A method and related device for analyzing and managing value-added service information of a photovoltaic product

Abstract

The application discloses a kind of photovoltaic product value-added service information analysis management method and related device, it is related to data processing technical field, the method includes: receiving user basic information and binding photovoltaic product information;User basic information and binding photovoltaic product information are carried out data check, and corresponding user profile is created based on data check result;Based on the use behavior information, the user portrait is constructed using label confidence analysis;Based on user portrait and user profile, value-added service demand analysis is carried out to generate the recommended value-added service list corresponding to the binding photovoltaic product of each user;Based on Markov chain, the benefit simulation prediction of target value-added service determined for each user is carried out;Based on target value-added service, the popularity analysis is carried out to generate target analysis report in combination with benefit simulation prediction data.The application can improve more comprehensive and accurate analysis value-added service condition, can know the specific use condition and use experience of each value-added service to user.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, in particular to a value-added service information analysis management method for photovoltaic products and related devices. BACKGROUND

[0002] With the rapid development of new energy technology, photovoltaic products occupy a higher and higher position in people's life, and thus various enterprises gradually introduce value-added services for photovoltaic products to improve user experience. At present, in the management of value-added services for photovoltaic products, it is necessary to build a user portrait to analyze the value-added services required by users. Usually, the user portrait is obtained by statistical analysis based on human experience, but this method is not comprehensive and accurate, which leads to inaccurate demand analysis of value-added services, so that the recommended value-added services analyzed ultimately cannot well fit the actual situation of users. At the same time, after users select the value-added services of photovoltaic products, there is currently a lack of benefit simulation prediction and popularity of the selected value-added services, which leads to the inability to effectively generate comprehensive and accurate analysis reports, so that the specific situation of each value-added service in photovoltaic products cannot be effectively known, and the value-added service analysis management of photovoltaic products fails to achieve the expected effect. SUMMARY

[0003] The present application aims to overcome the shortcomings of the prior art, and provides a value-added service information analysis management method for photovoltaic products and related devices, which can provide more comprehensive and accurate value-added service information analysis to know the specific use and experience of users for each value-added service.

[0004] To solve the above technical problems, the present application provides a value-added service information analysis management method for photovoltaic products, which comprises:

[0005] The backend server establishes a communication connection with each user terminal based on identity authentication, and receives the user basic information and the binding photovoltaic product information entered by each user terminal;

[0006] The user basic information and the binding photovoltaic product information are subjected to data verification to obtain a data verification result, and a corresponding user file is created based on the data verification result;

[0007] The browsing behavior information of each user for several value-added services of the binding photovoltaic product is obtained, and a user portrait is constructed based on the browsing behavior information using label confidence analysis;

[0008] Based on the user portrait and the user file, the demand analysis of value-added services for each user is performed to obtain corresponding value-added service demand data, and a recommended value-added service list corresponding to the binding photovoltaic product of each user is generated based on the value-added service demand data, and the recommended value-added service list is sent to each user terminal.

[0009] obtain the target value-added service determined by each user in the recommended value-added service list, simulate and predict the benefit of the target value-added service determined by each user based on a Markov chain, and obtain benefit simulation prediction data;

[0010] analyze the popularity of the target value-added service determined by each user, obtain value-added service popularity analysis data, and generate a target analysis report based on the benefit simulation prediction data and the value-added service popularity analysis data, and display the target analysis report in a corresponding visual component.

[0011] Optionally, the backend server establishes a communication connection with each user terminal based on identity authentication, comprising:

[0012] The backend server receives an authentication request sent by each user terminal, generates an identity based on the authentication request, and generates a signed identity certificate based on the identity using a certificate model;

[0013] The signed identity certificate is authenticated based on a differential confusion mechanism, and after the signed identity certificate is authenticated, the backend server establishes a communication connection with the corresponding user terminal.

[0014] Optionally, the data of the user basic information and the bound photovoltaic product information is checked to obtain a data check result, comprising:

[0015] The data of the user basic information and the bound photovoltaic product information is checked based on a data check algorithm to obtain a data check value;

[0016] A plurality of sub-numbers are generated based on the user basic information and the bound photovoltaic product information, and a plurality of decomposition coefficients are generated based on a public check code and each sub-number;

[0017] A corresponding synthetic number is generated based on each decomposition coefficient and the public check code, and the data of the user basic information and the bound photovoltaic product information is checked based on the synthetic number and the data check value to obtain a data check result.

[0018] Optionally, the user portrait is constructed based on the browsing behavior information using a tag confidence analysis, comprising:

[0019] An effective duration analysis is performed based on the browsing behavior information to obtain an effective browsing duration, and an interest degree analysis of the browsing behavior is performed based on the effective browsing duration using a scoring function to obtain interest degree analysis data;

[0020] performing browsing times analysis of a value-added service category based on the browsing behavior information, obtaining target browsing times, and generating browsing category weights based on browsing category historical weights and the target browsing times;

[0021] performing feature extraction on the browsing behavior information, obtaining target browsing features, and performing semantic similarity calculation and intent recognition processing based on the target browsing features, obtaining intent label data and intent label confidence;

[0022] constructing a user portrait based on the interest degree analysis data, browsing category weights, intent label data, and intent label confidence.

[0023] Optionally, performing value-added service demand analysis of each user based on the user portrait and user profile, obtaining corresponding value-added service demand data, and generating a recommended value-added service list corresponding to the bound photovoltaic product of each user based on the value-added service demand data, including:

[0024] performing initial value-added service demand analysis based on the user profile of each user, obtaining initial value-added service demand data;

[0025] performing collaborative filtering based on the user portrait of each user, obtaining a collaborative filtering result;

[0026] performing latent demand analysis based on the collaborative filtering result, obtaining latent demand analysis data, and performing value-added service recommendation heat analysis based on the latent demand analysis data using outlier data analysis, obtaining recommendation heat data;

[0027] performing interest change analysis based on the collaborative filtering result using an interest change analysis model, obtaining interest change data, and combining the initial value-added service demand data based on the latent demand analysis data, recommendation heat data, and interest change data to generate value-added service demand data corresponding to each user;

[0028] performing matching and sorting in a plurality of value-added services based on the value-added service demand data, obtaining a recommended value-added service list corresponding to the bound photovoltaic product of each user.

