Information pushing method and device, equipment, medium and program product

Abstract

The invention provides an information pushing method, and relates to the field of artificial intelligence, the field of finance or other fields. The method comprises the following steps: acquiring maintenance data of a user, wherein the maintenance data comprises static information data and dynamic behavior data of the user; n target maintenance rules are matched from a maintenance rule set based on the maintenance data, the maintenance rule set is obtained in advance according to interaction data between M maintenance personnel and a target user group, and N and M are integers larger than or equal to 1; determining respective trigger conditions of the N target maintenance rules; and when the maintenance data meets the trigger condition of any one of the N target maintenance rules, pushing information conforming to the target maintenance rule to the user.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence, finance or other fields, and more specifically, to an information push method, device, equipment, medium and program product. Background Art

[0002] Pushing information to users through SMS, email, apps, phone calls or official accounts is an important service and marketing tool. In the existing technology, it is usually a combination of manual and program methods. For example, bank account managers inform customers of preferential activities or business reminders through phone calls, online chats, and SMS messages, or use programs to automatically send new activities, new discounts, and other information to a large number of users through full message push.

[0003] In the process of implementing the invention concept of the present disclosure, the inventor found that different account managers use different customer maintenance methods, which bring different wiki effects and may reduce user experience. It is difficult to accurately determine the marketing timing by using program automation to send messages, and sending a large amount of invalid information causes a waste of computing resources. Summary of the invention

[0004] In view of the above problems, the present disclosure provides an information push method, apparatus, device, medium and program product.

[0005] According to the first aspect of the present disclosure, there is provided an information push method, characterized in that it includes: obtaining maintenance data of a user, the maintenance data including static information data and dynamic behavior data of the user; matching N target maintenance rules from a maintenance rule set based on the maintenance data, wherein the maintenance rule set is obtained in advance based on interaction data between M maintenance personnel and a target user group, and N and M are integers greater than or equal to 1 respectively; determining a trigger condition for each of the N target maintenance rules; and when the maintenance data meets the trigger condition of any one of the N target maintenance rules, pushing information that meets the target maintenance rule to the user.

[0006] According to an embodiment of the present disclosure, obtaining the maintenance rule set in advance includes: obtaining interaction data between each of the M maintenance personnel and a target user group; obtaining feedback data that meets preset conditions from the interaction data; obtaining corresponding behavior data from the interaction data based on the feedback data, wherein the behavior data characterizes the maintenance behavior of at least one maintenance personnel, and the feedback data characterizes the feedback behavior of at least one target user in response to the maintenance behavior; and performing cluster analysis on the behavior data to obtain the maintenance rule set.

[0007] According to an embodiment of the present disclosure, each target maintenance rule includes S candidate push time periods, and the S candidate push time periods are obtained by clustering the feedback time in the feedback data, and S is an integer greater than or equal to 1; when the maintenance data meets the triggering condition of any one of the N target maintenance rules, information that complies with the target maintenance rule is pushed to the user, including: pushing information in at least one time period among the S candidate push time periods.

[0008] According to an embodiment of the present disclosure, the S candidate push time periods are obtained by clustering feedback time in the feedback data, including: the S candidate push time periods corresponding to the user are obtained by clustering feedback time in the feedback data.

[0009] According to an embodiment of the present disclosure, pushing information for at least one time period in the S candidate push time periods includes: acquiring available push resources for each time period in the S candidate push time periods, the available resource data including hardware resources and software resources for executing information push; and determining the at least one time period for pushing information to the user based on the available push resources for each time period.

[0010] According to an embodiment of the present disclosure, when the maintenance data meets the triggering conditions of at least two of the N target maintenance rules, information that meets the at least two target maintenance rules is pushed to the user in a combined manner.

[0011] According to an embodiment of the present disclosure, merging and pushing information that complies with the at least two target maintenance rules to the user includes: obtaining at least two information templates that correspond one to one to the at least two target maintenance rules; extracting information elements to be pushed from the maintenance data; generating merged push information based on the information elements and the at least two information templates; and pushing the merged push information to the user.

[0012] According to an embodiment of the present disclosure, a priority is pre-assigned to each maintenance rule in the maintenance rule set, and pushing the merged push information to the user includes: determining the highest priority rule among the at least two target maintenance rules; and pushing information in at least one candidate time period corresponding to the highest priority rule.

[0013] Another aspect of the disclosed embodiment provides an information push device, characterized in that it includes: a data acquisition module, used to acquire maintenance data of a user, wherein the maintenance data includes static information data and dynamic behavior data of the user; a rule matching module, used to match N target maintenance rules from a maintenance rule set based on the maintenance data, wherein the maintenance rule set is obtained in advance based on interaction data between M maintenance personnel and a target user group, and N and M are integers greater than or equal to 1 respectively; a trigger determination module, used to determine the trigger conditions of each of the N target maintenance rules; and an information push module, used to push information that meets any of the N target maintenance rules to the user when the maintenance data meets the trigger conditions of the target maintenance rule.

