CN107016561B - Information processing method and device - Google Patents
Information processing method and device Download PDFInfo
- Publication number
- CN107016561B CN107016561B CN201610974022.7A CN201610974022A CN107016561B CN 107016561 B CN107016561 B CN 107016561B CN 201610974022 A CN201610974022 A CN 201610974022A CN 107016561 B CN107016561 B CN 107016561B
- Authority
- CN
- China
- Prior art keywords
- information
- public opinion
- service
- user
- opinion information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
Landscapes
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides an information processing method and device, wherein the method comprises the following steps: analyzing the acquired public opinion information, and determining that missing information to be complemented exists in the public opinion information; acquiring a service link log corresponding to the public opinion information; and obtaining the missing information according to the service link log, and completing the missing information to the public opinion information. The invention can realize the completion processing of the public sentiment information, thereby improving the information processing efficiency and improving the efficiency of effectively utilizing the public sentiment information.
Description
Technical Field
The present invention relates to computer technologies, and in particular, to an information processing method and apparatus.
Background
With the rapid development of network technology, a service user can install a service client on an intelligent terminal of the user and conveniently execute various service processes through the client, for example, online shopping, living payment, mobile phone recharging and the like can be realized. In addition, the user can also perform convenient problem feedback on the service processing through the client, for example, negative problems such as 'unable to pay electricity fee' and the like can be fed back, or positive evaluations such as 'too good life fee payment' and the like can be fed back.
The information fed back by the user through the service client or other social media may be referred to as public opinion information, which may be a kind of experience feedback of the user on service usage. Public sentiment information can be gathered to public sentiment intelligence platform to store public sentiment information to the platform database for follow-up the use. Technicians can analyze and locate the problem according to public opinion information, for example, which module causes the failure of 'unable to pay electricity fee', and solve the problem; moreover, product personnel can perform improvement of product experience optimization according to the feedback condition of public opinion information, and data scientists can analyze user behaviors based on the public opinion information. However, sometimes the question feedback submitted by the user is short, and even the expression mode is not in accordance with the normal statement structure, so that a great deal of effort is needed to analyze and infer the meaning of the user feedback information, and the efficiency of effectively utilizing the public opinion information is influenced.
Disclosure of Invention
In view of the above, the present invention provides an information processing method and apparatus to improve information processing efficiency.
Specifically, the invention is realized by the following technical scheme:
in a first aspect, an information processing method is provided, and the method includes:
analyzing the acquired public opinion information, and determining that missing information to be complemented exists in the public opinion information;
acquiring a service link log corresponding to the public opinion information;
and obtaining the missing information according to the service link log, and completing the missing information to the public opinion information.
In a second aspect, there is provided an information processing apparatus, the apparatus comprising:
the information analysis module is used for analyzing the acquired public opinion information and determining that the public opinion information has missing information to be complemented;
the log acquisition module is used for acquiring a service link log corresponding to the public opinion information;
and the log analysis module is used for obtaining the missing information according to the service link log and completing the missing information to the public opinion information.
According to the information processing method and the device, when the public opinion information is incomplete, missing information is analyzed according to the service link log corresponding to the public opinion information, and the completion processing of the public opinion information can be realized, so that the information processing efficiency is improved, and the efficiency of effectively utilizing the public opinion information is improved.
Drawings
Fig. 1 is a public opinion information processing system according to an embodiment of the present invention;
fig. 2 is a flow chart of an information processing method according to an embodiment of the present invention;
FIG. 3 illustrates a user public opinion representation with a comparative visualization;
FIG. 4 is a flow chart of another information processing method provided by the embodiment of the invention;
FIG. 5 is a schematic structural diagram of an information processing apparatus according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of another information processing apparatus according to an embodiment of the present invention.
