User evaluation acquisition method and system for natural gas energy metering

By obtaining natural gas statistics and user data, using user evaluation prediction models and making adjustments, the problem of user evaluation acquisition in the intelligent natural gas network is solved, and accurate prediction and improvement of the user experience of natural gas network is achieved, and service quality is improved.

CN114399112BActive Publication Date: 2024-11-15CHENGDU QINCHUAN IOT TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202210045107.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-01-14
Publication Date
2024-11-15
Estimated Expiration
2042-01-14

AI Technical Summary

Technical Problem

In the construction of smart natural gas networks, how to effectively obtain user reviews to improve the user experience of natural gas networks has become an urgent problem.

Method used

By obtaining natural gas statistics and user data in the target area, predicting user evaluations using the user evaluation prediction model, and determining whether the prediction results are abnormal based on the actual evaluation, and adjusting to obtain accurate user evaluation.

Benefits of technology

Accurate prediction and improvement of the user experience of the natural gas network has been achieved, data support is provided for the construction of the natural gas network, and user satisfaction and service quality are improved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114399112B_ABST
    Figure CN114399112B_ABST
Patent Text Reader

Abstract

The embodiments of the present specification provide a method and system for obtaining user evaluations that can be used for natural gas energy metering, the method comprising obtaining natural gas statistical data and regional user data within a preset time period of a target area; obtaining user evaluation prediction results based on the natural gas statistical data and the regional user data through a user evaluation prediction model; judging whether the user evaluation prediction results are abnormal based on actual user evaluations, and if the user evaluation prediction results are judged to be abnormal, adjusting the user evaluation prediction results.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of natural gas management, and in particular to a method and system for obtaining user evaluations that can be used for natural gas energy metering. Background Art

[0002] At present, with the rapid advancement of the construction of intelligent natural gas grid, the GIS geographic information service platform of the natural gas grid has also been gradually promoted and applied. It realizes the unified collection of natural gas grid resource information, provides geographic spatial information sharing and business application integration for the "generation, transmission, transformation, distribution, use, and adjustment" of the natural gas grid, and provides spatial geographic information and network topology information of natural gas grid equipment, which lays an important foundation for improving the informationization and automation level of the natural gas grid. The purpose of natural gas grid construction is to enhance the user's experience of natural gas use, that is, the construction and improvement of the natural gas network is closely related to the user's experience. How to obtain user evaluation in a forward-looking manner to improve the construction of the natural gas grid has become an urgent problem to be solved.

[0003] Therefore, it is necessary to provide a method and system for obtaining user evaluations that can be used for natural gas energy metering, so as to predict user evaluations. Summary of the invention

[0004] One of the embodiments of this specification provides a method for obtaining user evaluations that can be used for natural gas energy metering. The method for obtaining user evaluations that can be used for natural gas energy metering includes: obtaining natural gas statistical data and regional user data within a preset time period of a target area; obtaining user evaluation prediction results based on the natural gas statistical data and the regional user data through a user evaluation prediction model; judging whether the user evaluation prediction results are abnormal based on actual user evaluations, and if the user evaluation prediction results are judged to be abnormal, adjusting the user evaluation prediction results.

[0005] One of the embodiments of the present specification provides a user evaluation acquisition system that can be used for natural gas energy metering, including: the data acquisition module, used to obtain natural gas statistical data and regional user data within a preset time period of a target area; the evaluation prediction module, used to obtain user evaluation prediction results based on the natural gas statistical data and the regional user data through a user evaluation prediction model; the prediction adjustment module, used to determine whether the user evaluation prediction result is abnormal based on the actual user evaluation, and if the user evaluation prediction result is determined to be abnormal, adjust the user evaluation prediction result.

[0006] One of the embodiments of the present specification provides a method and device for obtaining user evaluations that can be used for natural gas energy metering, including a processor, wherein the processor is used to execute a method for obtaining user evaluations that can be used for natural gas energy metering.

