Computer intelligent service management system, method and equipment and storage medium

Abstract

The invention discloses a computer intelligent service management system, method and device and a storage medium, and the method comprises the following steps: obtaining related information of computer service used by a user, and storing the related information in a system database; analyzing input data and use behavior data of the user, and generating decision support information based on an analysis result; user portraits are completed by means of big data mining, user service demand features are clarified, and personalized service recommendation is provided; personalized service recommendation effects are monitored, user evaluation is collected, summarized and arranged, and a data analysis mode and a service strategy are optimized according to evaluation service quality and improvement effects; user precise service effects are collected, operation is repeated, a management method is optimized, and precise service management is achieved. According to the method, the use data of different services are processed in a centralized manner, the use behaviors, input data and preferences of the user are analyzed, a final analysis result of the heterogeneous information network relation graph is constructed by analyzing and mining the data, and accurate personalized recommendation is provided for the user.

Description

Technical Field

[0001] The present invention relates to the field of computer service management technology, and in particular to a computer intelligent service management system, method, device and storage medium based on network big data. Background Art

[0002] Computer system refers to the computer hardware, software and network system used for database management. Its characteristics are accurate and fast calculation and judgment, good versatility, easy to use, and can be connected to a network. With the rapid development of the Internet, the application of computer networks is becoming more and more extensive in various fields of daily life. At present, my country has entered the era of big data. Through distributed, big data centers, cloud platforms and other technical means, it has realized the effective collection and storage of massive data. In order to meet the needs of data analysis, some data mining technologies and data analysis technologies have been popularized and applied.

[0003] In the era of big data, computer services are frequently used, which enables computer platforms to master users' personal information, usage habits and other information, and to continuously refine the needs of computer users, and finally even implement them on the basis of personal behavior. When users search for a certain category of computer services, all similar service information will be displayed, and sometimes the meaning of the sentence entered by the user is not clear enough, and the results obtained also include many other irrelevant service categories, which makes users have no idea where to start and how to choose.

[0004] In view of this, this application is hereby filed. Summary of the invention

[0005] The technical problem to be solved by the present invention is that the meaning of the sentence expressed by the user input is not clear enough, and the result obtained also contains many other irrelevant service categories. The purpose is to provide a computer intelligent service management system, method, device and storage medium based on network big data, and centrally process the usage data of different services to form a big data center. On this basis, the user's usage behavior, input data and preferences are analyzed, and a heterogeneous information network relationship diagram is constructed through analysis and mining of known data. Then, the two aspects are integrated to obtain the final analysis result, and the service strategy is automatically optimized based on the analysis result to provide users with accurate personalized recommendations.

[0006] The present invention is achieved through the following technical solutions:

[0007] In a first aspect, the present invention provides a computer intelligent service management method based on network big data, comprising the following steps:

[0008] S1, collect structured data of computer services, obtain relevant information of users using computer services, wherein the user-related information includes user behavior and operation when using computer services, software usage information, network information, system logs, error reports, etc.; after pre-processing and data integration, place them uniformly in a distributed storage collection to establish a data center (system database);

[0009] S2, applies data mining and machine learning algorithms to analyze user input data and usage behavior data, mines valuable patterns and trends, and generates decision support information based on the analysis results, automatically optimizes service strategies, and provides personalized recommendations; the input data includes user input content, text input, mouse input, image and multimedia input, command input, option and setting input, identity authentication input, behavior input, etc.; usage behavior data includes browsing behavior data, interactive behavior data, purchase and consumption behavior, usage frequency and duration, social and content interaction data, game or in-application behavior data, etc.;

[0010] S3, converting decision support information into service actions. When providing services on the platform, it uses big data mining technology to complete user portraits, clarify the characteristics of user service needs, carry out targeted services, and provide users with personalized service recommendations;

[0011] S4, monitor the effectiveness of personalized service recommendations, collect user feedback, summarize and organize user evaluation data, conduct overall control based on existing information, evaluate service quality and improvement effects, and continuously optimize data analysis methods and service strategies;

[0012] S5, through the control of the whole process of service data, observes the effect of precise service for platform users, and finally achieves the optimal management of precise service for users through repeated operation and optimization of the management process.

