Message pushing method and device
By monitoring the online status of users in real time in e-commerce business and conducting value analysis on offline information, deciding whether to push messages or end online consultation, the problem of users being unable to receive important messages in a timely manner is solved, intelligent management of message push is realized, and user experience is improved.
Patent Information
- Application Number
- CN202411660752.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-20
- Publication Date
- 2025-03-18
AI Technical Summary
In e-commerce business, users cannot see important messages in time after exiting the application, resulting in a decrease in user service experience. Common message pushes do not judge the value of messages, resulting in interference to users and reducing users' attention to platform messages.
Monitor the user's online status in real time when the user is consulted online, obtain the latest consultation reply information when the user is offline, and conduct message value analysis on the offline information, and decide whether to push messages or end online consultation based on the value level.
By monitoring the user's online status in real time and conducting value analysis of offline information, intelligent management of message push is realized, ensuring that users can receive important information in a timely manner, avoid excessive interference with users, and improve user experience.
Smart Images

Figure CN119652858A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of computer technology, and in particular to a message pushing method and device thereof. Background Art
[0002] For all e-commerce businesses, including air ticket business, users will inevitably have questions and initiate customer service consultation before and after placing an order. It is normal for users to be offline for personal reasons during the consultation process, but because the customer service reply message is replied in the terminal, users cannot see important messages in time after exiting the application, which reduces the user's service experience. Common message push is pushed randomly without judging the value of the message, which causes great interference to users and reduces the importance of platform messages to users. Summary of the invention
[0003] In order to solve the technical problems existing in the background technology, the present invention provides a message pushing method and a device thereof.
[0004] A message push method proposed by the present invention comprises:
[0005] When starting an online consultation, monitor the user's online status in real time. When the user's online status is detected to be offline, obtain the latest consultation reply information and use the consultation reply information as offline information;
[0006] Perform message value analysis on offline information to obtain the value level corresponding to the offline information, including push level and non-push level;
[0007] Offline information processing is performed according to the value level to end the current online consultation or push the offline message to the user.
[0008] Preferably, the number of words in the offline information is within N words; and the message value analysis of the offline information to obtain the value level corresponding to the offline information specifically includes:
[0009] When the number of words in the offline information is within N words, preprocessing the offline information;
[0010] Split the preprocessed offline information into independent words and match them with the preset low-value word library;
[0011] When the separated independent words completely match the low-value word library, the value level corresponding to the offline message is not pushed;
[0012] When the separated independent words do not completely match the low-value vocabulary, the value level corresponding to the offline message is push level.
[0013] Preferably, the number of words in the offline information is greater than N words; and the message value analysis of the offline information to obtain the value level corresponding to the offline information specifically includes:
[0014] When the number of words in the offline information is greater than N words, preprocessing the offline information;
[0015] Split the preprocessed offline information into independent words and match them with the preset low-value word library;
[0016] When the split independent words have a matching degree with the low-value word library that is greater than or equal to the preset ratio of the number of words in the offline message, the value level corresponding to the offline message is the non-push level;
[0017] When the matching degree of the split independent words with the low-value word library is less than the preset ratio of the number of words in the offline message, the value level corresponding to the offline message is the push level.
[0018] Preferably, the preprocessing specifically includes:
[0019] After cleaning the special characters of the offline information and removing the extra spaces in the offline information, the offline message is standardized according to the preset standard format.
[0020] Preferably, the value level is specifically a push level; and the processing of offline information according to the value level and pushing offline messages to users specifically includes:
[0021] When the value level is determined to be the push level, the user's visiting path is obtained, and the offline message is pushed to the user according to the push method corresponding to the visiting path.
[0022] Preferably, the visiting path includes but is not limited to the user-side APP and the mini-program side; the push method corresponding to the user-side APP is specifically to directly push the offline message to the mobile phone message bar; the push method corresponding to the mini-program side is specifically to push to the program message bar corresponding to the mini-program side.
[0023] Preferably, it also includes:
[0024] When the user clicks on the mobile phone message bar or program message bar corresponding to the offline message, the user enters the online consultation page and switches the user's online status from offline to online.
[0025] Preferably, the value level is specifically a non-pushing level; and the processing of offline information according to the value level to end the current online consultation is specifically:
[0026] When the value level is determined to be a non-pushing level, the preset consultation closing countdown is started;
[0027] If the user's online status is still offline within the preset closing countdown time, the current online consultation will be terminated after the preset consultation closing countdown ends.