[0007] One of the embodiments of the present specification provides a computer-readable storage medium, wherein the storage medium stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes a method for obtaining user evaluations that can be used for natural gas energy metering. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:

[0009] Figure 1 is a schematic diagram of an application scenario of a method for obtaining user evaluations that can be used for natural gas energy metering according to some embodiments of this specification;

[0010] Figure 2 is an exemplary block diagram of a user evaluation acquisition system that can be used for natural gas energy metering according to some embodiments of this specification;

[0011] Figure 3 is an exemplary flow chart of a method for obtaining user evaluations that can be used for natural gas energy metering according to some embodiments of this specification;

[0012] Figure 4 It is an exemplary flow chart of determining labels of fault factor training samples based on faulty evaluation data and non-faulty evaluation data according to some embodiments of this specification. DETAILED DESCRIPTION

[0013] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of this specification. For ordinary technicians in this field, this specification can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0014] It should be understood that the "system", "device", "unit" and / or "module" used herein are a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

[0015] As shown in this specification and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "comprise" and "include" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0016] Flowcharts are used in this specification to illustrate the operations performed by the system according to the embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed precisely in order. Instead, the steps may be processed in reverse order or simultaneously. At the same time, other operations may also be added to these processes, or one or more operations may be removed from these processes.

[0017] Figure 1 It is a schematic diagram of an application scenario 100 of a user evaluation acquisition system that can be used for natural gas energy metering according to some embodiments of this specification.

[0018] Reference Figure 1 In some embodiments, the application scenario 100 may include a server 110 , a network 120 , one or more terminal devices 130 , and a storage device 140 .

[0019] The server 110 can be used to process data and / or information from at least one component of the application scenario 100 or an external data source (e.g., a cloud data center). For example, the server 110 can obtain natural gas statistical data and regional user data within a preset time period of the target area; obtain user evaluation prediction results based on the natural gas statistical data and regional user data through a user evaluation prediction model; and determine whether the user evaluation prediction results are abnormal based on the actual user evaluation, and if the user evaluation prediction results are abnormal, adjust the user evaluation prediction results. In some embodiments, during the processing, the server 110 can obtain data (such as instructions) from the storage device 140 or save the data (e.g., user evaluation prediction results) to the storage device 140, and can also read data (e.g., natural gas statistical data and regional user data within a preset time period, etc.) from other sources such as the terminal device 130 through the network 120 or output data (e.g., user evaluation prediction results, etc.) to the terminal device 130.

[0020] In some embodiments, the server 110 may be a single server or a server group. In some embodiments, the server 110 may be locally connected to the network 120 or remotely connected to the network 120. In some embodiments, the server 110 may be implemented on a cloud platform.

[0021] The network 120 may facilitate the exchange of information and / or data. In some embodiments, one or more components (eg, the server 110 , the terminal device 130 , etc.) in the application scenario 100 may send information and / or data to another component in the application scenario 100 via the network 120 .

[0022] The terminal device 130 refers to one or more terminal devices or software used by the user. In some embodiments, the terminal device 130 may be one or any combination of other devices with input and / or output functions, such as a mobile device, a tablet computer, a laptop computer, a desktop computer, etc. In some embodiments, the terminal device 130 may be used as a display terminal of the user, for obtaining and displaying the user evaluation prediction results determined by the server 110 via the network 120. The above examples are only used to illustrate the wide range of the terminal device 130 and are not intended to limit its scope.

[0023] The storage device 140 may be used to store data and / or instructions. In some embodiments, the storage device 140 may obtain data and / or instructions from, for example, the server 110, the terminal device 130, etc. In some embodiments, the storage device 140 may store data and / or instructions that the server 110 uses to execute or use to complete the exemplary methods described in this specification.

[0024] In some embodiments, the storage device 140 may include a mass storage device, a removable storage device, a volatile read-write memory, a read-only memory (ROM), etc., or any combination thereof. In some embodiments, the storage device 140 may be implemented on a cloud platform.

[0025] Figure 2 It is a module diagram of a user evaluation acquisition system 200 that can be used for natural gas energy metering according to some embodiments of this specification.