Detailed Description
Fig. 1 illustrates a public opinion information processing system, as shown in fig. 1, public opinion information fed back by a user 11 through a service client 12 can be collected and acquired by a public opinion intelligent platform 13, and the public opinion information is stored in a platform database 14. The information processing device 15 provided in the embodiment of the present application is responsible for performing public opinion intelligent analysis, and can obtain valuable public opinion analysis results according to public opinion information and other related information obtained by the public opinion intelligent platform 13.
In one example, it is assumed that the public opinion information fed back by the user is too short and fuzzy, for example, the user feeds back "no fee paid", and specific information such as electricity or water fee cannot be known. When performing the intelligent public opinion analysis, the information processing apparatus 15 according to the embodiment of the present application can complement the public opinion information into information with complete semantics by combining the fuzzy public opinion information with information such as user behavior logs and service operation logs. Referring to fig. 2 in combination, fig. 2 illustrates a flow of an information processing method, which may include:
in step 201, the acquired public opinion information is analyzed to determine that the public opinion information has missing information to be complemented.
Still taking the above feedback of "no fee paid" as an example, the public opinion information is fuzzy, for example, it is impossible to know whether the fee that cannot be paid is electricity or water; for another example, if the user feeds back "the electricity fee of the office of electric power in Hangzhou city is not paid for cheer", the user is a relatively clear public opinion information. In this example, the information processing apparatus may receive a large amount of public opinion information, including information with complete and clear semantics (e.g., the electricity charges of the office of the hangzhou city are not paid for), and also including information with unclear semantics (e.g., no fee is paid), and in this step, the information processing apparatus may analyze each piece of public opinion information to determine whether the information is clear and complete, and for the incomplete information like "no fee is paid", may continue to perform subsequent steps 202 and 203 to complete the information.
The embodiment of the present application provides an example of analyzing public opinion information, but the practical implementation is not limited thereto. For example, public opinion information can be segmented to obtain keywords; and identifying the service scene of the public opinion information by combining the keywords and the service association rule, and determining that the public opinion information is to be complemented if the corresponding service scene cannot be identified.
Examples are as follows: taking the example that a user feeds back public opinion information that electricity charges of the Hangzhou city electricity bureau cannot be paid for easily, the information can obtain a keyword that the Hangzhou city electricity bureau, the electricity charges and the electricity charges cannot be paid for through word segmentation, and a business type association rule is supposed to include that if the electricity charges occur, the business type to which the information belongs is electricity charge payment business; if the "power bureau in Hangzhou city" appears, it indicates that the payment institution to which the information belongs is the power bureau in Hangzhou city "], and the real service scene of the public opinion information can be identified by combining keywords, rules and user history information, for example," the user of power bureau in Hangzhou city with the account number of 123456 can not pay the power fee 18 minutes at 2016, 10, 01 and 8 days ". In another example, if the user feeds back the public opinion information "no fee paid", the keywords obtained by the word segmentation may include "no fee paid", and according to the business type association rule, the sole "fee" cannot identify which business belongs to, and then it may be determined that the public opinion information is not clear and incomplete.
Further, the above-mentioned service type association rule may be a condition for identifying a service type of public opinion information, for example, if a piece of public opinion information includes a keyword "a + B", it may be determined that the information belongs to the service type Y1, and if the public opinion information includes a keyword "C", it may be determined that the information belongs to the service type Y2. The traffic type association rule may be a default rule or may be a custom rule. In this example, if it is found through tests and experiments that the built-in general rule, such as the default rule described above, is not very accurate in identifying the service type, and has an error, a custom rule plug-in for performing correction processing on the rule may be loaded, so that the identification of the service type is more accurate. For example, assuming that the original business type association rule may be "if the public opinion information contains the keyword C, it is determined that the information belongs to the business type Y2", and the new rule after calibration may be "if the public opinion information contains the keywords C and D, it is determined that the information belongs to the business type Y2", that is, it is more accurate to identify Y2 by using a method having both the keywords C and D.
In step 202, a service link log corresponding to the public opinion information is obtained.
