Strategy generation method and device, strategy application method and device and electronic equipment

Abstract

The invention discloses a strategy generation method and device, a strategy application method and device and electronic equipment, and relates to the technical field of the Internet. According to the method, the process of dynamically allocating corresponding maintenance strategies to different users based on the user types of the different users can be realized, the maintenance strategy corresponding to each user can be quickly and effectively generated (or determined), and the situation of user loss is avoided. The method comprises the following steps: acquiring a behavior sequence of a target user, wherein the behavior sequence of the target user is used for representing an execution sequence of user events contained in the behavior sequence of the target user; based on the behavior sequence of the target user, a target strategy is generated, the target strategy is a strategy corresponding to a target user group, the target user group is a user group to which the target user belongs, and the user types of all users included in the target user group are the same; the user type of the target user is determined based on the user event contained in the behavior sequence of the target user.

Description

Technical Field

[0001] The present application relates to the field of Internet technology, and in particular to a policy generation method, a policy application method, a device and an electronic device. Background Art

[0002] Currently, there are a large number of machine learning algorithms that are used to predict potential mobile users (or off-network users).

[0003] After predicting potential carrier-switch users (or off-network users), feature analysis can be performed based on the complaint information (or complaint information) fed back by the users, and after analyzing the root cause of the complaint, a maintenance strategy for retaining potential carrier-switch users can be formulated based on the root cause of the complaint.

[0004] However, the number of users of operators is more than 10 million. The above process of formulating a maintenance strategy after receiving user complaints (or complaints) may not be able to quickly identify user pain points and provide effective solutions, resulting in user loss. Summary of the invention

[0005] The present application provides a strategy generation method, a strategy application method, a device and an electronic device, which solves the technical problem that the process of formulating a maintenance strategy after receiving user complaint information (or complaint information) may not be able to quickly identify user pain points and provide effective solutions, resulting in user loss.

[0006] The technical solution of the embodiment of the present application is as follows:

[0007] In a first aspect, a policy generation method is provided. The method may include: obtaining a behavior sequence of a target user, the behavior sequence of the target user being used to characterize the execution order of user events contained in the behavior sequence of the target user; generating a target policy based on the behavior sequence of the target user, the target policy being a policy corresponding to a target user group, the target user group being a user group to which the target user belongs, each user included in the target user group having the same user type, and the user type of the target user being determined based on the user events contained in the behavior sequence of the target user.

[0008] In the present application, after acquiring the target user's behavior sequence, the electronic device can determine the user type of the target user based on the user events included in the target user's behavior sequence, and determine the user group to which the target user belongs (i.e., the target user group) based on the target user's user type; finally, the electronic device determines the policy corresponding to the target user group as the target policy, that is, the process of generating the target policy based on the target user's behavior sequence can be realized. In an embodiment of the present application, the electronic device can dynamically assign corresponding maintenance policies to different users based on the user types of different users by determining the policy corresponding to the target user group as the target policy to be generated, and can quickly and effectively generate (or determine) the maintenance policy corresponding to each user to avoid user loss.

[0009] Optionally, the user events included in the behavior sequence of the target user are determined based on user data of the target user.

[0010] In the present application, the electronic device can accurately and effectively determine the user events included in the target user's behavior sequence based on the target user's user data, so that the electronic device can accurately and effectively generate a strategy adapted to the target user, namely, a target strategy, based on the target user's behavior sequence.

[0011] Optionally, the user data of the above-mentioned target user includes at least one item of the business domain data of the target user, the operation domain data of the target user and the service domain data of the target user. The business domain data of the target user is used to characterize the consumption habits of the target user, the operation domain data of the target user is used to characterize the network quality corresponding to the target user, and the service domain data of the target user is used to characterize the user perception of the target user.

[0012] In the present application, since the user data of the target user includes at least one of the business domain data of the target user, the operation domain data of the target user, and the service domain data of the target user, the electronic device can determine the user events contained in the behavior sequence of the target user based on the data of the at least one item. That is, the behavior sequence of each user can reflect the actual situation of each user when performing telecommunications services from multiple angles (including the consumption habits of each user, the network quality of each user, and the user perception of each user), and can fully portray the experience of each user. Thereby, in the subsequent process of generating the target strategy, the accuracy of the target strategy can be improved.

[0013] Optionally, the target user's behavior sequence includes multiple user events and respective timestamps of the multiple user events, and the target user's behavior sequence is obtained by sorting the multiple user events according to respective timestamps of the multiple user events.

[0014] In the present application, after the electronic device determines (or obtains) multiple user events and the respective timestamps of the multiple user events, it sorts the multiple user events according to the respective timestamps of the multiple user events, which can accurately and effectively reflect the user events that occur (or are executed) in chronological order when the target user is performing telecommunications services, that is, a correct and relevant behavior sequence that can effectively reflect the user behavior of each user can be obtained.

[0015] Optionally, the behavior sequence of the above-mentioned target user is determined based on a user behavior history graph, which includes a user node, an event node, and an edge connecting the user node and the event node, the user node is used to represent the user, the event node is used to represent the user event, and the edge is used to represent the timestamp of the user executing the user event.

