Enterprise data consultation service system based on big data

Abstract

The invention discloses an enterprise data consultation service system based on big data, which comprises a user management module, a service management module and a scoring module, and is characterized in that the user management module manages registration and login of an enterprise, collects some necessary basic data of the enterprise, scores the enterprise through the scoring module, and sends the score to the service management module; the service management module recommends services which may be interested in to users, analyzes consultation contents of enterprise clients, recommends related enterprise cases and solutions and collects satisfaction degrees of the users so as to judge whether the users need manual services or not, and recommends different levels of manual services through enterprise scores. The scoring module scores the manual service, overall service scoring is carried out through the user satisfaction degree and the manual service score, whether service feedback is carried out or not is determined according to the scoring result, and the problem that it is difficult for enterprise users to obtain wanted services through their own demands is effectively solved. The method has the characteristic of improving the service precision and the service efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of big data processing, and in particular to an enterprise data consulting service system based on big data. Background Art

[0002] Enterprise data consulting services are services that help enterprises manage and optimize their data resources. It can help enterprises develop data management strategies to support business goals and decisions, establish a data governance framework, ensure the quality, integrity and security of data, integrate data from different sources to provide a consistent view across the enterprise, and use advanced analytical tools and technologies to extract valuable insights from data.

[0003] Existing enterprise data consulting service systems have problems with data processing difficulties and inaccurate data analysis when processing huge amounts of enterprise data. Existing technologies generally use a combination of big data and enterprise data consulting service systems to provide enterprise data consulting services. However, in existing enterprise data consulting service systems, enterprise users often find it difficult to accurately find the corresponding service type through consulting information to provide corresponding enterprise data consulting services. In addition, in existing enterprise data consulting service systems, it is not considered that the user's satisfaction with the enterprise data consulting service affects service efficiency. Therefore, it is necessary to design an enterprise data consulting service system based on big data to improve service accuracy and service efficiency. Summary of the invention

[0004] The purpose of the present invention is to provide an enterprise data consulting service system based on big data to solve the problems raised in the above background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: a method for enterprise data consulting services based on big data, the specific steps of which include:

[0006] Step S1: The enterprise user registers and logs in, collects the basic data of the enterprise including basic information, financial data, market and sales data, human resources data, technology and R&D information, and customer and supplier information, enters the historical consultation records of the enterprise into the system, and scores the registered enterprise through analysis and processing of the collected data;

[0007] Step S2: The enterprise user inputs the consulting information, and the consulting information is processed by TF-IDF to extract the corresponding feature information. According to the feature information and the characteristics of different service types, the service type required by the user is determined. According to the service type selected by the enterprise user and the consulting information input, relevant enterprise cases and solutions are recommended to the enterprise user, and the service satisfaction is scored;

[0008] Step S3: The system determines whether to recommend manual service to the enterprise user based on the enterprise user's rating of service satisfaction, recommends manual service of different levels based on different enterprise ratings, and rates the manual service;

[0009] Step S4: The system collects the user's service satisfaction score and manual service score, and calculates the overall service score. The system determines whether it is necessary to collect feedback from the user based on the overall service score. The system integrates the feedback and uploads it to the management end.

[0010] According to the above technical solution, step S1 further includes the following steps:

[0011] Step S11: Enterprise users must first register the enterprise data consulting service system. During registration, enterprise users submit some basic information of the enterprise to the system, including enterprise registration information, financial data, market and sales data, human resources data, technology and R&D information, and customer and supplier information, and enter the basic information of the enterprise into the system;

[0012] Step 12: The system summarizes and concludes the enterprise's capital data to obtain three parameters related to the enterprise score, namely, market performance score X, financial status score Y and operation management score Z. The market performance score is divided into five levels: excellent, good, medium, poor and bad, represented by 5x, 4x, 3x, 2x, x respectively. The financial status score is divided into five levels: excellent, good, medium, poor and bad, represented by 5y, 4y, 3y, 2y, y respectively. The operation management score is divided into five levels: excellent, good, medium, poor and bad, represented by 5z, 4z, 3z, 2z, z respectively. The three values ​​of x, y and z are usually set manually. The enterprise score is obtained by summing the three scoring criteria to obtain the final score P. The expression of the enterprise score is:

[0013] P = X + Y + Z;

[0014] Step 13: The system divides enterprises into three levels: large enterprises, medium-sized enterprises, and small enterprises, which are represented by the three levels A, B, and C respectively. The total score P of the enterprise is calculated based on the scores of market performance, financial status, operation and management. The thresholds P1 and P2 are set based on manual experience, and P1>P2. When P>P1, the enterprise is determined to be a large enterprise and belongs to Class A. When P2<P<P1, the enterprise is determined to be a medium-sized enterprise and belongs to Class B. When P<P2, the enterprise is determined to be a small enterprise and belongs to Class C.

