Intelligent information consultation service system based on big data analysis

Through the big data analysis system, the consulting section is evaluated in popularity and satisfaction, which solves the problem of difficulty in analyzing the popularity and difficulty in evaluating management in the existing technology, and improves the satisfaction and intelligence of consulting services.

CN118981485AInactive Publication Date: 2024-11-19山东辛丁技术有限公司

Patent Information

Application Number
CN202411131130.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-17
Publication Date
2024-11-19
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The existing technology is difficult to conduct reasonable analysis of different consulting sections to judge their consulting popularity status, and it is impossible to accurately evaluate the feedback performance of sections with low consulting popularity, and it is impossible to comprehensively evaluate the management difficulty of the information consulting service platform, resulting in low intelligence. , affects the satisfaction of consulting services.

Method used

An intelligent information consulting service system based on big data analysis was designed, including section consulting analysis module, consulting satisfaction survey output module and maintenance management judgment module. It is evaluated through time-divided summary analysis, user consultation frequency and evaluation information, and marked High-frequency and low-frequency sections and generate management signals to strengthen supervision and improve consulting satisfaction.

Benefits of technology

The popularity and satisfaction analysis of the consulting section has been realized, the management of high-frequency sections and low-frequency sections has been improved, the management difficulty of the information consulting service platform has been judged, and the satisfaction and intelligence of consulting services have been significantly improved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118981485A_ABST
    Figure CN118981485A_ABST
Patent Text Reader

Abstract

The invention belongs to the technical field of information consultation service management, and particularly relates to an intelligent information consultation service system based on big data analysis, which comprises an information consultation service platform, a registration and login verification module, a section consultation analysis module, a consultation satisfaction survey output module, a maintenance management judgment module and a consultation management end. The section consultation analysis module analyzes to determine a high-frequency consultation section and a low-frequency consultation section, and the consultation satisfaction survey output module analyzes the consultation satisfaction condition of the low-frequency consultation section to determine a non-optimal consultation section and a precise consultation section. The management is enhanced for the high-frequency consultation section and the consultation non-optimal section subsequently, the management difficulty level for the information consultation service platform is judged through the analysis of the maintenance management judgment module, the supervision is enhanced for the information consultation service platform subsequently when the strong management signal is generated, the intelligent degree is high, and the efficiency is high. And the consultation service satisfaction degree can be improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

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

[0002] Information consulting services refer to information service activities in which information service departments, based on the needs of users, rely on professional knowledge, practical experience and innovation capabilities, fully develop and utilize information resources, use scientific methods and modern technical means to provide users with suggestions, plans, strategies, plans or measures to solve problems. They are widely used in finance, medical care, education, business and other fields; At present, when providing information consulting services, it is often difficult to conduct reasonable analysis on different consulting sections to determine their consulting popularity, and it is impossible to analyze the consulting sections with low consulting popularity to accurately evaluate their consulting feedback performance. In addition, it is impossible to comprehensively analyze and comprehensively evaluate the management difficulty of the information consulting service platform, which is not conducive to improving the satisfaction of consulting services and has a low degree of intelligence; In view of the above technical defects, a solution is now proposed. Summary of the invention

[0003] The purpose of the present invention is to provide an intelligent information consulting service system based on big data analysis, which solves the problems that the prior art is difficult to conduct reasonable analysis on different consulting sections to determine their consulting popularity, and is unable to analyze consulting sections with lower consulting popularity to accurately evaluate their consulting feedback performance, as well as is unable to comprehensively analyze and comprehensively evaluate the management difficulty of the information consulting service platform and the low level of intelligence.