[0026] Reference Figure 2 In some embodiments, a user evaluation acquisition system 200 that can be used for natural gas energy metering may include a data acquisition module 210 , an evaluation prediction module 220 , and a prediction adjustment module 230 .

[0027] The data acquisition module 210 may be used to acquire natural gas statistical data and regional user data within a preset time period in a target area.

[0028] The evaluation prediction module 220 can be used to obtain user evaluation prediction results based on natural gas statistical data and regional user data through a user evaluation prediction model.

[0029] The prediction adjustment module 230 can be used to determine whether the user evaluation prediction result is abnormal based on the actual user evaluation. If the user evaluation prediction result is determined to be abnormal, the user evaluation prediction result is adjusted. In some embodiments, the prediction adjustment module 230 can also be used to adjust the user evaluation prediction result based on the fault influencing factor. In some embodiments, the prediction adjustment module 230 can also be used to determine the fault influencing factor based on the natural gas statistical data and the fault rate through the fault factor prediction model. In some embodiments, the prediction adjustment module 230 can also be used to determine the label of the fault factor training sample used to train the fault factor prediction model based on the fault evaluation data and the fault-free evaluation data.

[0030] For more information about the data acquisition module 210, the evaluation prediction module 220, and the prediction adjustment module 230, see Figure 3 , Figure 4 The related descriptions will not be repeated here.

[0031] It should be noted that the above description of the user evaluation acquisition system 200 and its modules that can be used for natural gas energy metering is only for the convenience of description and cannot limit this specification to the scope of the embodiments. It is understandable that for those skilled in the art, after understanding the principle of the system, it is possible to arbitrarily combine the modules or form a subsystem to connect with other modules without deviating from this principle. In some embodiments, Figure 2 The data acquisition module 210, the evaluation prediction module 220, and the prediction adjustment module 230 disclosed in the specification can be different modules in a system, or a module can realize the functions of two or more modules mentioned above. For example, each module can share a storage module, or each module can have its own storage module. Such variations are all within the protection scope of this specification.

[0032] Figure 3 FIG. 3 is an exemplary flow chart of a method 300 for obtaining user evaluations of natural gas energy metering according to some embodiments of this specification. Figure 3 As shown, the process 300 includes the following steps. In some embodiments, the process 300 can be executed by the user evaluation acquisition system 200 that can be used for natural gas energy metering.

[0033] Step 310 , obtaining natural gas statistical data and regional user data within a preset time period of the target area. In some embodiments, step 310 may be performed by the data acquisition module 210 .

[0034] The target area may be a specific area. For example, the target area may be a province, a city, a county, a district, or an area of ​​a certain size arbitrarily specified by humans. In some embodiments, the data acquisition module 210 may acquire the target area from the server 110, the terminal device 130, the storage device 140, or an external data source.

[0035] The preset time period may be a specific time period, for example, a certain year, certain months, certain days, etc. In some embodiments, the data acquisition module 210 may acquire the preset time period from the server 110, the terminal device 130, the storage device 140 or an external data source.

[0036] The natural gas statistical data may be information related to the natural gas services provided to the target area. In some embodiments, the natural gas statistical data may include natural gas type, natural gas price, natural gas pressure, and natural gas consumption.

[0037] In some embodiments, the data acquisition module 210 may acquire natural gas statistical data from the server 110 , the terminal device 130 , the storage device 140 , or an external data source.

[0038] The regional user data may be data related to users in the target area. In some embodiments, the regional user data may include the number of users, user types, and natural gas usage distribution data, among which the number of users may represent the number of users in the target area; the user type may represent the type of each user in the target area, and the user type may include household users, commercial users (e.g., hotels, restaurants, canteens, etc.); the natural gas usage distribution data may represent the natural gas usage of each sub-area in the target area and the distribution of natural gas usage time in the area. In some embodiments, the natural gas usage distribution data may be expressed in the form of a heat map, a pie chart, a bar chart, etc. It can be understood that the target area is composed of multiple sub-areas, and the sub-area may be a street, a building, etc. in the target area.