[0014] Another aspect of an embodiment of the present disclosure provides an electronic device, including: one or more processors; and a memory for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors execute the method described above.

[0015] Another aspect of an embodiment of the present disclosure provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the processor executes the method as described above.

[0016] Another aspect of an embodiment of the present disclosure provides a computer program product, including a computer program, which implements the above method when executed by a processor.

[0017] One or more of the above embodiments have the following beneficial effects: by means of big data analysis, a set of maintenance rules is obtained in advance based on the interaction data between M maintenance personnel and the target user group, and the customer maintenance method with excellent wiki effect is solidified in a regularized manner. And the target maintenance rules are matched according to the user's static information data and dynamic behavior data, and personalized information is pushed. Thus, a unified customer maintenance method can be achieved through automated rule matching and personalized information push, the marketing timing can be accurately grasped, invalid information can be avoided to save computing resources, and the user experience can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The above contents and other objects, features and advantages of the present disclosure will become more apparent through the following description of the embodiments of the present disclosure with reference to the accompanying drawings, in which:

[0019] Figure 1 The following schematically shows an application scenario diagram of information push according to an embodiment of the present disclosure;

[0020] Figure 2 The flowchart of the information push method according to the embodiment of the present disclosure is schematically shown;

[0021] Figure 3 Schematically shows a flow chart of obtaining a maintenance rule set in advance according to an embodiment of the present disclosure;

[0022] Figure 4 A flowchart of selecting a time period for pushing information according to an embodiment of the present disclosure is schematically shown;

[0023] Figure 5 A flowchart of merging and pushing according to an embodiment of the present disclosure is schematically shown;

[0024] Figure 6 A flowchart of merging and pushing according to another embodiment of the present disclosure is schematically shown;

[0025] Figure 7 A schematic diagram of the structure of an information push device according to an embodiment of the present invention is shown;

[0026] Figure 8 A block diagram of an electronic device suitable for implementing the information push method according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0027] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present disclosure. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present disclosure.

[0028] In the technical solution of the present invention, the user information (including but not limited to user personal information, user image information, user device information, such as location information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved are all information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data comply with relevant laws, regulations and standards, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0029] In the scenario of using personal information for automated decision-making, the methods, devices, and systems provided by the embodiments of the present invention provide users with corresponding operation portals for users to choose to agree or reject the automated decision results. If the user chooses to reject, the expert decision-making process will be entered. The expression "automated decision-making" here refers to the activity of automatically analyzing and evaluating an individual's behavioral habits, interests and hobbies, or economic, health, credit status, etc. through a computer program, and making decisions. The expression "expert decision-making" here refers to the activity of making decisions by people who specialize in a certain field, have specialized experience, knowledge and skills, and have reached a certain level of professionalism.

[0030] Figure 1 The following schematically shows an application scenario diagram of information push according to an embodiment of the present disclosure. It should be noted that: Figure 1 What is shown are merely examples to which the embodiments of the present disclosure can be applied, so as to help those skilled in the art understand the technical content of the present disclosure, but it does not mean that the embodiments of the present disclosure cannot be used in other devices, systems, environments or scenarios.

[0031] like Figure 1 As shown, the application scenario 100 according to this embodiment may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for a communication link between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0032] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only examples).

[0033] The terminal devices 101 , 102 , and 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, and desktop computers.

[0034] The server 105 may be a server that provides various services, such as a background management server that provides support for websites browsed by users using the terminal devices 101, 102, and 103 (for example only). The background management server may analyze and process the received data such as user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal device. For example, the server 105 may be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud computing, network services, and middleware services.

[0035] It should be noted that the information push method provided in the embodiment of the present disclosure can generally be executed by at least one of a terminal device or a server. Accordingly, the information push device provided in the embodiment of the present disclosure can generally be set in at least one of a terminal device or a server.

[0036] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0037] The following will be based on Figure 1 The scene described by Figure 2~Figure 6 The information push method of the embodiment of the present disclosure is described in detail.

[0038] Figure 2 The flowchart of the information push method according to the embodiment of the present disclosure is schematically shown.

[0039] like Figure 2 As shown, this embodiment includes:

[0040] In operation S210, maintenance data of a user is acquired, where the maintenance data includes static information data and dynamic behavior data of the user.

[0041] For example, maintenance data refers to data needed in the customer maintenance process. Static information data includes basic information of users, such as gender, age, occupation, customer level, bank card type, etc. Dynamic behavior data includes behavior data generated by users in the process of using services, such as browsing history, transaction records, login frequency, etc. These data will be updated with user activities. For example, bank users' transfer records and account query frequency in online banking.