[0013] In a specific implementation, in step S1, Apache Kafka is used to process real-time data streams, business data information of different computer services is collected through multiple interfaces, the collected information is standardized, the data is written into the Kafka message queue and the database is updated in real time.

[0014] In a specific implementation, in step S1, a distributed storage method is used to complete data storage, an incremental backup method is used to complete the backup of changed data, and a random forest is used to construct a classification tree with the service project as the root node to classify the data.

[0015] In a specific implementation, in step S1, HDFS is selected to perform cluster reception of distributed files, with NameNode as the primary data node and DataNode as the slave node, to expand user data throughput.

[0016] In a specific implementation, in step S2, the edge computing concept is used to perform preliminary data processing on the service category, and then the information generated in the current service scenario: user operation information, service usage information, input data and user evaluation, is sent to the system for analysis to generate a data analysis report.

[0017] In a specific implementation, in step S2, natural language processing is used to analyze the user's input data, and the correlation between the input data and the service category is calculated by supporting a probabilistic distance function. The data is sorted according to the correlation, and the top K service types are selected to form a candidate recommendation set.

[0018] In a specific implementation, the calculation scheme of the correlation between the input data and the service category is as follows:

[0019] Assume that data Y has two service categories E1 and E2, whose basic probability distribution functions are m1 and m2 respectively, and their corresponding support probability functions are S m1 and S m2 , the formula of the support probability function of a single service category is as follows:

[0020]

[0021] Where A represents any service feature in service category E1; the support probability distance between E1 and E2 can be expressed as:

[0022]

[0023] In the formula, |S m1 (Y)-S m2 (Y)| represents the absolute value of the difference between the support probability function of the data Y between the two service categories. The value range of the support probability distance function is [0, 1]. The larger the value of the support probability distance, the smaller the similarity between the two service categories. The known service categories are divided according to the data, and the known service categories are arranged according to the calculated support probability, and the top K service types are screened out to form a candidate recommendation set.

[0024] In a specific implementation, in step S3, a heterogeneous information network relationship graph is constructed by analyzing and mining known data, and based on the user's current situation and the services used, machine learning is combined with the heterogeneous information network relationship graph to analyze the user's usage behavior data. At the same time, the candidate recommendation set is included in the analysis results for comprehensive consideration to provide users with personalized service recommendations.

[0025] In a specific implementation, in step S3, the construction process of the heterogeneous information network relationship diagram is as follows:

[0026] Generate M nodes corresponding to the user, and generate 2n nodes for the expected and unexpected situations of n services, and then generate n(n-1) possible preference nodes. Each preference data contains the services expected by the user and the services not expected by the user, represented by pd and pu respectively, where d represents the service content expected by the user and u represents the service content not expected by the user. By scanning the preference data set, add a connection between the user and the corresponding node in the preference layer for each user. Finally, scan the preference nodes, where the preference node p represents pd>p,u, find the corresponding association relationship nodes, and insert a connection between each node.

[0027] In a specific implementation, the heterogeneous information network relationship graph includes a user set U, a pairwise preference set P, and an association relationship set R;

[0028] User set U: contains user type nodes, representing each user;

[0029] Pairwise preference set P: contains all possible preference information, and each preference node is marked as i>j, indicating that the user prefers service i more;

[0030] Association set R: consists of I d and I u Representation, showing the set of what users expect and don’t expect from the service;

[0031] E UP = {u, p|f(u, p) = 1, u∈U, p∈P} is the edge set between nodes U and P, E PR ={p, r|s(p, r)=1, p∈P, r∈R} is the edge set between nodes P and R.

[0032] In a specific implementation, when the current user's relationship data contains corresponding preference information in the preference set, the user and the preference node are connected. UP Represents the connection between the user and the preference node;

[0033] When the current preference information is supported by the corresponding association node, the preference node and the association node are connected. PR Represents the connection between the preference node and the association node.