[0029] Optionally, performing benefit simulation prediction on the target value-added service determined for each user based on a Markov chain, obtaining benefit simulation prediction data, including:

[0030] obtaining historical benefit record data and historical user value-added service conversion data, and generating a time series-data distribution chain based on the historical benefit record data;

[0031] defining a state space and a state transition matrix based on the historical user value-added service conversion data, and determining a state transition probability function based on the state space and the state transition matrix.

[0032] Optimizing the state transition probability function based on an adaptive adjustment mechanism and a Bayesian estimation method to obtain an optimized state transition probability function;

[0033] Based on the optimized state transition probability function and the time-series-data distribution chain, a Markov chain is constructed, and a benefit simulation prediction model is generated using a recurrent neural network based on the Markov chain, and the benefit simulation prediction data is obtained by simulating and predicting the target value-added service determined by each user based on the benefit simulation prediction model.

[0034] Optionally, the popularity analysis based on the target value-added service determined by each user is performed to obtain value-added service popularity analysis data, including:

[0035] Obtain tracking state data of the target value-added service determined by each user, and generate a user rating matrix using a conditional variational autoencoder based on the tracking state data;

[0036] Based on the tracking state data, an element extraction is performed to obtain an evaluation element, and a feature input matrix is generated based on the evaluation element;

[0037] Based on the feature input matrix, a heat analysis model is used to calculate the heat data of each target value-added service;

[0038] Based on the heat data and the user rating matrix, a popularity analysis is performed to obtain value-added service popularity analysis data.

[0039] In addition, the present application also provides a value-added service information analysis management device for photovoltaic products, the device comprises:

[0040] An information input module: for the backend server to establish a communication connection with each user terminal based on identity authentication, and receive user basic information and binding photovoltaic product information input by each user terminal;

[0041] A user profile creation module: for data verification of the user basic information and the binding photovoltaic product information, obtaining a data verification result, and creating a corresponding user profile based on the data verification result;

[0042] A user portrait construction module: for obtaining browsing behavior information of each user on several value-added services of the binding photovoltaic product, and constructing a user portrait using label confidence analysis based on the browsing behavior information;

[0043] The value-added service recommendation module is configured to analyze value-added service demands of each user based on the user portrait and the user profile, obtain corresponding value-added service demand data, generate a recommended value-added service list corresponding to the binding photovoltaic product of each user based on the value-added service demand data, and send the recommended value-added service list to each user terminal.

[0044] The benefit simulation prediction module is configured to obtain a target value-added service determined by each user in the recommended value-added service list, perform benefit simulation prediction on the target value-added service determined by each user based on a Markov chain, and obtain benefit simulation prediction data.

[0045] The service popularity analysis and report generation module is configured to perform popularity analysis based on the target value-added service determined by each user, obtain value-added service popularity analysis data, generate a target analysis report based on the benefit simulation prediction data and the value-added service popularity analysis data, and display the target analysis report in a corresponding visual component.

[0046] In addition, the present application further provides an electronic device, which comprises a processor and a memory, wherein the memory is configured to store instructions, and the processor is configured to call the instructions in the memory, so that the electronic device executes the photovoltaic product value-added service information analysis management method described above.

[0047] In addition, the present application further provides a computer readable storage medium, which is characterized by storing computer instructions, and when the computer instructions run on an electronic device, the electronic device executes the photovoltaic product value-added service information analysis management method described above.

[0048] In this embodiment of the invention, basic information and bound photovoltaic product information entered by the user terminal are validated, and corresponding user profiles are created based on the validation results to ensure the accuracy and completeness of the user profile creation. User profiles are constructed using tag confidence analysis based on the user's browsing behavior information of several value-added services related to the bound photovoltaic products, making the constructed user profiles more comprehensive and accurate, and able to reflect the user's specific situation. Value-added service demand data corresponding to each user is generated based on potential demand analysis data, recommendation popularity data, and interest change data generated from the user profiles and user profiles, combined with initial value-added service demand data. This avoids excessive deviation between the obtained value-added service demand data and the user's actual needs. A recommended value-added service list corresponding to each user's bound photovoltaic products is generated based on the value-added service demand data, ensuring that the recommended value-added services better match the user's actual situation. Benefit simulation prediction is performed on the target value-added services determined by each user in the recommended value-added service list based on Markov chains, obtaining more accurate benefit simulation prediction data that reflects the benefits brought by using value-added services. Based on the popularity analysis of the target value-added services determined by each user, a target analysis report is generated based on the benefit simulation prediction data and the popularity analysis data of the value-added services. This makes the generated analysis report more comprehensive and accurate, thereby enabling us to understand the specific usage and user experience of each value-added service. Attached Figure Description

[0049] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0050] Figure 1 This is a flowchart illustrating the value-added service information analysis and management method for photovoltaic products in an embodiment of the present invention;

[0051] Figure 2 This is a flowchart illustrating a method for analyzing and managing value-added service information of photovoltaic products according to another embodiment of the present invention.

[0052] Figure 3 This is a schematic diagram of the structural composition of the value-added service information analysis and management device for photovoltaic products in an embodiment of the present invention;

[0053] Figure 4 This is a schematic diagram of the structural composition of the electronic device in an embodiment of the present invention. Detailed Implementation

[0054] With reference to the accompanying drawings, the technical solutions in the embodiments of the present application will be described clearly and completely. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all the other embodiments obtained by those skilled in the art without creative work fall within the protection scope of the present application.

[0055] Embodiment one

[0056] Please refer to Figure 1 , Figure 1 FIG. 1 is a flowchart of a photovoltaic product value-added service information analysis management method in an embodiment of the present application. The method comprises the following steps.