[0042] In operation S220 , N target maintenance rules are matched from a maintenance rule set based on the maintenance data, wherein the maintenance rule set is pre-obtained based on interaction data between M maintenance personnel and the target user group, and N and M are integers greater than or equal to 1, respectively.

[0043] The maintenance rule set includes one or more pre-set rules, which are pre-set based on the interaction data between the maintenance personnel and the target user group. From the preset rule set, the maintenance rule matching the user status is screened out to perform personalized information push.

[0044] For example, interaction data can include data from the following four types of wiki scenarios:

[0045] 1. Emotional maintenance: Push reminder messages such as holiday greetings, weather care, birthday wishes, etc. to customers during important festivals including but not limited to the Spring Festival, solar terms such as the Great Cold and the End of Heat, and special times such as the customer’s birthday.

[0046] 2. Important time points: Financing product marketing and promotional activities are pushed via text messages at special times including but not limited to Double Eleven and before the distribution of year-end bonuses to the agency customer base.

[0047] 3. Condition triggers: including but not limited to rights reminders, credit card binding consumption and target marketing, mobile banking activation, and marketing for funds over 50,000 yuan. Through RPA robots and flow platforms, we can follow up on customer rights, credit cards, mobile banking receipts or usage, funds over 50,000 yuan, and other related situations in real time, and send marketing and reminder information to customers when the corresponding trigger conditions are met.

[0048] 4. Important reminders: including but not limited to credit card annual fee reminder marketing, credit card expiration and card collection reminders, points redemption, document validity reminders and re-entry, etc. The RPA robot retrieves the relevant information and sends the corresponding SMS reminders.

[0049] In the process of matching N target maintenance rules, corresponding scenario keywords may be extracted from the maintenance data based on the above scenarios, and corresponding target maintenance rules may be searched in the maintenance rule set.

[0050] In operation S230, triggering conditions of respective N target maintenance rules are determined.

[0051] For example, a target maintenance rule is such as "If customer A has foreign currency transactions in the past month and the balance of the foreign currency account is less than a certain amount, then push the relevant information of foreign exchange purchase". The trigger condition is the condition set in the target maintenance rule. When the user's maintenance data meets these conditions, the information push will be triggered. For example, the trigger condition is the foreign currency transaction activity and account balance status of customer A. When the bank system detects that the user meets the trigger condition of the foreign exchange purchase push rule, it automatically sends the foreign exchange purchase reminder information to the user.

[0052] In operation S240, when the maintenance data meets the triggering condition of any one of the N target maintenance rules, information that meets the target maintenance rule is pushed to the user.

[0053] Taking the banking scenario as an example, with the authorization of the user or full authorization of all parties, the backend database of the banking system will collect the personal information form filled out by the user (static information data) as well as the user's online transaction records, login frequency, etc. (dynamic behavior data). Use database query languages, such as SQL, to extract and process user data. Data analysis applications can execute machine learning algorithms to analyze user data and match corresponding maintenance rules. For example, classification algorithms, such as support vector machines (SVM) or decision trees, are used to perform rule prediction and matching. The rule engine will parse the maintenance rules, extract condition parameters, and monitor whether the user data meets these conditions. When the conditions are triggered, a request is sent to the message push system. The message push system automatically sends relevant information to the user. For example, for business scenarios with high requirements for data timeliness (such as timely pushing "Credit Card Automatic Repayment Agreement" related marketing information to customers who have just completed credit card repayments), monitor the generation of new customer transaction files, and enable the streaming platform to automatically synchronize and obtain the customer information to be pushed in this scenario. For business scenarios with general requirements for data timeliness (such as sending a "birthday greeting" to a customer on his or her birthday), the customer information to be pushed in this scenario is obtained through the database (data is generally stored in the database with a time limit of T+1 or T+2).

[0054] According to the embodiments of the present disclosure, a maintenance rule set is obtained in advance based on the interaction data between M maintenance personnel and the target user group through big data analysis, and a customer maintenance method with excellent wiki effect is solidified in a regularized manner. And the target maintenance rules are matched according to the user's static information data and dynamic behavior data, and personalized information is pushed. Therefore, a unified customer maintenance method can be achieved through automated rule matching and personalized information push, the marketing timing can be accurately grasped, invalid information can be avoided to save computing resources, and the user experience can be improved.

[0055] Figure 3 The flowchart of obtaining a maintenance rule set in advance according to an embodiment of the present disclosure is schematically shown.

[0056] like Figure 3 As shown, this embodiment includes:

[0057] In operation S310, interaction data between M maintenance personnel and a target user group is obtained.

[0058] The target user group includes multiple users. By collecting interaction data based on the target user group served by one or more maintenance personnel, it is possible to analyze group behavior through big data and obtain maintenance methods with excellent performance.

[0059] In operation S320, feedback data meeting a preset condition is obtained from the interaction data.