[0039] In some embodiments, the data acquisition module 210 may acquire regional user data from the server 110 , the terminal device 130 , the storage device 140 , or an external data source.

[0040] Step 320 , obtaining a user evaluation prediction result based on natural gas statistical data and regional user data through a user evaluation prediction model. In some embodiments, step 320 may be performed by the evaluation prediction module 220 .

[0041] The user evaluation prediction result can represent the feedback of the users in the predicted target area on the natural gas usage experience in a certain period of time in the future. In some embodiments, the user evaluation prediction result can be expressed in the form of a score, a number of stars, etc. It can be understood that the higher the score, the better the natural gas usage experience of the users in the target area; the more stars, the better the natural gas usage experience of the users in the target area.

[0042] The user evaluation prediction model may be a machine learning model for predicting user evaluation prediction results. In some embodiments, the input of the user evaluation prediction model may be natural gas statistical data and regional user data, and the output of the user evaluation prediction model may be the user evaluation prediction results.

[0043] In some embodiments, the evaluation prediction module 220 can train the initial user evaluation prediction model through multiple labeled evaluation prediction training samples, wherein one evaluation prediction training sample corresponds to natural gas statistical data and regional user data in a sample time period of a sample area, and the label of the evaluation prediction training sample may include the user evaluation prediction result corresponding to the sample time period of the sample area. The label can be obtained by manual labeling, for example, it can be obtained by manual labeling based on historical user real evaluations.

[0044] In some embodiments, the evaluation prediction module 220 may train the initial user evaluation prediction model multiple times in a common manner (e.g., gradient descent, etc.) until the trained initial user evaluation prediction model meets a preset condition, and use the trained initial user evaluation prediction model as the user evaluation prediction model for predicting the user evaluation prediction result. The preset condition may be that the loss function of the updated initial user evaluation prediction model is less than a threshold, converges, or the number of training iterations reaches a threshold.

[0045] In some embodiments, the user evaluation prediction model can be one or any combination of a variational auto-encoder (VAE), a neural network model, and a deep learning model, wherein the neural network model can include a combination of one or more of a convolutional neural network (CNN), a recurrent neural network (RNN), a multi-layer neural network (MLP), a genetic adversarial neural network (GAN), etc.

[0046] Step 330 , judging whether the user evaluation prediction result is abnormal based on the user's actual evaluation. In some embodiments, step 330 may be performed by the prediction adjustment module 230 .

[0047] The actual user evaluation may characterize the actual natural gas usage experience of users in the target area during a preset time period. It is understandable that the actual user evaluation may be determined based on the actual evaluations of multiple users. For example, if the number of users who have provided feedback on the actual evaluation is 5, the actual user evaluation may be the average or median of the actual evaluations of the 5 users.

[0048] In some embodiments, the user's actual evaluation may be expressed in the form of text, score, number of stars, etc. In some embodiments, when the user's actual evaluation is text, the prediction adjustment module 230 may convert the text into a score or star rating. In some embodiments, the prediction adjustment module 230 may convert the text of the user's actual evaluation into a score or star rating based on preset rules. Among them, the preset rules may characterize the correspondence between text and scores or star ratings. For example, the preset rules may include: the user's actual evaluation is "very poor", and its corresponding score is -5 or its corresponding number of stars is 0; the user's actual evaluation is "very satisfied", and its corresponding score is 5 or its corresponding number of stars is 5; the user's actual evaluation is "average", and its corresponding score is 0 or its corresponding number of stars is 3. In some embodiments, the user's actual evaluation can be distributed on the regional map of the target area in the form of scores or thermal values.

[0049] In some embodiments, the prediction adjustment module 230 may obtain the user's actual evaluation from the server 110, the terminal device 130, the storage device 140 or an external data source. In some embodiments, the user's actual evaluation may be collected from the user terminal used by the user, for example, through the application used by the user.

