Value-added service information analysis and management method of photovoltaic product and related device

Abstract

The invention discloses a value-added service information analysis and management method of a photovoltaic product and a related device, and relates to the technical field of data processing, and the method comprises the steps: receiving user basic information and binding photovoltaic product information; performing data verification on the user basic information and the bound photovoltaic product information, and creating a corresponding user file based on a data verification result; based on the browsing behavior information, using label confidence analysis to construct a user portrait; carrying out value-added service demand analysis based on the user portrait and the user file to generate a recommended value-added service list corresponding to the bound photovoltaic product of each user; performing benefit simulation prediction on the target value-added service determined by each user based on the Markov chain; and performing popularity degree analysis based on the target value-added service to generate a target analysis report in combination with the benefit simulation prediction data. According to the invention, the value-added service condition can be analyzed more comprehensively and accurately, and the specific use condition and use experience of the user for each value-added service can be known.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method and related device for analyzing and managing value-added service information of photovoltaic products. Background Art

[0002] With the rapid development of new energy technologies, photovoltaic products have become more and more important in people's lives. As a result, various companies have gradually launched value-added services for photovoltaic products to improve the user experience. At present, in the management of value-added services for photovoltaic products, it is necessary to build user portraits to analyze the value-added services required by users. Usually, statistical analysis is performed through human experience to obtain user portraits, but this method is incomplete and inaccurate, resulting in the inability to accurately analyze the demand for value-added services, so that the recommended value-added services analyzed in the end cannot fit the actual situation of users well. 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, resulting in the inability to effectively generate sufficiently comprehensive and accurate analysis reports, which makes it impossible to effectively understand the specific situation of each value-added service in photovoltaic products, so that the value-added service analysis and management of photovoltaic products fail to achieve the expected results. Summary of the invention

[0003] The purpose of the present invention is to overcome the shortcomings of the prior art. The present invention provides a value-added service information analysis and management method and related devices for photovoltaic products, which can provide more comprehensive and accurate value-added service information analysis and understand the user's specific usage and experience of each value-added service.

[0004] In order to solve the above technical problems, the present invention provides a method for analyzing and managing value-added service information of photovoltaic products, the method comprising:

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

[0006] Performing data verification on the user's basic information and bound photovoltaic product information to obtain a data verification result, and creating a corresponding user profile based on the data verification result;

[0007] Obtaining browsing behavior information of each user for several value-added services bound to photovoltaic products, and constructing a user profile based on the browsing behavior information by using tag confidence analysis;

[0008] Analyze the value-added service needs of each user based on the user portrait and 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;

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

[0010] A popularity analysis is performed based on the target value-added services determined by each user to obtain the 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, and the target analysis report is displayed in the corresponding visualization component.

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

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

[0013] The signature identity certificate is authenticated based on a differential obfuscation mechanism, and after the signature identity certificate is authenticated, the back-end server establishes a communication connection with the corresponding user terminal.

[0014] Optionally, performing data verification on the user basic information and bound photovoltaic product information to obtain a data verification result includes:

[0015] Performing data verification calculation on the user basic information and bound photovoltaic product information based on a data verification algorithm to obtain a data verification value;

[0016] Generate a number of sub-numbers based on the user basic information and bound photovoltaic product information, and generate a number of decomposition coefficients based on the public verification code and each sub-number;

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

[0018] Optionally, constructing a user profile based on the browsing behavior information by using tag confidence analysis includes:

[0019] Performing effective time analysis based on the browsing behavior information to obtain effective browsing time, and performing interest analysis of the browsing behavior using a scoring function based on the effective browsing time to obtain interest analysis data;

[0020] Analyzing the number of views of the value-added service category based on the browsing behavior information to obtain a target number of views, and generating a browsing category weight based on the browsing category history weight using the target number of views;

[0021] Extract features from the browsing behavior information to obtain target browsing features, and perform semantic similarity calculation and intent recognition processing based on the target browsing features to obtain intent label data and intent label confidence;

[0022] A user portrait is constructed based on the interest analysis data, browsing category weights, intent label data and intent label confidence.

[0023] Optionally, the performing of value-added service demand analysis of each user based on the user portrait and user profile to obtain 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, includes:

[0024] Perform initial value-added service demand analysis based on the user profile of each user to obtain initial value-added service demand data;

[0025] Perform collaborative filtering based on the user profile of each user to obtain collaborative filtering results;

[0026] Based on the collaborative filtering results, potential demand analysis is used to obtain potential demand analysis data, and based on the potential demand analysis data, outlier data analysis is used to perform recommendation heat analysis of value-added services to obtain recommendation heat data;

[0027] Based on the collaborative filtering result, an interest change analysis is performed using an interest change analysis model to obtain interest change data, and based on the potential demand analysis data, the recommendation popularity data and the interest change data combined with the initial value-added service demand data, the value-added service demand data corresponding to each user is generated;

[0028] Based on the value-added service demand data, matching and sorting are performed among several value-added services to obtain a list of recommended value-added services corresponding to the bound photovoltaic products of each user.