[0057] S11: The back-end server establishes a communication connection with each user terminal based on identity authentication, and receives the user basic information and the bound photovoltaic product information entered by each user terminal;

[0058] In the specific implementation process of the present application, the back-end server establishes a communication connection with each user terminal based on identity authentication, which comprises: the back-end server receives the authentication request sent by each user terminal, generates an identity based on the authentication request, and generates a signed identity certificate based on the identity certificate model; the signed identity certificate is authenticated based on a differential confusion mechanism, and after the signed identity certificate is authenticated, the back-end server establishes a communication connection with the corresponding user terminal.

[0059] Specifically, each user sends an authentication request to the backend server in the user's own user terminal, the backend server receives the authentication request sent by each user terminal, parses the authentication request, obtains an identity identifier, generates a certificate signature request according to the identity identifier combined with the certificate identifier, performs public key authentication based on the certificate signature request, generates a corresponding sub-signature certificate using a sub-signature generation algorithm according to the public key authentication result, generates a user behavior certificate using a certificate model according to the authentication request, generates a bit fixed length hash value using a hash algorithm using all sub-signature certificates, identity identifiers and user behavior certificates, and performs asymmetric encryption based on the bit fixed length hash value to obtain a signed identity certificate. The signature identity certificate is authenticated based on the differential confusion mechanism, the identity coding information of the signature identity certificate is extracted to obtain the identity coding information, the differential confusion feature information in the identity coding information is extracted, the differential confusion feature component is generated according to the differential confusion feature information, the differential confusion probability of the differential confusion feature component is calculated, the first data and the second data are generated according to the differential confusion probability, the first data and the second data are matched, and the result of identity authentication is obtained according to the matching result, that is, the authentication result of the signature identity certificate is obtained. After the signature identity certificate is authenticated, the backend server establishes a communication connection with the corresponding user terminal, receives the user basic information and the binding photovoltaic product information entered by each user terminal, the user basic information includes name, contact information, location information, etc., and the binding photovoltaic product information includes the equipment type, purchase time, use time and unique identifier of the photovoltaic product purchased by the user.

[0060] S12: data verification is performed on the user basic information and the binding photovoltaic product information, a data verification result is obtained, and a corresponding user profile is created based on the data verification result.

[0061] In the specific implementation process of the present application, the data verification on the user basic information and the binding photovoltaic product information to obtain the data verification result comprises: performing data verification calculation on the user basic information and the binding photovoltaic product information based on a data verification algorithm to obtain a data verification value; generating a plurality of sub-numbers based on the user basic information and the binding photovoltaic product information, and generating a plurality of decomposition coefficients based on the public verification code and each sub-number; generating a corresponding synthetic number based on each decomposition coefficient and the public verification code, and performing data verification on the user basic information and the binding photovoltaic product information based on the synthetic number and the data verification value to obtain the data verification result.

[0062] Specifically, the user basic information and the binding photovoltaic product information are subjected to data verification calculation based on a data verification algorithm, the data verification algorithm is obtained through a preset data verification mechanism, so as to calculate a data verification value and obtain the data verification value. A plurality of sub-numbers are generated based on the user basic information and the binding photovoltaic product information, that is, the user basic information and the binding photovoltaic product information are grouped to obtain a plurality of sub-numbers, the sub-number is a sub-item divided in a data set, and a plurality of decomposition coefficients are generated based on a public verification code and each sub-number. The public verification code is obtained in a public data warehouse, and the decomposition coefficient corresponding to each sub-number is calculated by using the public verification code. The corresponding synthetic number is generated based on each decomposition coefficient and the public verification code, the generation of the synthetic number is carried out through a preset synthetic number calculation formula, and the user basic information and the binding photovoltaic product information are subjected to data verification based on the synthetic number and the data verification value. Each synthetic number is verified, whether each synthetic number is equal is verified, and the data verification value and a preset matching value are verified. If both of them are verified, it is indicated that the data transmission is complete. If both of them are not verified or one of them is not verified, it is determined that the transmission data is incomplete, there is data omission or the data is threatened by damage. The relevant management personnel is informed by the back-end server to repair the system, and then a prompt information is sent to inform the user to re-enter the data, so as to obtain a data verification result. The data verification result can effectively detect the problems faced by the data in the transmission process, and ensure the integrity of the entered data. The corresponding user profile is created based on the data verification result, that is, after the data verification is passed, the field is automatically matched and imported into the database to create the user profile.

[0063] S13: Obtain the browsing behavior information of each user on the plurality of value-added services of the binding photovoltaic product, and construct a user portrait based on the browsing behavior information by using label confidence analysis.

[0064] In the specific implementation process of the application, the user portrait is constructed based on the browsing behavior information by using label confidence analysis, including: performing effective duration analysis based on the browsing behavior information to obtain an effective browsing duration, and performing interest degree analysis of the browsing behavior by using a scoring function based on the effective browsing duration to obtain interest degree analysis data; performing browsing frequency analysis of a value-added service category based on the browsing behavior information to obtain a target browsing frequency, and generating a browsing category weight by using the target browsing frequency based on a browsing category historical weight; performing feature extraction on the browsing behavior information to obtain a target browsing feature, and performing semantic similarity calculation and intent recognition processing based on the target browsing feature to obtain intent label data and intent label confidence; and constructing a user portrait based on the interest degree analysis data, the browsing category weight, the intent label data and the intent label confidence.

