activation network format data, pre-activation network protocol data, pre-activation network performance parameter data, and internet leased line service type, a prediction model for internet leased line service type is trained. Based on acquired wireless network signal coverage area data, wireless network uplink signal strength data, wireless network downlink signal strength data, number of wireless network users, wireless network traffic data, and converged service coverage rate, a converged service coverage rate prediction model is trained. The trained internet leased line service type prediction model and converged service coverage rate prediction model are used to predict the value of target buildings, obtaining prediction results for the internet leased line service type and converged service coverage rate for each enterprise that has not yet activated internet leased line services. These results are then used for value assessment of the target buildings. The method provided in this application can improve the efficiency and accuracy of building value assessment.

Description

Technical Field

[0001] This invention relates to the field of internet business management technology, and in particular to a building value assessment method and system. Background Technology

[0002] Internet operators need to conduct regular valuation assessments of target buildings to help business personnel assess the potential for service activation when expanding dedicated internet lines and converged services. This would reduce reliance on channel partners and frontline staff canvassing buildings for these services. However, current building valuation methods generally rely on the subjective experience of frontline staff, leading to inaccurate results and low efficiency, and are ill-suited to the rapid development of the internet industry.

[0003] Therefore, improving the efficiency and accuracy of building valuation has become a pressing technical problem that needs to be solved by those skilled in the art. Summary of the Invention

[0004] This invention provides a building valuation method and system to solve the technical problem of how to improve the efficiency and accuracy of building valuation, thereby improving the efficiency and accuracy of internet business expansion.

[0005] In a first aspect, the present invention provides a building value assessment method, the method comprising: acquiring network format data, network protocol data, network performance parameter data, and Internet leased line service type of enterprises within the sample building before activation, as well as wireless network signal coverage area data, wireless network uplink signal strength data, wireless network downlink signal strength data, number of wireless network users, wireless network traffic data, and converged service coverage rate.

[0006] Based on the network format data before activation, the network protocol data before activation, the network performance parameter data before activation, and the Internet leased line service type, a prediction model for Internet leased line service type constructed using a backpropagation neural network is trained.

[0007] Based on the wireless network signal coverage area data, the wireless network uplink signal strength data, the wireless network downlink signal strength data, the number of wireless network users, the wireless network traffic data, and the converged service coverage rate, a converged service coverage rate prediction model constructed using a deep neural network is trained.

[0008] During the real-time evaluation process, the current network format data, current network protocol data, and current network performance parameter data of each enterprise in the target building that has not opened Internet leased line services are input into the trained Internet leased line service type prediction model to obtain the Internet leased line service type prediction result for each enterprise that has not opened Internet leased line services.

[0009] Based on the current wireless network signal coverage area data, current wireless network uplink signal strength data, current wireless network downlink signal strength data, current wireless network traffic data, and current number of wireless network users of the target building, the converged service coverage prediction model that has been trained is used to predict the converged service coverage of each target building, and the converged service coverage prediction result is obtained.

[0010] The prediction results of the Internet leased line service type and the prediction results of the converged service coverage are analyzed, and the target building is valued based on the analysis results to obtain the value assessment result of the target building.

[0011] Preferably, the step of training an Internet leased line service type prediction model constructed using a backpropagation neural network based on the pre-activation network format data, the pre-activation network protocol data, the pre-activation network performance parameter data, and the Internet leased line service type includes:

[0012] Based on the mapping relationship between the pre-activation network format data, pre-activation network protocol data, and pre-activation network performance parameter data of enterprises that have activated Internet leased line services and the Internet leased line service type, construct an Internet leased line service dataset;

[0013] Based on the mapping relationship between the network format data, network protocol data, and network performance parameter data of enterprises that have not yet opened Internet leased line services and the demand for Internet leased line services, a dataset of Internet leased line services that has not yet opened is constructed.

[0014] The prediction model for the Internet leased line service type is trained using the datasets of the already activated Internet leased line service and the datasets of the not activated Internet leased line service.

[0015] Preferably, training the converged service demand prediction model constructed using a deep neural network based on the wireless network signal coverage area data, the wireless network uplink signal strength data, the wireless network downlink signal strength data, the number of wireless network users, the wireless network traffic data, and the converged service coverage rate includes:

[0016] The ratio of the wireless network signal coverage area data to the high-frequency usage area of ​​the building is used as the indoor signal coverage ratio.

[0017] The average uplink signal strength data of the wireless network in each area of ​​each of the sample buildings is taken as the first indoor signal strength.

[0018] The average downlink signal strength data of the wireless network in each area of ​​each of the sample buildings is used as the second indoor signal strength.

[0019] Calculate a second ratio of the number of wireless network users in each of the sample buildings to the sum of the number of wireless network users in all the sample buildings, and a third ratio of the wireless network user traffic data in each of the sample buildings to the sum of the wireless network traffic data in all the sample buildings. Determine the wireless network demand level based on the sum of the second ratio and the third ratio.

[0020] The indoor signal coverage ratio, the first indoor signal strength, the second indoor signal strength, and the wireless network demand level are used as inputs, and the converged service coverage rate is used as the output to train the converged service demand prediction model.