[0050] In some embodiments, the prediction adjustment module 230 may determine whether the user evaluation prediction result is abnormal based on the user's actual evaluation. In some embodiments, the prediction adjustment module 230 may compare the user's actual evaluation with the user evaluation prediction result to determine whether the user evaluation prediction result is abnormal. For example, the prediction adjustment module 230 may calculate the difference between the user's actual evaluation and the user evaluation prediction result, and determine whether the user evaluation prediction result is abnormal based on the difference. For example, the prediction adjustment module 230 may calculate the score difference between the score corresponding to the user evaluation prediction result and the score corresponding to the user's actual evaluation, and determine whether the score difference is within a preset score difference range (for example, -1 to 1). If the score difference is not within the preset score difference range, the user evaluation prediction result is determined to be abnormal. For another example, the prediction adjustment module 230 may calculate the star difference between the number of stars corresponding to the user evaluation prediction result and the number of stars corresponding to the user's actual evaluation, and determine whether the star difference is within a preset star difference range (for example, -1 to 1). If the star difference is not within the preset star difference range, the user evaluation prediction result is determined to be abnormal.

[0051] Step 340 : If it is determined that the user evaluation prediction result is abnormal, the user evaluation prediction result is adjusted. In some embodiments, step 340 may be performed by the prediction adjustment module 230 .

[0052] In some embodiments, the prediction adjustment module 230 may adjust the user evaluation prediction results in the following ways: adjusting the user evaluation prediction results from a positive review to a negative review, increasing or decreasing the score corresponding to the user evaluation prediction results, increasing or decreasing the number of stars corresponding to the user evaluation prediction results, etc.

[0053] In some embodiments, the prediction adjustment module 230 may adjust the user evaluation prediction result based on the relevant data. In some embodiments, the relevant data may include the user's actual evaluation. For example, the prediction adjustment module 230 may adjust the user evaluation prediction result based on the user's actual evaluation. For example, the prediction adjustment module 230 may adjust the user evaluation prediction result to the mean of the user evaluation prediction result and the user's actual evaluation.

[0054] In some embodiments, the relevant data may include a fault impact factor. In some embodiments, the prediction adjustment module 230 may adjust the user evaluation prediction result based on the fault impact factor. Among them, the fault impact factor may be a parameter for adjusting the user evaluation prediction result determined based on the natural gas failure rate. By way of example, when the fault impact factor is 1, the prediction adjustment module 230 may increase the score corresponding to the user evaluation prediction result by one point or increase the number of stars by one star. By way of another example, when the fault impact factor is -2, the prediction adjustment module 230 may increase or decrease the score corresponding to the user evaluation prediction result by two points or increase the number of stars by two stars.

[0055] In some embodiments, the prediction and adjustment module 230 may determine the fault influencing factor based on the natural gas statistical data and the fault rate within the preset time period of the target area through the fault factor prediction model. Among them, the fault rate may characterize the frequency of natural gas equipment failure within the preset time period of the target area. In some embodiments, the prediction and adjustment module 230 may determine the fault rate based on data related to the natural gas equipment failure. For example, the data related to the natural gas equipment failure may include the time of gas supply stoppage within the preset time period of the target area, and the prediction and adjustment module 230 may use the proportion of the time of gas supply stoppage to the preset time period as the fault rate. For another example, the data related to the natural gas equipment failure may include the total number of natural gas terminal devices and the number of natural gas terminal devices that have failed, and the prediction and adjustment module 230 may use the proportion of the number of natural gas terminal devices that have failed to the total number of natural gas terminal devices as the fault rate. In some embodiments, the prediction and adjustment module 230 may obtain data related to natural gas equipment failure from the server 110, the terminal device 130, the storage device 140 or an external data source.

[0056] In some embodiments, the prediction adjustment module 230 may directly obtain the failure rate from the server 110 , the terminal device 130 , the storage device 140 , or an external data source.