[0034] In a specific implementation, in step S3, the user's current service scenario and historical service scenarios are analyzed in association, and the specific steps are as follows:

[0035] Initialize thresholds α and β;

[0036] Use database query statements to retrieve information, obtain historical records of user-related operations, and build data sets;

[0037] Get the historical service record of the corresponding user F(H) = {F 1H , F 2H , …, F NH};

[0038] Analyze the service information used by the current user F = {F1, F2, ... F N};

[0039] Calculate the similarity between the current service and the historical service sim_bh = sim(F N , F NH );

[0040] Compare sim_bh with the threshold α. If sim_bh>α, push the service through the recommendation method. Specifically, the recommendation method is an information push operation recognized by the user in the computer, or an information push operation defaulted by the computer, and the recommended service is sent to the user for selection.

[0041] In a specific implementation, in step S3, big data mining technology is used to build a user portrait for the new user, and the content information in the existing user portrait is updated, and the user portrait is sent to step S2 for re-analysis and mining.

[0042] In a specific implementation, in step S4, a machine learning algorithm is used to evaluate service quality and improvement effects, and data analysis methods and service strategies are optimized based on the evaluation results.

[0043] In a second aspect, the present invention provides a computer intelligent service management system for executing the computer intelligent service management method based on network big data, comprising a data preparation module, a data analysis module, a service push module and a system configuration module;

[0044] The data preparation module is used to obtain relevant information about the user's use of computer services and store it in the system database;

[0045] The data analysis module is used to analyze the user's input data and usage behavior data;

[0046] The service push module is used to provide users with personalized service recommendations based on data analysis;

[0047] The system configuration module is used to manage user identity information and system background settings.

[0048] In a third aspect, the present invention provides a computer intelligent service management device based on network big data, characterized in that the computer intelligent service management device comprises: a memory, a processor, and a program stored in the memory for implementing the computer intelligent service management method,

[0049] The memory is used to store a program for implementing a computer intelligent service management method;

[0050] The processor is used to execute a program for implementing the computer intelligent service management method to implement the steps of the computer intelligent service management method.

[0051] In a fourth aspect, the present invention provides a readable storage medium storing a program for implementing a computer intelligent service management method, wherein the program for implementing a computer intelligent service management method is executed by a processor to implement the steps of the computer intelligent service management method.

[0052] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0053] 1. A computer intelligent service management system, method, device and storage medium based on network big data provided by the embodiment of the present invention centrally processes the usage data of different services to form a big data center, and analyzes the user's usage behavior, input data and preferences on this basis, constructs a heterogeneous information network relationship diagram through analysis and mining of known data, and then obtains the final analysis result by integrating the two aspects, automatically optimizes the service strategy based on the analysis result, and provides users with accurate personalized recommendations;

[0054] 2. The computer intelligent service management system, method, device and storage medium based on network big data provided by the embodiment of the present invention can establish a user portrait for each user during the service process to obtain more accurate analysis results and accurately recommend service content to customers, which is of great significance for the management of computer services;

[0055] 3. A computer intelligent service management system, method, device and storage medium based on network big data provided by the embodiment of the present invention collects changes in user needs and usage behaviors, as well as platform browsing history trajectories, and obtains user behavior patterns and preferences through data analysis, thereby providing accurate services for users;

[0056] 4. The computer intelligent service management system, method, device and storage medium based on network big data provided by the embodiments of the present invention can manage the precise services for computer platform users, which can not only improve the service experience for platform users, but also is an important way for computer platforms to improve service quality, enhance competitiveness and control mainstream products. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0058] Figure 1 A flowchart of a computer intelligent service management method based on network big data provided by an embodiment of the present invention;

[0059] Figure 2 A framework diagram of a computer intelligent service management system based on network big data constructed for an embodiment of the present invention. DETAILED DESCRIPTION

[0060] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with embodiments and drawings. The exemplary embodiments of the present invention and their description are only used to explain the present invention and are not intended to limit the present invention.