[0021] Preferably, the analysis of the prediction results for the Internet leased line service type and the prediction results for the converged service coverage, and the valuation of the target building based on the analysis results, to obtain the valuation result of the target building, includes:

[0022] Based on the prediction results of the Internet leased line service types, the number of enterprises with Internet leased line service needs and the number of Internet leased line service types in the target building are obtained;

[0023] Calculate the fourth ratio between the number of enterprises and the preset threshold number of enterprises;

[0024] Calculate the fifth ratio of the number of Internet leased line service types to the total number of Internet leased line service types;

[0025] The fourth ratio, the fifth ratio, and the predicted coverage of the integrated services are weighted and fused together. Based on the weighted fusion result, the target building is classified into value levels to obtain the value assessment result of the target building.

[0026] Preferably, the method further includes:

[0027] The valuation results will be sent to internet business development personnel and the cloud.

[0028] Obtain the accuracy evaluation of the value assessment results from the internet business development personnel, and send the accuracy evaluation results to the cloud;

[0029] Based on the value assessment results and the accuracy evaluation results, the prediction model for Internet leased line service types and the prediction model for converged service coverage are periodically optimized.

[0030] Secondly, the present invention also provides a building value assessment system to implement the building value assessment method described above. The system includes: a data acquisition unit, a first model training unit, a second model training unit, an Internet leased line service type prediction unit, a converged service coverage prediction unit, and a building value assessment unit.

[0031] The data acquisition unit is used to acquire network format data, network protocol data, network performance parameter data, and Internet leased line service type of enterprises in the sample building before activation, as well as wireless network signal coverage area data, wireless network uplink signal strength data, wireless network downlink signal strength data, number of wireless network users, wireless network traffic data, and converged service coverage rate.

[0032] The first model training unit is used to train an Internet leased line service type prediction model constructed using a backpropagation neural network based on the pre-activation network format data, the pre-activation network protocol data, the pre-activation network performance parameter data, and the Internet leased line service type.

[0033] The second model training unit is used to train a converged service coverage prediction model constructed using a deep neural network based on the wireless network signal coverage area data, the wireless network uplink signal strength data, the wireless network downlink signal strength data, the number of wireless network users, the wireless network traffic data, and the converged service coverage rate.

[0034] The Internet leased line service type prediction unit is used to input the current network format data, current network protocol data, and current network performance parameter data of each enterprise in the target building that has not opened Internet leased line services into the trained Internet leased line service type prediction model during the real-time evaluation process, so as to obtain the Internet leased line service type prediction result for each enterprise that has not opened Internet leased line services.

[0035] The converged service coverage prediction unit is used to predict the converged service coverage of each target building based on the current wireless network signal coverage area data, current wireless network uplink signal strength data, current wireless network downlink signal strength data, current wireless network traffic data, and current number of wireless network users of the target building, using the trained converged service coverage prediction model, and to obtain the converged service coverage prediction result.

[0036] The building valuation unit is used to analyze the prediction results of the Internet leased line service type and the prediction results of the converged service coverage, and to evaluate the value of the target building based on the analysis results, thereby obtaining the valuation result of the target building.

[0037] The first model training unit is further configured to: construct an established internet leased line service dataset based on the mapping relationship between the pre-establishment network format data, pre-establishment network protocol data, and pre-establishment network performance parameter data of enterprises that have established internet leased line services and the internet leased line service type; construct an unestablished internet leased line service dataset based on the mapping relationship between the pre-establishment network format data, pre-establishment network protocol data, and pre-establishment network performance parameter data of enterprises that have not established internet leased line services and the lack of internet leased line service demand; and train the internet leased line service type prediction model using the established internet leased line service dataset and the unestablished internet leased line service dataset.

[0038] Preferably, the second model training unit is further configured to: use the first ratio of the wireless network signal coverage area data to the high-frequency usage area of ​​the building as the indoor signal coverage ratio; use the average uplink signal strength data of the wireless network in each area of ​​each sample building as the first indoor signal strength; use the average downlink signal strength data of the wireless network in each area of ​​each sample building as the second indoor signal strength; calculate the second ratio of the number of wireless network users in each sample building to the sum of the number of wireless network users in all sample buildings, and the third ratio of the wireless network traffic data in each sample building to the sum of the wireless network user traffic data in all sample buildings; determine the wireless network demand level based on the sum of the second ratio and the third ratio; and use the indoor signal coverage ratio, the first indoor signal strength, the second indoor signal strength, and the wireless network demand level as inputs, and the converged service coverage rate as output, to train the converged service demand prediction model.

[0039] Preferably, the building value assessment unit is further configured to: obtain the number of enterprises with internet leased line service needs and the number of internet leased line service types within the target building based on the prediction results of the internet leased line service types; calculate a fourth ratio of the number of enterprises to a preset threshold for the number of enterprises; calculate a fifth ratio of the number of internet leased line service types to the total number of internet leased line service types; perform a weighted fusion of the fourth ratio, the fifth ratio, and the prediction results of the converged service coverage rate; classify the target building into value levels based on the weighted fusion results; and obtain the value assessment results of the target building.