[0016] In the present application, since the user behavior history graph includes user nodes for representing users, event nodes for representing user events, and edges for representing the timestamps of users executing user events, the electronic device can conveniently and quickly determine the behavior sequence of each user based on the user behavior history graph, thereby improving the rate of generating corresponding strategies for each user.

[0017] Optionally, the above-mentioned obtaining of the behavior sequence of the target user specifically includes: obtaining the user identifier of the target user; querying a user behavior history graph based on the user identifier of the target user, determining a target user node from the user behavior history graph, the node identifier of the target user node is the same as the user identifier of the target user, the user behavior history graph includes a user node, an event node, and an edge connecting the user node and the event node, the user node is used to represent the user, the event node is used to represent the user event, and the edge is used to represent the timestamp of the user executing the user event; determining the user events represented by multiple event nodes as multiple user events included in the behavior sequence of the target user, the multiple event nodes are event nodes that have edges with the target user node; determining the timestamp represented by each of the multiple edges as the timestamp of each of the multiple user events, wherein one edge is used to connect the target user node and an event node among the multiple event nodes; sorting the multiple user events according to their respective timestamps to obtain the behavior sequence of the target user.

[0018] In the present application, after obtaining the user ID of the target user, the electronic device can determine the target user node from the user behavior history graph, the node ID of the target user node is the same as the user ID of the target user, and the target user node is used to characterize the target user; then the electronic device can determine the user events represented by multiple event nodes in the user behavior history graph that have edges (or connection relationships) with the target user node as multiple user events included in the behavior sequence of the target user, and determine the timestamps represented by the multiple edges between the target user node and the multiple event nodes in the user behavior history graph as the timestamps of the multiple user events; finally, the electronic device can sort the multiple user events according to the timestamps of the multiple user events to obtain the behavior sequence of the target user. That is, the electronic device can conveniently and quickly determine the user events performed by each user and the timestamps of the user events performed by each user based on the user ID of each user and the user behavior history graph, which can improve the efficiency of obtaining the behavior sequence of each user.

[0019] Optionally, the user events included in the above-mentioned target user's behavior sequence include negative perception events and / or subjective feedback events, wherein the negative perception event is used to characterize the passive consumption behavior corresponding to the target user, and the subjective feedback event is used to characterize the active complaint behavior corresponding to the target user.

[0020] In the present application, since the user events included in the target user's behavior sequence include negative perception events and / or subjective feedback events, that is, the electronic device can characterize the user behavior of each user in the process of performing telecommunications services in the form of passive consumption behavior corresponding to each user and active complaint behavior corresponding to each user, and can comprehensively and completely obtain the behavior sequence of each user.

[0021] Optionally, the target strategy is determined based on a common behavior sequence corresponding to the target user group, and the common behavior sequence corresponding to the target user group is determined based on a behavior sequence of each user included in the target user group.

[0022] In the present application, after determining the target user group, the electronic device can determine the common behavior sequence corresponding to the target user group based on the behavior sequence of each user included in the target user group, and accurately and effectively determine the target strategy based on the common behavior sequence corresponding to the target user group. That is, the electronic device can accurately and effectively determine the maintenance strategy corresponding to each user based on the most frequently occurring behavior pattern with time sequence characteristics corresponding to the user group to which each user belongs, thereby reducing the portability / off-network situation of each user.

[0023] Optionally, the target strategy is determined based on at least one business indicator, and the at least one business indicator is determined based on an event type of user events included in a common behavior sequence corresponding to the target user group.

[0024] In the present application, after determining the common behavior sequence corresponding to the target user group, the electronic device can accurately and effectively determine at least one business indicator related to the target user group based on the event type of the user event included in the common behavior sequence, and finally determine the target strategy based on the at least one business indicator. That is, the electronic device can accurately and effectively determine the maintenance strategy corresponding to each user based on the business indicator related to the user group to which each user belongs, which can improve the accuracy of strategy generation.

[0025] Optionally, the event type of the user events included in the common behavior sequence corresponding to the target user group includes at least one of a marketing type, a wireless type, and a home broadband type.

[0026] In the present application, the common behavior sequence corresponding to a user group can also be understood as the common service history corresponding to the user group. By performing scenario-based classification on each user event included in the common behavior sequence and obtaining the event type of each user event included in the common behavior sequence, a common behavior sequence with scenario-based business meaning can be formed, so that a maintenance strategy with scenario-based business meaning can be assigned to each user, thereby improving the practicality of the strategy.

[0027] Optionally, the above-mentioned target strategy is a strategy corresponding to a target value, and the target value is a value that matches at least one value in a numerical strategy relationship, and the at least one value is a value corresponding to the at least one business indicator. The numerical strategy relationship includes multiple values ​​and a strategy corresponding to each of the multiple values.