For example, if public opinion information fed back by a certain user through a service client is "no fee paid", it is likely that the user fails to pay when paying through service client software, and thus the problem of "no fee paid" is fed back. The server corresponding to the client is an actual processing party of business operation, and the problem that payment fails when a user sees at the client may be that a certain functional module of the server operates abnormally or a payment mechanism is abnormal. Meanwhile, the monitoring platform for monitoring the service operation condition can record the log and the performance snapshot of the service operation abnormal moment respectively. According to the above, when a public opinion information feedback problem occurs, the client, the server and the monitoring end all have the performance, and the occurring problem can be deduced reversely by analyzing the performances of the several aspects.
In this example, the public opinion time corresponding to the public opinion information may be obtained as follows: the service monitoring method comprises the steps of a user behavior log of a service client, a service flow log of a service server and a service monitoring log. The several logs described above may be collectively referred to as a traffic link log. The public opinion time corresponding to the public opinion information may be the time when the public opinion information is collected, and also the time when the user feeds back the question, and the time when the question usually occurs is closer to the time when the user feeds back the question, for example, within several hours. Therefore, the log information of the user in the client, the server and the monitoring platform can be obtained according to the range interval of the public sentiment time, and the specific time when the user has a problem and the specific problem can be analyzed through the information.
In addition, the service link logs in this step may be obtained, for example, in a manner that when a user feeds back a problem at a client, automatic uploading of the client logs is triggered, the client logs may be uploaded to a log platform, the log platform may also collect server logs, and the logs and monitoring logs of the monitoring system may both be filed in a data warehouse.
In step 203, the missing information is obtained according to the service link log, and the missing information is supplemented to the public opinion information.
This step is used to determine the missing information of the incomplete public opinion information in the above step 201 according to the analysis of the service link log. For example, user behavior analysis, service flow analysis and system performance analysis may be performed according to the service link log to obtain a service operated by a user behavior, a flow processing result corresponding to the service, and a performance expression result corresponding to the flow processing; and if the operation service, the flow processing result and the performance expression result have problem points corresponding to the public opinion information, determining the missing information according to the problem points.
For example: still taking the public opinion information 'no fee paying' as an example, through the user behavior analysis recorded by the client log, the user can know that the user clicks and operates the service options on the APP side such as 'life fee paying-water fee' and the like at the client, and the operation is performed under the service options; moreover, according to the process log of the server, it can be seen that the server fails in the process of processing the water charge, and meanwhile, the problems of high resource occupation and the like occur in the system performance at the time are monitored and found. By combining the information and the public opinion information 'payment can not be made', the fact that the water payment of the Hangzhou water affair group fails is known to be fed back by the user. Then, the original public sentiment information 'no payment' can be completed, and the completed missing information can include information of 'Hangzhou water affair group, water fee, no payment' and the like.
Through the steps, the information processing device completes semantic completion of unclear public opinion information automatically according to log analysis, so that the problem of the public opinion feedback can be determined, the problem can be quickly positioned, and the problem can be quickly solved.
The information processing method of the embodiment analyzes missing information according to the service link log corresponding to the public opinion information when the public opinion information is incomplete, can realize complete processing of the public opinion information, thereby improving the information processing efficiency, and improving the efficiency of effectively utilizing the public opinion information, for example, technical personnel can quickly position and solve the existing problems according to the public opinion information, and product personnel and data scientists can also quickly utilize the public opinion information to perform product experience improvement and user behavior analysis.
In another example, the information processing method according to the embodiment of the present application can analyze the public opinion information with unclear completion according to the service link log, and provide the public opinion representation of the user dimension according to the related information obtained in the process of completing the public opinion information.
User public opinion portrayal: the user model is a labeled user model abstracted according to information such as natural attributes (such as sex and age) of a user, public opinion comment tendency (such as whether the user is a question of a recommendation class or not, spitting and the like), public opinion occurrence time, business behavior (such as whether the user is based on evaluation of using a life payment business or evaluation of business abnormality).