[0060] In operation S330 , corresponding behavior data is obtained from the interaction data based on the feedback data, wherein the behavior data represents a maintenance behavior of at least one maintenance person, and the feedback data represents a feedback behavior of at least one target user in response to the maintenance behavior.

[0061] Interaction data includes the interaction data between maintenance personnel and user groups. For example, maintenance behaviors include greeting messages, birthday wishes, and promotional event reminders sent by maintenance personnel to users at a certain time. Behavior data includes time, communication method, communication frequency, communication content, and speech templates. Feedback behaviors include feedback actions taken by users after receiving maintenance behaviors, such as expressing gratitude, asking for event details, and hanging up the phone immediately. Feedback data includes the content expressed by users, sentiment analysis results, communication frequency, service evaluation, etc. Sentiment analysis results can be predicted using trained machine learning models based on the content and tone of user expressions.

[0062] Feedback data can be filtered, for example, to eliminate data where users give negative reviews. The preset condition can be that the same maintenance behavior receives a number of positive reviews that meet a preset number of people (such as 1,000 people, just an example). Each maintenance behavior can also be scored, and the preset condition is the scoring standard value (such as 90 points, with a full score of 100 points, just an example).

[0063] In operation S340, cluster analysis is performed on the behavior data to obtain a maintenance rule set.

[0064] For example, first, select or construct a feature set that can represent maintenance behavior from the behavior data. And select a suitable clustering algorithm, such as K-means, hierarchical clustering, DBSCAN, etc. Then, taking K-means as an example, the number of clusters can be predetermined by methods such as the Elbow Method and the Silhouette Coefficient. Then, run the clustering algorithm to divide the behavior data into multiple clusters. Each cluster represents a group of similar maintenance behaviors. Then, analyze each cluster and extract maintenance rules, such as statistical analysis of the data within the cluster to identify common features and patterns. Finally, verify the effectiveness of the rules obtained by cluster analysis by actually applying these rules and collecting feedback. Adjust and optimize according to the feedback. Construct the extracted maintenance rule set into a form that can be used by the system, such as a decision tree, rule base, etc.

[0065] According to the embodiments of the present disclosure, by clustering and analyzing the behavioral data of the interaction between the maintenance personnel and the users to obtain the maintenance rule set, it is possible to formulate push rules more accurately according to the relationship between the maintenance behavior and the feedback, which not only improves the personalization and accuracy of the information push, but also enhances the user experience.

[0066] In other embodiments, some rules of the maintenance rule set may also come from non-interactive data such as business processes, industry experience, or data analysis. For example, a certain time period based on big data analysis is the peak period for active users to conduct transactions, so pushing relevant activity information to users during this time period may achieve better results than other time periods. Therefore, maintenance rules can not only come from direct feedback from users, but also be obtained from other sources, such as industry experience, data analysis, etc.

[0067] In some embodiments, each target maintenance rule includes S candidate push time periods, where the S candidate push time periods are obtained by clustering feedback times in feedback data, and S is an integer greater than or equal to 1.

[0068] When the maintenance data meets the triggering condition of any one of the N target maintenance rules, the information that meets the target maintenance rule is pushed to the user, including:

[0069] Information is pushed in at least one of the S candidate push time periods. The time period can be selected for push based on computer resources, the number of pushees, or a random strategy.

[0070] Exemplarily, the candidate push time periods include time periods that may be suitable for pushing information, which are obtained by analyzing feedback data such as the user's active time. For example, if the data shows that the user often checks bank information between 8 and 9 p.m., then this time period may be selected as a candidate push time period. Alternatively, if the interaction data shows that when calling or pushing information to the user between 5 and 6 a.m. on weekends, it usually gets a bad review, then this time period is excluded.

[0071] Feedback time clustering means analyzing the time of user feedback and dividing these times into different groups (clusters) to find the most likely time period for users to view information. For example, the K-means algorithm is used to cluster the time points when users view information to determine the candidate push time periods. The feedback time can include a specific time point, such as 7:30 in the morning, or the difference between the time when the information arrives and the time when it is viewed.

[0072] According to the embodiments of the present disclosure, by determining the candidate push time periods through cluster analysis, optimization can be performed for the specific active time of the user, thereby increasing the probability of the user reading the information. The message opening rate and user interaction rate can be improved, thereby improving the efficiency of information transmission. Avoiding pushing information during the user's inactive time reduces interference to the user and improves the user experience. Allowing multiple push time periods provides greater flexibility and adaptability for information push strategies.

[0073] In some embodiments, the S candidate push time periods are obtained by clustering the feedback time in the feedback data, including: the S candidate push time periods corresponding to the user are obtained by clustering the feedback time in the feedback data.