[0028] In the present application, a numerical policy relationship is a correspondence between multiple numerical values ​​and multiple policies, specifically one numerical value corresponds to one policy. The target numerical value is a numerical value that matches at least one numerical value in the numerical policy relationship, which can also be understood as the target numerical value being the same as the at least one numerical value, that is, the policy corresponding to the target numerical value is the policy corresponding to at least one numerical value (or at least one business indicator). The electronic device can easily and quickly determine the maintenance strategy related to the business indicator corresponding to the user group to which each user belongs in the numerical policy relationship, thereby improving the efficiency of strategy generation.

[0029] Optionally, the policy generation method also includes: querying a numerical policy relationship based on at least one numerical value, determining a target numerical value that matches the at least one numerical value from the numerical policy relationship, the numerical policy relationship including multiple numerical values ​​and a policy corresponding to each of the multiple numerical values, the at least one numerical value being a numerical value corresponding to the at least one business indicator; and determining the policy corresponding to the target numerical value as the target policy.

[0030] In the present application, the electronic device can determine a target value that matches (or is the same as) the at least one value from the value policy relationship based on at least one value (i.e., the value corresponding to at least one business indicator), and determine the policy corresponding to the target value as the target policy. It is possible to quickly output a personalized maintenance policy corresponding to the business indicator related to the user group corresponding to each user, thereby ensuring the improvement of user service experience perception from the source and increasing user satisfaction.

[0031] Optionally, the strategy generation method also includes: determining the number of users corresponding to each of a plurality of behavior sequences, the plurality of behavior sequences being determined based on the behavior sequences of each of a plurality of users included in the target user group; and determining the behavior sequences in the plurality of behavior sequences whose corresponding number of users is greater than or equal to a first quantity threshold as the common behavior sequences corresponding to the target user group.

[0032] In the present application, since the multiple behavior sequences are determined based on the behavior sequences of the multiple users included in the target user group, the multiple behavior sequences can comprehensively reflect the behavior habits of each user in the target user group in performing telecommunication services (or user events performed in the process of performing telecommunication services). The behavior sequences corresponding to the number of users in the multiple behavior sequences being greater than or equal to the first quantity threshold can reflect the behavior habits of a large number (or majority) of users in the target user group, and thus can reflect the behavior characteristics of the target user group as a whole, that is, can accurately and effectively characterize the behavior characteristics of the user type corresponding to the target user group, and can then allocate appropriate maintenance strategies to the target users based on the behavior characteristics.

[0033] Optionally, the policy generation method also includes: obtaining a behavior sequence of each user among the multiple users included in the target user group; performing a preset operation on at least one user event included in the behavior sequence of each user to obtain the multiple behavior sequences, wherein the execution order of the user events included in each behavior sequence in the multiple behavior sequences remains unchanged, and the preset operation includes a deletion operation.

[0034] In the present application, the electronic device can obtain the behavior sequence of each user among the multiple users included in the target user group, and perform a preset operation on at least one user event included in the behavior sequence of each user, that is, multiple behavior sequences can be obtained. That is, the electronic device can accurately and effectively determine multiple behavior sequences that can fully reflect the behavior habits of each user in the target user group in the process of conducting telecommunications services based on the behavior habits of each user included in the target user group in the process of conducting telecommunications services, and then accurately determine the common behavior sequence corresponding to each user group, so as to formulate customized strategies for each user group, guide market personnel to complete maintenance, and improve service efficiency.

[0035] Optionally, the above-mentioned target strategy is a strategy corresponding to a first behavior sequence, which is determined from at least one behavior sequence based on the similarity between each behavior sequence in at least one behavior sequence and the behavior sequence of the target user, and the at least one behavior sequence is a behavior sequence included in the common behavior sequence corresponding to the target user group.

[0036] In the present application, one behavior sequence in the at least one behavior sequence corresponds to one strategy, and the electronic device can determine the similarity between each behavior sequence in the at least one behavior sequence and the behavior sequence of the target user, thereby determining the first behavior sequence from the at least one behavior sequence and determining the strategy corresponding to the first behavior sequence as the target strategy. That is, the electronic device can determine the first behavior sequence similar to the behavior sequence of the target user based on the similarity algorithm, and the first behavior sequence can characterize the behavior habits similar to those of the target user when performing telecommunications services to a certain extent, thereby being able to quickly allocate effective target strategies to the target user, which helps to support low-cost and efficient user retention.

[0037] Optionally, the common behavior sequences corresponding to the above-mentioned target user group include at least one behavior sequence, and the strategy generation method also includes: determining the similarity between each behavior sequence in the at least one behavior sequence and the behavior sequence of the target user; determining the strategy corresponding to the first behavior sequence as the target strategy, and the first behavior sequence is the behavior sequence in the at least one behavior sequence that has the greatest similarity with the behavior sequence of the target user.

[0038] In the present application, the similarity between the first behavior sequence and the behavior sequence of the target user is the greatest, indicating that the first behavior sequence is most similar to the behavior sequence of the target user, and it can also be understood that the behavior habits represented by the first behavior sequence are most similar to the behavior habits of the target user in conducting telecommunications services. At this time, the electronic device determines the strategy corresponding to the first behavior sequence as the target strategy, that is, it can accurately and effectively assign the corresponding maintenance strategy to the target user, so that the maintenance and retention strategy for each potential porting / off-network user can be accurately formulated.