Fig. 3 illustrates a user's public opinion representation, as shown in fig. 3, for example, a user may feedback much public opinion information, and the user can be known from various aspects by collecting the public opinion information of the user. For example, the user can know the business participation and feedback information of the user, for example, the user often participates in the marketing activities of life payment, frequently gives a good comment, and can accurately feed back the problem when the business is abnormal. In addition, in the process of completing the public opinion information illustrated in fig. 2, the public opinion time when the user uploads the public opinion information, the service type of the user, the service link log of the client, the server, and the like are also obtained. These are all information related to the user, and are a part of the public opinion representation of the user, that is, the public opinion representation of the user is equivalent to a set of multidimensional information such as user service usage and evaluation, service marketing participation and feedback, evaluation/feedback frequency, and public opinion information related log snapshot.
For example, as shown in the example of fig. 1, after the information processing device 15 completes the public opinion representation of the user through intelligent analysis of the public opinion, the public opinion representation can be provided to the public opinion intelligent platform 13. Because the user public opinion portrait already contains multi-aspect information, the user public opinion portrait can be used by people with different roles, the emphasis on the attention points of different roles are different, and different contents in the public opinion portrait can be selected for use. For example, a technician can select information related to problems in a public sentiment portrait, such as service link logs and public sentiment information, analyze and locate the problems, and repair faults; product experts can optimize product experience according to the business model and public opinion information; the data scientist can analyze the public sentiment habit and loyalty of the user according to the public sentiment time, the service type and other information so as to guide the user to popularize the product more accurately. It can be seen that the provision of the user's public opinion representation makes the use of information more efficient.
How to perfect the public opinion portrait in the process of analyzing the public opinion information after the public opinion information is collected is described as follows with reference to the flow of fig. 4. As shown in fig. 4, may include:
in step 401, public opinion information fed back by a user is received.
In this example, there may be many public opinion information collected, for example, the example part of user feedback is as follows:
the user A: the life payment is too good!
And a user B: the electricity fee cannot be paid.
And a user C: the fee can not be paid.
After receiving the public sentiment information fed back by many users, the public sentiment information can be preprocessed, and the preprocessing can include, for example, extracting key information from the public sentiment information fed back by the users, and removing useless stop words (stop words, which are equivalent to non-key words) which cannot represent substantial problems.
In step 402, it is determined whether the user has a public opinion figure.
If the user has a public opinion portrait, the public opinion portrait of the user can be perfected after the analysis processing of the public opinion information fed back by the user, for example, the content obtained by the analysis of the public opinion information is added into the portrait of the user; if the user does not have a public sentiment portrait, then the user may be created with his public sentiment portrait. Therefore, if the determination result is yes, step 403 is executed, otherwise, step 404 is executed.
If the collected public opinion information comprises information fed back by a plurality of users, any one of the public opinion information can be judged whether the public opinion portrait exists in the corresponding user which is the feedback person of the public opinion information.
In step 403, the public opinion figure of the user is extracted.
In step 404, a public opinion picture of the user is constructed, including natural attributes of the user.
For example, when the user feeds back public opinion information at the client, the user may carry some natural attributes of the user, including information such as gender, age, and city. The public opinion portrait of the user can be constructed according to the existing natural attributes, and after public opinion information is analyzed subsequently, the content of the public opinion portrait is enriched and improved.
In step 405, sentiment analysis is performed on the public sentiment information, and sentiment marking is performed.
The step can analyze the emotional tendency of each piece of public sentiment information. For example, user A may feedback that "Life Payment is too good! "is a positive emotion, which is in the superficies. The problem that the user B and the user C can not pay fee is negative emotion, namely, the service has a problem. For example, the public sentiment information may be marked with "+" to indicate that the information is a positive emotion, and may be marked with "-" to indicate that the information is a negative emotion.