[0029] Optionally, the benefit simulation prediction of the target value-added service determined by each user based on the Markov chain to obtain benefit simulation prediction data includes:

[0030] Acquire 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;

[0031] Defining a state space and a state transfer matrix based on the historical user value-added service conversion data, and determining a state transfer probability function based on the state space and the state transfer 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] A Markov chain is constructed based on the optimized state transition probability function and the time series-data distribution chain, and a benefit simulation prediction model is generated based on the Markov chain using a recurrent neural network. Based on the benefit simulation prediction model, benefit simulation prediction is performed on the target value-added service determined by each user to obtain benefit simulation prediction data.

[0034] Optionally, performing popularity analysis on the target value-added services determined by each user to obtain the value-added service popularity analysis data includes:

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

[0036] Extracting elements based on the tracking status data to obtain evaluation elements, and generating a feature input matrix based on the evaluation elements;

[0037] Calculate the heat data of each target value-added service using a heat analysis model based on the feature input matrix;

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

[0039] In addition, the present invention also provides a device for analyzing and managing value-added service information of photovoltaic products, the device comprising:

[0040] Information entry module: used for the back-end server to establish a communication connection with each user terminal based on identity authentication, and receive the basic user information and bound photovoltaic product information entered by each user terminal;

[0041] User profile creation module: used to perform data verification on the user's basic information and bound photovoltaic product information, obtain data verification results, and create a corresponding user profile based on the data verification results;

[0042] User portrait building module: used to obtain browsing behavior information of each user for several value-added services bound to photovoltaic products, and build user portraits based on the browsing behavior information by using tag confidence analysis;

[0043] Value-added service recommendation module: used to analyze the value-added service needs of each user based on the user portrait and user profile, obtain corresponding value-added service demand data, and generate a recommended value-added service list corresponding to the bound photovoltaic products of each user based on the value-added service demand data, and send the recommended value-added service list to each user terminal;

[0044] Benefit simulation prediction module: used to obtain the target value-added services determined by each user in the recommended value-added service list, perform benefit simulation prediction on the target value-added services determined by each user based on the Markov chain, and obtain benefit simulation prediction data;

[0045] Service popularity analysis and report generation module: used to perform popularity analysis based on the target value-added services 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 the corresponding visualization component.

[0046] In addition, the present invention also provides an electronic device, which includes 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 above-mentioned value-added service information analysis and management method for photovoltaic products.

[0047] In addition, the present invention also provides a computer-readable storage medium, characterized in that the computer-readable storage medium stores computer instructions, and when the computer instructions are executed on an electronic device, the electronic device executes the above-mentioned value-added service information analysis and management method for photovoltaic products.

[0048] In an embodiment of the present invention, data verification is performed on the basic information and bound photovoltaic product information entered by the user terminal, and a corresponding user profile is created based on the data verification result to ensure the accuracy and completeness of the user profile creation. A user portrait is constructed based on the user's browsing behavior information for several value-added services bound to photovoltaic products using label confidence analysis, so that the constructed user portrait is more comprehensive and accurate and can reflect the specific situation of the user. Based on the potential demand analysis data, recommended heat data and interest change data generated by the user profile and user portrait, combined with the initial value-added service demand data, the value-added service demand data corresponding to each user is generated to avoid excessive deviation between the obtained value-added service demand data and the actual needs of the user. Based on the value-added service demand data, a recommended value-added service list corresponding to the bound photovoltaic products of each user is generated, so that the recommended value-added services can better fit the actual situation of the user. Based on the Markov chain, the benefit simulation prediction of the target value-added services determined by each user in the recommended value-added service list can obtain more accurate benefit simulation prediction data, reflecting the benefits brought by the use of value-added services. Popularity analysis is performed based on the target value-added services determined by each user, and a 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, thereby being able to understand the user's specific usage and experience of each value-added service. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0050] Figure 1 is a flow chart of a method for analyzing and managing value-added service information of photovoltaic products in an embodiment of the present invention;

[0051] Figure 2 is a flow chart of a method for analyzing and managing value-added service information of photovoltaic products in another embodiment of the present invention;

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

[0053] Figure 4 It is a schematic diagram of the structure of an electronic device in an embodiment of the present invention. DETAILED DESCRIPTION