[0039] Optionally, the common behavior sequences corresponding to the above-mentioned target user group include at least one behavior sequence, each behavior sequence in the at least one behavior sequence has the same similarity with the behavior sequence of the target user, and the target strategy is a strategy corresponding to a second behavior sequence, which is determined from the at least one behavior sequence based on the event difference corresponding to each behavior sequence in the at least one behavior sequence, wherein the event difference corresponding to a behavior sequence is determined based on the number of user events between each user event included in the behavior sequence and the last user event included in the behavior sequence of the target user.

[0040] In the present application, since the event difference corresponding to a behavior sequence is determined based on the number of user events between each user event included in the behavior sequence and the last user event (also understood as a landmark event) included in the behavior sequence of the target user, the event difference corresponding to the behavior sequence can accurately characterize the degree of association between each user event included in the behavior sequence and portability (or leaving the network), so that an effective maintenance strategy can be determined for the target user based on the degree of association, thereby improving the effectiveness of user maintenance.

[0041] Optionally, the strategy generation method further includes: determining an event difference corresponding to each behavior sequence in the at least one behavior sequence; and determining a behavior sequence having the smallest event difference in the at least one behavior sequence as the second behavior sequence.

[0042] In the present application, if the event difference corresponding to a certain behavior sequence in the at least one behavior sequence is the smallest, it means that the correlation between each user event included in the behavior sequence and the portability (or off-network) is greater (the closer the correlation is), and the behavior sequence can accurately reflect the real reason why the user may portability (or off-network). In this way, the electronic device determines the behavior sequence as the second behavior sequence, and then determines the strategy corresponding to the second behavior sequence as the target strategy, which can accurately identify the user behavior characteristics based on the user events with a greater degree of correlation, and generate personalized and highly accurate maintenance strategies.

[0043] Optionally, the strategy generation method further includes: if the number of users corresponding to the target user event is greater than or equal to a second number threshold, determining the target user event as a key event, the target user event being a user event included in the common behavior sequence corresponding to the target user group.

[0044] In the present application, if the number of users corresponding to the target user event is greater than or equal to the second number threshold, it means that the number of users corresponding to the target user event is large, that is, a large number of users have executed the target user event. At this time, the electronic device can determine that the target user event is a key event. While identifying the key event, it conducts a retrospective analysis of the root cause of the key event to formulate a maintenance strategy that can effectively retain users who transfer / leave the network, thereby improving the success rate of maintenance.

[0045] Optionally, the common behavior sequence corresponding to the target user group includes at least two behavior sequences, the target user event is a user event included in the converged behavior sequence corresponding to the target user group, and the converged behavior sequence corresponding to the target user group is determined based on the at least two behavior sequences.

[0046] In the present application, since the converged behavior sequence corresponding to a user group aggregates all common behavior sequences corresponding to the user group, the converged behavior sequence can reflect the behavioral habits corresponding to the user group as a whole. And since the target user event is the user event included in the converged behavior sequence corresponding to the target user group, the electronic device can accurately screen out the key events associated with the user type corresponding to the target user group, thereby improving the retention success rate of each type of user.

[0047] Optionally, the strategy generation method further includes: aggregating the same user events included in the at least two behavior sequences, and sorting the different user events included in the at least two behavior sequences in chronological order of timestamps to obtain an aggregated behavior sequence corresponding to the target user group.

[0048] In the present application, for all user events included in at least two behavior sequences included in the common service sequence corresponding to the target user group, the electronic device aggregates the same user events, that is, the same user events can be merged and deduplicated, reducing the size of the behavior sequence (specifically the converged behavior sequence) and saving storage resources. The electronic device sorts different user events in the order of timestamps, which can fully cover every user event included in the common service sequence corresponding to the target user group, thereby ensuring the integrity of the common service sequence.

[0049] Optionally, the number of users corresponding to the above-mentioned target user event is determined based on a common behavior history graph, which includes at least two event nodes and an edge connecting the at least two event nodes, one event node is used to represent a user event, and the edge is used to represent the number of users corresponding to the downstream event node connected to the edge.

[0050] In the present application, since the common behavior history graph can represent multiple user events and the number of users corresponding to each of the multiple user events, the electronic device can accurately and effectively determine the number of users corresponding to the target user event from the common behavior history graph, thereby improving the efficiency of determining the number of users corresponding to each user event.

[0051] Optionally, the strategy generation method also includes: obtaining the event identifier of the target user event; querying the common behavior history graph based on the event identifier of the target user event, and determining the target event node from the common behavior history graph, the node identifier of the target event node is the same as the event identifier of the target user event, the common behavior history graph includes at least two event nodes and an edge connecting the at least two event nodes, one event node is used to represent a user event, and the edge is used to represent the number of users corresponding to the downstream event node connected to the edge; the number of users represented by the target edge is determined as the number of users corresponding to the target user event, and the downstream event node connected to the target edge is the target event node.