The emotion marks of the public sentiment information can provide basis for subsequent information analysis. For example, if all feedback is to be viewed for questionable public opinion information, the information with emotion marked "-" may be selected; alternatively, information with emotion marked "-" is treated as priority information.
In step 406, the public sentiment information is segmented, and the service type of the public sentiment information is identified.
The processing of this step can be seen in the embodiment of fig. 2, and will not be described in detail.
In step 407, whether the public opinion information satisfies the clustering condition is determined.
For example, if public opinion information can identify a belonging traffic type, clustering may be performed according to the traffic type. For example, if several pieces of information belong to a "life payment" service, the pieces of information can be classified into a category, which is public opinion information about the life payment service. That is, the clustering condition in this step may be to see whether the public opinion information has accurately identified the service type.
If the clustering condition is satisfied, step 408 may be performed; otherwise, step 409 is performed.
In step 408, clustering marks are carried out on the public sentiment information.
The step can cluster the public opinion information belonging to a service type, and mark that the information belongs to a service type. For example, the "unable to pay" feedback from the user B may be marked as belonging to the life payment service, and may be grouped with other public opinion information related to the life payment service. The clustering of public opinion information helps to analyze the public opinion information as a whole, for example, how much information in mass public opinion information is related to a certain service type, thereby helping to analyze the service according to the public opinion.
In step 409, the public sentiment information is complementally marked.
For example, user C may not know "no fee paid" and may mark this information as pending.
For the public opinion information which is already clustered, the steps 410 and 411 can be further executed continuously.
In step 410, a rating marking of the public opinion priority is performed.
For example, if the information such as "life payment is too good" is fed back, the information generally does not need emergency treatment and has lower priority; if the problem information such as 'unable to pay the electricity fee' is fed back, the priority can be set to be higher, and emergency treatment is needed. Therefore, the priority of the public opinion information can be distinguished according to whether the public opinion information needs emergency treatment or not.
Furthermore, even if the clustering of the public sentiment information is performed in step 408, the processing in this step may separately mark the priority of each piece of public sentiment information, for example, the information of the negative sentiment mark may be set to have higher priority according to the sentiment mark fed back by a certain piece of public sentiment information. For another example, public opinion information related to the type of the payment service may be uniformly set as a higher priority according to the clustering mark.
In step 411, the business model is analyzed.
In this step, the business model of the user corresponding to each piece of public opinion information can be analyzed according to the public opinion information. For example, in step 406, it is recognized that the service type of the public opinion information is life payment, and the service model analysis in this step can further obtain more specific information, for example, the public opinion information is the sub-type of "electric charge" under the life payment service, and the payment mechanism is "electricity bureau in the state of hang", etc. The business model is more detailed business information of a business related to public opinion information.
Next, as shown in fig. 4, whether the public opinion information needs to be complemented or not, whether the public opinion information already participates in the clustering or not, step 412 may be continuously performed.
In step 412, a service link log corresponding to the public opinion information is obtained.
The processing of this step can be combined with the embodiment shown in fig. 2, and will not be described in detail. Even if the public opinion information is clustered and has clear semantics, the log acquisition of the step can be executed as the supplementary content of the user public opinion image corresponding to the public opinion information, so that the method can be executed no matter whether the public opinion information needs to be supplemented or not.
In step 413, it is determined whether the public opinion information needs to be completed.
If completion is required, go to step 414; otherwise, step 415 may be performed. Since the mark to be completed is already made on the incomplete public opinion information in the step 409, the step can easily know whether the completion needs to be performed according to the mark.
In step 414, the public opinion information is complemented according to the service link log, and the service model is extracted.
For example, the "no payment" fed back by the user C may be supplemented as a water fee of an organization in a certain city. In addition, the step can also extract the service model, namely acquiring more detailed service information.
In step 415, the public opinion image of the user is completed.