[0054] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0055] Embodiment 1

[0056] See also Figure 1 , Figure 1 : is a flow chart of a method for analyzing and managing value-added service information of photovoltaic products in an embodiment of the present invention, the method comprising:

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

[0058] In the specific implementation process of the present invention, the back-end server establishes a communication connection with each user terminal based on identity authentication, including: the back-end server receives an authentication request sent by each user terminal, generates an identity identifier based on the authentication request, and generates a signed identity certificate based on the identity identifier using a certificate model; the signed identity certificate is authenticated based on a differential obfuscation mechanism, and after the signed identity certificate authentication is passed, 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 his / her user terminal. The backend server receives the authentication request sent by each user terminal, parses the authentication request, obtains the identity identifier, generates a certificate signing request based on the identity identifier combined with the certificate identifier, performs public key authentication based on the certificate signing request, generates a corresponding sub-signature certificate based on the public key authentication result using the sub-signature generation algorithm, generates a user behavior certificate based on the authentication request using the certificate model, generates a hash value of a fixed bit length using the hash algorithm for all sub-signature certificates, identity identifiers and user behavior certificates, and performs asymmetric encryption based on the hash value of the fixed bit length to obtain a signed identity certificate. Perform authentication processing on the signed identity certificate based on the differential obfuscation mechanism, extract identity coding information from the signed identity certificate, obtain identity coding information, extract differential obfuscation feature information from the identity coding information, generate differential obfuscation feature components based on the differential obfuscation feature information, calculate the differential obfuscation probability of the differential obfuscation feature components, generate first data and second data based on the differential obfuscation probability, match the first data and the second data, and obtain the result of identity authentication based on the matching result, that is, obtain the authentication result of the signed identity certificate. After the signature identity certificate authentication is passed, the back-end server establishes a communication connection with the corresponding user terminal, and receives the basic user information and bound photovoltaic product information entered by each user terminal. The basic user information includes name, contact information, location information, etc. The bound photovoltaic product information includes the device type, purchase time, usage time and unique identifier of the photovoltaic product purchased by the user.

[0060] S12: performing data verification on the user's basic information and bound photovoltaic product information to obtain a data verification result, and creating a corresponding user profile based on the data verification result;

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

[0062] Specifically, a data verification calculation is performed on the user basic information and the bound photovoltaic product information based on a data verification algorithm, and a data verification algorithm is obtained through a preset data verification mechanism, thereby calculating a data verification value to obtain a data verification value. A number of sub-numbers are generated based on the user basic information and the bound photovoltaic product information, that is, the user basic information and the bound photovoltaic product information are grouped to obtain a number of sub-numbers, where the sub-numbers are sub-items separated from the data set, and a number of decomposition coefficients are generated based on the public verification code and each sub-number, and the public verification code is obtained in the public data warehouse, and the corresponding decomposition coefficient is calculated for each sub-number using the public verification code. Generate corresponding composite numbers based on each decomposition coefficient and public verification code, generate composite numbers through a preset composite number calculation formula, and perform data verification on the user basic information and bound photovoltaic product information based on the composite number and data verification value, verify each composite number, verify whether each composite number is equal, and verify the data verification value and the preset matching value. If both are verified, it means that the data transmission is complete. If both are not verified or one of them is not verified, it is determined that the transmitted data is incomplete, there is data omission or data is threatened with damage. The back-end server notifies the relevant management personnel to repair the system, and then sends a prompt message to notify the user to re-enter the data to obtain the data verification result, which can effectively detect the problems faced by the data during the transmission process and ensure the integrity of the input data. Create a corresponding user profile based on the data verification result, that is, after the data verification is passed, automatically match the field and import it into the database to create a user profile.

[0063] S13: Obtain browsing behavior information of each user for several value-added services bound to photovoltaic products, and construct a user profile based on the browsing behavior information by using tag confidence analysis;

[0064] In the specific implementation process of the present invention, the user portrait is constructed based on the browsing behavior information using label confidence analysis, including: performing effective time analysis based on the browsing behavior information to obtain effective browsing time, and performing interest analysis on the browsing behavior based on the effective browsing time using a scoring function to obtain interest analysis data; performing browsing times analysis on the value-added service category based on the browsing behavior information to obtain a target browsing times, and generating browsing category weights using the target browsing times based on browsing category history weights; performing feature extraction on the browsing behavior information to obtain target browsing features, and performing semantic similarity calculation and intent recognition processing based on the target browsing features to obtain intent label data and intent label confidence; and constructing a user portrait based on the interest analysis data, browsing category weights, intent label data, and intent label confidence.