[0004] To achieve the above object, the present invention provides the following technical solutions: An intelligent information consulting service system based on big data analysis, including an information consulting service platform, a registration and login verification module, a section consulting analysis module, a consulting satisfaction survey output module, a maintenance management judgment module and a consulting management terminal; The information consulting service platform contains several consulting sections, and the corresponding consulting section is marked as target section i, where i is a natural number greater than 1; The registration and login verification module is used to register users and store user registration information, mark successfully registered users as registered users, and authenticate the identity of registered users when they log in. If the identity authentication is correct, the corresponding registered users are allowed to log in to the information consulting service platform; The section consultation analysis module analyzes the user consultation status of the target section i during the detection period, marks the target section i as a high-frequency consultation section or a low-frequency consultation section through analysis, and sends the high-frequency consultation section to the consultation management end via the information consultation service platform, and sends the low-frequency consultation section to the consultation satisfaction survey output module; The consultation satisfaction survey output module analyzes the consultation satisfaction status of each low-frequency consultation section during the detection period, marks the corresponding low-frequency consultation section as a non-optimal consultation section or a precise consultation section through analysis, and sends the non-optimal consultation section to the consultation management end through the information consultation service platform; The maintenance management judgment module judges the management difficulty of the information consulting service platform through analysis, generates a strong management signal or a weak management signal accordingly, and sends the strong management signal or the weak management signal to the consulting management end via the information consulting service platform.

[0005] Furthermore, the specific analysis process of the section consultation analysis module is as follows: The section consultation evaluation value of the target section i during the detection period is obtained through time-phase summary analysis, and the section consultation evaluation value is numerically compared with the preset section consultation evaluation threshold. If the section consultation evaluation value exceeds the preset section consultation evaluation threshold, the target section i is marked as a high-frequency consultation section; if the section consultation evaluation value does not exceed the preset section consultation evaluation threshold, the target section i is marked as a low-frequency consultation section.

[0006] Furthermore, the specific analysis process of time-phase summary analysis is as follows: Several detection time periods are set within the detection period, the number of information consultations and the number of users involved in the target section i within the corresponding detection time period are collected and marked as the consultation frequency detection value and the consultant detection value, respectively, the consultation frequency detection value and the consultant detection value are numerically compared with the preset consultation frequency detection threshold and the preset consultant detection threshold, respectively, if the consultation frequency detection value or the consultant detection value exceeds the corresponding preset threshold, the corresponding detection time period is marked as a hot inquiry period; The number of hot inquiry time periods in the detection period is obtained and the ratio is calculated with the total number of detection time periods to obtain the hot inquiry detection value, and the consultation frequency detection values ​​of all detection time periods in the detection period are averaged to obtain the consultation frequency table value, and the consultation person detection values ​​of all detection time periods in the detection period are averaged to obtain the consultation person table value; the section consultation evaluation value is obtained by numerically calculating the hot inquiry detection value, the consultation frequency table value and the consultation person table value.

[0007] Furthermore, the specific analysis process of the consultation satisfaction survey output module is as follows: Obtain all consultation evaluation information after information consultation in the corresponding low-frequency consultation section during the detection period, and mark the consultation evaluation information that is dissatisfied with the corresponding consultation results as abnormal evaluation information; obtain the number of abnormal evaluation information and mark it as the abnormal evaluation detection value, and calculate the ratio of the abnormal evaluation detection value to the total number of consultation evaluation information in the corresponding low-frequency consultation section during the detection period to obtain the abnormal evaluation ratio; And obtain the number of registered users who made consulting evaluations in the corresponding low-frequency consulting section during the detection period and mark them as the human evaluation number inspection value, and mark the number of registered users who made different evaluation information as the human evaluation different inspection value, and mark the ratio of the human evaluation different inspection value to the human evaluation number inspection value as the human evaluation different ratio value; The consultation satisfaction poor value is obtained by numerically calculating the abnormal review detection value, the abnormal review proportion detection value, the human review abnormal detection value and the human review abnormal proportion value, and the consultation satisfaction poor value is numerically compared with the preset consultation satisfaction poor threshold. If the consultation satisfaction poor value exceeds the preset consultation satisfaction poor threshold, the corresponding low-frequency consultation section will be marked as a consultation non-excellent section; if the consultation satisfaction poor value does not exceed the preset consultation satisfaction poor threshold, the corresponding low-frequency consultation section will be marked as a consultation accurate section.