As shown in fig. 4, in the steps 402 to 404 at the beginning of the process, the public opinion portraits of the users are extracted, and after the above intelligent analysis processing of the public opinion information, some new information about the users are obtained, such as the priority of the public opinion information, the affiliated service type, the service link log, the service model, the emotional tendency of the public opinion information, etc., which can be used to supplement and improve the public opinion portraits of the users, so that the public opinion portraits of the users are richer, and the understanding of the users is increased.
In addition, for a certain user, a plurality of pieces of public opinion information may be fed back, for example, the user feeds back a piece of public opinion information about the use experience of the life payment service today, and feeds back a use problem about the mobile phone recharging service after one week. In the user public opinion portrait, general data obtained by integrating a plurality of pieces of public opinion information can be included, for example, the user often feeds back public opinion information in a time period from 9 o 'clock to 10 o' clock in the evening, which indicates that the user is active in the time period; or, the user often uses the life payment service and feeds back the service problem and improvement suggestion. The general data can obtain the information such as the public sentiment habit, loyalty and the like of the user, and is beneficial to improving the utilization accuracy and the utilization efficiency of the information in the follow-up public sentiment portrait of the user.
In step 416, the similarity of the information content is determined for different pieces of public opinion information, and similar public opinions are associated. For example, the public opinion content fed back by some users may be the same question, for example, a plurality of users all feed back the electric charge and cannot pay, so the step may find the public opinion information belonging to the same question through the similarity calculation method, and mark and associate the information to indicate that the information belongs to the same category of questions.
For the intelligent analysis of public opinion information, there may be other analysis processes, which are not described in detail.
The information processing method of the embodiment can be based on the analysis and processing of public opinion information, the public opinion portrait of a user corresponding to the public opinion information is supplemented and perfected, the content of the public opinion portrait is richer, more data are provided for the utilization of the content of subsequent portrait, for example, technical personnel can find high-risk codes according to service link logs in the public opinion portrait, product personnel can optimize product experience according to the public opinion information in the public opinion portrait, data scientists can analyze the public opinion habits and loyalty of the user according to information such as public opinion time and service types, and the user is guided to be promoted.
In order to realize the method, the invention also provides an information processing device. As shown in fig. 5, the apparatus may include: an information analysis module 51, a log acquisition module 52 and a log analysis module 53.
The information analysis module 51 is configured to analyze the acquired public opinion information and determine that missing information to be completed exists in the public opinion information;
a log obtaining module 52, configured to obtain a service link log corresponding to the public opinion information;
and the log analysis module 53 is configured to obtain the missing information according to the service link log, and complement the missing information to the public opinion information.
In one example, the traffic link log comprises: the service monitoring method comprises the steps of a user behavior log of a service client, a service flow log of a service server and a service monitoring log.
In an example, the information analysis module 51 is specifically configured to: carrying out word segmentation processing on the public opinion information to obtain a keyword; and identifying the service scene of the public opinion information by combining the keywords and the service association rule, and determining that the public opinion information is to be completed if the corresponding service scene cannot be identified.
In an example, the log analysis module 53 is specifically configured to: performing user behavior analysis, service flow analysis and system performance analysis according to the service link logs to obtain operation services of user behaviors, flow processing results corresponding to the services and performance expression results corresponding to the flow processing; and if the operation service, the flow processing result and the performance expression result have problem points corresponding to the public opinion information, determining the missing information according to the problem points.
In one example, as shown in fig. 6, the apparatus may further include: an information providing module 54, configured to provide a user public opinion representation of a user corresponding to the public opinion information, where the user public opinion representation includes all or part of: the service model comprises the natural attributes of the user, public opinion comment tendency and service behavior determined according to the public opinion information, public opinion time, the service link log and the service model to which the public opinion information belongs.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (8)
1. An information processing method, characterized in that the method comprises:
analyzing the acquired public opinion information, and determining that missing information to be complemented exists in the public opinion information; the public opinion information is feedback information of a user aiming at a service result;
acquiring a service link log corresponding to the public opinion information; the traffic link log comprises: a user behavior log of a service client, a service flow log and a service monitoring log of a service server;
obtaining the missing information according to the service link log, and completing the missing information to the public opinion information;
the obtaining the missing information according to the service link log includes:
performing user behavior analysis, service flow analysis and system performance analysis according to the service link logs to obtain operation services of user behaviors, flow processing results corresponding to the services and performance expression results corresponding to the flow processing;
and if the operation service, the flow processing result and the performance expression result have problem points corresponding to the public opinion information, determining the missing information according to the problem points.