[0061] In the following description, a large number of specific details are set forth in order to provide a thorough understanding of the present invention. However, it is apparent to those of ordinary skill in the art that these specific details do not have to be employed to practice the present invention. In other embodiments, in order to avoid confusing the present invention, well-known structures are not specifically described.

[0062] Throughout the specification, references to "one embodiment," "an embodiment," "an example," or "an example" mean that a particular feature, structure, or characteristic described in conjunction with the embodiment or example is included in at least one embodiment of the present invention. Therefore, the phrases "one embodiment," "an embodiment," "an example," or "an example" appearing in various places throughout the specification do not necessarily all refer to the same embodiment or example. In addition, particular features, structures, or characteristics may be combined in one or more embodiments or examples in any suitable combination and / or sub-combination. In addition, it will be appreciated by those of ordinary skill in the art that the figures provided herein are for illustrative purposes and that the figures are not necessarily drawn to scale. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0063] In the description of the present invention, the directions or positional relationships indicated by terms such as “front”, “rear”, “left”, “right”, “up”, “down”, “vertical”, “horizontal”, “high”, “low”, “inside” and “outside” are based on the directions or positional relationships shown in the accompanying drawings and are only for the convenience of describing the present invention and simplifying the description. They do not indicate or imply that the device or element referred to must have a specific direction, be constructed and operated in a specific direction. Therefore, they should not be understood as limiting the scope of protection of the present invention.

[0064] Example 1

[0065] like Figure 1 As shown, an embodiment of the present invention provides a computer intelligent service management method based on network big data, comprising the following steps:

[0066] S1, collect structured data of computer services, obtain relevant information of users using computer services, wherein the user-related information includes user behavior and operation when using computer services, software usage information, network information, system logs, error reports, etc.; after pre-processing and data integration, place them uniformly in a distributed storage collection to establish a data center (system database);

[0067] S2, applies data mining and machine learning algorithms to analyze user input data and usage behavior data, mines valuable patterns and trends, and generates decision support information based on the analysis results, automatically optimizes service strategies, and provides personalized recommendations; the input data includes user input content, text input, mouse input, image and multimedia input, command input, option and setting input, identity authentication input, behavior input, etc.; usage behavior data includes browsing behavior data, interactive behavior data, purchase and consumption behavior, usage frequency and duration, social and content interaction data, game or in-application behavior data, etc.;

[0068] S3, converting decision support information into service actions. When providing services on the platform, it uses big data mining technology to complete user portraits, clarify the characteristics of user service needs, carry out targeted services, and provide users with personalized service recommendations;

[0069] S4, monitor the effectiveness of personalized service recommendations, collect user feedback, summarize and organize user evaluation data, conduct overall control based on existing information, evaluate service quality and improvement effects, and continuously optimize data analysis methods and service strategies;

[0070] S5, through the control of the whole process of service data, observes the effect of precise service for platform users, and finally achieves the optimal management of precise service for users through repeated operation and optimization of the management process.

[0071] In a specific implementation, in step S1, Apache Kafka is used to process real-time data streams, business data information of different computer services is collected through multiple interfaces, the collected information is standardized, the data is written into the Kafka message queue and the database is updated in real time.

[0072] In a specific implementation, in step S1, a distributed storage method is used to complete data storage, an incremental backup method is used to complete the backup of changed data, and a random forest is used to construct a classification tree with the service project as the root node to classify the data.

[0073] In a specific implementation, in step S1, HDFS is selected to perform cluster reception of distributed files, with NameNode as the primary data node and DataNode as the slave node, to expand user data throughput.

[0074] In a specific implementation, in step S2, the edge computing concept is used to perform preliminary data processing on the service category, and then the information generated in the current service scenario: user operation information, service usage information, input data and user evaluation, is sent to the system for analysis to generate a data analysis report.

[0075] In a specific implementation, in step S2, natural language processing is used to analyze the user's input data, and the correlation between the input data and the service category is calculated by supporting a probabilistic distance function. The data is sorted according to the correlation, and the top K service types are selected to form a candidate recommendation set.