[0057] In some embodiments, the prediction adjustment module 230 may train the initial user evaluation prediction model through a plurality of labeled fault factor training samples, wherein a fault factor training sample corresponds to natural gas statistical data and failure rate in a sample time period of a sample area, and the label of the fault factor training sample may include the fault impact factor corresponding to the sample time period of the sample area. In some embodiments, the label of the fault factor training sample may be manually annotated.

[0058] Combination Figure 4 In some embodiments, the prediction adjustment module 230 may determine the label 430 of the fault factor training sample 440 for training the fault factor prediction model 460 based on the faulty evaluation data 410 and the non-faulty evaluation data 420. The faulty evaluation data 410 may be the evaluation of users who used the natural gas terminal equipment that had a fault during a sample period of a sample area; the non-faulty evaluation data 420 may be the evaluation of users who used the natural gas terminal equipment that had no fault during a sample period of a sample area. In some embodiments, the faulty evaluation data 410 and the non-faulty evaluation data 420 may be expressed in the form of scores, star ratings, etc.

[0059] It can be understood that there may be multiple users who use the natural gas terminal equipment that has failed during the sample time period of a sample area, and the prediction adjustment module 230 can determine the faulty evaluation data 410 based on the evaluations of the multiple users. For example, the prediction adjustment module 230 can take the average of the evaluations of the multiple users as the faulty evaluation data 410. For example, the users who used the natural gas terminal equipment that had failed during the sample time period X of the sample area A and submitted evaluations include user 1, user 2, and user 3, wherein the evaluation of user 1 is 3 stars, the evaluation of user 2 is 2 stars, and the evaluation of user 3 is 1 star, then the faulty evaluation data 410 corresponding to the sample time period X of the sample area A = (3+2+1) / 3 = 2 stars.

[0060] It is understandable that there may be multiple users who use natural gas terminal equipment that has not experienced any failure during a sample period in a sample area, and the prediction adjustment module 230 may determine the fault-free evaluation data 420 based on the evaluations of the multiple users. For example, the prediction adjustment module 230 may take the average of the evaluations of the multiple users as the fault-free evaluation data 420.

[0061] In some embodiments, the prediction adjustment module 230 may directly obtain the faulty evaluation data 410 and the non-faulty evaluation data 420 from the server 110 , the terminal device 130 , the storage device 140 , or an external data source.

[0062] In some embodiments, the prediction adjustment module 230 may also predict the non-fault evaluation data 420 of the fault factor training sample 440 based on the non-fault evaluation prediction model 470. The input of the non-fault evaluation prediction model 470 may be the natural gas data 480 and the sub-region user data 490 of the non-fault sub-region of the fault factor training sample 440, and the output of the non-fault evaluation prediction model 470 may be the non-fault evaluation data 420, wherein the natural gas data 480 of the non-fault sub-region may be the information related to the natural gas service of the sub-region without fault in the sample region corresponding to the fault factor training sample 440, for example, the type of natural gas provided to the sub-region without fault, the natural gas price, the natural gas pressure and the natural gas consumption, etc.; the sub-region user data 490 is the user-related data of the non-fault sub-region in the sample region corresponding to the fault factor training sample 440, for example, the number of users in the sub-region, the user type and the natural gas usage distribution data, etc.

[0063] In some embodiments, the prediction adjustment module 230 may train the initial fault-free evaluation prediction model through a plurality of labeled fault-free evaluation training samples, wherein one fault-free evaluation training sample corresponds to natural gas data and sub-region user data of a fault-free sub-region within a sample time period of a sample region, and the label of the fault factor training sample may include the fault-free evaluation data 420 corresponding to the sample time period of the sample region. In some embodiments, the label of the fault-free evaluation training sample may be manually annotated.

[0064] In some embodiments, the prediction adjustment module 230 may train the initial fault-free evaluation prediction model multiple times in a common manner (e.g., gradient descent, etc.) until the trained initial fault-free evaluation prediction model meets a preset condition, and use the trained initial fault-free evaluation prediction model as the fault-free evaluation prediction model 470 for predicting the fault-free evaluation data 420. The preset condition may be that the loss function of the updated initial fault-free evaluation prediction model is less than a threshold, converges, or the number of training iterations reaches a threshold.