2. The method of claim 1, wherein the analyzing the obtained public opinion information to determine that there is missing information to be complemented in the public opinion information comprises:
carrying out word segmentation processing on the public opinion information to obtain a keyword;
and identifying the service scene of the public opinion information by combining the keywords and the service association rule, and determining that the public opinion information is to be completed if the corresponding service scene cannot be identified.
3. The method of claim 2, wherein the business association rule comprises: default rules, custom rules, or new rules calibrated to the original rules through a rule plug-in.
4. The method of claim 1, further comprising:
providing a user public opinion portrait of a user corresponding to the public opinion information, wherein the user public opinion portrait comprises all or part of the following parts: the service model comprises the natural attributes of the user, public opinion comment tendency and service behavior determined according to the public opinion information, public opinion time, the service link log and the service model to which the public opinion information belongs.
5. The method of claim 1, further comprising:
and judging the similarity of information contents of different public opinion information, and associating similar public opinions.
6. An information processing apparatus characterized in that the apparatus comprises:
the information analysis module is used for analyzing the acquired public opinion information and determining that the public opinion information has missing information to be complemented; the public opinion information is feedback information of a user aiming at a service result;
the log acquisition module is used for acquiring a service link log corresponding to the public opinion information; the traffic link log comprises: a user behavior log of a service client, a service flow log and a service monitoring log of a service server;
the log analysis module is used for obtaining the missing information according to the service link log and completing the missing information to the public opinion information;
the log analysis module is specifically configured to: performing user behavior analysis, service flow analysis and system performance analysis according to the service link logs to obtain operation services of user behaviors, flow processing results corresponding to the services and performance expression results corresponding to the flow processing; and if the operation service, the flow processing result and the performance expression result have problem points corresponding to the public opinion information, determining the missing information according to the problem points.
7. The apparatus of claim 6,
the information analysis module is specifically configured to: carrying out word segmentation processing on the public opinion information to obtain a keyword; and identifying the service scene of the public opinion information by combining the keywords and the service association rule, and determining that the public opinion information is to be completed if the corresponding service scene cannot be identified.
8. The apparatus of claim 6, further comprising:
the information providing module is used for providing a user public opinion portrait of a user corresponding to the public opinion information, and the user public opinion portrait comprises all or part of the following parts: the service model comprises the natural attributes of the user, public opinion comment tendency and service behavior determined according to the public opinion information, public opinion time, the service link log and the service model to which the public opinion information belongs.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610974022.7A CN107016561B (en) | 2016-10-28 | 2016-10-28 | Information processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610974022.7A CN107016561B (en) | 2016-10-28 | 2016-10-28 | Information processing method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107016561A CN107016561A (en) | 2017-08-04 |
| CN107016561B true CN107016561B (en) | 2020-10-20 |
Family
ID=59439418
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610974022.7A Active CN107016561B (en) | 2016-10-28 | 2016-10-28 | Information processing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107016561B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110059234A (en) * | 2019-04-16 | 2019-07-26 | 珠海卓邦科技有限公司 | Water utilities anomalous event method for detecting and device, computer installation and storage medium |