[0065] Specifically, the browsing behavior information of each user for several value-added services bound to photovoltaic products is obtained. The browsing behavior information includes the operation data, browsing time and online consultation of the value-added services browsed by the user. The value-added services include photovoltaic product hosting services and photovoltaic housekeeper services. Based on the browsing behavior information, effective time analysis is performed, and the browsing time of the value-added services browsed in the browsing behavior information is extracted. If the browsing time does not exceed the first preset time threshold, the browsing time is invalidated and removed. If the browsing time exceeds the second preset time threshold, it means that the user may be in an on-hook state, and the browsing time cannot be used as an effective browsing time. After the browsing time of each value-added service is compared, the effective browsing time can be obtained. Based on the effective browsing time, the scoring function is used to perform the interest analysis of the browsing behavior, and the effective browsing value-added services are determined according to the effective browsing time. The target interest of each effective browsing value-added service is calculated according to the scoring function, that is, the interest analysis data is obtained. Based on the browsing behavior information, the browsing times of the value-added service categories are analyzed, that is, the browsing times of the users browsing each value-added service category are counted to obtain the target browsing times, and the browsing category weights are generated using the target browsing times based on the browsing category history weights. Feature extraction is performed on the browsing behavior information, the online consultation information in the browsing behavior information is embedded and encoded to obtain an embedding vector, the embedded vector is semantically encoded to obtain an encoding vector, the encoding vector is globally pooled to obtain a pooling vector, the pooling vector is linearly activated and fully connected using a feedforward neural network to obtain the target browsing features, that is, the target consulting information text features are obtained, and semantic similarity calculation and intent recognition processing are performed based on the target browsing features, the target browsing features are vectorized to obtain a target browsing feature vector, the target browsing feature vector is vectorized and nonlinearly mapped to obtain a transformed semantic vector and a mapped semantic vector, the semantic channel weights are calculated based on the transformed semantic vector and the mapped semantic vector, and the intention label and the intention label confidence are output based on the semantic feature weights using the knowledge graph embedding model combined with the prediction function, the intention label is the value-added service type label of the user's intention consultation, that is, the intention label data and the intention label confidence are obtained. A user portrait is constructed based on the interest analysis data, browsing category weights, intent label data and intent label confidence.

[0066] S14: Analyze the value-added service needs of each user based on the user portrait and 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;

[0067] In the specific implementation process of the present invention, the value-added service demand analysis of each user is performed based on the user portrait and user profile 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 an 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 collaborative filtering results; using potential demand analysis based on the collaborative filtering results to obtain potential demand analysis data, and using outlier data analysis based on the potential demand analysis data to perform recommendation heat analysis of the value-added service to obtain recommendation heat data; using an interest change analysis model based on the collaborative filtering results to perform interest change analysis to obtain interest change data, and generating value-added service demand data corresponding to each user based on the potential demand analysis data, the recommended heat data and the interest change data combined with the initial value-added service demand data; matching and sorting among several 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, an initial value-added service demand analysis is performed based on the user profile of each user, that is, the initial value-added service is matched according to the bound photovoltaic product type in the user profile and the user's address, and the initial value-added service demand data is obtained. Collaborative filtering is performed based on the user portrait of each user. Collaborative filtering is a commonly used technology in recommendation systems, which is mainly used to generate personalized recommendations based on the user's behavior and preferences and other users' information. Similar users are matched according to the user portrait, and the selected purchase history of similar users for value-added services is obtained to filter the value-added services that the user may be interested in, that is, to obtain collaborative filtering results. Based on the collaborative filtering results, potential demand analysis is used, that is, potential demand analysis of value-added services is performed based on the filtered value-added services that the user may be interested in combined with the intention label data in the user portrait to obtain potential demand analysis data, and outlier data analysis is used based on the potential demand analysis data to perform recommendation heat analysis of value-added services, obtain the recommendation index of each value-added service of potential demand according to the potential demand analysis data, calculate the mean and standard deviation of the recommendation index, calculate the outlier degree according to the mean and standard deviation of the recommendation index, determine the recommendation heat according to the calculated outlier degree, and obtain recommendation heat data. Based on the collaborative filtering results, the interest change analysis model is used to perform interest change analysis, the value-added service interest data of users in each historical time period in the user management system is obtained, and an interest heat map is constructed based on the value-added service interest data. Through the heat map, the interest change analysis can be performed prospectively, and the user interest migration process is modeled according to the value-added service interest data of each time period to obtain the user interest migration model, and the transfer probability of the user interest point is calculated based on the user interest migration model. The user interest migration characteristics are obtained according to the transfer probability of the user interest point, and the interest change model is constructed according to the user interest migration characteristics and the interest heat map. According to the collaborative filtering results and the user portrait, the interest change analysis model is used to perform interest change analysis to obtain interest change data, and the value-added service demand data corresponding to each user is generated based on the potential demand analysis data, the recommended heat data and the interest change data combined with the initial value-added service demand data. Matching and sorting are performed among several value-added services based on the value-added service demand data, that is, the required value-added services are screened out from several value-added services according to the value-added service demand data, and then the screened value-added services are sorted according to the value-added service demand data, and a recommended value-added service list corresponding to the photovoltaic products bound to each user is obtained, and the recommended value-added service list is sent to each user terminal.