[0065] In some embodiments, the fault-free evaluation prediction model can be one or any combination of a neural network model and a deep learning model, wherein the neural network model can include a combination of one or more of a convolutional neural network (CNN), a recurrent neural network (RNN), a multi-layer neural network (MLP), a genetic adversarial neural network (GAN), etc.

[0066] In some embodiments, by predicting the non-fault evaluation data of the fault factor training samples based on the non-fault evaluation prediction model, the non-fault evaluation data corresponding to the fault factor training samples can be determined quickly and accurately.

[0067] It is understandable that the prediction adjustment module 230 may also predict the fault-free evaluation data of the target area within a preset time period by using the fault-free evaluation prediction model.

[0068] In some embodiments, the prediction adjustment module 230 may determine the label 430 of the fault factor training sample 440 used to train the fault factor prediction model 460 based on the difference between the non-fault evaluation data 420 and the faulty evaluation data 410. For example, if the difference between the non-fault evaluation data 420 and the faulty evaluation data 410 of the fault factor training sample 440 is -1, the label 430 of the fault factor training sample 440 is -1. For another example, if the difference between the non-fault evaluation data 420 and the faulty evaluation data 410 of the fault factor training sample 440 is 1 star, the label 430 of the fault factor training sample 440 is 1.

[0069] In some embodiments, by determining the labels 430 of the fault factor training samples 440 used to train the fault factor prediction model 460 based on the faulty evaluation data 410 and the non-faulty evaluation data 420, the labels 430 of the fault factor training samples 440 can be made more accurate, thereby improving the efficiency of training the fault factor prediction model 460.

[0070] In some embodiments, the prediction adjustment module 230 may train the initial fault factor prediction model 450 multiple times in a common manner (e.g., gradient descent, etc.) until the trained initial fault factor prediction model 450 meets a preset condition, and use the trained initial fault factor prediction model 450 as the fault factor prediction model 460 for predicting fault influencing factors. The preset condition may be that the loss function of the updated initial fault factor prediction model 450 is less than a threshold, converges, or the number of training iterations reaches a threshold.

[0071] In some embodiments, the fault factor prediction model can be one or any combination of a neural network model and a deep learning model, wherein the neural network model can include a combination of one or more of a convolutional neural network (CNN), a recurrent neural network (RNN), a multi-layer neural network (MLP), a genetic adversarial neural network (GAN), etc.

[0072] In some embodiments, the fault influencing factor is determined by using a fault factor prediction model based on natural gas statistical data and a fault rate in a preset time period of a target area, so that the fault influencing factor can be determined quickly and accurately.

[0073] In some embodiments, the user evaluation prediction results are adjusted based on the fault impact factor so that the adjusted user evaluation prediction results are closer to the user's actual experience.

[0074] In some embodiments, a user evaluation prediction model is used to obtain user evaluation prediction results based on natural gas statistical data and regional user data, and whether the user evaluation prediction results are abnormal is judged based on the actual user evaluation. If the user evaluation prediction results are judged to be abnormal, the user evaluation prediction results are adjusted, thereby realizing the prediction of user evaluations and providing a basis for improving the construction of the natural gas network.

[0075] It should be noted that the above description of process 300 is only for example and illustration, and does not limit the scope of application of this specification. For those skilled in the art, various modifications and changes can be made to process 300 under the guidance of this specification. However, these modifications and changes are still within the scope of this specification.

[0076] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements and corrections to this specification. Such modifications, improvements and corrections are suggested in this specification, so such modifications, improvements and corrections still belong to the spirit and scope of the exemplary embodiments of this specification.

[0077] At the same time, this specification uses specific words to describe the embodiments of this specification. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures or characteristics in one or more embodiments of this specification can be appropriately combined.