[0015] According to the above technical solution, step S2 further includes the following steps:

[0016] Step S21: The enterprise user inputs consulting information into the system. The system preprocesses the consulting information text and splits the text data into multiple terms. The TF-IDF algorithm calculates the term frequency P and the inverse document frequency W of each term in the split consulting information in the entire document, and multiplies the term frequency and the inverse document frequency to obtain the TF-IDF value S = W × P of the term in the document. A threshold S0 is artificially defined based on historical experience. When S>S0, the term can be used as a feature of the consulting information. The terms that meet the condition S>S0 are collected and used as the feature R of the consulting information. The probability that the feature R belongs to different service types is calculated through the multi-classification logistic regression algorithm. Where R is the characteristic value of the consultation information, i = 1, 2, ..., k, k is the number of service types of the service system, is the weight vector of service type k, b i is the bias term for service type k, b i Obtained by the gradient descent algorithm, the probability is selected The largest type of service is the service that business users need;

[0017] Step S22: The system establishes corresponding enterprise case and solution databases according to different service types. The system pre-processes the data in the corresponding enterprise case and solution database according to the service type selected by the enterprise user, extracts the feature H of the enterprise case and solution through the TF-IDF algorithm, and uses the nearest neighbor algorithm to extract the feature H of the enterprise case and solution. Calculate the similarity F between the feature R of the consulting information and the feature H of the enterprise cases and solutions, and manually set a threshold F0 to recommend enterprise cases and solutions that meet the condition F>F0 to enterprise users;

[0018] Step S23: Enterprise users rate their satisfaction with the service. User satisfaction δ is divided into four levels, namely excellent, good, average, and poor. The satisfaction rating criteria include system response time Q, solution relevance W, and user help E. These three rating criteria are all 100 points. Based on historical experience, weights of 0.2, 0.3, and 0.5 are added to the three rating criteria. The calculation formula for user satisfaction δ is:

[0019] δ=0.2Q+0.3W+0.5E.

[0020] According to the above technical solution, step S3 further includes the following steps:

[0021] Step S31: By manually setting thresholds δ1, δ2, and δ3, and δ1>δ2>δ3, when δ>δ1, the user satisfaction is excellent, when δ1>δ>δ2, the user satisfaction is good, when δ2>δ>δ3, the user satisfaction is average, and when δ<δ3, the user satisfaction is poor. When the user satisfaction is average or poor, the system recommends the user to perform manual service;

[0022] Step S32: The system evaluates the manual service level by three standards: working time T, service experience M and processing capacity N. The working time score is divided into three levels: ≤3 years, ≤5 years and >5 years, which are represented by 3t, 2t and t respectively. The service experience score is divided into three levels: experienced, relatively skilled and general experience, which are represented by 3m, 2m and m respectively. The processing capacity score is divided into three levels, which are represented by 3n, 2n and n respectively. The three values ​​of t, m and n are usually set manually. The enterprise score is obtained by summing the three scoring standards to obtain the final score ε. The expression of manual service level is:

[0023] ε=T+M+N;

[0024] Step S33: selecting different levels of manual services based on the enterprise's evaluation results. The levels of manual services are divided into three levels: expert level, professional level and skilled level. When the enterprise evaluation result is level A, expert level manual services are selected; when the enterprise evaluation result is level B, professional level manual services are selected; when the enterprise evaluation result is level C, skilled level manual services are selected;

[0025] Step S34: recommending different levels of manual services to enterprises with different rating levels. When the enterprise user finishes the manual service, the system sends a manual service rating request to the enterprise user.