[0040] Preferably, the system further includes a model optimization unit;

[0041] The model optimization unit is used to send the value assessment results to internet business development personnel and the cloud; obtain the accuracy evaluation of the value assessment results from the internet business development personnel and send the accuracy evaluation results to the cloud; and periodically optimize the internet leased line service type prediction model and the converged service coverage prediction model based on the value assessment results and the accuracy evaluation results.

[0042] This invention provides a building valuation method and system. Compared with the prior art, the embodiments of this invention have the following advantages:

[0043] By identifying the types of internet services within the target building that require dedicated internet lines, and predicting the probability of opening converged services in the target building, the value of each target building can be assessed, thereby improving the efficiency and accuracy of internet service expansion. Attached Figure Description

[0044] Figure 1 This is a schematic diagram of the steps of a building valuation method provided in a preferred embodiment of the present invention;

[0045] Figure 2 This is a schematic diagram of a building valuation system provided in a preferred embodiment of the present invention. Detailed Implementation

[0046] The embodiments of the present invention are described in detail below with reference to the accompanying drawings. The embodiments are provided for illustrative purposes only and should not be construed as limiting the invention. The accompanying drawings are for reference and illustration only and do not constitute a limitation on the scope of protection of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of this invention. In the description of this invention, the terms "first," "second," "third," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Therefore, a feature defined with "first," "second," "third," etc., may explicitly or implicitly include one or more of that feature. In the description of this invention, unless otherwise stated, "a plurality of" means two or more.

[0047] In the description of this invention, it should be noted that, unless otherwise expressly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to fixed connections, detachable connections, or integral connections; they can refer to mechanical connections or electrical connections; they can refer to direct connections or indirect connections through an intermediate medium; and they can refer to communication within two components. The terms "vertical," "horizontal," "left," "right," "upper," "lower," and similar expressions used herein are for illustrative purposes only and do not indicate or imply that the device or component referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as limiting the invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items. Those skilled in the art will understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0048] In the description of this invention, it should be noted that, unless otherwise defined, all technical and scientific terms used in this invention have the same meaning as commonly understood by one of ordinary skill in the art. The terminology used in this specification is for the purpose of describing specific embodiments only and is not intended to limit the invention. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0049] Please see Figure 1 In an embodiment of the present invention, a building value assessment method is provided, the method comprising:

[0050] S1. Obtain the network format data, network protocol data, and network performance parameter data before activation, as well as the internet leased line service type, wireless network signal coverage area data, wireless network uplink signal strength data, wireless network downlink signal strength data, number of wireless network users, and converged service coverage rate for enterprises within the sample buildings. The sample buildings can be understood as buildings within the target area where business personnel have conducted a manual assessment of building value, and where the coverage rates of both internet leased line services and converged internet services have reached the corresponding thresholds. For enterprises that have already activated internet leased line services, the network format data, network protocol data, and network performance parameter data before activation are the network format data, network protocol data, and network performance parameter data prior to the activation of the internet leased line service, and the internet leased line service type is the actual type of internet leased line service activated. For enterprises that have not activated internet leased line services, the network format data, network protocol data, and network performance parameter data before activation are the current network format data, network protocol data, and network performance parameter data, and the internet leased line service type is "no internet leased line service requirement."

[0051] In the building value assessment method provided in the preferred embodiment of the present invention, the target area is an administrative region. By calling data from the Internet business management resource database, the method obtains the following data for sample buildings within the target area: network format data, network protocol data, network performance parameter data, and Internet leased line service type; wireless network signal coverage area data, wireless network uplink signal strength data, wireless network downlink signal strength data, number of wireless network users, and converged service coverage rate.

[0052] The network performance parameters data should include at least: network quality, network demand, and network security. Network quality should include at least: network latency, network packet loss rate, network speed, channel utilization, throughput, and network stability; network demand should include at least: network broadband package tariffs, which should be divided into high-cost, medium-cost, and low-cost packages; network security should include at least: network security level.

[0053] Network security levels refer to the classification of information systems or networks into different levels based on security risk assessments, in order to meet the needs of information system security protection. Corresponding network security measures and management systems are then implemented according to different security requirements. Network security levels are divided into five levels, from level one to level five, with each level representing an increase in protection level.

[0054] S2. Based on the pre-activation network format data, pre-activation network protocol data, pre-activation network performance parameter data, and the Internet leased line service type, train the Internet leased line service type prediction model constructed using a backpropagation neural network. The Internet leased line service type prediction model can, in principle, be constructed using existing machine learning model construction methods capable of predicting Internet leased line services. However, to ensure the efficiency, accuracy, and generalization of the prediction analysis, this embodiment preferably uses a backpropagation neural network model. Based on the mapping relationship between the pre-activation network format data, pre-activation network protocol data, and pre-activation network performance parameter data of enterprises that have activated Internet leased line services and the Internet leased line service type, construct an activated Internet leased line service dataset. Based on the mapping relationship between the pre-activation network format data, pre-activation network protocol data, and pre-activation network performance parameter data of enterprises that have not activated Internet leased line services and the lack of Internet leased line service demand, construct an unactivated Internet leased line service dataset. Using the pre-activation network format data, pre-activation network protocol data, and pre-activation network performance parameter data of both activated and non-activated Internet leased line service datasets as input, and the corresponding Internet leased line service type or no Internet leased line service requirement as output, the Internet leased line service type prediction model constructed using a backpropagation neural network is trained to obtain the trained Internet leased line service type prediction model.