[0008] Furthermore, the specific analysis process of the maintenance management judgment module includes: Obtain all high-frequency consultation sections and non-optimal consultation sections of the information consultation service platform during the detection period, and mark the number ratio values ​​of high-frequency consultation sections and the number ratio values ​​of non-optimal consultation sections as high-frequency consultation detection ratio values ​​and non-optimal consultation detection ratio values, respectively; The consultation feedback inspection time value and push supervision frequency value during the detection period are obtained, and the growth rate of registered users of the information consulting service platform during the detection period is marked as the registration growth rate value; the maintenance judgment value is obtained by numerically calculating the high-frequency consultation inspection value, the consultation non-optimal inspection value, the consultation feedback inspection time value, the push supervision frequency value and the registration growth rate value, and the maintenance judgment value is numerically compared with the preset maintenance judgment threshold. If the maintenance judgment value exceeds the preset maintenance judgment threshold, a strong management signal is generated; if the maintenance judgment value does not exceed the preset maintenance judgment threshold, a weak management signal is generated.

[0009] Furthermore, the maintenance management judgment module is connected to the consultation feedback timeliness analysis module and the information push supervision module in communication. The consultation feedback timeliness analysis module is used to collect the information feedback time of the information consultation service platform when conducting information consultation, calculate the average of all information feedback time in the detection period to obtain the consultation feedback detection time value, and send the consultation feedback detection time value to the maintenance management judgment module; The information push supervision module is used to push corresponding information to the registered user when the registered user logs in to the information consulting service platform. If the corresponding registered user does not click to view the pushed information, the corresponding information push process will be marked as a push-unconscious process; the number of push-unconscious processes during the detection period is obtained, and the ratio of the number of push-unconscious processes to the total number of information pushes during the detection period is marked as a push supervision anomaly value, and the push supervision anomaly value is sent to the maintenance management judgment module.

[0010] Furthermore, the information push supervision module is communicated with the personnel section matching analysis module. The personnel section matching analysis module is used to trace back from the login time as the end point when the corresponding registered user logs in and set a tracing period with a duration of L1. The high matching sections of the corresponding registered user in the tracing period are determined through analysis, and the high matching sections of the corresponding registered user are sent to the information push supervision module. The information push supervision module pushes the information of the corresponding high matching section to the corresponding registered user when the corresponding registered user logs in.

[0011] Furthermore, the specific analysis process of the personnel section matching analysis module is as follows: All consultation sections consulted by the corresponding registered user during the traceability period are obtained, and the corresponding consultation section consulted is marked as the section to be analyzed by the corresponding registered user; the total number of consultations by the corresponding registered user in the corresponding section to be analyzed during the traceability period is collected and marked as the total consultation frequency value, and the length of stay in the corresponding section to be analyzed is collected during the corresponding login consultation process, and the ratio of the length of stay to the duration of the corresponding login consultation process is marked as the section stay time ratio; Compare the section dwell time value with the preset section dwell time value. If the section dwell time value exceeds the preset section dwell time threshold, mark the corresponding login consultation process as the target consultation process of the corresponding section to be analyzed. Obtain all the stay durations of the corresponding registered users for the corresponding section to be analyzed during the tracing period and calculate the sum to obtain the total section stay duration, and mark the ratio of the number of target consultation processes of the corresponding registered users for the corresponding section to be analyzed during the tracing period to the total number of logged-in consultation processes as the target consultation frequency value; The matching evaluation value is obtained by numerically calculating the total consultation frequency value, the total section stay time value and the target consultation frequency value. All sections to be analyzed of the corresponding registered user are sorted in descending order according to the matching evaluation value, and the section to be analyzed that is ranked first is marked as a high-matching section of the corresponding registered user.

[0012] Compared with the prior art, the present invention has the following beneficial effects: 1. In the present invention, the high-frequency consultation section and the low-frequency consultation section are analyzed by the section consultation analysis module, and the consultation satisfaction survey output module analyzes the consultation satisfaction status of the low-frequency consultation section to determine the consultation non-optimal section and the consultation precision section, and subsequently strengthens the management of the high-frequency consultation section and the consultation non-optimal section, and analyzes the management difficulty of the information consultation service platform by the maintenance management judgment module, and subsequently strengthens the supervision of the information consultation service platform when a strong management signal is generated, which is conducive to significantly improving the satisfaction of the consultation service; 2. In the present invention, a tracing period is set when the corresponding registered user logs in through the personnel section matching analysis module, and the high matching section of the corresponding registered user in the tracing period is determined through analysis, and the high matching section of the corresponding registered user is sent to the information push supervision module. The information push supervision module pushes the information of the corresponding high matching section to the corresponding registered user when the corresponding registered user logs in, which is conducive to quickly pushing the information content that each registered user is interested in as much as possible, and has a high degree of intelligence. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to facilitate understanding by those skilled in the art, the present invention is further described below in conjunction with the accompanying drawings; Figure 1 This is a system block diagram of Embodiment 1 of the present invention; Figure 2 This is a system block diagram of Embodiment 2 of the present invention. DETAILED DESCRIPTION

[0014] 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.