[0074] For example, customer A has used the services of Bank A for more than 10 years, and there is a large amount of feedback data in these 10 years. Clustering algorithms can be used to process this data to identify S candidate push time periods. These time periods are when customer A is most likely to view and interact with information. The information push can be adapted to the needs of each user, making the information push more accurate, improving the user's opening and interaction rate, and thus increasing the effectiveness of information push.

[0075] In some embodiments, since the user's behavior pattern may change over time and in different scenarios, the push period may be dynamically updated to match the user's latest needs. For example, the latest user feedback data may be obtained regularly (such as weekly or monthly), cluster analysis may be performed again, and the push period may be updated.

[0076] Figure 4 The flowchart of selecting a time period for pushing information according to an embodiment of the present disclosure is schematically shown.

[0077] like Figure 4 As shown, this embodiment includes pushing information in at least one time period in S candidate push time periods, specifically including:

[0078] In operation S410, available push resources in each of S candidate push time periods are obtained, and the available resource data includes hardware resources and software resources for executing information push.

[0079] For example, hardware resources usually include the processing capacity of the server (such as the utilization rate of the CPU and GPU), hard disk storage space, memory usage, and the status of network devices. Software resources usually include the bandwidth usage of the system, the average load of the server, the delay time of a specific service (such as database query), the number of pending tasks in the system queue, etc. For example, the resource monitoring module in the push system monitors the usage of hardware and software resources in real time. The decision module is used to determine the push period based on the resource situation.

[0080] In operation S420, at least one time period for pushing information to the user is determined based on available push resources in each time period.

[0081] Continuing with the example of the banking scenario, the marketing department of the bank wants to push credit product information to users. First, the time periods when users are most likely to log in to the bank APP from 6pm to 7pm and from 8pm to 9pm are analyzed. This time period is selected as one of the candidate push time periods. Subsequently, the available push resources between 6pm and 7pm are evaluated, and it is found that users are highly active during this time period, but hardware resources (such as server capacity and network bandwidth) may be bottlenecked due to the evening peak network traffic. In order to dynamically allocate resources based on real-time resource utilization and the urgency of the task, information push is selected from 8pm to 9pm when users are highly active but other tasks are less. Not only can it arrive during the time period when users are most likely to open, but the push process will not be affected by resource limitations.

[0082] According to the embodiments of the present disclosure, by considering the availability of hardware resources and software resources required for information push, the success rate of information push and the response rate of users can be improved, while ensuring the efficient execution of push tasks.

[0083] In some embodiments, in order to avoid excessively disturbing customers, a certain limit is imposed on the number of times a certain customer is reached, and a limited number of SMS messages are sent to customers who meet multiple reach conditions or the same reach condition is met multiple times within a certain time period. The implementation method is as follows:

[0084] 1. The full amount of information about historically reached customers in each business scenario is entered into the target directory of the local server according to the scenario.

[0085] 2. Through interconnection (Xshell executes hql script trigger), new customer data is regularly migrated (database data is generally once a day, and streaming data is generally real-time) from the remote (head office) HADOOP / MPP cluster to the server of the local cluster, and key data is encrypted or desensitized. The storage time of data on the local server can be limited to the maximum time period required by the "anti-disturbance" requirement (for example, in a scenario where "customers can only be reached once a quarter", the storage period is one quarter).

[0086] 3. According to the "do not disturb" requirements (such as "can be reached twice in total", "can reach the customer once within half a year", etc.), match the new data with the historical data. If the customer meets the "do not disturb" conditions, filter the data, otherwise retain it.

[0087] In some embodiments, to avoid excessively disturbing customers, when the maintenance data meets the triggering conditions of at least two of N target maintenance rules, information that meets at least two target maintenance rules is pushed to the user in a combined manner.

[0088] For example, in a banking scenario, several maintenance rules are set, such as "account balance is less than 1,000 yuan" and "no transaction activity in the past month" as conditions for triggering users to accept maintenance information. The bank's system regularly checks each user's account and records the rule conditions that are met. Customer A's account balance drops to 950 yuan, and there is no transaction activity in a month, which meets the conditions of the above two rules. The bank's push system will automatically merge the two pieces of information and send a push message to Customer A, reminding the user to pay attention to his account balance and reminding the user to pay attention to the inactivity of the account.

[0089] According to the embodiments of the present disclosure, the push strategy is optimized, the frequency of information reception by users is reduced, and the interference felt by users is reduced by merging push messages, which saves time for users because they only need to read and respond to one message, while also ensuring the effective delivery of information.

[0090] Figure 5 The flowchart of merge push according to an embodiment of the present disclosure is schematically shown.

[0091] like Figure 5 As shown, in this embodiment, information that meets at least two target maintenance rules is pushed to the user in a combined manner, including:

[0092] In operation S510, at least two information templates corresponding to at least two target maintenance rules are obtained.

[0093] For example, a message template is a pre-designed message framework for sending a specific type of message. Each template corresponds to one or more maintenance rules. For example, for the insufficient balance rule, the message template may contain the text: "Your account balance is less than [amount], please recharge in time."