[0065] Specifically, the browsing behavior information of each user on the value-added services bound to the photovoltaic product is acquired, the browsing behavior information includes operation data, browsing duration and online consultation of the value-added services browsed by the user, the value-added services include photovoltaic product hosting service and photovoltaic housekeeper service, effective duration analysis is performed based on the browsing behavior information, the browsing duration of the value-added services browsed in the browsing behavior information is extracted, if the browsing duration does not exceed a first preset duration threshold, the browsing duration is invalidated and removed, if the browsing duration exceeds a second preset duration threshold, it is indicated that the user may be in an offline state, the browsing duration cannot be used as effective browsing duration, until the browsing duration of each value-added service is compared, the effective browsing duration can be obtained. Interest degree analysis of the browsing behavior is performed based on the effective browsing duration using a scoring function, the effective browsing value-added services are determined according to the effective browsing duration, and the target interest degree of each effective browsing value-added service is calculated according to the scoring function using the effective browsing duration, that is, the interest degree analysis data is obtained. The browsing times of the value-added service categories are analyzed based on the browsing behavior information, that is, the browsing times of each value-added service category browsed by the user are counted, the target browsing times are obtained, and the browsing category weight is generated based on the target browsing times using the browsing category historical weight. The features of the browsing behavior information are extracted, the online consultation information in the browsing behavior information is embedded and coded to obtain an embedded vector, the embedded vector is semantically coded to obtain a coded vector, the coded vector is globally pooled to obtain a pooled vector, the pooled vector is linearly activated and fully connected using a feedforward neural network to obtain target browsing features, that is, target consultation information text features are obtained, semantic similarity calculation and intent recognition processing are performed based on the target browsing features, the target browsing features are vectorized to obtain target browsing feature vectors, the target browsing feature vectors are vectorized and nonlinearly mapped to obtain transformed semantic vectors and mapped semantic vectors, the semantic channel weight is calculated according to the transformed semantic vectors and the mapped semantic vectors, the intent label and the intent label confidence are output based on the semantic feature weight using a knowledge graph embedding model combined with a prediction function, the intent label is the value-added service type label consulted by the user, that is, the intent label data and the intent label confidence are obtained. The user portrait is constructed based on the interest degree analysis data, the browsing category weight, the intent label data and the intent label confidence.

[0066] S14: Based on the user portrait and the user profile, the value-added service demand analysis of each user is performed, the corresponding value-added service demand data is obtained, and the recommended value-added service list corresponding to the bound photovoltaic product of each user is generated based on the value-added service demand data, and the recommended value-added service list is sent to each user terminal.

[0067] In the implementation of the present application, the value-added service demand analysis of each user based on the user portrait and user profile is performed to obtain corresponding value-added service demand data, and a recommended value-added service list corresponding to the bound photovoltaic product of each user is generated based on the value-added service demand data, including: performing initial value-added service demand analysis based on the user profile of each user to obtain initial value-added service demand data; performing collaborative filtering based on the user portrait of each user to obtain a collaborative filtering result; using latent demand analysis based on the collaborative filtering result to obtain latent demand analysis data, and using outlier data analysis based on the latent demand analysis data to perform recommendation heat analysis of value-added services to obtain recommendation heat data; using interest change analysis based on the collaborative filtering result to obtain interest change data, and generating corresponding value-added service demand data of each user based on the initial value-added service demand data, the latent demand analysis data, the recommendation heat data and the interest change data; and performing matching and sorting in a plurality of value-added services based on the value-added service demand data to obtain a recommended value-added service list corresponding to the bound photovoltaic product of each user.

[0068] Specifically, initial value-added service demand analysis is performed based on the user profiles of the users, i.e., initial value-added services are matched according to the bound photovoltaic product types in the user profiles and the addresses of the users to obtain initial value-added service demand data. Collaborative filtering is performed based on the user portraits of the users. Collaborative filtering is a commonly used technique in recommendation systems and is mainly used to generate personalized recommendations according to the behaviors and preferences of users and the information of other users. Similar users are matched according to the user portraits, and the selected purchase history of the value-added services by the similar users is obtained to filter the value-added services that the users are likely to be interested in, i.e., to obtain a collaborative filtering result. Latent demand analysis is performed based on the collaborative filtering result, i.e., latent demand analysis of value-added services is performed according to the selected value-added services that the users are likely to be interested in and the intent label data in the user portraits to obtain latent demand analysis data. Recommendation heat analysis of value-added services is performed based on the latent demand analysis data using outlier data analysis. A recommendation index of each value-added service of the latent demand is obtained according to the latent demand analysis data. The mean and standard deviation of the recommendation index are calculated. The degree of outlying is calculated according to the mean and standard deviation of the recommendation index. The recommendation heat is determined according to the calculated degree of outlying. Recommendation heat data is obtained. Interest change analysis is performed using an interest change analysis model based on the collaborative filtering result. Value-added service interest data of the users in the historical time periods in the user management system is obtained. An interest heat map is constructed based on the value-added service interest data. The interest change analysis can be performed prospectively through the heat map. A user interest migration process model is obtained by modeling the user interest migration process according to the value-added service interest data of each time period. The transfer probability of the user interest points is calculated based on the user interest migration model. The user interest migration features are obtained according to the transfer probability of the user interest points. The interest change model is constructed according to the user interest migration features and the interest heat map. Interest change analysis is performed using the interest change analysis model according to the collaborative filtering result in combination with the user portraits. Interest change data is obtained. The value-added service demand data corresponding to each user is generated based on the latent demand analysis data, the recommendation heat data, and the interest change data in combination with the initial value-added service demand data. Matching and sorting are performed in the several value-added services based on the value-added service demand data, i.e., the required value-added services are selected from the several value-added services according to the value-added service demand data, and the selected value-added services are sorted according to the value-added service demand data. A recommended value-added service list corresponding to the bound photovoltaic products of each user is obtained. The recommended value-added service list is sent to each user terminal.

[0069] S15: Obtain the target value-added service determined by each user in the recommended value-added service list. Perform benefit simulation prediction on the target value-added service determined by each user based on a Markov chain to obtain benefit simulation prediction data.