[0052] In the present application, after obtaining the event identifier of the target user event, the electronic device can determine the target event node from the common behavior history graph, the node identifier of the target event node is the same as the event identifier of the target user event, and the target event node can represent the target user event; then the electronic device can determine the target edge from the common behavior history graph, and the downstream event node connected to the target edge is the target event node; finally, the electronic device can determine the number of users represented by the target edge as the number of users corresponding to the target user event. That is, the electronic device can conveniently and quickly determine the number of users corresponding to each user event from the common behavior history graph based on the event identifier of each user event, thereby improving the rate at which the electronic device identifies key events and further improving the success rate of maintaining (off-network) users.

[0053] Optionally, the user type of the target user is used to characterize the grouping information of the target user, and the grouping information of the target user includes one or more of the location information of the target user, the perception type corresponding to the target user, the risk level of the target user, the age of the target user and the gender of the target user.

[0054] In the present application, since the user type of the target user is used to characterize the grouping information of the target user, the grouping information of the target user includes one or more of the location information of the target user, the perception type corresponding to the target user, the risk level of the target user, the age of the target user, and the gender of the target user. That is, the electronic device can group each user or determine the user type of each user from multiple angles such as location information, perception type, risk level, age, and gender, and can comprehensively and accurately determine the user group (or customer group) to which each user belongs based on the labels that may cause porting / off-network, and then determine maintenance strategies with specific service values ​​for different user groups.

[0055] In a second aspect, a policy application method is provided. The method may include: obtaining a target policy, the target policy including a target measure, the target policy being a policy corresponding to a target user group, the target user group being a user group to which a target user belongs, each user included in the target user group having the same user type, the user type of the target user being determined based on a user event included in a behavior sequence of the target user, the behavior sequence of the target user being used to characterize an execution order of the user event included in the behavior sequence of the target user; and executing the target measure on the target user based on the target policy so that the target user is in a stable state.

[0056] In the present application, after obtaining the target strategy, the electronic device can execute the target measures on the target user based on the target strategy, so that the target user is in a stable state. That is, the electronic device can obtain the maintenance strategy dynamically allocated to different users according to the user types of different users, and then maintain and retain each user based on the maintenance strategy, which can avoid the situation of each user switching / leaving the network and improve the success rate of maintenance.

[0057] Optionally, the user events included in the behavior sequence of the target user are determined based on user data of the target user.

[0058] In the present application, the electronic device can accurately and effectively determine the user events included in the target user's behavior sequence based on the target user's user data, so that the electronic device can accurately and effectively generate a strategy adapted to the target user, namely, a target strategy, based on the target user's behavior sequence.

[0059] Optionally, the user data of the above-mentioned target user includes at least one item of the business domain data of the target user, the operation domain data of the target user and the service domain data of the target user. The business domain data of the target user is used to characterize the consumption habits of the target user, the operation domain data of the target user is used to characterize the network quality corresponding to the target user, and the service domain data of the target user is used to characterize the user perception of the target user.

[0060] In the present application, since the user data of the target user includes at least one of the business domain data of the target user, the operation domain data of the target user, and the service domain data of the target user, the electronic device can determine the user events contained in the behavior sequence of the target user based on the data of the at least one item. That is, the behavior sequence of each user can reflect the actual situation of each user when performing telecommunications services from multiple angles (including the consumption habits of each user, the network quality of each user, and the user perception of each user), and can fully portray the experience of each user. Thereby, in the subsequent process of generating the target strategy, the accuracy of the target strategy can be improved.

[0061] Optionally, the target user's behavior sequence includes multiple user events and respective timestamps of the multiple user events, and the target user's behavior sequence is obtained by sorting the multiple user events according to respective timestamps of the multiple user events.

[0062] In the present application, after the electronic device determines (or obtains) multiple user events and the respective timestamps of the multiple user events, it sorts the multiple user events according to the respective timestamps of the multiple user events, which can accurately and effectively reflect the user events that occur (or are executed) in chronological order when the target user is performing telecommunications services, that is, a correct and relevant behavior sequence that can effectively reflect the user behavior of each user can be obtained.

[0063] Optionally, the behavior sequence of the above-mentioned target user is determined based on a user behavior history graph, which includes a user node, an event node, and an edge connecting the user node and the event node, the user node is used to represent the user, the event node is used to represent the user event, and the edge is used to represent the timestamp of the user executing the user event.

[0064] In the present application, since the user behavior history graph includes user nodes for representing users, event nodes for representing user events, and edges for representing the timestamps of users executing user events, the electronic device can conveniently and quickly determine the behavior sequence of each user based on the user behavior history graph, thereby improving the rate of generating corresponding strategies for each user.

[0065] Optionally, the policy application method also includes: obtaining a user identifier of the target user; querying a user behavior history graph based on the user identifier of the target user, determining a target user node from the user behavior history graph, the node identifier of the target user node being the same as the user identifier of the target user, the user behavior history graph including a user node, an event node, and an edge connecting the user node and the event node, the user node being used to represent the user, the event node being used to represent the user event, and the edge being used to represent the timestamp of the user executing the user event; determining user events represented by multiple event nodes as multiple user events included in the behavior sequence of the target user, the multiple event nodes being event nodes having edges with the target user node; determining the timestamps represented by each of the multiple edges as the timestamps of each of the multiple user events, wherein one edge is used to connect the target user node and one of the multiple event nodes; sorting the multiple user events according to their respective timestamps to obtain the behavior sequence of the target user.