[0015] Embodiment 1: Figure 1 As shown, the present invention proposes an intelligent information consulting service system based on big data analysis, including an information consulting service platform, a registration and login verification module, a section consulting analysis module, a consulting satisfaction survey output module, a maintenance management judgment module and a consulting management terminal; The information consulting service platform contains several consulting sections (each consulting section has different information types, such as several sections for different industries, each section is responsible for information consulting feedback of the corresponding industry), and the corresponding consulting section is marked as target section i, and i is a natural number greater than 1; The registration and login verification module is used to register users and store user registration information, mark successfully registered users as registered users, and authenticate the registered users when they log in. If the identity authentication is correct, the corresponding registered users are allowed to log in to the information consultation service platform; among them, the identity authentication methods include password verification, fingerprint verification, mobile phone verification code verification, etc.

[0016] The section consultation analysis module analyzes the user consultation status of the target section i during the detection period (preferably, the detection period is twenty days), marks the target section i as a high-frequency consultation section or a low-frequency consultation section through analysis, and sends the high-frequency consultation section to the consultation management end through the information consultation service platform, which can accurately feedback the consultation popularity status of each consultation section during the detection period, strengthen supervision of the high-frequency consultation section in the future, and continuously update, improve and correct the information of the high-frequency consultation section to ensure the accuracy of the consultation feedback information; the specific analysis process of the section consultation analysis module is as follows: Several detection time periods are set within the detection period, the number of information consultations and the number of users involved in the target section i within the corresponding detection time period are collected and marked as the consultation frequency detection value and the consultant detection value, respectively, and the consultation frequency detection value and the consultant detection value are numerically compared with the preset consultation frequency detection threshold and the preset consultant detection threshold, respectively. If the consultation frequency detection value or the consultant detection value exceeds the corresponding preset threshold, indicating that the consultation in the corresponding detection time period is relatively busy, the corresponding detection time period is marked as a hot inquiry time period; The number of hot inquiry time periods in the detection period is obtained and the ratio thereof is calculated with the total number of detection time periods to obtain the hot inquiry detection value, and the consultation frequency detection values ​​of all detection time periods in the detection period are averaged to obtain the consultation frequency table value, and the consultation person detection values ​​of all detection time periods in the detection period are averaged to obtain the consultation person table value; By formula The hot inquiry detection value ZYi, the consultation frequency table value ZWi and the consultation person table value ZNi are numerically calculated to obtain the section consultation evaluation value ZXi; wherein rh1, rh2 and rh3 are preset proportional coefficients, rh1>rh3>rh2>0; and the larger the value of the section consultation evaluation value ZXi, the more important it is for the target section i; The section consultation evaluation value ZXi is numerically compared with the preset section consultation evaluation threshold. If the section consultation evaluation value ZXi exceeds the preset section consultation evaluation threshold, indicating that the importance of the target section i is relatively strong, the target section i is marked as a high-frequency consultation section; if the section consultation evaluation value ZXi does not exceed the preset section consultation evaluation threshold, indicating that the importance of the target section i is relatively weak, the target section i is marked as a low-frequency consultation section.