[0070] In the implementation of the present application, the benefit simulation prediction of the target value-added service determined for each user based on the Markov chain obtains benefit simulation prediction data, including: obtaining historical benefit record data and historical user value-added service conversion data, and generating a time-series-data distribution chain based on the historical benefit record data; defining a state space and a state transition matrix based on the historical user value-added service conversion data, and determining a state transition probability function based on the state space and the state transition matrix; optimizing the state transition probability function based on an adaptive adjustment mechanism and a Bayesian estimation method to obtain an optimized state transition probability function; constructing a Markov chain based on the optimized state transition probability function and the time-series-data distribution chain, and generating a benefit simulation prediction model using a recurrent neural network based on the Markov chain, and performing benefit simulation prediction of the target value-added service determined for each user based on the benefit simulation prediction model to obtain benefit simulation prediction data.

[0071] Specifically, each user selects a value-added service desired by the user in a recommended value-added service list, and then purchases the value-added service. The user terminal sends data to the background server to obtain a target value-added service determined by each user in the recommended value-added service list, obtain historical benefit record data and historical user value-added service conversion data, the historical benefit record data includes benefit data recorded over time after each user purchases a value-added service in a past time period, the historical user value-added service conversion data includes situation data of a user converting another value-added service after purchasing a value-added service in the past, and a time-series-data distribution chain is generated based on the historical benefit record data. Time-series distribution information is extracted according to the historical benefit record data to obtain the time-series distribution information. Time-series chaos analysis and multi-dimensional phase space reconstruction are performed according to the time-series distribution information to obtain a benefit time-series change matrix, and the time-series-data distribution chain is constructed according to the benefit time-series change matrix. A state space and a state transition matrix are defined based on the historical user value-added service conversion data, and a state transition probability function is determined based on the state space and the state transition matrix. The state transition probability function is optimized based on an adaptive adjustment mechanism and a Bayesian estimation method, a weighted factor is introduced to adjust the state transition probability function, a weighted state transition probability function is obtained, the weighted state transition probability function is updated based on the adaptive adjustment mechanism, an updated weighted state transition probability function is obtained, and the updated weighted state transition probability function is improved and optimized based on the Bayesian estimation method to obtain an optimized state transition probability function. A Markov chain is constructed based on the optimized state transition probability function and the time-series-data distribution chain, the constructed Markov chain is more reliable, can reveal the dynamic characteristics and change rules of benefits over time, and a benefit simulation prediction model is generated based on the Markov chain using a recurrent neural network. The target value-added service determined by each user is simulated and predicted based on the benefit simulation prediction model to obtain benefit simulation prediction data, and the obtained benefit simulation prediction data is more accurate.

[0072] S16: Based on the target value-added service determined by each user, popularity analysis is performed to obtain value-added service popularity analysis data, and a target analysis report is generated based on the benefit simulation prediction data and the value-added service popularity analysis data. The target analysis report is displayed in a corresponding visual component.

[0073] In the implementation of the present application, the popularity analysis based on the target value-added services determined by each user obtains value-added service popularity analysis data, including: obtaining tracking state data of the target value-added services determined by each user, generating a user rating matrix based on the tracking state data using a conditional variational autoencoder; performing element extraction based on the tracking state data to obtain evaluation elements and generating a feature input matrix based on the evaluation elements; calculating the heat data of each target value-added service using a heat analysis model based on the feature input matrix; and performing popularity analysis based on the heat data and the user rating matrix to obtain value-added service popularity analysis data.

[0074] Specifically, the tracking state data of the target value-added services determined by each user is obtained, and the tracking state data is the tracking data of the subsequent state of the target value-added services. A user rating matrix is generated based on the tracking state data using a conditional variational autoencoder. Element extraction is performed based on the tracking state data to obtain evaluation elements, including service conversion time, service stop time, and service management data. The tracking state data is input into a layer-by-layer loss compensation encoder for dimension reduction and feature extraction to obtain target features. Element extraction is performed on the target features based on a loss compensation deep neural network, and a feature input matrix is generated based on the evaluation elements. The heat data of each target value-added service is calculated using a heat analysis model based on the feature input matrix. The heat analysis model uses a generative adversarial network model. Popularity analysis is performed based on the heat data and the user rating matrix. The corresponding weight coefficients are used to calculate the popularity based on the heat data and the user rating matrix to obtain value-added service popularity analysis data. The benefit simulation prediction data and the value-added service popularity analysis data are used to generate a target analysis report. The benefit simulation prediction data and the value-added service popularity analysis data are input into a report template to automatically generate a target analysis report. The target analysis report is displayed in a corresponding visual component for management personnel to view, so that the management personnel can intuitively understand the value-added service situation of the photovoltaic product to make decisions for subsequent service adjustments.

[0075] In the embodiment of the present application, the basic information and the binding photovoltaic product information entered by the user terminal are subjected to data verification, and a corresponding user profile is created based on the data verification result, so as to ensure the accuracy and integrity of the user profile creation. The user portrait is constructed by using tag confidence analysis based on the browsing behavior information of the user on a plurality of value-added services of the binding photovoltaic product, so that the constructed user portrait is more comprehensive and accurate, and can reflect the specific situation of the user. The value-added service demand data corresponding to each user is generated based on the potential demand analysis data, the recommendation popularity data and the interest change data generated by the user profile and the user portrait, in combination with the initial value-added service demand data, so as to avoid that the deviation of the obtained value-added service demand data from the actual demand of the user is too large. The recommended value-added service list corresponding to the binding photovoltaic product of each user is generated based on the value-added service demand data, so that the recommended value-added service can better fit the actual situation of the user. The benefit simulation prediction is performed on the target value-added service of each user in the recommended value-added service list based on Markov chain, so that more accurate benefit simulation prediction data can be obtained, which reflects the income brought by the use of the value-added service. The popularity analysis is performed on the target value-added service determined by each user, and the target analysis report is generated based on the benefit simulation prediction data and the value-added service popularity analysis data, so that the generated analysis report is more comprehensive and accurate, and thus the specific use situation and use experience of the user on each value-added service can be known.