[0069] S15: 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 the Markov chain to obtain benefit simulation prediction data;

[0070] In the specific implementation process of the present invention, the benefit simulation prediction of the target value-added service determined by each user is performed based on the Markov chain to obtain the 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 transfer matrix based on the historical user value-added service conversion data, and determining a state transfer probability function based on the state space and the state transfer matrix; optimizing the state transfer probability function based on an adaptive adjustment mechanism and a Bayesian estimation method to obtain an optimized state transfer probability function; constructing a Markov chain based on the optimized state transfer probability function and the time series-data distribution chain, and generating a benefit simulation prediction model based on the Markov chain using a recurrent neural network, and performing benefit simulation prediction on the target value-added service determined by each user based on the benefit simulation prediction model to obtain benefit simulation prediction data.

[0071] Specifically, each user selects the value-added service he wants in the recommended value-added service list, and then purchases the value-added service. The user terminal sends data to the background server, obtains the target value-added service determined by each user in the recommended value-added service list, obtains historical benefit record data and historical user value-added service conversion data, the historical benefit record data includes the time-varying revenue data recorded after each user purchased the value-added service in the past time period, and the historical user value-added service conversion data includes the situation data of the user converting to another value-added service after purchasing the value-added service in the past, and generates a time series-data distribution chain based on the historical benefit record data, extracts time series distribution information based on the historical revenue record data, obtains time series distribution information, performs time series chaos analysis and multi-dimensional phase space reconstruction based on the time series distribution information, obtains the revenue time series change matrix, and constructs a time series-data distribution chain based on the revenue time series change matrix. Define the state space and state transition matrix based on the historical user value-added service conversion data, and determine the state transition probability function based on the state space and state transition matrix. Based on the adaptive adjustment mechanism and Bayesian estimation method, the state transfer probability function is optimized, a weighting factor is introduced to perform weighted adjustment on the state transfer probability function, and a weighted state transfer probability function is obtained. The weighted state transfer probability function is dynamically updated according to the adaptive adjustment mechanism to obtain an updated weighted state transfer probability function. The updated weighted state transfer probability function is improved and optimized according to the Bayesian estimation method to obtain an optimized state transfer probability function. A Markov chain is constructed based on the optimized state transfer probability function and the time series-data distribution chain, so that the constructed Markov chain can be more reliable and can reveal the dynamic characteristics and change laws of benefits over time. A benefit simulation prediction model is generated based on the Markov chain using a recurrent neural network. Based on the benefit simulation prediction model, benefit simulation prediction is performed on the target value-added services determined by each user to obtain benefit simulation prediction data, so that the obtained benefit simulation prediction data is more accurate.

[0072] S16: Perform popularity analysis based on the target value-added services determined by each user to 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 visualization component.

[0073] In the specific implementation process of the present invention, the popularity analysis is performed based on the target value-added services determined by each user to obtain the value-added service popularity analysis data, including: obtaining the tracking status data of the target value-added services determined by each user, and generating a user rating matrix based on the tracking status data using a conditional variational autoencoder; extracting elements based on the tracking status 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; performing a popularity analysis based on the heat data and the user rating matrix to obtain the value-added service popularity analysis data.

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

[0075] In an embodiment of the present invention, data verification is performed on the basic information and bound photovoltaic product information entered by the user terminal, and a corresponding user profile is created based on the data verification result to ensure the accuracy and completeness of the user profile creation. A user portrait is constructed based on the user's browsing behavior information for several value-added services bound to photovoltaic products using label confidence analysis, so that the constructed user portrait is more comprehensive and accurate and can reflect the specific situation of the user. Based on the potential demand analysis data, recommended heat data and interest change data generated by the user profile and user portrait, combined with the initial value-added service demand data, the value-added service demand data corresponding to each user is generated to avoid excessive deviation between the obtained value-added service demand data and the actual needs of the user. Based on the value-added service demand data, a recommended value-added service list corresponding to the bound photovoltaic products of each user is generated, so that the recommended value-added services can better fit the actual situation of the user. Based on the Markov chain, the benefit simulation prediction of the target value-added services determined by each user in the recommended value-added service list can obtain more accurate benefit simulation prediction data, reflecting the benefits brought by the use of value-added services. Popularity analysis is performed based on the target value-added services determined by each user, and a 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, thereby being able to understand the user's specific usage and experience of each value-added service.