[0028] Preferably, it also includes:
[0029] Build a low-value word library, classify low-value words related to flight consultation into preset categories, and store them in the low-value word library.
[0030] A message push device proposed by the present invention includes:
[0031] The data monitoring module is used to monitor the user's online status in real time when starting online consultation. When the user's online status is detected to be offline, the latest consultation reply information is obtained and the consultation reply information is used as offline information.
[0032] The data analysis module is used to analyze the value of offline information to obtain the value level corresponding to the offline information, and the value level includes push level and non-push level;
[0033] The data push module is used to process offline information according to the value level to end the current online consultation or push offline messages to the user.
[0034] In the present invention, the proposed message push method and device monitor the user's online status in real time when starting online consultation. When the user's online status is detected to be offline, the latest consultation reply information is obtained and the consultation reply information is used as offline information; the message value analysis is performed on the offline information to obtain the value level corresponding to the offline information, and the value level includes push level and non-push level; the offline information is processed according to the value level to end the current online consultation or push the offline message to the user. By monitoring the user's online status in real time and performing value analysis on the offline information, intelligent management of message push is achieved, which not only ensures that the user can receive important information, but also avoids excessive interference to the user, thereby improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS
[0035] Figure 1 A schematic diagram of the work flow structure of a message push method proposed by the present invention;
[0036] Figure 2 A schematic diagram of the device architecture of a message push device proposed by the present invention. DETAILED DESCRIPTION
[0037] Reference Figure 1 and Figure 2 , a message push method proposed by the present invention comprises:
[0038] When starting an online consultation, the user's online status is monitored in real time. When the user's online status is detected to be offline, the latest consultation reply information is obtained and the consultation reply information is used as offline information.
[0039] The offline information is analyzed for its message value to obtain the value level corresponding to the offline information, and the value level includes push level and non-push level.
[0040] In this embodiment, when the number of words in the offline information is within N words, the offline information is preprocessed; the preprocessed offline information is split into independent words and matched with a preset low-value vocabulary; when the split independent words completely match the low-value vocabulary, the value level corresponding to the offline message is the non-push level; when the split independent words do not completely match the low-value vocabulary, the value level corresponding to the offline message is the push level.
[0041] In this embodiment, when the number of words in the offline information is greater than N words, the offline information is preprocessed; the preprocessed offline information is split into independent words and matched with a preset low-value vocabulary; when the matching degree between the split independent words and the low-value vocabulary is greater than or equal to the preset ratio of the number of words in the offline information, the value level corresponding to the offline message is the non-push level; when the matching degree between the split independent words and the low-value vocabulary is less than the preset ratio of the number of words in the offline information, the value level corresponding to the offline message is the push level.
[0042] In this embodiment, the preprocessing specifically includes: cleaning the special characters in the offline information and removing the redundant spaces in the offline information, and then performing standardization processing on the offline message according to a preset standard format.
[0043] In this embodiment, the importance of offline messages is judged, that is, matching and scoring is performed through the established low-value word library; if the customer service reply message is within 10 words, separate words are split to match in the low-value word library, if all words are matched, it means that the message is of low value and does not need to be pushed, if there are words that are not matched, the message needs to be pushed. If the customer service reply message is more than 10 words, more than 80% of the words hit the low-value word library and do not need to be pushed, otherwise the user needs to be pushed.
[0044] Offline information processing is performed according to the value level to end the current online consultation or push the offline message to the user.
[0045] In this embodiment, the value level is specifically a push level; offline information processing is performed according to the value level, and the offline message is pushed to the user, specifically including: when the value level is determined to be a push level, the user's visiting path is obtained, and the offline message is pushed to the user according to the push method corresponding to the visiting path.
[0046] In this embodiment, the visiting path includes but is not limited to the user-side APP and the mini-program side; the push method corresponding to the user-side APP is specifically to directly push the offline message to the mobile phone message bar; the push method corresponding to the mini-program side is specifically to push to the program message bar corresponding to the mini-program side.
[0047] In this embodiment, it also includes:
[0048] When the user clicks on the mobile phone message bar or program message bar corresponding to the offline message, the user enters the online consultation page and switches the user's online status from offline to online.
[0049] In this embodiment, the value level is specifically the non-pushing level; the offline information is processed according to the value level to end the current online consultation, specifically:
[0050] When the value level is determined to be a non-pushing level, the preset consultation closing countdown is started;
[0051] If the user's online status is still offline within the preset closing countdown time, the current online consultation will be terminated after the preset consultation closing countdown ends.