[0026] According to the above technical solution, step S34 further includes the following steps:

[0027] Step S341: Enterprise users divide the manual service rating θ into four levels, namely excellent, good, average, and poor. The manual service rating criteria include service attitude J, problem solving K, and user experience L. These three rating criteria are all in percentage. Based on historical experience, the weights of 0.35, 0.35, and 0.3 are added to the three rating criteria. The calculation formula for the satisfaction degree θ of problem solving is:

[0028] θ=0.35J+0.35K+0.3L

[0029] Step S342: By manually setting thresholds θ1, θ2, and θ3, and θ1>θ2>θ3, when θ>θ1, the manual service score is excellent, when θ1>θ>θ2, the manual service score is good, when θ2>θ>θ3, the manual service score is average, and when θ<θ3, the manual service score is poor.

[0030] According to the above technical solution, step S4 further includes the following steps:

[0031] Step S41: The system calculates the overall service score μ by collecting the user service satisfaction δ and the manual service score θ. The expression of μ is:

[0032] μ=0.3δ+0.7θ

[0033] Step S42: The thresholds μ1, μ2, and μ3 are artificially set based on historical experience, and μ1>μ2>μ3. When μ>μ1, the overall service score is excellent; when μ1>μ>μ2, the overall service score is good; when μ2>μ>μ3, the overall service score is average; and when μ<μ3, the overall service score is poor. When the overall service is excellent, the system does not collect feedback from corporate users. When the overall service score is good, average, or poor, the system collects feedback information from corporate users and uploads the collected feedback information to the management end.

[0034] According to the above technical solution, the enterprise data consulting service system includes:

[0035] User management module, used to manage user registration and login, and collect basic information of the enterprise;

[0036] Service management module, used to manage and select different types of consulting services;

[0037] The scoring module is used to score various services provided in the system.

[0038] According to the above technical solution, the user management module includes:

[0039] Registration unit, used for enterprise users to register services;

[0040] Login unit, used for enterprise users to log in;

[0041] Data collection unit, used to collect some basic information of enterprises.

[0042] According to the above technical solution, the service management module includes:

[0043] A service recommendation unit is used to recommend services that may be of interest to users based on user history data;

[0044] A service selection unit, used to select different service types to solve the problem;

[0045] The manual service unit is used to provide manual services to users.

[0046] According to the above technical solution, the enterprise scoring module includes:

[0047] Enterprise rating unit, used to comprehensively rate different enterprises;

[0048] A satisfaction rating unit is used to rate the user's satisfaction with the service;

[0049] A manual service rating unit, used for users to rate manual services;

[0050] The service scoring unit is used to obtain the overall service score through the satisfaction score and the manual service score. The feedback unit is used to receive feedback information from enterprise users and upload it to the management end.

[0051] Compared with the prior art, the beneficial effects achieved by the present invention are: the present invention collects some necessary basic data of enterprises to score the enterprises, recommends services that may be needed by analyzing the historical consultation data of enterprise users, recommends relevant enterprise cases and solutions based on the user's service needs, and recommends users to perform manual services by setting up user satisfaction ratings. The overall service evaluation is obtained through the satisfaction level and the manual service rating, and it is determined whether to provide user feedback, which effectively solves the problem that enterprise users find it difficult to obtain the desired services through their own needs, and has the characteristics of improving service accuracy and service efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0053] Figure 1 A flowchart of the steps of an enterprise data consulting service method based on big data provided in Example 2 of the present invention.

[0054] Figure 2 A schematic diagram of the module composition of an enterprise data consulting service system based on big data provided in Example 2 of the present invention. DETAILED DESCRIPTION

[0055] 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.

[0056] Embodiment 1: This embodiment can be applied to the scenario of enterprise data consulting. The method can be executed by an enterprise data consulting service system based on big data provided by Embodiment 2. The method specifically includes the following steps:

[0057] Step S1: The enterprise user registers and logs in, collects the basic data of the enterprise including basic information, financial data, market and sales data, human resources data, technology and R&D information, and customer and supplier information, enters the historical consultation records of the enterprise into the system, and scores the registered enterprise through analysis and processing of the collected data;

[0058] Step S2: The enterprise user inputs the consulting information, and the consulting information is processed by TF-IDF to extract the corresponding feature information. According to the feature information and the characteristics of different service types, the service type required by the user is determined. According to the service type selected by the enterprise user and the consulting information input, relevant enterprise cases and solutions are recommended to the enterprise user, and the service satisfaction is scored;

[0059] Step S3: The system determines whether to recommend manual service to the enterprise user based on the enterprise user's rating of service satisfaction, recommends manual service of different levels based on different enterprise ratings, and rates the manual service;

[0060] Step S4: The system collects the user's service satisfaction score and manual service score, and calculates the overall service score. The system determines whether it is necessary to collect feedback from the user based on the overall service score. The system integrates the feedback and uploads it to the management end.