[0076] In a specific implementation, the calculation scheme of the correlation between the input data and the service category is as follows:

[0077] Assume that data Y has two service categories E1 and E2, whose basic probability distribution functions are m1 and m2 respectively, and their corresponding support probability functions are S m1 and S m2 , the formula of the support probability function of a single service category is as follows:

[0078]

[0079] Where A represents any service feature in service category E1; the support probability distance between E1 and E2 can be expressed as:

[0080]

[0081] In the formula, |S m1 (Y)-S m2(Y)| represents the absolute value of the difference between the support probability function of the data Y between the two service categories. The value range of the support probability distance function is [0, 1]. The larger the value of the support probability distance, the smaller the similarity between the two service categories. The known service categories are divided according to the data, and the known service categories are arranged according to the calculated support probability, and the top K service types are screened out to form a candidate recommendation set.

[0082] In a specific implementation, in step S3, a heterogeneous information network relationship graph is constructed by analyzing and mining known data, and based on the user's current situation and the services used, machine learning is combined with the heterogeneous information network relationship graph to analyze the user's usage behavior data. At the same time, the candidate recommendation set is included in the analysis results for comprehensive consideration to provide users with personalized service recommendations.

[0083] In a specific implementation, in step S3, the construction process of the heterogeneous information network relationship diagram is as follows:

[0084] Generate M nodes corresponding to the user, and generate 2n nodes for the expected and unexpected situations of n services, and then generate n(n-1) possible preference nodes. Each preference data contains the services expected by the user and the services not expected by the user, represented by pd and pu respectively, where d represents the service content expected by the user and u represents the service content not expected by the user. By scanning the preference data set, add a connection between the user and the corresponding node in the preference layer for each user. Finally, scan the preference nodes, where the preference node p represents pd>p,u, find the corresponding association relationship nodes, and insert a connection between each node.

[0085] In a specific implementation, the heterogeneous information network relationship graph includes a user set U, a pairwise preference set P, and an association relationship set R;

[0086] User set U: contains user type nodes, representing each user;

[0087] Pairwise preference set P: contains all possible preference information, and each preference node is marked as i>j, indicating that the user prefers service i more;

[0088] Association set R: consists of I d and I u Representation, showing the set of what users expect and don’t expect from the service;

[0089] E UP = {u, p|f(u, p) = 1, u∈U, p∈P} is the edge set between nodes U and P, E PR ={pr|s(p,r)=1,p∈P,r∈R} is the edge set between nodes P and R.

[0090] In a specific implementation, when the current user's relationship data contains corresponding preference information in the preference set, the user and the preference node are connected. UP Represents the connection between the user and the preference node;

[0091] When the current preference information is supported by the corresponding association node, the preference node and the association node are connected. PR Represents the connection between the preference node and the association node.

[0092] In a specific implementation, in step S3, the user's current service scenario and historical service scenarios are analyzed in association, and the specific steps are as follows:

[0093] Initialize thresholds α and β;

[0094] Use database query statements to retrieve information, obtain historical records of user-related operations, and build data sets;

[0095] Get the historical service record of the corresponding user F(H) = {F 1H , F 2H , …, F NH};

[0096] Analyze the service information used by the current user F = {F1, F2, ... F N};

[0097] Calculate the similarity between the current service and the historical service sim_bh = sim(F N , F NH );

[0098] Compare sim_bh with the threshold α. If sim_bh>α, push the service through the recommendation method. Specifically, the recommendation method is an information push operation recognized by the user in the computer, or an information push operation defaulted by the computer, and the recommended service is sent to the user for selection.

[0099] In a specific implementation, in step S3, big data mining technology is used to build a user portrait for the new user, and the content information in the existing user portrait is updated, and the user portrait is sent to step S2 for re-analysis and mining.

[0100] In a specific implementation, in step S4, a machine learning algorithm is used to evaluate service quality and improvement effects, and data analysis methods and service strategies are optimized based on the evaluation results.