[0055] S3. Based on the wireless network signal coverage area data, the wireless network uplink signal strength data, the wireless network downlink signal strength data, the number of wireless network users, the wireless network traffic data, and the converged service coverage rate, train the converged service coverage rate prediction model constructed using a deep neural network; wherein, the wireless network signal coverage area data is the total signal coverage range of the distributed wireless network system in each sample building, such as the indoor distributed wireless network system coverage range of Building A being 800m. 2 The uplink signal strength data of the wireless network refers to the uplink signal strength of the indoor wireless network system in each area of ​​the sample building, and the downlink signal strength data refers to the downlink signal strength of the indoor wireless network system in each area of ​​the sample building. Table 1 shows the signal strength of the indoor distribution system in each area of ​​Building A.

[0056] Table 1

[0057] Building A, Floor Region a Area b Region c 1st floor 4M / s 3.5M / s 10M / s 2nd floor 1M / s 3M / s 5M / s …… …… …… …… Nth floor xM / s yM / s zM / s

[0058] For the number of wireless network users, IP addresses within a building that are used for more than 4 hours daily are defined as wireless network users in that building. The number of wireless network users in each building is denoted as A. The mobile data plans of the wireless network users in each sample building are obtained, resulting in the wireless network traffic data B for each sample building. The sum of the number of wireless network users A in each sample building is the total number of wireless network users S, and the sum of the wireless network traffic data B in each sample building is the total wireless network traffic data D.

[0059] Obtain the area of ​​each floor of each sample building. Excluding the area of ​​elevators and restrooms on each floor, the sum of the remaining areas of each sample building is the high-frequency usage area of ​​the corresponding sample building. For example, the high-frequency usage area of ​​Building A is 750.

[0060] The training process for the fusion business coverage prediction model built using deep neural networks includes:

[0061] Based on the wireless network signal coverage area, high-frequency usage area, wireless network uplink signal strength, wireless network downlink signal strength, number of wireless network users, and wireless network traffic data of each sample building, the indoor distribution signal coverage ratio, first indoor distribution signal strength, second indoor distribution signal strength, and wireless network demand level of each building are obtained.

[0062] Specifically, the ratio of the wireless network signal coverage area to the building's high-frequency usage area is used as the building's indoor signal coverage ratio. For example, the indoor signal coverage ratio of Building A is 750 / 800 = 0.94.

[0063] The average uplink signal strength data of the wireless network in each area of ​​each sample building is taken as the first indoor signal strength of that building.

[0064] The average downlink signal strength data of the wireless network in each area of ​​each sample building is used as the second indoor signal strength of that building.

[0065] Calculate the second ratio of the number of wireless network users in each sample building to the sum of the number of wireless network users in all sample buildings, and the third ratio of the wireless network user traffic data in each sample building to the sum of the wireless network user traffic data in all sample buildings. Calculate the sum of the second and third ratios. The calculation formula is as follows:

[0066]

[0067] Based on the size of the P-value, the wireless network demand of the sample buildings is divided into three levels: high demand, medium demand, and low demand, thus determining the wireless network demand level of the buildings.

[0068] The coverage rate of integrated services is the ratio of the number of enterprises that have opened integrated building services to the total number of enterprises in the building.

[0069] Using the indoor signal coverage ratio, first indoor signal strength, second indoor signal strength, and wireless network requirement level of all sample buildings as inputs, and the corresponding converged service coverage rate as output, the building converged service activation prediction model constructed using a deep neural network is trained to obtain the trained building converged service activation prediction model.

[0070] S4. During the real-time evaluation process, the current network format data, current network protocol data, and current network performance parameter data of each enterprise in the target building that has not yet activated its dedicated internet service are input into the trained dedicated internet service type prediction model to obtain the dedicated internet service type prediction result for each enterprise. Specifically, taking the building to be evaluated as the target building, the current network format data, current network protocol data, and current network performance parameter data collected from each enterprise in the target building that has not yet activated its dedicated internet service are input into the trained enterprise dedicated internet service demand prediction model to obtain the dedicated internet service type prediction result for each enterprise. The dedicated internet service type prediction result includes the specific type of internet service or no dedicated internet service demand.

[0071] S5. Based on the current wireless network signal coverage area data, current wireless network uplink signal strength data, current wireless network downlink signal strength data, current wireless network traffic data, and current number of wireless network users of the target building, the converged service coverage rate prediction model, trained in advance, is used to predict the converged service coverage rate of each target building, and the converged service coverage rate prediction result is obtained; based on the collected current wireless network signal coverage area data, current wireless network uplink signal strength data, current wireless network downlink signal strength data, current wireless network traffic data, and current number of wireless network users of the target building, the current indoor distributed antenna system (DAS) signal coverage ratio, first indoor distributed antenna system (DAS) signal strength, first indoor distributed antenna system (DAS) signal strength, and wireless network demand level of the target building are calculated, and input into the trained building converged service activation prediction model, and the converged service coverage rate prediction result of each target building is output.