[0061] In the embodiment of the present invention, step S1 further includes the following steps:

[0062] Step S11: Enterprise users must first register the enterprise data consulting service system. During registration, enterprise users submit some basic information of the enterprise to the system, including enterprise registration information, financial data, market and sales data, human resources data, technology and R&D information, and customer and supplier information, and enter the basic information of the enterprise into the system;

[0063] Step 12: The system summarizes and concludes the enterprise's capital data to obtain three parameters related to the enterprise score, namely, market performance score X, financial status score Y and operation management score Z. The market performance score is divided into five levels: excellent, good, medium, poor and bad, represented by 5x, 4x, 3x, 2x, x respectively. The financial status score is divided into five levels: excellent, good, medium, poor and bad, represented by 5y, 4y, 3y, 2y, y respectively. The operation management score is divided into five levels: excellent, good, medium, poor and bad, represented by 5z, 4z, 3z, 2z, z respectively. The three values ​​of x, y and z are usually set manually. The enterprise score is obtained by summing the three scoring criteria to obtain the final score P. The expression of the enterprise score is:

[0064] P = X + Y + Z;

[0065] Step 13: The system divides enterprises into three levels: large enterprises, medium-sized enterprises, and small enterprises, which are represented by the three levels A, B, and C respectively. The total score P of the enterprise is calculated based on the scores of market performance, financial status, operation and management. The thresholds P1 and P2 are set based on manual experience, and P1>P2. When P>P1, the enterprise is determined to be a large enterprise and belongs to Class A. When P2<P<P1, the enterprise is determined to be a medium-sized enterprise and belongs to Class B. When P<P2, the enterprise is determined to be a small enterprise and belongs to Class C.

[0066] In the embodiment of the present invention, step S2 further includes the following steps:

[0067] Step S21: The enterprise user inputs consulting information into the system. The system preprocesses the consulting information text and splits the text data into multiple terms. The TF-IDF algorithm calculates the term frequency P and the inverse document frequency W of each term in the split consulting information in the entire document, and multiplies the term frequency and the inverse document frequency to obtain the TF-IDF value S = W × P of the term in the document. A threshold S0 is artificially defined based on historical experience. When S>S0, the term can be used as a feature of the consulting information. The terms that meet the condition S>S0 are collected and used as the feature R of the consulting information. The probability that the feature R belongs to different service types is calculated through the multi-classification logistic regression algorithm. Where R is the characteristic value of the consultation information, i = 1, 2, ..., k, k is the number of service types of the service system, is the weight vector of service type k, b i is the bias term for service type k, b i Obtained by the gradient descent algorithm, the probability is selected The largest type of service is the service that business users need;

[0068] Type of service, passed;

[0069] Step S22: The system establishes corresponding enterprise case and solution databases according to different service types. The system pre-processes the data in the corresponding enterprise case and solution database according to the service type selected by the enterprise user, extracts the feature H of the enterprise case and solution through the TF-IDF algorithm, and uses the nearest neighbor algorithm to extract the feature H of the enterprise case and solution. Calculate the similarity F between the feature R of the consulting information and the feature H of the enterprise cases and solutions, and manually set a threshold F0 to recommend enterprise cases and solutions that meet the condition F>F0 to enterprise users;

[0070] Step S23: Enterprise users rate their satisfaction with the service. User satisfaction δ is divided into four levels, namely excellent, good, average, and poor. The satisfaction rating criteria include system response time Q, solution relevance W, and user help E. These three rating criteria are all in percentage. Based on historical experience, weights of 0.2, 0.3, and 0.5 are added to the three rating criteria. The calculation formula for user satisfaction δ is:

[0071] δ=0.2Q+0.3W+0.5E;

[0072] In an embodiment of the present invention, step S3 further includes the following steps:

[0073] Step S31: By artificially setting thresholds δ1, δ2, and δ3, and δ1>δ2>δ3, when δ>δ1, the user satisfaction is excellent, when δ1>δ>δ2, the user satisfaction is good, when δ2>δ>δ3, the user satisfaction is average, and when δ<δ3, the user satisfaction is poor. When the user satisfaction is average or poor, the system recommends that the user receive manual service.