[0076] Embodiment two

[0077] Please refer to Figure 2 , Figure 2 is a flowchart of a photovoltaic product value-added service information analysis management method in another embodiment of the present application. The method comprises:

[0078] S201: The back-end server establishes a communication connection with each user terminal based on identity authentication, and receives the user basic information and the binding photovoltaic product information entered by each user terminal;

[0079] S202: The user basic information and the binding photovoltaic product information are subjected to data verification, a data verification result is obtained, and a corresponding user profile is created based on the data verification result;

[0080] S203: The browsing behavior information of each user on a plurality of value-added services of the binding photovoltaic product is obtained, and a user portrait is constructed by using tag confidence analysis based on the browsing behavior information;

[0081] S204: The value-added service demand analysis of each user is performed based on the user portrait and the user profile, corresponding value-added service demand data is obtained, and a recommended value-added service list corresponding to the binding photovoltaic product of each user is generated based on the value-added service demand data, and the recommended value-added service list is sent to each user terminal;

[0082] S205: Obtain the target value-added service determined by each user in the recommended value-added service list, obtain the historical benefit record data and historical user value-added service conversion data, and generate a time-series-data distribution chain based on the historical benefit record data;

[0083] S206: Define a state space and a state transition matrix based on the historical user value-added service conversion data, and determine a state transition probability function based on the state space and the state transition matrix;

[0084] S207: Optimize the state transition probability function based on an adaptive adjustment mechanism and a Bayesian estimation method to obtain an optimized state transition probability function;

[0085] S208: Construct a Markov chain based on the optimized state transition probability function and the time-series-data distribution chain, generate a benefit simulation prediction model using a recurrent neural network based on the Markov chain, perform benefit simulation prediction on the target value-added service determined by each user based on the benefit simulation prediction model, and obtain benefit simulation prediction data;

[0086] S209: Perform popularity analysis based on the target value-added service determined by each user, obtain value-added service popularity analysis data, generate a target analysis report based on the benefit simulation prediction data and the value-added service popularity analysis data, and display the target analysis report in the corresponding visual component.

[0087] In the embodiment of the present application, the basic information and the binding photovoltaic product information entered by the user terminal are subjected to data verification, and a corresponding user profile is created based on the data verification result, so as to ensure the accuracy and integrity of the user profile creation. The user portrait is constructed based on the browsing behavior information of the user on a plurality of value-added services of the binding photovoltaic product by using the label confidence analysis, so that the constructed user portrait is more comprehensive and accurate, and can reflect the specific situation of the user. The value-added service demand data corresponding to each user is generated based on the potential demand analysis data, the recommendation popularity data and the interest change data generated by the user profile and the user portrait, in combination with the initial value-added service demand data, so as to avoid that the deviation of the obtained value-added service demand data from the actual demand situation of the user is too large. The recommended value-added service list corresponding to the binding photovoltaic product of each user is generated based on the value-added service demand data, so that the recommended value-added service can better fit the actual situation of the user. The benefit simulation prediction of the target value-added service of each user in the recommended value-added service list is performed based on the Markov chain, so that more accurate benefit simulation prediction data can be obtained, and the benefits brought by the use of the value-added service are reflected. The popularity analysis of the target value-added service determined by each user is performed, and the target analysis report is generated based on the benefit simulation prediction data and the value-added service popularity analysis data, so that the generated analysis report is more comprehensive and accurate, and thus the specific use situation and use experience of the user on each value-added service can be known.

[0088] Embodiment three

[0089] Please refer to Figure 3 , Figure 3 is a structural composition schematic diagram of the value-added service information analysis management device of the photovoltaic product in the embodiment of the present application. The device comprises:

[0090] The information entry module 31 is used for the back-end server to establish a communication connection with each user terminal based on identity authentication, and receive the user basic information and the binding photovoltaic product information entered by each user terminal.

[0091] The user profile creation module 32 is used for performing data verification on the user basic information and the binding photovoltaic product information, obtaining a data verification result, and creating a corresponding user profile based on the data verification result.

[0092] The user portrait construction module 33 is used for obtaining the browsing behavior information of each user on a plurality of value-added services of the binding photovoltaic product, and constructing a user portrait based on the browsing behavior information by using label confidence analysis.

[0093] The value-added service recommendation module 34 is configured to analyze value-added service demands of each user based on the user portrait and the user profile, obtain corresponding value-added service demand data, generate a recommended value-added service list corresponding to the bound photovoltaic product of each user based on the value-added service demand data, and send the recommended value-added service list to each user terminal.

[0094] The benefit simulation prediction module 35 is configured to obtain a target value-added service determined by each user in the recommended value-added service list, perform benefit simulation prediction on the target value-added service determined by each user based on a Markov chain, and obtain benefit simulation prediction data.

[0095] The service popularity analysis and report generation module 36 is configured to perform popularity analysis based on the target value-added service determined by each user, obtain value-added service popularity analysis data, and generate a target analysis report based on the benefit simulation prediction data and the value-added service popularity analysis data, and display the target analysis report in a corresponding visual component.

[0096] In the embodiment of the present application, the implementation of the device item can refer to the implementation of the method item described above, which will not be repeated here.

[0097] In the embodiment of the present application, the basic information and the bound photovoltaic product information entered by the user terminal are subjected to data verification, and a corresponding user profile is created based on the data verification result, so as to ensure the accuracy and integrity of the user profile creation. The user portrait is constructed based on the browsing behavior information of the user on a plurality of value-added services of the bound photovoltaic product using label confidence analysis, so that the constructed user portrait is more comprehensive and accurate, and can reflect the specific situation of the user. The value-added service demand data corresponding to each user is generated based on the potential demand analysis data, the recommendation popularity data and the interest change data generated by the user profile and the user profile, and the initial value-added service demand data, so as to avoid that the deviation of the obtained value-added service demand data from the actual demand of the user is too large. The recommended value-added service list corresponding to the bound photovoltaic product of each user is generated based on the value-added service demand data, so that the recommended value-added service can better fit the actual situation of the user. The benefit simulation prediction data of each user is obtained by performing benefit simulation prediction on the target value-added service determined by each user in the recommended value-added service list based on the Markov chain, which reflects the benefits brought by the use of value-added services. The target analysis report is generated based on the benefit simulation prediction data and the value-added service popularity analysis data, so that the generated analysis report is more comprehensive and accurate, and thus the specific use and experience of each value-added service by the user can be known.