[0017] The section consultation analysis module sends the low-frequency consultation section to the consultation satisfaction survey output module. The consultation satisfaction survey output module analyzes the consultation satisfaction status of each low-frequency consultation section during the detection period, and marks the corresponding low-frequency consultation section as a non-optimal consultation section or a precise consultation section through analysis, thereby realizing secondary analysis of the low-frequency consultation section. The non-optimal consultation sections are sent to the consultation management end through the information consultation service platform, which can reasonably analyze and accurately feedback the consultation feedback satisfaction status of each low-frequency consultation section, and strengthen the management of the non-optimal consultation sections in the future, improve and correct the information of the non-optimal consultation sections, and ensure the accuracy of the subsequent consultation feedback of the non-optimal consultation sections, thereby improving the consultation satisfaction; the specific analysis process of the consultation satisfaction survey output module is as follows: Obtain all consultation evaluation information after information consultation in the corresponding low-frequency consultation section during the detection period, and mark the consultation evaluation information that is dissatisfied with the corresponding consultation results as abnormal evaluation information; obtain the number of abnormal evaluation information and mark it as the abnormal evaluation detection value, and calculate the ratio of the abnormal evaluation detection value to the total number of consultation evaluation information in the corresponding low-frequency consultation section during the detection period to obtain the abnormal evaluation ratio; And obtain the number of registered users who made consulting evaluations in the corresponding low-frequency consulting section during the detection period and mark them as the human evaluation number inspection value, and mark the number of registered users who made different evaluation information as the human evaluation different inspection value, and mark the ratio of the human evaluation different inspection value to the human evaluation number inspection value as the human evaluation different ratio value; By formula The abnormal evaluation detection value MYi, the abnormal evaluation ratio detection value MPi, the human evaluation abnormal detection value MSi and the human evaluation ratio value MFi are numerically calculated to obtain the consultation satisfaction poor table value MXi; wherein c1, c2, c3, c4 are preset proportional coefficients with values ​​greater than zero, and the larger the value of the consultation satisfaction poor table value MXi, the worse the consultation feedback performance of the corresponding low-frequency consultation section during the detection period; The consultation satisfaction poor table value MXi is numerically compared with the preset consultation satisfaction poor table threshold. If the consultation satisfaction poor table value MXi exceeds the preset consultation satisfaction poor table threshold, it indicates that the consultation feedback performance of the corresponding low-frequency consultation section during the detection period is poor, and the corresponding low-frequency consultation section is marked as a non-excellent consultation section; if the consultation satisfaction poor table value MXi does not exceed the preset consultation satisfaction poor table threshold, it indicates that the consultation feedback performance of the corresponding low-frequency consultation section during the detection period is good, and the corresponding low-frequency consultation section is marked as an accurate consultation section.

[0018] The maintenance management judgment module determines the management difficulty of the information consulting service platform through analysis, and generates a strong management signal or a weak management signal accordingly, and sends the strong management signal or the weak management signal to the consulting management end through the information consulting service platform. When a strong management signal is generated, the information consulting service platform is subsequently strengthened for supervision, so that corresponding management plans can be made in a convenient, timely and reasonable manner, with a high degree of intelligence. The specific analysis process of the maintenance management judgment module is as follows: Obtain all high-frequency consultation sections and non-optimal consultation sections of the information consultation service platform during the detection period, and mark the number ratio values ​​of high-frequency consultation sections and the number ratio values ​​of non-optimal consultation sections as high-frequency consultation detection ratio values ​​and non-optimal consultation detection ratio values, respectively; Obtain the consultation feedback inspection time value and push supervision frequency value during the inspection period, and mark the growth rate of registered users of the information consultation service platform during the inspection period as the registration growth rate value; The high-frequency consultation inspection value QW, the consultation non-optimal inspection value NY, the consultation feedback inspection time value FK, the push supervision frequency value SM and the registration growth rate value YS are numerically calculated by the formula WY=(up1*QW+up2*NY+up3*FK+up4*SM+up5*YS) / 5 to obtain the maintenance judgment value WY; among them, up1, up2, up3, up4, up5 are preset proportional coefficients with values ​​greater than zero, and the larger the value of the maintenance judgment value WY, the greater the management difficulty of information consultation management during the detection period, and the more management needs to be strengthened; The maintenance judgment value WY is numerically compared with the preset maintenance judgment threshold. If the maintenance judgment value WY exceeds the preset maintenance judgment threshold, it indicates that the management difficulty of information consultation management during the detection period is relatively large and management needs to be strengthened, then a strong management signal is generated; if the maintenance judgment value WY does not exceed the preset maintenance judgment threshold, it indicates that the management difficulty of information consultation management during the detection period is relatively small, then a weak management signal is generated.