[0072] S6. Analyze the prediction results of the Internet leased line service types and the prediction results of the converged service coverage rate, and conduct a value assessment of the target building based on the analysis results to obtain the value assessment result of the target building; specifically, based on the prediction results of the Internet leased line service types, obtain the number of enterprises with Internet leased line service needs and the number of Internet leased line service types in the target building; the number of enterprises with Internet leased line service needs includes enterprises that have already opened Internet leased line services and enterprises whose prediction results are specific Internet leased line services; calculate the fourth ratio of the number of enterprises to the preset threshold number of enterprises; further, based on the prediction results of the Internet leased line service types, count the number of Internet leased line service types, and calculate the fifth ratio of the number of Internet leased line service types to the total number of Internet leased line service types; perform a weighted fusion of the fourth ratio, the fifth ratio, and the converged service coverage rate prediction results, and classify the target building into value levels based on the weighted fusion results to obtain the value assessment result of the target building. The formula used for weighted fusion is:

[0073] Q = αC1 + βC2 + χC3

[0074] Where Q represents the weighted fusion result, C1 represents the fourth ratio, C2 represents the fifth ratio, C3 represents the predicted fusion service coverage result, and α, β, and χ are the weighted fusion coefficients, with α + β + χ = 1. The values ​​of α, β, and χ are obtained by fitting relevant data from the sample buildings.

[0075] The target building is classified into value levels based on the weighted fusion results. The weighted fusion results are judged based on the range of different value levels set in advance and the range of multiple weighted fusion results to obtain the value assessment results of the target building. The value assessment results can be set in specific ways as needed. In the preferred embodiment of this application, the value assessment results include: high value, medium value and low value.

[0076] In a preferred embodiment of the present invention, after obtaining the value assessment results of the target building, the value assessment results are sent to the Internet business development personnel and the cloud. The Internet business development personnel prioritize the promotion of Internet business to high-value buildings based on the value assessment results, thereby improving the efficiency and accuracy of Internet business development.

[0077] Internet business development personnel evaluate the accuracy of the value assessment results based on the actual situation during the internet business development process, and send the accuracy evaluation results to the cloud.

[0078] Based on the value assessment results and accuracy evaluation results, the parameters of the Internet leased line service type prediction model and the converged service coverage prediction model are regularly optimized to improve the accuracy of the prediction of Internet leased line service type and converged service coverage.

[0079] In a preferred embodiment of the present invention, network format data, network protocol data, network performance parameter data, and Internet leased line service type of enterprises within the sample building before activation are acquired, along with wireless network signal coverage area data, wireless network uplink signal strength data, wireless network downlink signal strength data, number of wireless network users, wireless network traffic data, and converged service coverage rate. Based on the network format data, network protocol data, network performance parameter data, and Internet leased line service type before activation, an Internet leased line service type prediction model constructed using a backpropagation neural network is trained. Based on the wireless network signal coverage area data, wireless network uplink signal strength data, wireless network downlink signal strength data, number of wireless network users, wireless network traffic data, and converged service coverage rate, a converged service coverage rate prediction model constructed using a deep neural network is trained. During real-time evaluation, the current network format data, current network protocol data, and current network performance parameter data of each enterprise in the target building that has not yet activated internet leased line services are input into a trained internet leased line service type prediction model to obtain the prediction result of the internet leased line service type for each enterprise. Based on the current wireless network signal coverage area data, current wireless network uplink signal strength data, current wireless network downlink signal strength data, current wireless network traffic data, and current number of wireless network users in the target building, a trained converged service coverage prediction model is used to predict the converged service coverage of each target building, obtaining the converged service coverage prediction result. The prediction results of internet leased line service type and converged service coverage are analyzed, and the value of the target building is assessed based on the analysis results, obtaining the value assessment result of the target building. The building value assessment method provided in this application identifies the types of internet services with internet leased line service needs in the target building, predicts the probability of the target building activating converged services, and thus assesses the value of each target building, improving the efficiency and accuracy of internet service expansion.

[0080] Accordingly, such as Figure 2 As shown, based on a building value assessment method, this embodiment of the invention also provides a building value assessment system to implement the building value assessment method disclosed in this embodiment of the invention. The system includes: a data acquisition unit 1, a first model training unit 2, a second model training unit 3, an Internet leased line service type prediction unit 4, a converged service coverage prediction unit 5, and a building value assessment unit 6.

[0081] The data acquisition unit 1 is used to acquire network format data, network protocol data, network performance parameter data, and Internet leased line service type of enterprises in the sample building before activation, as well as wireless network signal coverage area data, wireless network uplink signal strength data, wireless network downlink signal strength data, number of wireless network users, wireless network traffic data, and converged service coverage rate.

[0082] The first model training unit 2 is used to train an Internet leased line service type prediction model constructed using a backpropagation neural network based on the pre-activation network format data, the pre-activation network protocol data, the pre-activation network performance parameter data, and the Internet leased line service type.