[0094] In operation S520, information elements to be pushed are extracted from the maintenance data.

[0095] Information elements refer to specific information points extracted from the user's maintenance data and used to fill in the information template. For example, if the user's account balance is 900 yuan, then "900 yuan" is an information element.

[0096] In operation S530, merged push information is generated based on the information element and at least two information templates.

[0097] In operation S540, the combined push information is pushed to the user.

[0098] Merged push information refers to combining multiple messages into one message and then pushing it to the user.

[0099] For example, according to the business scenarios corresponding to the maintenance rules, a speech template is set up in advance and imported into the system. Variable positions (such as customer name, product name, product expiration date, etc.) are reserved in the template. When the speech template is triggered, the information elements corresponding to different customers can be filled in the template respectively.

[0100] For example, if Customer A triggers two rules, "Account balance is less than 1,000 yuan" and "No transaction activity in the past month", the bank's push system will perform the following operations: First, obtain the information templates corresponding to the two rules. The first template may be a balance warning template, and the second is an account inactivity warning template. Then, extract information elements from Customer A's maintenance data, such as an account balance of 950 yuan and the last transaction date one month ago. Then, using these information elements, the system generates a merged message based on the preset template: "Dear Customer A, your account balance is less than 950 yuan, and there has been no transaction activity in the past month. For the safety of your account, please log in to the bank APP in time to check and perform necessary operations."

[0101] Next, determine the current capacity and push data size of the customer contact channel (such as smart outbound calls, SMS, mobile banking, corporate WeChat, etc.). Take the SMS channel as an example. If the current outbound SMS balance of the online channel (quasi-real-time) is X, if the current data to be pushed is greater than X, then filter the top X customers according to a certain set condition (such as sorting customers by salary amount from high to low), and store them in the local server historical push record (such as 1. in the data storage and filtering section). The remaining customers are automatically discarded and not recorded in the historical push record. If the current data to be pushed is less than or equal to X, retain all customers and store them in the local server historical push record.

[0102] Then, through the API, the target customer contact channel interface is called, such as intelligent outbound calls, batch SMS, online SMS (quasi-real-time), mobile banking, corporate WeChat, etc., to push the processed information to the customer. Finally, a message reminder is sent to the bank's internal equipment of the customer manager in real time to inform him of the customer information push status, and all outbound call logs are automatically retained.

[0103] According to the embodiments of the present disclosure, by merging push information, users can avoid the trouble of receiving multiple messages, simplifying the user's information processing process. By using information templates and elements, push information tailored to the user's personal situation can be generated, improving the standardization of information.

[0104] When multiple rules are triggered at the same time, define a priority strategy to determine which rules are more important. Priority strategies may be set based on factors such as the business importance of the rules, user preferences, etc. For example, the priority of the rules can be dynamically adjusted based on data such as the number of times the rules are triggered, the conversion rate corresponding to the rules, and user feedback related to the rules.

[0105] In some embodiments, in operation S530, the merged push information is generated according to the priority, and the information corresponding to the rule with a high priority is placed in the front position, and the content accounts for a larger proportion.

[0106] Figure 6 The following schematically shows a flowchart of merge push according to another embodiment of the present disclosure.

[0107] like Figure 6 As shown, this embodiment is one of the embodiments of operation S540, pre-assigning a priority to each maintenance rule in the maintenance rule set, and pushing the combined push information to the user includes:

[0108] In operation S610, a highest priority rule among at least two target maintenance rules is determined.

[0109] In operation S620, information is pushed in at least one candidate time period corresponding to the highest priority rule.

[0110] The highest priority rule refers to the one with the highest priority among all triggered target maintenance rules. By determining the highest priority rule and its corresponding push period, important information can be conveyed more effectively, allowing users to pay enough attention to important information.

[0111] Based on the above information push method, the present disclosure also provides an information push device. Figure 7 Further elaboration.

[0112] Figure 7 The structure block diagram of the information push device according to an embodiment of the present invention is schematically shown.

[0113] like Figure 7 The information pushing device 700 may include a data acquisition module 710 , a rule matching module 720 , a trigger determination module 730 and an information pushing module 740 .

[0114] The data acquisition module 710 may perform operation S210 to acquire maintenance data of the user, where the maintenance data includes static information data and dynamic behavior data of the user.

[0115] The rule matching module 720 may perform operation S220 to match N target maintenance rules from a maintenance rule set based on the maintenance data, wherein the maintenance rule set is pre-obtained based on interaction data between M maintenance personnel and the target user group, and N and M are integers greater than or equal to 1 respectively.

[0116] The trigger determination module 730 may perform operation S230 to determine the trigger conditions of each of the N target maintenance rules.

[0117] The information push module 740 may perform operation S240 to push information that complies with any one of the N target maintenance rules to the user when the maintenance data meets the triggering condition of the target maintenance rule.