[0019] Embodiment 2: Figure 2 As shown, the difference between this embodiment and the first embodiment is that the maintenance management judgment module is connected to the consultation feedback timeliness analysis module and the information push supervision module in communication, and the consultation feedback timeliness analysis module is used to collect the information feedback time of the information consultation service platform when conducting information consultation (that is, the interval between the time when the corresponding registered user conducts consultation and the time when the platform makes feedback); The consultation feedback detection time value FK is obtained by averaging the time lengths of all information feedback within the detection period, and the consultation feedback detection time value FK is sent to the maintenance management judgment module to provide data support for the analysis process of the maintenance management judgment module and ensure the comprehensiveness and accuracy of its analysis results. It should be noted that the larger the value of the consultation feedback detection time value FK, the less timely the consultation feedback during the detection period is overall.

[0020] Furthermore, the information push supervision module is used to push corresponding information to the registered user when the registered user logs in to the information consulting service platform. If the corresponding registered user does not click to view the pushed information, indicating that the corresponding registered user is not interested in the pushed information, the corresponding information push process is marked as a push-insensitive process; The number of times the senseless process is pushed during the detection period is obtained, and the ratio of the number of times the senseless process is pushed to the total number of information pushes during the detection period is marked as the push supervision frequency difference value SM, and the push supervision frequency difference value SM is sent to the maintenance management judgment module to provide data support for the analysis process of the maintenance management judgment module, and further ensure the comprehensiveness and accuracy of its analysis results; it should be noted that the larger the value of the push supervision frequency difference value SM, the worse the accuracy of the information push during the detection period.

[0021] Furthermore, the information push supervision module is connected to the personnel section matching analysis module in communication. The personnel section matching analysis module is used to trace back the corresponding registered user from the login time as the end point of time and set the tracing period of L1. Preferably, L1 is seventy-two hours; and determine the high matching section of the corresponding registered user in the tracing period through analysis; And the high matching sections of the corresponding registered users are sent to the information push supervision module. The information push supervision module pushes the information of the corresponding high matching sections to the corresponding registered users when they log in, which is conducive to quickly pushing the information content that they are interested in to each registered user as much as possible, with a high degree of intelligence; the specific analysis process of the personnel section matching analysis module is as follows: All consultation sections consulted by the corresponding registered user during the traceability period are obtained, and the corresponding consultation section consulted is marked as the section to be analyzed by the corresponding registered user; the total number of consultations by the corresponding registered user in the corresponding section to be analyzed during the traceability period is collected and marked as the total consultation frequency value, and the length of stay in the corresponding section to be analyzed is collected during the corresponding login consultation process, and the ratio of the length of stay to the duration of the corresponding login consultation process is marked as the section stay time ratio; Compare the section dwell time value with the preset section dwell time value. If the section dwell time value exceeds the preset section dwell time threshold, it indicates that the corresponding login consultation process is mainly for the consultation of the corresponding section to be analyzed, then mark the corresponding login consultation process as the target consultation process of the corresponding section to be analyzed; Obtain all the stay durations of the corresponding registered users for the corresponding section to be analyzed during the tracing period and calculate the sum to obtain the total section stay duration, and mark the ratio of the number of target consultation processes of the corresponding registered users for the corresponding section to be analyzed during the tracing period to the total number of logged-in consultation processes as the target consultation frequency value; The total consultation frequency value PKi, the total section stay time value RLi and the target consultation frequency value XNi are numerically calculated using the formula PXi=(ew1*PKi+ew2*RLi) / ew3+ew3*XNi to obtain the matching evaluation value PXi, wherein ew1, ew2 and ew3 are preset proportional coefficients, ew3>ew1>ew2>0; and, the larger the matching evaluation value PXi, the greater the corresponding registered user's current consulting interest in the corresponding section to be analyzed; all sections to be analyzed of the corresponding registered user are sorted in descending order according to the matching evaluation value, and the section to be analyzed that is ranked first is marked as a high-matching section of the corresponding registered user.