[0083] The second model training unit 3 is used to train a converged service coverage prediction model constructed using a deep neural network based on the wireless network signal coverage area data, the wireless network uplink signal strength data, the wireless network downlink signal strength data, the number of wireless network users, the wireless network traffic data, and the converged service coverage rate.

[0084] The Internet leased line service type prediction unit 4 is used to input the current network format data, current network protocol data and current network performance parameter data of each enterprise in the target building that has not opened Internet leased line service into the trained Internet leased line service type prediction model during the real-time evaluation process, so as to obtain the Internet leased line service type prediction result for each enterprise that has not opened Internet leased line service.

[0085] The converged service coverage prediction unit 5 is used to predict the converged service coverage of each target building based on the current wireless network signal coverage area data, current wireless network uplink signal strength data, current wireless network downlink signal strength data, current wireless network traffic data, and current number of wireless network users of the target building, using the trained converged service coverage prediction model, and to obtain the converged service coverage prediction result.

[0086] The building value assessment unit 6 is used to analyze the prediction results of the Internet leased line service type and the prediction results of the converged service coverage, and to conduct a value assessment of the target building based on the analysis results, thereby obtaining the value assessment result of the target building.

[0087] The first model training unit 2 is further configured to: construct an established internet leased line service dataset based on the mapping relationship between the pre-establishment network format data, pre-establishment network protocol data, and pre-establishment network performance parameter data of enterprises that have established internet leased line services and the internet leased line service type; construct an unestablished internet leased line service dataset based on the mapping relationship between the pre-establishment network format data, pre-establishment network protocol data, and pre-establishment network performance parameter data of enterprises that have not established internet leased line services and the lack of internet leased line service demand; and train the internet leased line service type prediction model using the established internet leased line service dataset and the unestablished internet leased line service dataset.

[0088] The second model training unit 3 is further configured to use the first ratio of the wireless network signal coverage area data to the high-frequency usage area of ​​the building as the indoor signal coverage ratio; use the average uplink signal strength data of the wireless network in each area of ​​each sample building as the first indoor signal strength; use the average downlink signal strength data of the wireless network in each area of ​​each sample building as the second indoor signal strength; calculate the second ratio of the number of wireless network users in each sample building to the sum of the number of wireless network users in all sample buildings, and the third ratio of the wireless network user traffic data in each sample building to the sum of the wireless network user traffic data in all sample buildings; determine the wireless network demand level based on the sum of the second ratio and the third ratio; and train the converged service demand prediction model using the indoor signal coverage ratio, the first indoor signal strength, the second indoor signal strength, and the wireless network demand level as inputs and the converged service coverage rate as output.

[0089] The building value assessment unit 6 is further configured to obtain the number of enterprises with internet leased line service needs and the number of internet leased line service types in the target building based on the prediction results of the internet leased line service types; calculate the fourth ratio of the number of enterprises to a preset threshold for the number of enterprises; calculate the fifth ratio of the number of internet leased line service types to the total number of internet leased line service types; perform weighted fusion of the fourth ratio, the fifth ratio, and the prediction results of the converged service coverage rate; classify the target building into value levels based on the weighted fusion results; and obtain the value assessment results of the target building.

[0090] The system also includes a model optimization unit;

[0091] The model optimization unit is used to send the value assessment results to internet business development personnel and the cloud; obtain the accuracy evaluation of the value assessment results from the internet business development personnel and send the accuracy evaluation results to the cloud; and periodically optimize the internet leased line service type prediction model and the converged service coverage prediction model based on the value assessment results and the accuracy evaluation results.

[0092] For specific limitations regarding a building valuation system, please refer to the above-described limitations regarding a building valuation method; they will not be repeated here. Those skilled in the art will recognize that the various modules and steps described in conjunction with the embodiments disclosed in this invention can be implemented in hardware, software, or a combination of both. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this invention.

[0093] This embodiment provides a building value assessment method and system to address the technical problem of improving the efficiency and accuracy of building value assessment. The building value assessment method of this application includes: acquiring pre-activation network format data, pre-activation network protocol data, pre-activation network performance parameter data, and internet leased line service types for enterprises within a sample building, as well as wireless network signal coverage area data, wireless network uplink signal strength data, wireless network downlink signal strength data, number of wireless network users, wireless network traffic data, and converged service coverage rate; training an internet leased line service type prediction model constructed using a backpropagation neural network based on the pre-activation network format data, pre-activation network protocol data, pre-activation network performance parameter data, and internet leased line service types; and training a converged service coverage rate prediction model constructed using a deep neural network based on the wireless network signal coverage area data, wireless network uplink signal strength data, wireless network downlink signal strength data, number of wireless network users, wireless network traffic data, and converged service coverage rate. In the real-time evaluation process, the current network format data, current network protocol data, and current network performance parameter data of each enterprise in the target building that has not yet activated internet leased line services are input into the trained internet leased line service type prediction model to obtain the prediction result of the internet leased line service type for each enterprise that has not yet activated internet leased line services. Based on the current wireless network signal coverage area data, current wireless network uplink signal strength data, current wireless network downlink signal strength data, current wireless network traffic data, and current number of wireless network users in the target building, the trained converged service coverage prediction model is used to predict the converged service coverage of each target building to obtain the converged service coverage prediction result. The prediction results of internet leased line service type and converged service coverage are analyzed, and the value of the target building is assessed based on the analysis results to obtain the value assessment result of the target building. The building value assessment method provided in this application obtains the types of internet services with internet leased line service needs in the target building, predicts the probability of the target building activating converged services, and conducts value assessment for each target building to improve the efficiency and accuracy of internet service expansion.