[0098] The computer readable storage medium provided by the embodiment of the present application stores a computer program, and the program is executed by a processor to realize the photovoltaic product value-added service information analysis management method of any one of the above embodiments. The computer readable storage medium includes but is not limited to any type of disk (including floppy disk, hard disk, optical disk, CD-ROM, and magneto-optical disk), ROM (Read-Only Memory), RAM (Random AcceSS Memory), EPROM (EraSable Programmable Read-Only Memory), EEPROM (Electrically EraSable Programmable Read-Only Memory), flash memory, magnetic card or optical card. That is, the storage device includes any medium that stores or transmits information in a form capable of being read by a device (for example, a computer, a mobile phone), which can be a read-only memory, a magnetic disk or an optical disk, etc.

[0099] Embodiment four

[0100] Please refer to Figure 4 , Figure 4 is a structural composition schematic diagram of an electronic device in the embodiment of the present application.

[0101] The embodiment of the present application further provides an electronic device, as shown in Figure 4 , the electronic device includes a memory 41, a processor 43, and a computer program 42 stored in the memory 41 and executable on the processor 43. Those skilled in the art can understand that Figure 3The electronic device shown does not constitute a limitation on all devices, and can include more or fewer components than shown, or combine some components. The memory 41 can be used to store computer programs 42 and various functional modules, and the processor 43 runs the computer programs 42 stored in the memory 41 to perform various functional applications and data processing of the device. The memory can be an internal memory or an external memory, or include both the internal memory and the external memory. The internal memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, or random access memory. The external memory can include a hard disk, a floppy disk, a ZIP disk, a USB disk, a magnetic tape, etc. The processor 43 can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor, a single-chip processor, or the processor 43 can also be any conventional processor, etc. The processor and the memory disclosed in the present application include but are not limited to these types of processors and memories. The processor and the memory disclosed in the present application are only examples and are not limited.

[0102] As an embodiment, the electronic device includes one or more processors 43, a memory 41, and one or more computer programs 42, wherein the one or more computer programs 42 are stored in the memory 41 and configured to be executed by the one or more processors 43, and the one or more computer programs 42 are configured to perform the value-added service information analysis management method of the photovoltaic product in any one of the above embodiments. For the specific implementation process, please refer to the above embodiments, which will not be repeated here.

[0103] In the embodiment of the present application, the basic information and the binding photovoltaic product information entered by the user terminal are subjected to data verification, and a corresponding user profile is created based on the data verification result, so as to ensure the accuracy and integrity of the user profile creation. The user portrait is constructed based on the browsing behavior information of the user on a plurality of value-added services of the binding photovoltaic product by using the tag confidence analysis, so that the constructed user portrait is more comprehensive and accurate, and can reflect the specific situation of the user. The value-added service demand data corresponding to each user is generated based on the potential demand analysis data, the recommendation popularity data and the interest change data generated by the user profile and the user portrait, and the initial value-added service demand data, so as to avoid that the deviation of the obtained value-added service demand data from the actual demand situation of the user is too large. The recommended value-added service list corresponding to the binding photovoltaic product of each user is generated based on the value-added service demand data, so that the recommended value-added service can better fit the actual situation of the user. The benefit simulation prediction of the target value-added service of each user in the recommended value-added service list is performed based on the Markov chain, so that more accurate benefit simulation prediction data can be obtained, and the benefits brought by the use of the value-added service are reflected. The popularity analysis of the target value-added service determined by each user is performed, and the target analysis report is generated based on the benefit simulation prediction data and the value-added service popularity analysis data, so that the generated analysis report is more comprehensive and accurate, and thus the specific use situation and use experience of the user on each value-added service can be known.

[0104] In addition, the photovoltaic product value-added service information analysis management method and the related device provided by the embodiment of the present application are described in detail above, and the principles and implementation modes of the present application are described by using specific examples in this paper. The above embodiment description is only used to help understand the method of the present application and its core idea; at the same time, for those skilled in the art, according to the idea of the present application, the specific implementation mode and application range will be changed, and the above description should not be understood as the limitation of the present application.

Claims

1. A method of analyzing and managing value-added service information of a photovoltaic product, characterized by, The method comprises: The backend server establishes a communication connection with each user terminal based on identity authentication, and receives user basic information and binding photovoltaic product information entered by each user terminal; Data verification is performed on the user basic information and binding photovoltaic product information to obtain a data verification result, and a corresponding user profile is created based on the data verification result; Obtain the browsing behavior information of each user on the binding photovoltaic product of the user, and construct the user portrait based on the browsing behavior information using the label confidence analysis; Based on the user portrait and user profile, the demand analysis of each user's value-added service is carried out, the corresponding value-added service demand data is obtained, and the recommended value-added service list corresponding to the binding photovoltaic product of each user is generated based on the value-added service demand data, and the recommended value-added service list is sent to each user terminal; Obtain the target value-added service determined by each user in the recommended value-added service list, and perform benefit simulation prediction on the target value-added service determined by each user based on Markov chain to obtain benefit simulation prediction data; Based on the target value-added service determined by each user, the popularity analysis data of the value-added service is obtained, and the target analysis report is generated based on the benefit simulation prediction data and the popularity analysis data of the value-added service, and the target analysis report is displayed in the corresponding visual component.

2. The method of claim 1, wherein the value-added service information of the photovoltaic product is analyzed and managed. The backend server establishes a communication connection with each user terminal based on identity authentication, comprising: The backend server receives an authentication request sent by each user terminal, generates an identity based on the authentication request, and generates a signed identity certificate based on the identity using a certificate model; The signed identity certificate is authenticated based on a differential confusion mechanism, and after the signed identity certificate is authenticated, the backend server establishes a communication connection with the corresponding user terminal.