[0076] Embodiment 2

[0077] See also Figure 2 , Figure 2 : is a flow chart of a method for analyzing and managing value-added service information of photovoltaic products in another embodiment of the present invention, the method comprising:

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

[0079] S202: performing data verification on the user's basic information and bound photovoltaic product information to obtain a data verification result, and creating a corresponding user profile based on the data verification result;

[0080] S203: Obtain browsing behavior information of each user for several value-added services bound to photovoltaic products, and construct a user profile based on the browsing behavior information by using tag confidence analysis;

[0081] S204: Analyze the value-added service needs of each user based on the user portrait and 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;

[0082] S205: Obtain the 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, and generate a time series-data distribution chain based on the historical benefit record data;

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

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

[0085] S208: 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 based on the Markov chain using a recurrent neural network, and performing benefit simulation prediction on the target value-added service determined by each user based on the benefit simulation prediction model to obtain benefit simulation prediction data;

[0086] S209: Perform popularity analysis based on the target value-added services determined by each user to obtain the 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 visualization component.

[0087] In an embodiment of the present invention, data verification is performed on the basic information and bound photovoltaic product information entered by the user terminal, and a corresponding user profile is created based on the data verification result to ensure the accuracy and completeness of the user profile creation. A user portrait is constructed based on the user's browsing behavior information for several value-added services bound to photovoltaic products using label confidence analysis, so that the constructed user portrait is more comprehensive and accurate and can reflect the specific situation of the user. Based on the potential demand analysis data, recommended heat data and interest change data generated by the user profile and user portrait, combined with the initial value-added service demand data, the value-added service demand data corresponding to each user is generated to avoid excessive deviation between the obtained value-added service demand data and the actual needs of the user. Based on the value-added service demand data, a recommended value-added service list corresponding to the bound photovoltaic products of each user is generated, so that the recommended value-added services can better fit the actual situation of the user. Based on the Markov chain, the benefit simulation prediction of the target value-added services determined by each user in the recommended value-added service list can obtain more accurate benefit simulation prediction data, reflecting the benefits brought by the use of value-added services. Popularity analysis is performed based on the target value-added services determined by each user, and a 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, thereby being able to understand the user's specific usage and experience of each value-added service.

[0088] Embodiment 3

[0089] See also Figure 3 , Figure 3 : is a schematic diagram of the structure of a device for analyzing and managing value-added service information of photovoltaic products in an embodiment of the present invention, the device comprising:

[0090] Information input module 31: used for the back-end server to establish a communication connection with each user terminal based on identity authentication, and receive the basic user information and bound photovoltaic product information entered by each user terminal;

[0091] The user profile creation module 32 is used to perform data verification on the user's basic information and the bound photovoltaic product information, obtain a data verification result, and create a corresponding user profile based on the data verification result;

[0092] User portrait building module 33: used to obtain browsing behavior information of each user for several value-added services bound to photovoltaic products, and build user portraits based on the browsing behavior information by using tag confidence analysis;

[0093] The value-added service recommendation module 34 is used to analyze the value-added service needs of each user based on the user portrait and user profile, obtain corresponding value-added service demand data, and 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 used to obtain the target value-added service determined by each user in the recommended value-added service list, and to perform benefit simulation prediction on the target value-added service determined by each user based on the Markov chain to obtain benefit simulation prediction data;

[0095] Service popularity analysis and report generation module 36: used to perform popularity analysis based on the target value-added services 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 the corresponding visualization component.

[0096] In the specific implementation process of the present invention, the specific implementation method of the device item can refer to the implementation method of the above-mentioned method item, which will not be repeated here.

[0097] In an embodiment of the present invention, data verification is performed on the basic information and bound photovoltaic product information entered by the user terminal, and a corresponding user profile is created based on the data verification result to ensure the accuracy and completeness of the user profile creation. A user portrait is constructed based on the user's browsing behavior information for several value-added services bound to photovoltaic products using label confidence analysis, so that the constructed user portrait is more comprehensive and accurate and can reflect the specific situation of the user. Based on the potential demand analysis data, recommended heat data and interest change data generated by the user profile and user portrait, combined with the initial value-added service demand data, the value-added service demand data corresponding to each user is generated to avoid excessive deviation between the obtained value-added service demand data and the actual needs of the user. Based on the value-added service demand data, a recommended value-added service list corresponding to the bound photovoltaic products of each user is generated, so that the recommended value-added services can better fit the actual situation of the user. Based on the Markov chain, the benefit simulation prediction of the target value-added services determined by each user in the recommended value-added service list can obtain more accurate benefit simulation prediction data, reflecting the benefits brought by the use of value-added services. Popularity analysis is performed based on the target value-added services determined by each user, and a 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, thereby being able to understand the user's specific usage and experience of each value-added service.