[0094] The various embodiments in this specification are described in a progressive manner. For directly identical or similar parts of the embodiments, refer to each other. Each embodiment focuses on its differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments. It should be noted that the technical features of the above embodiments can be combined arbitrarily. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as the combination of these technical features does not contradict each other, it should be considered within the scope of this specification.

[0095] The above-described embodiments are merely preferred embodiments of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the invention. It should be noted that those skilled in the art can make various improvements and substitutions without departing from the principles of the present invention, and these improvements and substitutions should also be considered within the scope of protection of the present invention. Therefore, the scope of protection of this invention should be determined by the scope of the claims.

Claims

1. A method for assessing building value, characterized in that, The method includes: Obtain network format data, network protocol data, network performance parameter data, and Internet leased line service type of enterprises in the sample building before activation, as well as wireless network signal coverage area data, wireless network uplink signal strength data, wireless network downlink signal strength data, number of wireless network users, wireless network traffic data, and converged service coverage rate. Based on the network format data before activation, the network protocol data before activation, the network performance parameter data before activation, and the Internet leased line service type, a prediction model for Internet leased line service type constructed using a backpropagation neural network is trained. Based on the wireless network signal coverage area data, the wireless network uplink signal strength data, the wireless network downlink signal strength data, the number of wireless network users, the wireless network traffic data, and the converged service coverage rate, a converged service coverage rate prediction model constructed using a deep neural network is trained. During the real-time evaluation process, the current network format data, current network protocol data, and current network performance parameter data of each enterprise in the target building that has not opened Internet leased line services are input into the trained Internet leased line service type prediction model to obtain the Internet leased line service type prediction result for each enterprise that has not opened Internet leased line services. Based on the current wireless network signal coverage area data, current wireless network uplink signal strength data, current wireless network downlink signal strength data, current wireless network traffic data, and current number of wireless network users of the target building, the converged service coverage prediction model that has been trained is used to predict the converged service coverage of each target building, and the converged service coverage prediction result is obtained. The prediction results of the Internet leased line service type and the prediction results of the converged service coverage are analyzed, and the target building is valued based on the analysis results to obtain the value assessment result of the target building.

2. The building valuation method as described in claim 1, characterized in that, The step of training an Internet leased line service type prediction model constructed using a backpropagation neural network based on the pre-activation network format data, the pre-activation network protocol data, the pre-activation network performance parameter data, and the Internet leased line service type includes: Based on the mapping relationship between the pre-activation network format data, pre-activation network protocol data, and pre-activation network performance parameter data of enterprises that have activated Internet leased line services and the Internet leased line service type, construct an Internet leased line service dataset; Based on the mapping relationship between the network format data, network protocol data, and network performance parameter data of enterprises that have not yet opened Internet leased line services and the demand for Internet leased line services, a dataset of Internet leased line services that has not yet opened is constructed. The prediction model for the Internet leased line service type is trained using the datasets of the already activated Internet leased line service and the datasets of the not activated Internet leased line service.

3. The building valuation method as described in claim 1, characterized in that, The process of training a converged service demand prediction model constructed using a deep neural network, based on the wireless network signal coverage area data, the wireless network uplink signal strength data, the wireless network downlink signal strength data, the number of wireless network users, the wireless network traffic data, and the converged service coverage rate, includes: The ratio of the wireless network signal coverage area data to the high-frequency usage area of ​​the building is used as the indoor signal coverage ratio. The average uplink signal strength data of the wireless network in each area of ​​each of the sample buildings is taken as the first indoor signal strength. The average downlink signal strength data of the wireless network in each area of ​​each of the sample buildings is used as the second indoor signal strength. Calculate a second ratio of the number of wireless network users in each of the sample buildings to the sum of the number of wireless network users in all the sample buildings, and a third ratio of the wireless network traffic data in each of the sample buildings to the sum of the wireless network user traffic data in all the sample buildings. Determine the wireless network demand level based on the sum of the second ratio and the third ratio. The indoor signal coverage ratio, the first indoor signal strength, the second indoor signal strength, and the wireless network demand level are used as inputs, and the converged service coverage rate is used as the output to train the converged service demand prediction model.

4. The building valuation method as described in claim 1, characterized in that, The analysis of the prediction results for the Internet leased line service type and the prediction results for the converged service coverage, and the subsequent valuation of the target building based on the analysis results, yields the valuation result of the target building, including: Based on the prediction results of the Internet leased line service types, the number of enterprises with Internet leased line service needs and the number of Internet leased line service types in the target building are obtained; Calculate the fourth ratio between the number of enterprises and the preset threshold number of enterprises; Calculate the fifth ratio of the number of Internet leased line service types to the total number of Internet leased line service types; The fourth ratio, the fifth ratio, and the predicted coverage of the integrated services are weighted and fused together. Based on the weighted fusion result, the target building is classified into value levels to obtain the value assessment result of the target building.