[0022] The working principle of the present invention: when in use, the user consultation status of each consultation section during the detection period is analyzed through the section consultation analysis module, which can accurately feedback the consultation popularity of each consultation section during the detection period and determine the high-frequency consultation section and the low-frequency consultation section, and the consultation satisfaction status of each low-frequency consultation section during the detection period is analyzed through the consultation satisfaction survey output module to achieve secondary analysis of the low-frequency consultation section, and the analysis is used to determine the non-optimal consultation section and the precise consultation section, and the management of the high-frequency consultation section and the non-optimal consultation section is strengthened in the future, and the maintenance management judgment module is used to analyze to determine the management difficulty of the information consultation service platform, and when a strong management signal is generated, the supervision of the information consultation service platform is strengthened in the future, so that corresponding management plans can be made conveniently, timely and reasonably, with a high degree of intelligence, which is conducive to improving the satisfaction with the consultation service.

[0023] The above formulas are all dimensionless and numerical calculations. The formula is a formula obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formula are set by technicians in this field according to actual conditions. The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the contents of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that technicians in the relevant technical field can understand and use the present invention well. The present invention is only limited by the claims and their full scope and equivalents.

Claims

1. An intelligent information consulting service system based on big data analysis, It is characterized in that It includes information consulting service platform, registration and login verification module, section consulting analysis module, consulting satisfaction survey output module, maintenance management judgment module and consulting management terminal; The information consulting service platform contains several consulting sections, and the corresponding consulting section is marked as target section i, where i is a natural number greater than 1; The registration and login verification module is used to register users and store user registration information, mark successfully registered users as registered users, and authenticate the identity of registered users when they log in. If the identity authentication is correct, the corresponding registered users are allowed to log in to the information consulting service platform; The section consultation analysis module analyzes the user consultation status of the target section i during the detection period, marks the target section i as a high-frequency consultation section or a low-frequency consultation section through analysis, and sends the high-frequency consultation section to the consultation management end via the information consultation service platform, and sends the low-frequency consultation section to the consultation satisfaction survey output module; The consultation satisfaction survey output module analyzes the consultation satisfaction status of each low-frequency consultation section during the detection period, marks the corresponding low-frequency consultation section as a non-optimal consultation section or a precise consultation section through analysis, and sends the non-optimal consultation section to the consultation management end through the information consultation service platform; The maintenance management judgment module judges the management difficulty of the information consulting service platform through analysis, generates a strong management signal or a weak management signal accordingly, and sends the strong management signal or the weak management signal to the consulting management end via the information consulting service platform.

2. According to claim 1, an intelligent information consulting service system based on big data analysis, It is characterized in that The specific analysis process of the section consultation analysis module is as follows: The section consultation evaluation value of the target section i during the detection period is obtained by summarizing and analyzing the sections in different time periods. If the section consultation evaluation value exceeds the preset section consultation evaluation threshold, the target section i is marked as a high-frequency consultation section. If the section consultation evaluation value does not exceed the preset section consultation evaluation threshold, the target section i is marked as a low-frequency consultation section.

3. According to claim 2, an intelligent information consulting service system based on big data analysis, It is characterized in that The specific analysis process of time-phase summary analysis is as follows: Several detection periods are set during the detection period, and the number of information consultations and the number of users involved in the target section i in the corresponding detection period are collected and marked as the consultation frequency detection value and the consultant detection value respectively. If the consultation frequency detection value or the consultant detection value exceeds the corresponding preset threshold, the corresponding detection period is marked as a hot inquiry period; The number of hot inquiry time periods in the detection period is obtained and the ratio thereof is calculated with the total number of detection time periods to obtain the hot inquiry detection value, and the consultation frequency detection values ​​of all detection time periods in the detection period are averaged to obtain the consultation frequency table value, and the consultation person detection values ​​of all detection time periods in the detection period are averaged to obtain the consultation person table value; The section consultation evaluation value is obtained by numerically calculating the hot inquiry detection value, the consultation frequency table value and the consultant table value.