[0098] A computer-readable storage medium is provided in an embodiment of the present invention, wherein a computer program is stored on the computer-readable storage medium, and when the program is executed by a processor, a method for analyzing and managing the value-added service information of a photovoltaic product in any one of the above embodiments is implemented. 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 can store or transmit information in a readable form by a device (e.g., a computer, a mobile phone), which can be a read-only memory, a disk or an optical disk, etc.

[0099] Embodiment 4

[0100] See also Figure 4 , Figure 4 It is a schematic diagram of the structure of an electronic device in an embodiment of the present invention.

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

[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 are configured to be executed by the one or more processors 43, and the one or more computer programs 42 are configured to execute the value-added service information analysis and management method for photovoltaic products in any of the above-mentioned embodiments. Please refer to the above-mentioned embodiments for the specific implementation process, which will not be repeated here.

[0103] In an embodiment of the present invention, data verification is performed on the basic information and bound photovoltaic product information entered by the user terminal, and a corresponding user profile is created based on the data verification result to ensure the accuracy and completeness of the user profile creation. A user portrait is constructed based on the user's browsing behavior information for several value-added services bound to photovoltaic products using label confidence analysis, so that the constructed user portrait is more comprehensive and accurate and can reflect the specific situation of the user. Based on the potential demand analysis data, recommended heat data and interest change data generated by the user profile and user portrait, combined with the initial value-added service demand data, the value-added service demand data corresponding to each user is generated to avoid excessive deviation between the obtained value-added service demand data and the actual needs of the user. Based on the value-added service demand data, a recommended value-added service list corresponding to the bound photovoltaic products of each user is generated, so that the recommended value-added services can better fit the actual situation of the user. Based on the Markov chain, the benefit simulation prediction of the target value-added services determined by each user in the recommended value-added service list can obtain more accurate benefit simulation prediction data, reflecting the benefits brought by the use of value-added services. Popularity analysis is performed based on the target value-added services determined by each user, and a 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, thereby being able to understand the user's specific usage and experience of each value-added service.

[0104] In addition, the above is a detailed introduction to the value-added service information analysis and management method and related devices for a photovoltaic product provided by an embodiment of the present invention. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for general technical personnel in this field, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A method for analyzing and managing value-added service information of photovoltaic products, characterized in that: The method comprises: The back-end server establishes a communication connection with each user terminal based on identity authentication, and receives the basic user information and bound photovoltaic product information entered by each user terminal; Performing data verification on the user's basic information and bound photovoltaic product information to obtain a data verification result, and creating a corresponding user profile based on the data verification result; Obtaining browsing behavior information of each user for several value-added services bound to photovoltaic products, and constructing a user profile based on the browsing behavior information by using tag confidence analysis; Analyze the value-added service needs of each user based on the user portrait and 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; Obtain the target value-added services determined by each user in the recommended value-added service list, perform benefit simulation prediction on the target value-added services determined by each user based on the Markov chain, and obtain benefit simulation prediction data; A popularity analysis is performed based on the target value-added services determined by each user to obtain the 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, and the target analysis report is displayed in the corresponding visualization component.

2. The method for analyzing and managing value-added service information of photovoltaic products according to claim 1, characterized in that: The backend server establishes a communication connection with each user terminal based on identity authentication, including: The back-end server receives the authentication request sent by each user terminal, generates an identity identifier based on the authentication request, and generates a signed identity certificate based on the identity identifier using a certificate model; The signature identity certificate is authenticated based on a differential obfuscation mechanism, and after the signature identity certificate is authenticated, the back-end server establishes a communication connection with the corresponding user terminal.

3. The method for analyzing and managing value-added service information of photovoltaic products according to claim 1, characterized in that: The data verification of the basic information of the user and the bound photovoltaic product information to obtain the data verification result includes: Performing data verification calculation on the user basic information and bound photovoltaic product information based on a data verification algorithm to obtain a data verification value; Generate a number of sub-numbers based on the user basic information and bound photovoltaic product information, and generate a number of decomposition coefficients based on the public verification code and each sub-number; A corresponding composite number is generated based on each decomposition coefficient and the public verification code, and data verification is performed on the user basic information and the bound photovoltaic product information based on the composite number and the data verification value to obtain a data verification result.