[0066] In the present application, after obtaining the user ID of the target user, the electronic device can determine the target user node from the user behavior history graph, the node ID of the target user node is the same as the user ID of the target user, and the target user node is used to characterize the target user; then the electronic device can determine the user events represented by multiple event nodes in the user behavior history graph that have edges (or connection relationships) with the target user node as multiple user events included in the behavior sequence of the target user, and determine the timestamps represented by the multiple edges between the target user node and the multiple event nodes in the user behavior history graph as the timestamps of the multiple user events; finally, the electronic device can sort the multiple user events according to the timestamps of the multiple user events to obtain the behavior sequence of the target user. That is, the electronic device can conveniently and quickly determine the user events performed by each user and the timestamps of the user events performed by each user based on the user ID of each user and the user behavior history graph, which can improve the efficiency of obtaining the behavior sequence of each user.

[0067] Optionally, the user events included in the above-mentioned target user's behavior sequence include negative perception events and / or subjective feedback events, wherein the negative perception event is used to characterize the passive consumption behavior corresponding to the target user, and the subjective feedback event is used to characterize the active complaint behavior corresponding to the target user.

[0068] In the present application, since the user events included in the target user's behavior sequence include negative perception events and / or subjective feedback events, that is, the electronic device can characterize the user behavior of each user in the process of performing telecommunications services in the form of passive consumption behavior corresponding to each user and active complaint behavior corresponding to each user, and can comprehensively and completely obtain the behavior sequence of each user.

[0069] Optionally, the target strategy is determined based on a common behavior sequence corresponding to the target user group, and the common behavior sequence corresponding to the target user group is determined based on a behavior sequence of each user included in the target user group.

[0070] In the present application, after determining the target user group, the electronic device can determine the common behavior sequence corresponding to the target user group based on the behavior sequence of each user included in the target user group, and accurately and effectively determine the target strategy based on the common behavior sequence corresponding to the target user group. That is, the electronic device can accurately and effectively determine the maintenance strategy corresponding to each user based on the most frequently occurring behavior pattern with time sequence characteristics corresponding to the user group to which each user belongs, thereby reducing the portability / off-network situation of each user.

[0071] Optionally, the target strategy is determined based on at least one business indicator, and the at least one business indicator is determined based on an event type of user events included in a common behavior sequence corresponding to the target user group.

[0072] In the present application, after determining the common behavior sequence corresponding to the target user group, the electronic device can accurately and effectively determine at least one business indicator related to the target user group based on the event type of the user event included in the common behavior sequence, and finally determine the target strategy based on the at least one business indicator. That is, the electronic device can accurately and effectively determine the maintenance strategy corresponding to each user based on the business indicator related to the user group to which each user belongs, which can improve the accuracy of strategy generation.

[0073] Optionally, the event type of the user events included in the common behavior sequence corresponding to the target user group includes at least one of a marketing type, a wireless type, and a home broadband type.

[0074] In the present application, the common behavior sequence corresponding to a user group can also be understood as the common service history corresponding to the user group. By performing scenario-based classification on each user event included in the common behavior sequence and obtaining the event type of each user event included in the common behavior sequence, a common behavior sequence with scenario-based business meaning can be formed, so that a maintenance strategy with scenario-based business meaning can be assigned to each user, thereby improving the practicality of the strategy.

[0075] Optionally, the above-mentioned target strategy is a strategy corresponding to a target value, and the target value is a value that matches at least one value in a numerical strategy relationship, and the at least one value is a value corresponding to the at least one business indicator. The numerical strategy relationship includes multiple values ​​and a strategy corresponding to each of the multiple values.

[0076] In the present application, a numerical policy relationship is a correspondence between multiple numerical values ​​and multiple policies, specifically one numerical value corresponds to one policy. The target numerical value is a numerical value that matches at least one numerical value in the numerical policy relationship, which can also be understood as the target numerical value being the same as the at least one numerical value, that is, the policy corresponding to the target numerical value is the policy corresponding to at least one numerical value (or at least one business indicator). The electronic device can easily and quickly determine the maintenance strategy related to the business indicator corresponding to the user group to which each user belongs in the numerical policy relationship, thereby improving the efficiency of strategy generation.

[0077] Optionally, the policy application method also includes: querying a numerical policy relationship based on at least one numerical value, determining a target numerical value that matches the at least one numerical value from the numerical policy relationship, the numerical policy relationship including multiple numerical values ​​and a policy corresponding to each of the multiple numerical values, the at least one numerical value being a numerical value corresponding to the at least one business indicator; and determining the policy corresponding to the target numerical value as the target policy.