5. The building valuation method as described in claim 1, characterized in that, The method further includes: The valuation results will be sent to internet business development personnel and the cloud. Obtain the accuracy evaluation of the value assessment results from the internet business development personnel, and send the accuracy evaluation results to the cloud; Based on the value assessment results and the accuracy evaluation results, the prediction model for Internet leased line service types and the prediction model for converged service coverage are periodically optimized.

6. A building valuation system, implementing the building valuation method according to any one of claims 1-5, characterized in that, The system includes: a data acquisition unit, a first model training unit, a second model training unit, an internet leased line service type prediction unit, a converged service coverage prediction unit, and a building value assessment unit. The data acquisition unit is used to acquire network format data, network protocol data, network performance parameter data, and Internet leased line service type of enterprises in the sample building before activation, as well as wireless network signal coverage area data, wireless network uplink signal strength data, wireless network downlink signal strength data, number of wireless network users, wireless network traffic data, and converged service coverage rate. The first model training unit is used to train an Internet leased line service type prediction model constructed using a backpropagation neural network based on the pre-activation network format data, the pre-activation network protocol data, the pre-activation network performance parameter data, and the Internet leased line service type. The second model training unit is used to train a converged service coverage prediction model constructed using a deep neural network based on the wireless network signal coverage area data, the wireless network uplink signal strength data, the wireless network downlink signal strength data, the number of wireless network users, the wireless network traffic data, and the converged service coverage rate. The Internet leased line service type prediction unit is used to input the current network format data, current network protocol data, and current network performance parameter data of each enterprise in the target building that has not opened Internet leased line services into the trained Internet leased line service type prediction model during the real-time evaluation process, so as to obtain the Internet leased line service type prediction result for each enterprise that has not opened Internet leased line services. The converged service coverage prediction unit is used to predict the converged service coverage of each target building based on the current wireless network signal coverage area data, current wireless network uplink signal strength data, current wireless network downlink signal strength data, current wireless network traffic data, and current number of wireless network users of the target building, using the trained converged service coverage prediction model, and to obtain the converged service coverage prediction result. The building valuation unit is used to analyze the prediction results of the Internet leased line service type and the prediction results of the converged service coverage, and to evaluate the value of the target building based on the analysis results, thereby obtaining the valuation result of the target building.

7. The building valuation system as described in claim 6, characterized in that, The first model training unit is further configured to: construct an established internet leased line service dataset based on the mapping relationship between the pre-establishment network format data, pre-establishment network protocol data, and pre-establishment network performance parameter data of enterprises that have established internet leased line services and the internet leased line service type; construct an unestablished internet leased line service dataset based on the mapping relationship between the pre-establishment network format data, pre-establishment network protocol data, and pre-establishment network performance parameter data of enterprises that have not established internet leased line services and the lack of internet leased line service demand; and train the internet leased line service type prediction model using the established internet leased line service dataset and the unestablished internet leased line service dataset.

8. The building valuation system as described in claim 6, characterized in that, The second model training unit is further configured to use the first ratio of the wireless network signal coverage area data to the high-frequency usage area of ​​the building as the indoor signal coverage ratio; use the average uplink signal strength data of the wireless network in each area of ​​each sample building as the first indoor signal strength; and use the average downlink signal strength data of the wireless network in each area of ​​each sample building as the second indoor signal strength. Calculate a second ratio of the number of wireless network users in each of the sample buildings to the sum of the number of wireless network users in all the sample buildings, and a third ratio of the wireless network traffic data in each of the sample buildings to the sum of the wireless network user traffic data in all the sample buildings. Determine the wireless network demand level based on the sum of the second ratio and the third ratio. The indoor signal coverage ratio, the first indoor signal strength, the second indoor signal strength, and the wireless network demand level are used as inputs, and the converged service coverage rate is used as the output to train the converged service demand prediction model.

9. The building valuation system as described in claim 6, characterized in that, The building value assessment unit is also used to obtain the number of enterprises with internet leased line service needs and the number of internet leased line service types in the target building based on the prediction results of the internet leased line service types; calculate the fourth ratio of the number of enterprises to the preset threshold of the number of enterprises; and calculate the fifth ratio of the number of internet leased line service types to the total number of internet leased line service types. The fourth ratio, the fifth ratio, and the predicted coverage of the integrated services are weighted and fused together. Based on the weighted fusion result, the target building is classified into value levels to obtain the value assessment result of the target building.

10. The building valuation system as described in claim 6, characterized in that, The system also includes a model optimization unit; The model optimization unit is used to send the value assessment results to internet business development personnel and the cloud; obtain the accuracy evaluation of the value assessment results from the internet business development personnel, and send the accuracy evaluation results to the cloud; Based on the value assessment results and the accuracy evaluation results, the prediction model for Internet leased line service types and the prediction model for converged service coverage are periodically optimized.

Images