4. The method for analyzing and managing value-added service information of photovoltaic products according to claim 1, characterized in that: The step of constructing a user profile based on the browsing behavior information by using tag confidence analysis includes: Performing effective time analysis based on the browsing behavior information to obtain effective browsing time, and performing interest analysis of the browsing behavior using a scoring function based on the effective browsing time to obtain interest analysis data; Analyzing the number of views of the value-added service category based on the browsing behavior information to obtain a target number of views, and generating a browsing category weight based on the browsing category history weight using the target number of views; Extract features from the browsing behavior information to obtain target browsing features, and perform semantic similarity calculation and intent recognition processing based on the target browsing features to obtain intent label data and intent label confidence; A user portrait is constructed based on the interest analysis data, browsing category weights, intent label data and intent label confidence.

5. The method for analyzing and managing value-added service information of photovoltaic products according to claim 1, characterized in that: 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: Perform initial value-added service demand analysis based on the user profile of each user to obtain initial value-added service demand data; Perform collaborative filtering based on the user profile of each user to obtain collaborative filtering results; Based on the collaborative filtering results, potential demand analysis is used to obtain potential demand analysis data, and based on the potential demand analysis data, outlier data analysis is used to perform recommendation heat analysis of value-added services to obtain recommendation heat data; Based on the collaborative filtering result, an interest change analysis is performed using an interest change analysis model to obtain interest change data, and based on the potential demand analysis data, the recommendation popularity data and the interest change data combined with the initial value-added service demand data, the value-added service demand data corresponding to each user is generated; Based on the value-added service demand data, matching and sorting are performed among several value-added services to obtain a list of recommended value-added services corresponding to the bound photovoltaic products of each user.

6. The photovoltaic product value-added service information analysis and management method according to claim 1, characterized in that: The benefit simulation prediction of the target value-added service determined by each user is performed based on the Markov chain to obtain benefit simulation prediction data, including: Acquire 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; Defining a state space and a state transfer matrix based on the historical user value-added service conversion data, and determining a state transfer probability function based on the state space and the state transfer 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; A Markov chain is constructed based on the optimized state transition probability function and the time series-data distribution chain, and a benefit simulation prediction model is generated based on the Markov chain using a recurrent neural network. Based on the benefit simulation prediction model, benefit simulation prediction is performed on the target value-added service determined by each user to obtain benefit simulation prediction data.

7. The method for analyzing and managing value-added service information of photovoltaic products according to claim 1, characterized in that: The popularity analysis of the target value-added services determined by each user to obtain the value-added service popularity analysis data includes: Acquire tracking status data of target value-added services determined by each user, and generate a user rating matrix based on the tracking status data using a conditional variational autoencoder; Extracting elements based on the tracking status data to obtain evaluation elements, and generating a feature input matrix based on the evaluation elements; Calculate the heat data of each target value-added service using a heat analysis model based on the feature input matrix; A popularity analysis is performed based on the heat data and the user rating matrix to obtain value-added service popularity analysis data.

8. A value-added service information analysis and management device for photovoltaic products, characterized in that: The device comprises: Information entry module: used for the back-end server to establish a communication connection with each user terminal based on identity authentication, and receive the basic user information and bound photovoltaic product information entered by each user terminal; User profile creation module: used to perform data verification on the user's basic information and bound photovoltaic product information, obtain data verification results, and create a corresponding user profile based on the data verification results; User portrait building module: used to obtain browsing behavior information of each user for several value-added services bound to photovoltaic products, and build user portraits based on the browsing behavior information by using tag confidence analysis; Value-added service recommendation module: used to analyze the value-added service needs of each user based on the user portrait and user profile, obtain corresponding value-added service demand data, and generate a recommended value-added service list corresponding to the bound photovoltaic products of each user based on the value-added service demand data, and send the recommended value-added service list to each user terminal; Benefit simulation prediction module: used to obtain the target value-added services determined by each user in the recommended value-added service list, and perform benefit simulation prediction on the target value-added services determined by each user based on the Markov chain to obtain benefit simulation prediction data; Service popularity analysis and report generation module: used to perform popularity analysis based on the target value-added services 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 the corresponding visualization component.

9. An electronic device, comprising a processor and a memory, characterized in that: 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 and management method for photovoltaic products according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and when the computer instructions are executed on an electronic device, the electronic device executes the value-added service information analysis and management method for photovoltaic products according to any one of claims 1 to 7.

Images