3. The method of claim 1, wherein the value-added service information of the photovoltaic product is analyzed and managed. The data verification of the user basic information and binding photovoltaic product information is carried out to obtain the data verification result, comprising: Based on the data verification algorithm, the data verification calculation of the user basic information and binding photovoltaic product information is carried out to obtain the data verification value; Based on the user basic information and binding photovoltaic product information, a plurality of sub-numbers are generated, and a plurality of decomposition coefficients are generated based on the public verification code and each sub-number; Based on each decomposition coefficient and the public verification code, a corresponding synthetic number is generated, and the data verification of the user basic information and binding photovoltaic product information is carried out based on the synthetic number and the data verification value to obtain the data verification result.

4. The method of claim 1, wherein the value-added service information of the photovoltaic product is analyzed and managed. The user portrait is constructed based on the browsing behavior information using the label confidence analysis, comprising: Based on the browsing behavior information, the effective duration analysis is carried out to obtain the effective browsing duration, and the interest degree analysis of the browsing behavior is carried out based on the effective browsing duration using the scoring function to obtain the interest degree analysis data; Based on the browsing behavior information, the browsing times analysis of the value-added service category is carried out to obtain the target browsing times, and the browsing category weight is generated based on the target browsing times using the browsing category historical weight; The browsing behavior information is subjected to feature extraction to obtain target browsing features, and semantic similarity calculation and intent recognition processing are performed based on the target browsing features to obtain intent label data and intent label confidence; Based on the interest analysis data, browsing category weight, intent label data and intent label confidence, a user portrait is constructed.

5. The method of claim 1, wherein the method further comprises: The user portrait and user profile are used to analyze the value-added service demand of each user to obtain corresponding value-added service demand data, and a recommended value-added service list corresponding to the binding photovoltaic product of each user is generated based on the value-added service demand data, including: Based on the user profile of each user, initial value-added service demand analysis is performed to obtain initial value-added service demand data; Collaborative filtering is performed based on the user profile of each user to obtain a collaborative filtering result; Based on the collaborative filtering result, latent demand analysis is performed to obtain latent demand analysis data, and a recommended heat analysis of value-added services is performed based on the latent demand analysis data using outlier data analysis to obtain recommended heat data; Based on the collaborative filtering result, interest change analysis is performed using an interest change analysis model to obtain interest change data, and the initial value-added service demand data is combined with the latent demand analysis data, recommended heat data and interest change data to generate value-added service demand data corresponding to each user; Based on the value-added service demand data, matching and sorting are performed among a plurality of value-added services to obtain a recommended value-added service list corresponding to the binding photovoltaic product of each user.

6. The photovoltaic product value-added service information analysis management method according to claim 1, characterized by, The benefit simulation prediction data is obtained by simulating and predicting the benefit of the target value-added service determined for each user based on the Markov chain, including: Obtain historical benefit record data and historical user value-added service conversion data, and generate a time-series-data distribution chain based on the historical benefit record data; Define a state space and a state transition matrix based on the historical user value-added service conversion data, and determine a state transition probability function based on the state space and the state transition matrix; Optimize the state transition probability function based on an adaptive adjustment mechanism and a Bayesian estimation method to obtain an optimized state transition probability function; Construct a Markov chain based on the optimized state transition probability function and the time-series-data distribution chain, and generate a benefit simulation prediction model using a recurrent neural network based on the Markov chain, and simulate and predict the benefit of the target value-added service determined for each user based on the benefit simulation prediction model to obtain benefit simulation prediction data.

7. The photovoltaic product value-added service information analysis management method according to claim 1, characterized by, The popularity analysis data of the value-added service is obtained by analyzing the popularity of the target value-added service determined for each user, including: Obtain tracking state data of the target value-added service determined for each user, and generate a user rating matrix using a conditional variational autoencoder based on the tracking state data; Based on the tracking state data, factor extraction is performed to obtain evaluation factors, and a feature input matrix is generated based on the evaluation factors; The heat data of each target value-added service is calculated using a heat analysis model based on the feature input matrix; The popularity analysis data of the value-added service is obtained by analyzing the popularity based on the heat data and the user rating matrix.

8. An apparatus for analyzing and managing value-added service information of a photovoltaic product, characterized by, The device comprises: An information entry module: for the backend server to establish a communication connection with each user terminal based on identity authentication, and receive user basic information and binding photovoltaic product information entered by each user terminal; A user profile creation module: for data verification on the user basic information and binding photovoltaic product information, obtaining a data verification result, and creating a corresponding user profile based on the data verification result; A user portrait construction module: for obtaining browsing behavior information of each user on several value-added services of the binding photovoltaic product, and constructing a user portrait based on the browsing behavior information using label confidence analysis; A value-added service recommendation module: for analyzing the value-added service demand of each user based on the user portrait and user profile, obtaining corresponding value-added service demand data, and generating a recommended value-added service list corresponding to the binding photovoltaic product of each user based on the value-added service demand data, and sending the recommended value-added service list to each user terminal; A benefit simulation prediction module: for obtaining the target value-added service determined by each user in the recommended value-added service list, and performing benefit simulation prediction on the target value-added service determined by each user based on Markov chain, obtaining benefit simulation prediction data; A service popularity analysis and report generation module: for analyzing the popularity of the target value-added service determined by each user, obtaining value-added service popularity analysis data, and generating a target analysis report based on the benefit simulation prediction data and value-added service popularity analysis data, and displaying the target analysis report in the corresponding visual component. 9.An electronic device comprising a processor and a memory, wherein The memory is used to store instructions, and the processor is used to call the instructions in the memory, so that the electronic device executes the value-added service information analysis management method of the photovoltaic product as claimed in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer instructions, when the computer instructions run on the electronic device, make the electronic device execute the value-added service information analysis management method of the photovoltaic product as claimed in any one of claims 1 to 7.

Images