[0078] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences described in this specification, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some invention embodiments that are currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0079] Similarly, it should be noted that in order to simplify the description disclosed in this specification and thus help understand one or more embodiments of the invention, in the above description of the embodiments of this specification, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the subject matter of this specification are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0080] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise specified, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may change according to the required features of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of this specification are approximate values, in specific embodiments, the setting of such numerical values ​​is as accurate as possible within the feasible range.

[0081] Each patent, patent application, patent application publication, and other materials, such as articles, books, specifications, publications, documents, etc., cited in this specification are hereby incorporated by reference in their entirety. Except for application history documents that are inconsistent with or conflicting with the contents of this specification, documents that limit the broadest scope of the claims of this specification (currently or later attached to this specification) are also excluded. It should be noted that if the descriptions, definitions, and / or use of terms in the materials attached to this specification are inconsistent or conflicting with the contents described in this specification, the descriptions, definitions, and / or use of terms in this specification shall prevail.

[0082] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A method for obtaining user evaluation that can be used for natural gas energy metering, comprising: Obtain natural gas statistics and regional user data within a preset time period in the target area; The user area data is data related to users in the target area, including the number of users, user types and natural gas usage distribution data; the user types include household users and commercial users; the natural gas usage distribution data represents the natural gas usage of each sub-area in the target area and the distribution of natural gas usage time in the area; A user evaluation prediction model is used to obtain a user evaluation prediction result based on the natural gas statistical data and the regional user data, wherein the user evaluation prediction result is a predicted user feedback on the natural gas usage experience; the user evaluation prediction model is one or any combination of a variational autoencoder, a neural network model, and a deep learning model; Based on the natural gas statistical data and failure rate in the preset time period of the target area, a failure influence factor is determined through a failure factor prediction model, wherein the failure influence factor refers to a parameter for adjusting the user evaluation prediction result; the failure factor prediction model is one or any combination of a neural network model and a deep learning model; the labels of the failure factor training samples used to train the failure factor prediction model are determined based on the failure evaluation data and the non-fault evaluation data; Judging whether the user evaluation prediction result is abnormal based on the actual user evaluation, and if the user evaluation prediction result is judged to be abnormal, adjusting the user evaluation prediction result based on the fault influencing factor; The actual user evaluation represents the actual natural gas usage experience of the users in the target area during a preset time period.

2. A user evaluation acquisition system that can be used for natural gas energy metering, comprising: A data acquisition module is used to acquire natural gas statistical data and regional user data within a preset time period of a target area; the user regional data is data related to users in the target area, including the number of users, user types and natural gas usage distribution data; the user types include household users and commercial users; the natural gas usage distribution data represents the natural gas usage of each sub-area in the target area and the distribution of natural gas usage time in the area; An evaluation prediction module, used to obtain a user evaluation prediction result based on the natural gas statistical data and the regional user data through a user evaluation prediction model, wherein the user evaluation prediction result is a predicted user feedback on the natural gas use experience; the user evaluation prediction model is one or any combination of a variational autoencoder, a neural network model and a deep learning model; A prediction adjustment module, used to determine a fault influence factor through a fault factor prediction model based on the natural gas statistical data and the fault rate within the preset time period of the target area, wherein the fault influence factor refers to a parameter for adjusting the user evaluation prediction result; the fault factor prediction model is one or any combination of a neural network model and a deep learning model; the labels of the fault factor training samples used to train the fault factor prediction model are determined based on the fault evaluation data and the non-fault evaluation data; The evaluation prediction model is further used to judge whether the user evaluation prediction result is abnormal based on the user's actual evaluation, and if the user evaluation prediction result is judged to be abnormal, adjust the user evaluation prediction result based on the fault influencing factor; The actual user evaluation represents the actual natural gas usage experience of the users in the target area during a preset time period.

3. A method and device for obtaining user evaluations that can be used for natural gas energy metering, comprising a processor, wherein the processor is used to execute the method for obtaining user evaluations that can be used for natural gas energy metering as claimed in claim 1.

4. A computer-readable storage medium, wherein the storage medium stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the method for obtaining user evaluations that can be used for natural gas energy metering as claimed in claim 1.