[0118] In some embodiments, the information push module 740 may perform operations S410 to S420, operations S510 to S540, and operations S610 to S620, which will not be described in detail herein.

[0119] In some embodiments, the information push device 700 may further include a rule extraction module, which may execute operations S310 to S340, which will not be described in detail herein.

[0120] For the parts not mentioned in the device part, they can be understood with reference to the various embodiments of the above method. That is, the device part includes modules for executing the various steps of any one of the method embodiments described above. In addition, the implementation methods, technical problems solved, functions implemented, and technical effects achieved of each module / unit / subunit, etc. in the device part embodiment are respectively the same or similar to the implementation methods, technical problems solved, functions implemented, and technical effects achieved of each corresponding step in the method part embodiment, and will not be repeated here.

[0121] According to an embodiment of the present disclosure, any multiple modules among the data acquisition module 710, the rule matching module 720, the trigger determination module 730 and the information push module 740 can be combined into one module for implementation, or any one of the modules can be split into multiple modules. Alternatively, at least part of the functions of one or more of these modules can be combined with at least part of the functions of other modules and implemented in one module.

[0122] According to an embodiment of the present disclosure, at least one of the data acquisition module 710, the rule matching module 720, the trigger determination module 730 and the information push module 740 may be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application specific integrated circuit (ASIC), or may be implemented by hardware or firmware such as any other reasonable way of integrating or packaging the circuit, or by any one of the three implementation methods of software, hardware and firmware or by an appropriate combination of any of them. Alternatively, at least one of the data acquisition module 710, the rule matching module 720, the trigger determination module 730 and the information push module 740 may be at least partially implemented as a computer program module, and when the computer program module is run, the corresponding function may be executed.

[0123] Figure 8A block diagram of an electronic device suitable for implementing the information push method according to an embodiment of the present disclosure is schematically shown.

[0124] like Figure 8 As shown, the electronic device 800 according to an embodiment of the present disclosure includes a processor 801, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 802 or a program loaded from a storage part 808 to a random access memory (RAM) 803. The processor 801 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or a related chipset and / or a dedicated microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 801 may also include an onboard memory for caching purposes. The processor 801 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.

[0125] In RAM 803, various programs and data required for the operation of electronic device 800 are stored. Processor 801, ROM 802 and RAM 803 are connected to each other via bus 804. Processor 801 performs various operations of the method flow according to the embodiment of the present disclosure by executing the program in ROM 802 and / or RAM 803. It should be noted that the program can also be stored in one or more memories other than ROM 802 and RAM 803. Processor 801 can also perform various operations of the method flow according to the embodiment of the present disclosure by executing the program stored in one or more memories.

[0126] According to an embodiment of the present disclosure, the electronic device 800 may further include an input / output (I / O) interface 805, which is also connected to the bus 804. The electronic device 800 may further include one or more of the following components connected to the I / O interface 805: an input portion 806 including a keyboard, a mouse, etc. An output portion 807 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc. A storage portion 808 including a hard disk, etc. And a communication portion 809 including a network interface card such as a LAN card, a modem, etc. The communication portion 809 performs communication processing via a network such as the Internet. A drive 810 is also connected to the I / O interface 805 as needed. A removable medium 811, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 810 as needed, so that the computer program read therefrom is installed into the storage portion 808 as needed.

[0127] The present disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments. It may also exist independently without being assembled into the device / apparatus / system. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the method according to the embodiment of the present disclosure is implemented.

[0128] According to an embodiment of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, for example, it may include but is not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, an apparatus or a device. For example, according to an embodiment of the present disclosure, the computer-readable storage medium may include the ROM 802 and / or RAM 803 described above and / or one or more memories other than ROM 802 and RAM 803.

[0129] The embodiment of the present disclosure also includes a computer program product, which includes a computer program, and the computer program contains program code for executing the method shown in the flowchart. When the computer program product is run in a computer system, the program code is used to enable the computer system to implement the method provided by the embodiment of the present disclosure.

[0130] The above functions defined in the system / device of the embodiment of the present disclosure are executed when the computer program is executed by the processor 801. According to the embodiment of the present disclosure, the system, device, module, unit, etc. described above can be implemented by a computer program module.

[0131] In one embodiment, the computer program may rely on tangible storage media such as optical storage devices, magnetic storage devices, etc. In another embodiment, the computer program may also be transmitted and distributed in the form of signals on a network medium, and downloaded and installed through the communication part 809, and / or installed from a removable medium 811. The program code contained in the computer program may be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0132] In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 809, and / or installed from the removable medium 811. When the computer program is executed by the processor 801, the above functions defined in the system of the embodiment of the present disclosure are performed. According to the embodiment of the present disclosure, the system, device, means, module, unit, etc. described above can be implemented by a computer program module.