[0101] Example 2

[0102] like Figure 2As shown, the embodiment of the present invention provides a computer intelligent service management system for executing the computer intelligent service management method based on network big data described in Example 1, including a data preparation module, a data analysis module, a service push module and a system configuration module;

[0103] The data preparation module is used to obtain relevant information about the user's use of computer services and store it in the system database;

[0104] The data analysis module is used to analyze the user's input data and usage behavior data;

[0105] The service push module is used to provide users with personalized service recommendations based on data analysis;

[0106] The system configuration module is used to manage user identity information and system background settings.

[0107] Example 3

[0108] The embodiment of the present invention provides a computer intelligent service management device based on network big data, characterized in that the computer intelligent service management device comprises: a memory, a processor, and a program stored in the memory for implementing the computer intelligent service management method,

[0109] The memory is used to store a program for implementing a computer intelligent service management method;

[0110] The processor is used to execute a program for implementing the computer intelligent service management method to implement the steps of the computer intelligent service management method.

[0111] Example 4

[0112] An embodiment of the present invention provides a readable storage medium, on which is stored a program for implementing a computer intelligent service management method, and the program for implementing the computer intelligent service management method is executed by a processor to implement the steps of the computer intelligent service management method.

[0113] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A computer intelligent service management method based on network big data, characterized in that: The steps include: S1, collects structured data of computer services, obtains relevant information about users’ use of computer services, and stores it in the system database; S2, analyzing the user's input data and usage behavior data, and generating decision support information based on the analysis results; S3, converts decision support information into service actions, uses big data mining technology to complete user portraits, clarifies user service demand characteristics, and provides users with personalized service recommendations; S4, monitor the effectiveness of personalized service recommendations, collect and summarize user evaluation data, and optimize data analysis methods and service strategies based on the evaluation of service quality and improvement effects; S5, collect the precise service effects of users, repeat operations and optimize management methods to achieve precise service management for users.

2. According to claim 1, a computer intelligent service management method based on network big data is characterized in that: In step S1, Apache Kafka is used to process real-time data streams, business data information of different computer services is collected through multiple interfaces, the collected information is standardized, the data is written into the Kafka message queue and the database is updated in real time.

3. According to the computer intelligent service management method based on network big data according to claim 1, it is characterized in that: In step S1, a distributed storage method is used to complete data storage, an incremental backup method is used to complete the backup of changed data, and a random forest is used to build a classification tree with the service project as the root node to classify the data.

4. A computer intelligent service management method based on network big data according to claim 3, characterized in that: In step S1, HDFS is selected to perform cluster reception of distributed files, with Name Node as the primary data node and DataNode as the slave node, to expand user data throughput.

5. According to claim 3, a computer intelligent service management method based on network big data is characterized in that: In step S2, the edge computing concept is used to perform preliminary data processing on the service category, and then the information generated in the current service scenario: user operation information, service usage information, input data and user evaluation, is sent to the system for analysis to generate a data analysis report.

6. A computer intelligent service management method based on network big data according to claim 1, characterized in that: In step S2, natural language processing is used to analyze the user's input data, and the correlation between the input data and the service categories is calculated by supporting a probability distance function. The data is sorted according to the correlation, and the top K service types are selected to form a candidate recommendation set.

7. A computer intelligent service management method based on network big data according to claim 6, characterized in that: The calculation scheme of the correlation between input data and service categories is as follows: Assume that data Y has two service categories E1 and E2, whose basic probability distribution functions are m1 and m2 respectively, and their corresponding support probability functions are S m1 and S m2 , the formula of the support probability function of a single service category is as follows: Where A represents any service feature in service category E1; the support probability distance between E1 and E2 can be expressed as: In the formula, |S m1 (Y)-S m2 (Y)| represents the absolute value of the difference between the support probability function of the data Y between the two service categories. The value range of the support probability distance function is [0, 1]. The larger the value of the support probability distance, the smaller the similarity between the two service categories. The known service categories are divided according to the data, and the known service categories are arranged according to the calculated support probability, and the top K service types are screened out to form a candidate recommendation set.