[0074] Step S32: The system evaluates the manual service level by three standards: working time T, service experience M and processing capacity N. The working time score is divided into three levels: ≤3 years, ≤5 years and >5 years, which are represented by 3t, 2t and t respectively. The service experience score is divided into three levels: experienced, relatively skilled and general experience, which are represented by 3m, 2m and m respectively. The processing capacity score is divided into three levels, which are represented by 3n, 2n and n respectively. The three values ​​of t, m and n are usually set manually. The enterprise score is obtained by summing the three scoring standards to obtain the final score ε. The expression of manual service level is:

[0075] ε=T+M+N;

[0076] Step S33: selecting different levels of manual services based on the enterprise's evaluation results. The levels of manual services are divided into three levels: expert level, professional level and skilled level. When the enterprise evaluation result is level A, expert level manual services are selected; when the enterprise evaluation result is level B, professional level manual services are selected; when the enterprise evaluation result is level C, skilled level manual services are selected;

[0077] Step S34: recommending different levels of manual services to enterprises with different rating levels. When the enterprise user finishes the manual service, the system sends a manual service rating request to the enterprise user.

[0078] In the embodiment of the present invention, step S34 further includes the following steps:

[0079] Step S341: Enterprise users divide the manual service rating θ into four levels, namely excellent, good, average, and poor. The manual service rating criteria include service attitude J, problem solving K, and user experience L. These three rating criteria are all in percentage. Based on historical experience, the weights of 0.35, 0.35, and 0.3 are added to the three rating criteria. The calculation formula for the satisfaction degree θ of problem solving is:

[0080] θ=0.35J+0.35K+0.3L

[0081] Step S342: By manually setting thresholds θ1, θ2, and θ3, and θ1>θ2>θ3, when θ>θ1, the manual service score is excellent, when θ1>θ>θ2, the manual service score is good, when θ2>θ>θ3, the manual service score is average, and when θ<θ3, the manual service score is poor.

[0082] In an embodiment of the present invention, step S4 further includes the following steps:

[0083] Step S41: The system calculates the overall service score μ by collecting the user service satisfaction δ and the manual service score θ. The expression of μ is:

[0084] μ=0.3δ+0.7θ

[0085] Step S42: The thresholds μ1, μ2, and μ3 are artificially set based on historical experience, and μ1>μ2>μ3. When μ>μ1, the overall service score is excellent; when μ1>μ>μ2, the overall service score is good; when μ2>μ>μ3, the overall service score is average; and when μ<μ3, the overall service score is poor. When the overall service is excellent, the system does not collect feedback from corporate users. When the overall service score is good, average, or poor, the system collects feedback information from corporate users and uploads the collected feedback information to the management end.

[0086] Embodiment 2: Embodiment 2 of the present invention provides an enterprise data consulting service system based on big data. Figure 2 A schematic diagram of the module composition of a big data-based enterprise data consulting service system provided in the second embodiment of the present invention is shown in FIG. Figure 2 As shown, the system includes:

[0087] User management module, used to manage user registration and login, and collect basic information of the enterprise;

[0088] Service management module, used to manage and select different types of consulting services;

[0089] The scoring module is used to score various services provided in the system.

[0090] In some embodiments of the present invention, comprising:

[0091] Registration unit, used for enterprise users to register services;

[0092] Login unit, used for enterprise users to log in;

[0093] The charging unit is used for enterprise users to pay for services and receive refunds;

[0094] Data collection unit, used to collect some basic information of enterprises.

[0095] In some embodiments of the present invention, comprising:

[0096] A service recommendation unit is used to recommend services that may be of interest to users based on user history data;

[0097] A service selection unit, used to select different service types to solve the problem;

[0098] The manual service unit is used to provide manual services to users.

[0099] In some embodiments of the present invention, comprising:

[0100] Enterprise rating unit, used to comprehensively rate different enterprises;

[0101] A satisfaction rating unit is used to rate the user's satisfaction with the service;

[0102] A manual service rating unit, used for users to rate manual services;

[0103] The service rating unit is used to obtain an overall service rating through the satisfaction rating and the manual service rating.