| CN110781380A (en) * | 2019-09-09 | 2020-02-11 | 深圳壹账通智能科技有限公司 | Information pushing method and device, computer equipment and storage medium |
| CN114328389B (en) * | 2021-12-31 | 2022-06-17 | 浙江汇鼎华链科技有限公司 | Big data file analysis processing system and method under cloud computing environment |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103294814A (en) * | 2013-06-07 | 2013-09-11 | 百度在线网络技术（北京）有限公司 | Search result recommendation method, system and search engine |
| CN105447080A (en) * | 2015-11-05 | 2016-03-30 | 华建宇通科技(北京)有限责任公司 | Query completion method in community ask-answer search |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8311556B2 (en) * | 2009-01-22 | 2012-11-13 | Htc Corporation | Method and system for managing images and geographic location data in a mobile device |
| US9760946B1 (en) * | 2010-11-24 | 2017-09-12 | Nyse Arca Llc | Methods and apparatus for detecting gaps in a sequence of messages, requesting missing messages and/or responding to requests for messages |
| CN105005683A (en) * | 2015-06-17 | 2015-10-28 | 北京锐易特软件技术有限公司 | Caching system and method for solving data normalization problem of regional medical system |
-
2016
- 2016-10-28 CN CN201610974022.7A patent/CN107016561B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103294814A (en) * | 2013-06-07 | 2013-09-11 | 百度在线网络技术（北京）有限公司 | Search result recommendation method, system and search engine |
| CN105447080A (en) * | 2015-11-05 | 2016-03-30 | 华建宇通科技(北京)有限责任公司 | Query completion method in community ask-answer search |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107016561A (en) | 2017-08-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11663405B2 (en) | Machine learning applications for temporally-related events | |
| WO2019214245A1 (en) | Information pushing method and apparatus, and terminal device and storage medium | |
| CN108885623B (en) | Semantic analysis system and method based on knowledge graph | |
| US20190034963A1 (en) | Dynamic sentiment-based mapping of user journeys | |
| CN106874134B (en) | Work order type processing method, device and system | |
| US20170109676A1 (en) | Generation of Candidate Sequences Using Links Between Nonconsecutively Performed Steps of a Business Process | |
| CN114840486B (en) | User behavior data acquisition method and system and cloud platform | |
| US20170109667A1 (en) | Automaton-Based Identification of Executions of a Business Process | |
| US20170109636A1 (en) | Crowd-Based Model for Identifying Executions of a Business Process | |
| CN113127746B (en) | Information pushing method based on user chat content analysis and related equipment thereof | |
| US20170109639A1 (en) | General Model for Linking Between Nonconsecutively Performed Steps in Business Processes | |
| EP3608799A1 (en) | Search method and apparatus, and non-temporary computer-readable storage medium | |
| CN107016561B (en) | Information processing method and device | |
| US20170109638A1 (en) | Ensemble-Based Identification of Executions of a Business Process | |
| CN105095415A (en) | Method and apparatus for confirming network emotion | |
| CN112070564B (en) | Advertisement pulling method, device and system and electronic equipment | |
| CN114925260A (en) | Intelligent bidding information fitting method | |
| CN110399473A (en) | The method and apparatus for determining answer for customer problem | |
| CN113312468A (en) | Conversation mode-based conversation recommendation method, device, equipment and medium | |
| CN113689152B (en) | Fault early warning processing method and device, electronic equipment and storage medium | |
| CN111126071A (en) | Method and device for determining questioning text data and data processing method of customer service group | |
| US20220382982A1 (en) | System and method of automatic topic detection in text | |
| CN116484109B (en) | Customer portrait analysis system and method based on artificial intelligence | |
| CN111858560A (en) | Financial data automated testing and monitoring system based on data warehouse | |
| CN110674020B (en) | APP intelligent recommendation method and device and computer readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20200925 Address after: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman Islands Applicant after: Innovative advanced technology Co.,Ltd. Address before: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman Islands Applicant before: Advanced innovation technology Co.,Ltd. Effective date of registration: 20200925 Address after: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman Islands Applicant after: Advanced innovation technology Co.,Ltd. Address before: A four-storey 847 mailbox in Grand Cayman Capital Building, British Cayman Islands Applicant before: Alibaba Group Holding Ltd. |