[0052] In this embodiment, it also includes:
[0053] Build a low-value word library, classify low-value words related to flight consultation into preset categories, and store them in the low-value word library.
[0054] Specifically, the low-value message library enumerates words that have no actual business meaning, such as good, yes, welcome, sorry, etc.
[0055] Reference Figure 1 and Figure 2 , a message push device proposed by the present invention comprises:
[0056] The data monitoring module is used to monitor the user's online status in real time when starting online consultation. When the user's online status is detected to be offline, the latest consultation reply information is obtained and the consultation reply information is used as offline information.
[0057] The data analysis module is used to analyze the value of offline information to obtain the value level corresponding to the offline information, and the value level includes push level and non-push level;
[0058] The data push module is used to process offline information according to the value level to end the current online consultation or push offline messages to the user.
[0059] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.
Claims
1. A message push method, characterized in that: include: When starting an online consultation, monitor the user's online status in real time. When the user's online status is detected to be offline, obtain the latest consultation reply information and use the consultation reply information as offline information; Perform message value analysis on offline information to obtain the value level corresponding to the offline information, including push level and non-push level; Offline information processing is performed according to the value level to end the current online consultation or push the offline message to the user.
2. The message push method according to claim 1, characterized in that: The number of words in the offline information is within N words; and the message value analysis of the offline information to obtain the value level corresponding to the offline information specifically includes: When the number of words in the offline information is within N words, preprocessing the offline information; Split the preprocessed offline information into independent words and match them with the preset low-value word library; When the separated independent words completely match the low-value word library, the value level corresponding to the offline message is not pushed; When the separated independent words do not completely match the low-value vocabulary, the value level corresponding to the offline message is push level.
3. The message push method according to claim 1, characterized in that: The number of words in the offline information is greater than N words; and the message value analysis of the offline information to obtain the value level corresponding to the offline information specifically includes: When the number of words in the offline information is greater than N words, preprocessing the offline information; Split the preprocessed offline information into independent words and match them with the preset low-value word library; When the split independent words have a matching degree with the low-value word library that is greater than or equal to the preset ratio of the number of words in the offline message, the value level corresponding to the offline message is the non-push level; When the matching degree of the split independent words with the low-value word library is less than the preset ratio of the number of words in the offline message, the value level corresponding to the offline message is the push level.
4. The message push method according to claim 2 or 3, characterized in that: The pre-processing specifically includes: After cleaning the special characters of the offline information and removing the extra spaces in the offline information, the offline message is standardized according to the preset standard format.
5. The message push method according to claim 1, characterized in that: The value level is specifically a push level; the processing of offline information according to the value level and pushing offline messages to users specifically includes: When the value level is determined to be the push level, the user's visiting path is obtained, and the offline message is pushed to the user according to the push method corresponding to the visiting path.
6. The message push method according to claim 5, characterized in that: The visiting path includes but is not limited to the user-side APP and the mini-program side; the push method corresponding to the user-side APP is specifically to directly push the offline message to the mobile phone message bar; the push method corresponding to the mini-program side is specifically to push to the program message bar corresponding to the mini-program side.
7. The message push method according to claim 6, characterized in that: Also includes: When the user clicks on the mobile phone message bar or program message bar corresponding to the offline message, the user enters the online consultation page and switches the user's online status from offline to online.
8. The message push method according to claim 1, characterized in that: The value level is specifically the non-pushing level; and the processing of offline information according to the value level to end the current online consultation is specifically: When the value level is determined to be a non-pushing level, the preset consultation closing countdown is started; If the user's online status is still offline within the preset closing countdown time, the current online consultation will be terminated after the preset consultation closing countdown ends.
9. The message push method according to claim 1, characterized in that: Also includes: Build a low-value word library, classify low-value words related to flight consultation into preset categories, and store them in the low-value word library.
10. A message push device, characterized in that: include: The data monitoring module is used to monitor the user's online status in real time when starting online consultation. When the user's online status is detected to be offline, the latest consultation reply information is obtained and the consultation reply information is used as offline information; The data analysis module is used to analyze the value of offline information to obtain the value level corresponding to the offline information, and the value level includes push level and non-push level; The data push module is used to process offline information according to the value level to end the current online consultation or push offline messages to the user.