[0078] In the present application, the electronic device can determine a target value that matches (or is the same as) the at least one value from the value policy relationship based on at least one value (i.e., the value corresponding to at least one business indicator), and determine the policy corresponding to the target value as the target policy. It is possible to quickly output a personalized maintenance policy corresponding to the business indicator related to the user group corresponding to each user, thereby ensuring the improvement of user service experience perception from the source and increasing user satisfaction.

[0079] Optionally, the policy application method also includes: determining the number of users corresponding to each of a plurality of behavior sequences, the plurality of behavior sequences being determined based on the behavior sequences of each of a plurality of users included in the target user group; and determining the behavior sequences in the plurality of behavior sequences whose corresponding number of users is greater than or equal to a first quantity threshold as the common behavior sequences corresponding to the target user group.

[0080] In the present application, since the multiple behavior sequences are determined based on the behavior sequences of the multiple users included in the target user group, the multiple behavior sequences can comprehensively reflect the behavior habits of each user in the target user group in performing telecommunication services (or user events executed in the process of performing telecommunication services). The behavior sequences corresponding to the number of users in the multiple user sequences being greater than or equal to the first quantity threshold can reflect the behavior habits of a large number (or majority) of users in the target user group, and thus can reflect the behavior characteristics of the target user group as a whole, that is, can accurately and effectively characterize the behavior characteristics of the user type corresponding to the target user group, and can then allocate appropriate maintenance strategies to the target users based on the behavior characteristics.

[0081] Optionally, the policy application method also includes: obtaining a behavior sequence of each user among the multiple users included in the target user group; performing a preset operation on at least one user event included in the behavior sequence of each user to obtain the multiple behavior sequences, wherein the execution order of the user events included in each behavior sequence in the multiple behavior sequences remains unchanged, and the preset operation includes a deletion operation.

[0082] In the present application, the electronic device can obtain the behavior sequence of each user among the multiple users included in the target user group, and perform a preset operation on at least one user event included in the behavior sequence of each user, that is, multiple behavior sequences can be obtained. That is, the electronic device can accurately and effectively determine multiple behavior sequences that can fully reflect the behavior habits of each user in the target user group in the process of conducting telecommunications services based on the behavior habits of each user included in the target user group in the process of conducting telecommunications services, and then accurately determine the common behavior sequence corresponding to each user group, so as to formulate customized strategies for each user group, guide market personnel to complete maintenance, and improve service efficiency.

[0083] Optionally, the above-mentioned target strategy is a strategy corresponding to a first behavior sequence, which is determined from at least one behavior sequence based on the similarity between each behavior sequence in at least one behavior sequence and the behavior sequence of the target user, and the at least one behavior sequence is a behavior sequence included in the common behavior sequence corresponding to the target user group.

[0084] In the present application, one behavior sequence in the at least one behavior sequence corresponds to one strategy, and the electronic device can determine the similarity between each behavior sequence in the at least one behavior sequence and the behavior sequence of the target user, thereby determining the first behavior sequence from the at least one behavior sequence and determining the strategy corresponding to the first behavior sequence as the target strategy. That is, the electronic device can determine the first behavior sequence similar to the behavior sequence of the target user based on the similarity algorithm, and the first behavior sequence can characterize the behavior habits similar to those of the target user when performing telecommunications services to a certain extent, thereby being able to quickly allocate effective target strategies to the target user, which helps to support low-cost and efficient user retention.

[0085] Optionally, the common behavior sequences corresponding to the above-mentioned target user group include at least one behavior sequence. Optionally, the policy application method also includes: determining the similarity between each behavior sequence in the at least one behavior sequence and the behavior sequence of the target user; determining the policy corresponding to the first behavior sequence as the target policy, and the first behavior sequence is the behavior sequence in the at least one behavior sequence with the greatest similarity to the behavior sequence of the target user.

[0086] In the present application, the similarity between the first behavior sequence and the behavior sequence of the target user is the greatest, indicating that the first behavior sequence is most similar to the behavior sequence of the target user, and it can also be understood that the behavior habits represented by the first behavior sequence are most similar to the behavior habits of the target user in conducting telecommunications services. At this time, the electronic device determines the strategy corresponding to the first behavior sequence as the target strategy, that is, it can accurately and effectively assign the corresponding maintenance strategy to the target user, so that the maintenance and retention strategy for each potential porting / off-network user can be accurately formulated.

[0087] Optionally, the common behavior sequences corresponding to the above-mentioned target user group include at least one behavior sequence, each behavior sequence in the at least one behavior sequence has the same similarity with the behavior sequence of the target user, and the target strategy is a strategy corresponding to a second behavior sequence, which is determined from the at least one behavior sequence based on the event difference corresponding to each behavior sequence in the at least one behavior sequence, wherein the event difference corresponding to a behavior sequence is determined based on the number of user events between each user event included in the behavior sequence and the last user event included in the behavior sequence of the target user.

[0088] In the present application, since the event difference corresponding to a behavior sequence is determined based on the number of user events between each user event included in the behavior sequence and the last user event (also understood as a landmark event) included in the behavior sequence of the target user, the event difference corresponding to the behavior sequence can accurately characterize the degree of association between each user event included in the behavior sequence and portability (or leaving the network), so that an effective maintenance strategy can be determined for the target user based on the degree of association, thereby improving the effectiveness of user maintenance.