[0133] According to an embodiment of the present disclosure, the program code for executing the computer program provided by the embodiment of the present disclosure can be written in any combination of one or more programming languages. Specifically, these computing programs can be implemented using high-level process and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, Java, C++, python, "C" language or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on the remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, using an Internet service provider to connect through the Internet).

[0134] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0135] It will be appreciated by those skilled in the art that the features described in the various embodiments and / or claims of the present disclosure may be combined and / or combined in a variety of ways, even if such combinations and / or combinations are not explicitly described in the present disclosure. In particular, the features described in the various embodiments and / or claims of the present disclosure may be combined and / or combined in a variety of ways without departing from the spirit and teachings of the present disclosure. All of these combinations and / or combinations fall within the scope of the present disclosure.

[0136] The embodiments of the present disclosure are described above. However, these embodiments are only for illustrative purposes and are not intended to limit the scope of the present disclosure. Although the embodiments are described above separately, this does not mean that the measures in the various embodiments cannot be used in combination to advantage. The scope of the present disclosure is defined by the attached claims and their equivalents. Without departing from the scope of the present disclosure, those skilled in the art may make a variety of substitutions and modifications, which should all fall within the scope of the present disclosure.

Claims

1. An information push method, characterized in that: include: Acquire maintenance data of the user, wherein the maintenance data includes static information data and dynamic behavior data of the user; Matching N target maintenance rules from a maintenance rule set based on the maintenance data, wherein the maintenance rule set is pre-obtained based on interaction data between M maintenance personnel and the target user group, and N and M are integers greater than or equal to 1 respectively; Determine the triggering conditions of each of the N target maintenance rules; When the maintenance data meets the triggering condition of any one of the N target maintenance rules, information that meets the target maintenance rule is pushed to the user.

2. The method according to claim 1, characterized in that The maintenance rule set obtained in advance includes: Obtaining interaction data between each of the M maintenance personnel and the target user group; Obtaining feedback data that meets preset conditions from the interaction data; Obtaining corresponding behavior data from the interaction data based on the feedback data, wherein the behavior data represents a maintenance behavior of at least one maintenance person, and the feedback data represents a feedback behavior of at least one target user in response to the maintenance behavior; Cluster analysis is performed on the behavior data to obtain the maintenance rule set.

3. The method according to claim 2, characterized in that Each target maintenance rule includes S candidate push time periods, where the S candidate push time periods are obtained by clustering feedback time in the feedback data, and S is an integer greater than or equal to 1; When the maintenance data meets the triggering condition of any one of the N target maintenance rules, pushing information that meets the target maintenance rule to the user includes: Information is pushed in at least one time period among the S candidate push time periods.

4. The method according to claim 3, characterized in that: The S candidate push time periods are obtained by clustering the feedback time in the feedback data and include: The S candidate push time periods corresponding to the user are obtained by clustering the feedback time in the feedback data.

5. The method according to claim 3, characterized in that: The information pushed for at least one time period in the S candidate push time periods includes: Acquire available push resources for each of the S candidate push time periods, wherein the available resource data includes hardware resources and software resources for executing information push; The at least one time period for pushing information to the user is determined based on the available push resources in each time period.

6. The method according to claim 3 or 5, characterized in that: When the maintenance data meets the triggering conditions of at least two of the N target maintenance rules, information that meets the at least two target maintenance rules is pushed to the user in a combined manner.

7. The method according to claim 6, characterized in that The information that complies with the at least two target maintenance rules is pushed to the user in a combined manner, including: Acquire at least two information templates corresponding to the at least two target maintenance rules; extracting information elements to be pushed from the maintenance data; Generate a merged push message based on the information element and the at least two information templates; The combined push information is pushed to the user.

8. The method according to claim 7, characterized in that Pre-assigning a priority to each maintenance rule in the maintenance rule set, and pushing the combined push information to the user comprises: determining a highest priority rule among the at least two target maintenance rules; Information is pushed in at least one candidate time period corresponding to the highest priority rule.

9. An information push device, characterized in that: include: A data acquisition module, used to acquire maintenance data of a user, wherein the maintenance data includes static information data and dynamic behavior data of the user; A rule matching module, configured to match N target maintenance rules from a maintenance rule set based on the maintenance data, wherein the maintenance rule set is obtained in advance based on interaction data between M maintenance personnel and a target user group, and N and M are integers greater than or equal to 1 respectively; A trigger determination module, used to determine the trigger conditions of each of the N target maintenance rules; The information push module is used to push information that meets any one of the N target maintenance rules to the user when the maintenance data meets the triggering condition of the target maintenance rule.

10. An electronic device, comprising: one or more processors; a memory for storing one or more computer programs, It is characterized in that the one or more processors execute the one or more computer programs to implement the steps of the method according to any one of claims 1 to 8.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

12. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images