[0104] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0105] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for enterprise data consulting services based on big data, characterized by: The specific steps of the method include: Step S1: Enterprise users register and log in, collect the basic data of the enterprise, including enterprise basic information, financial data, market and sales data, human resources data, technology and R & D information, and customer and supplier information, enter the enterprise's historical consultation records into the system, and score the registered enterprise through the analysis and processing of the collected data. Step S2: Enterprise users input consultation information, process it through TF-IDF consultation information, extract corresponding feature information, judge the service type required by the user according to the feature information and the characteristics of different service types, and recommend relevant enterprise cases and solutions to the enterprise users based on the service type selected by the enterprise users and the input consultation information, and score the satisfaction degree of the service. Step S3: The system judges whether to recommend manual service to the enterprise users according to the score of the enterprise users' satisfaction with the service, recommends different levels of manual service according to different enterprise scores, and scores the manual service. Step S4: The system collects the service satisfaction score and the manual service score of the user, calculates the overall service score, judges whether it is necessary to collect feedback from the user through the overall service score, integrates the feedback, and uploads it to the management terminal.

2. According to claim 1, a method for enterprise data consulting service based on big data is characterized by: The said step S1 further includes the following steps: Step S11: Enterprise users first need to register for the enterprise data consultation service system. When registering, enterprise users submit some basic information of the enterprise, including enterprise registration information, financial data, market and sales data, human resources data, technology and R & D information, and customer and supplier information, and enter the enterprise basic information into the system. Step 12: The system summarizes and concludes three parameters related to the enterprise score through the enterprise's basic data, namely the market performance score X, the financial condition score Y, and the operation and management score Z. Among them, the market performance score is divided into 5 levels: excellent, good, medium, poor, and bad, which are represented by 5x, 4x, 3x, 2x, and x respectively. The financial condition score is divided into 5 levels: excellent, good, medium, poor, and bad, which are represented by 5y, 4y, 3y, 2y, and y respectively. The operation and management score is divided into 5 levels: excellent, good, medium, poor, and bad, which are represented by 5z, 4z, 3z, 2z, and z respectively. Among them, the three values of x, y, and z are usually set manually. The enterprise score is obtained by summing up the three scoring criteria, and the expression of the enterprise score is: P = X + Y + Z; Step 13: The system classifies enterprises into three levels: large enterprises, medium-sized enterprises, and small enterprises, which are replaced by the three levels A, B, and C respectively. Calculate the total score P of the enterprise according to the scores of market performance, financial condition, operation, and management. Set the thresholds P1 and P2 according to manual experience, and P1 > P2. When P > P1, it is determined that the enterprise is a large enterprise belonging to level A. When P2 < P < P1, it is determined that the enterprise is a medium-sized enterprise belonging to level B. When P < P2, it is determined that the enterprise is a small enterprise belonging to level C.

3. The enterprise data consulting service method based on big data according to claim 2 is characterized by: The said step S2 further includes the following steps: Step S21: The enterprise user inputs consulting information into the system. The system preprocesses the consulting information text and splits the text data into terms. The TF-IDF algorithm calculates the term frequency P and the inverse document frequency W of each term in the entire document after the split consulting information, and multiplies the term frequency and the inverse document frequency to obtain the TF-IDF value S = W × P of the term in the document. A threshold S0 is artificially defined based on historical experience. When S>S0, the term can be used as a feature of the consulting information. The terms that meet the condition S>S0 are collected and used as the feature R of the consulting information. The probability that the feature R belongs to different service types is calculated through the multi-classification logistic regression algorithm. Where R is the characteristic value of the consultation information, i = 1, 2, ..., k, k is the number of service types of the service system, is the weight vector of service type k, b i is the bias term for service type k, b i Obtained by the gradient descent algorithm, the probability is selected The largest type of service is the service that business users need; Step S22: The system establishes corresponding enterprise case and solution databases according to different service types. The system pre-processes the data in the corresponding enterprise case and solution database according to the service type selected by the enterprise user, extracts the feature H of the enterprise case and solution through the TF-IDF algorithm, and uses the nearest neighbor algorithm to extract the feature H of the enterprise case and solution. Calculate the similarity F between the feature R of the consulting information and the feature H of the enterprise cases and solutions, and manually set a threshold F0 to recommend enterprise cases and solutions that meet the condition F>F0 to enterprise users; Step S23: Enterprise users rate their satisfaction with the service. User satisfaction δ is divided into four levels, namely excellent, good, average, and poor. The satisfaction rating criteria include system response time Q, solution relevance W, and user help E. These three rating criteria are all in percentage. Based on historical experience, weights of 0.2, 0.3, and 0.5 are added to the three rating criteria. The calculation formula for user satisfaction δ is: δ=0.2Q+0.3W+0.5E.