8. A computer intelligent service management method based on network big data according to claim 7, characterized in that: In step S3, a heterogeneous information network relationship diagram is constructed by analyzing and mining known data. Based on the user's current situation and the services used, machine learning is combined with the heterogeneous information network relationship diagram to analyze the user's usage behavior data. At the same time, the candidate recommendation set is included in the analysis results for comprehensive consideration to provide users with personalized service recommendations.

9. A computer intelligent service management method based on network big data according to claim 8, characterized in that: In step S3, the construction process of the heterogeneous information network relationship diagram is as follows: Generate M nodes corresponding to the user, and generate 2n nodes for the expected and unexpected situations of n services, and then generate n(n-1) possible preference nodes. Each preference data contains the services expected by the user and the services not expected by the user, represented by pd and pu respectively, where d represents the service content expected by the user and u represents the service content not expected by the user. By scanning the preference data set, add a connection between the user and the corresponding node in the preference layer for each user. Finally, scan the preference nodes, where the preference node p represents pd>p,u, find the corresponding association relationship nodes, and insert a connection between each node.

10. A computer intelligent service management method based on network big data according to claim 9, characterized in that: The heterogeneous information network relationship graph includes a user set U, a pairwise preference set P and an association relationship set R; User set U: contains user type nodes, representing each user; Pairwise preference set P: contains all possible preference information, and each preference node is marked as i>j, indicating that the user prefers service i more; Association set R: consists of I d and I u Representation, showing the set of what users expect and don’t expect from the service; E UP = {u, p|f(u, p) = 1, u∈U, p∈P} is the edge set between nodes U and P, E PR ={p, r|s(p, r)=1, p∈P, r∈R} is the edge set between nodes P and R.

11. A computer intelligent service management method based on network big data according to claim 10, characterized in that: When the current user's relationship data contains the corresponding preference information in the preference set, the user and the preference node are connected, R UP Represents the connection between the user and the preference node; When the current preference information is supported by the corresponding association node, the preference node and the association node are connected. PR Represents the connection between the preference node and the association node.

12. A computer intelligent service management method based on network big data according to claim 8, characterized in that: In step S3, the user's current service scenario and historical service scenarios are correlated and analyzed. The specific steps are as follows: Initialize thresholds α and β; Use database query statements to retrieve information, obtain historical records of user-related operations, and build data sets; Get the historical service record of the corresponding user F(H) = {F 1H , F 2H , …, F NH }; Analyze the service information used by the current user F = {F1, F2, ... F N }; Calculate the similarity between the current service and the historical service sim_bh = sim(F N , F NH ); Compare Sim_bh with the threshold α. If sim_bh>α, push the service through the recommendation method.

13. A computer intelligent service management method based on network big data according to claim 1, characterized in that: In step S3, big data mining technology is used to build a user portrait for the new user, and the content information in the existing user portrait is updated, and the user portrait is sent to step S2 for re-analysis and mining.

14. A computer intelligent service management method based on network big data according to claim 1, characterized in that: In step S4, a machine learning algorithm is used to evaluate the service quality and improvement effect, and the data analysis method and service strategy are optimized based on the evaluation results.

15. A computer intelligent service management system for executing the computer intelligent service management method based on network big data as claimed in any one of claims 1 to 14, characterized in that: It includes data preparation module, data analysis module, service push module and system configuration module; The data preparation module is used to obtain relevant information about the user's use of computer services and store it in the system database; The data analysis module is used to analyze the user's input data and usage behavior data; The service push module is used to provide users with personalized service recommendations based on data analysis; The system configuration module is used to manage user identity information and system background settings.

16. A computer intelligent service management device based on network big data, characterized in that: The computer intelligent service management device comprises: a memory, a processor and a program stored in the memory for implementing the computer intelligent service management method. The memory is used to store a program for implementing a computer intelligent service management method; The processor is used to execute a program for implementing the computer intelligent service management method to implement the steps of the computer intelligent service management method according to any one of claims 1 to 14.

17. A readable storage medium, characterized in that: The readable storage medium stores a program for implementing the computer intelligent service management method, and the program for implementing the computer intelligent service management method is executed by a processor to implement the steps of the computer intelligent service management method according to any one of claims 1 to 14.

Images