4. According to claim 1, an intelligent information consulting service system based on big data analysis, It is characterized in that The specific analysis process of the consulting satisfaction survey output module is as follows: Obtain all consultation evaluation information after information consultation in the corresponding low-frequency consultation section during the detection period, and mark the consultation evaluation information that is dissatisfied with the corresponding consultation results as abnormal evaluation information; The number of different evaluation information is obtained and marked as different evaluation detection value, and the different evaluation detection value is calculated by ratio between the different evaluation detection value and the total number of consulting evaluation information of the corresponding low-frequency consulting section during the detection period to obtain the different evaluation ratio detection value; And obtain the number of registered users who made consulting evaluations in the corresponding low-frequency consulting section during the detection period and mark them as the human evaluation number inspection value, and mark the number of registered users who made different evaluation information as the human evaluation different inspection value, and mark the ratio of the human evaluation different inspection value to the human evaluation number inspection value as the human evaluation different ratio value; The consultation satisfaction poor value is obtained by numerically calculating the abnormal review detection value, abnormal review percentage detection value, human review abnormal detection value and human review abnormal percentage value. If the consultation satisfaction poor value exceeds the preset consultation satisfaction poor threshold, the corresponding low-frequency consultation section is marked as a consultation non-excellent section. If the consultation satisfaction score does not exceed the preset consultation satisfaction score threshold, the corresponding low-frequency consultation section will be marked as a precise consultation section.

5. According to claim 1, an intelligent information consulting service system based on big data analysis, It is characterized in that The specific analysis process of the maintenance management judgment module includes: Obtain all high-frequency consultation sections and non-optimal consultation sections of the information consultation service platform during the detection period, and mark the number ratio values ​​of high-frequency consultation sections and the number ratio values ​​of non-optimal consultation sections as high-frequency consultation detection ratio values ​​and non-optimal consultation detection ratio values, respectively; The maintenance judgment value is obtained by numerically calculating the high-frequency consultation inspection value, the consultation non-optimal inspection value, the consultation feedback inspection time value, the push supervision frequency value and the registration growth rate value. If the maintenance judgment value exceeds the preset maintenance judgment threshold, a strong management signal is generated; if the maintenance judgment value does not exceed the preset maintenance judgment threshold, a weak management signal is generated.

6. According to claim 5, an intelligent information consulting service system based on big data analysis, It is characterized in that The maintenance management judgment module is connected to the consultation feedback timeliness analysis module and the information push supervision module. The consultation feedback timeliness analysis module is used to collect the information feedback time of the information consultation service platform during information consultation, calculate the average of all information feedback time in the detection period to obtain the consultation feedback detection time value, and send the consultation feedback detection time value to the maintenance management judgment module; The information push supervision module is used to push corresponding information to the registered user when the registered user logs in to the information consulting service platform. If the corresponding registered user does not click to view the pushed information, the corresponding information push process will be marked as a push-unconscious process; the number of push-unconscious processes during the detection period is obtained, and the ratio of the number of push-unconscious processes to the total number of information pushes during the detection period is marked as a push supervision anomaly value, and the push supervision anomaly value is sent to the maintenance management judgment module.

7. According to claim 6, an intelligent information consulting service system based on big data analysis, It is characterized in that The information push supervision module is communicated with the personnel section matching analysis module. The personnel section matching analysis module is used to trace back from the login time as the end point of time when the corresponding registered user logs in and set a tracing period with a duration of L1. The high-matching section of the corresponding registered user in the tracing period is determined through analysis, and the high-matching section of the corresponding registered user is sent to the information push supervision module. The information push supervision module pushes the information of the corresponding high-matching section to the corresponding registered user when the corresponding registered user logs in.

8. According to claim 7, an intelligent information consulting service system based on big data analysis, It is characterized in that The specific analysis process of the personnel section matching analysis module is as follows: Obtain all consultation sections consulted by the corresponding registered user during the traceability period, and mark the corresponding consultation section consulted as the section to be analyzed for the corresponding registered user; The matching evaluation value is obtained by numerically calculating the total consultation frequency value, the total section stay time value and the target consultation frequency value. All sections to be analyzed of the corresponding registered user are sorted in descending order according to the matching evaluation value, and the section to be analyzed that is ranked first is marked as a high-matching section of the corresponding registered user.

Citation Information

Patent Citations

  • Internet-based multifunctional information technology consultation service system

    CN115883626A

  • Intelligent customer service robot based on artificial intelligence and application method thereof

    CN116955574A

  • Physical education supply borrowing and returning management system based on Internet of Things

    CN117314317A

  • Website security intelligent management system based on Internet

    CN118041617A

  • Wiring intelligent management system suitable for weak current wiring project

    CN118468498A

Cited By

  • Intelligent law and treatment platform management service system

    CN119379519A