4. The enterprise data consulting service method based on big data according to claim 3 is characterized by: The step S3 further comprises the following steps: Step S31: By manually setting thresholds δ1, δ2, and δ3, and δ1>δ2>δ3, when δ>δ1, the user satisfaction is excellent, when δ1>δ>δ2, the user satisfaction is good, when δ2>δ>δ3, the user satisfaction is average, and when δ<δ3, the user satisfaction is poor. When the user satisfaction is average or poor, the system recommends the user to perform manual service; Step S32: The system evaluates the manual service level by three standards: working time T, service experience M and processing capacity N. The working time score is divided into three levels: ≤3 years, ≤5 years and >5 years, which are represented by 3t, 2t and t respectively. The service experience score is divided into three levels: experienced, relatively skilled and general experience, which are represented by 3m, 2m and m respectively. The processing capacity score is divided into three levels, which are represented by 3n, 2n and n respectively. The three values ​​of t, m and n are usually set manually. The enterprise score is obtained by summing the three scoring standards to obtain the final score ε. The expression of manual service level is: ε=T+M+N; Step S33: selecting different levels of manual services based on the enterprise's evaluation results. The levels of manual services are divided into three levels: expert level, professional level and skilled level. When the enterprise evaluation result is level A, expert level manual services are selected; when the enterprise evaluation result is level B, professional level manual services are selected; when the enterprise evaluation result is level C, skilled level manual services are selected; Step S34: recommending different levels of manual services to enterprises with different rating levels. When the enterprise user finishes the manual service, the system sends a manual service rating request to the enterprise user.

5. The enterprise data consulting service method based on big data according to claim 4 is characterized by: The step S34 further comprises the following steps: Step S341: Enterprise users divide the manual service rating θ into four levels, namely excellent, good, average, and poor. The manual service rating criteria include service attitude J, problem solving K, and user experience L. These three rating criteria are all in percentage. Based on historical experience, the weights of 0.35, 0.35, and 0.3 are added to the three rating criteria. The calculation formula for the satisfaction degree θ of problem solving is: θ=0.35J+0.35K+0.3L Step S342: By manually setting thresholds θ1, θ2, and θ3, and θ1>θ2>θ3, when θ>θ1, the manual service score is excellent, when θ1>θ>θ2, the manual service score is good, when θ2>θ>θ3, the manual service score is average, and when θ<θ3, the manual service score is poor.

6. The enterprise data consulting service method based on big data according to claim 5 is characterized by: The step S4 further comprises the following steps: Step S41: The system calculates the overall service score μ by collecting the user service satisfaction δ and the manual service score θ. The expression of μ is: μ=0.3δ+0.7θ Step S42: The thresholds μ1, μ2, and μ3 are artificially set based on historical experience, and μ1>μ2>μ3. When μ>μ1, the overall service score is excellent; when μ1>μ>μ2, the overall service score is good; when μ2>μ>μ3, the overall service score is average; when μ<μ3, the overall service score is poor. When the overall service is excellent, the system does not collect feedback from corporate users. When the overall service score is good, average, or poor, the system collects feedback information from corporate users and uploads the collected feedback information to the management end.

7. An enterprise data consulting service system based on big data, characterized by: The system comprises: User management module, used to manage user registration and login, and collect basic information of the enterprise; Service management module, used to manage and select different types of consulting services; The scoring module is used to score various services provided in the system.

8. The enterprise data consulting service system based on big data according to claim 7 is characterized by: The user management module comprises: Registration unit, used for enterprise users to register services; Login unit, used for enterprise users to log in; Data collection unit, used to collect some basic information of enterprises.

9. The enterprise data consulting service system based on big data according to claim 8, characterized in that: The service management module includes: A service recommendation unit is used to recommend services that may be of interest to users based on user history data; A service selection unit, used to select different service types to solve the problem; The manual service unit is used to provide manual services to users.

10. The enterprise data consulting service system based on big data according to claim 9, characterized in that: The scoring module includes: Enterprise rating unit, used to comprehensively rate different enterprises; A satisfaction rating unit is used to rate the user's satisfaction with the service; A manual service rating unit, used for users to rate manual services; Service rating unit, used to derive the overall service rating through satisfaction rating and manual service rating The feedback unit is used to receive feedback information from enterprise users and upload it to the management end.

Images