[0089] Optionally, the strategy application method further includes: determining an event difference corresponding to each behavior sequence in the at least one behavior sequence; and determining a behavior sequence having the smallest event difference in the at least one behavior sequence as the second behavior sequence.

[0090] In the present application, if the event difference corresponding to a certain behavior sequence in the at least one behavior sequence is the smallest, it means that the correlation between each user event included in the behavior sequence and the portability (or off-network) is greater (the closer the correlation is), and the behavior sequence can accurately reflect the real reason why the user may portability (or off-network). In this way, the electronic device determines the behavior sequence as the second behavior sequence, and then determines the strategy corresponding to the second behavior sequence as the target strategy, which can accurately identify the user behavior characteristics based on the user events with a greater degree of correlation, and generate personalized and highly accurate maintenance strategies.

[0091] Optionally, the policy application method further includes: if the number of users corresponding to the target user event is greater than or equal to a second number threshold, determining the target user event as a key event, the target user event being a user event included in the common behavior sequence corresponding to the target user group.

[0092] In the present application, if the number of users corresponding to the target user event is greater than or equal to the second number threshold, it means that the number of users corresponding to the target user event is large, that is, a large number of users have executed the target user event. At this time, the electronic device can determine that the target user event is a key event. While identifying the key event, it conducts a retrospective analysis of the root cause of the key event to formulate a maintenance strategy that can effectively retain users who transfer / leave the network, thereby improving the success rate of maintenance.

[0093] Optionally, the common behavior sequence corresponding to the target user group includes at least two behavior sequences, the target user event is a user event included in the converged behavior sequence corresponding to the target user group, and the converged behavior sequence corresponding to the target user group is determined based on the at least two behavior sequences.

[0094] In the present application, since the converged behavior sequence corresponding to a user group aggregates all common behavior sequences corresponding to the user group, the converged behavior sequence can reflect the behavioral habits corresponding to the user group as a whole. And since the target user event is the user event included in the converged behavior sequence corresponding to the target user group, the electronic device can accurately screen out the key events associated with the user type corresponding to the target user group, thereby improving the retention success rate of each type of user.

[0095] Optionally, the policy application method further includes: aggregating the same user events included in the at least two behavior sequences, and sorting the different user events included in the at least two behavior sequences in chronological order of timestamps to obtain an aggregated behavior sequence corresponding to the target user group.

[0096] In the present application, for all user events included in at least two behavior sequences included in the common service sequence corresponding to the target user group, the electronic device aggregates the same user events, that is, the same user events can be merged and deduplicated, reducing the size of the behavior sequence (specifically the converged behavior sequence) and saving storage resources. The electronic device sorts different user events in the order of timestamps, which can fully cover every user event included in the common service sequence corresponding to the target user group, thereby ensuring the integrity of the common service sequence.

[0097] Optionally, the number of users corresponding to the above-mentioned target user event is determined based on a common behavior history graph, which includes at least two event nodes and an edge connecting the at least two event nodes, one event node is used to represent a user event, and the edge is used to represent the number of users corresponding to the downstream event node connected to the edge.

[0098] In the present application, since the common behavior history graph can represent multiple user events and the number of users corresponding to each of the multiple user events, the electronic device can accurately and effectively determine the number of users corresponding to the target user event from the common behavior history graph, thereby improving the efficiency of determining the number of users corresponding to each user event.

[0099] Optionally, the strategy application method also includes: obtaining the event identifier of the target user event; querying the common behavior history graph based on the event identifier of the target user event, and determining the target event node from the common behavior history graph, the node identifier of the target event node is the same as the event identifier of the target user event, the common behavior history graph includes at least two event nodes and an edge connecting the at least two event nodes, one event node is used to represent a user event, and the edge is used to represent the number of users corresponding to the downstream event node connected to the edge; the number of users represented by the target edge is determined as the number of users corresponding to the target user event, and the downstream event node connected to the target edge is the target event node.

[0100] In the present application, after obtaining the event identifier of the target user event, the electronic device can determine the target event node from the common behavior history graph, the node identifier of the target event node is the same as the event identifier of the target user event, and the target event node can represent the target user event; then the electronic device can determine the target edge from the common behavior history graph, and the downstream event node connected to the target edge is the target event node; finally, the electronic device can determine the number of users represented by the target edge as the number of users corresponding to the target user event. That is, the electronic device can conveniently and quickly determine the number of users corresponding to each user event from the common behavior history graph based on the event identifier of each user event, thereby improving the rate at which the electronic device identifies key events and further improving the success rate of maintaining (off-network) users.

[0101] Optionally, the user type of the target user is used to characterize the grouping information of the target user, and the grouping information of the target user includes one or more of the location information of the target user, the perception type corresponding to the target user, the risk level of the target user, the age of the target user and the gender of the target user.

[0102] In the present application, since the user type of the target user is used to characterize the grouping information of the target user, the grouping information of the target user includes one or more of the location information of the target user, the perception type corresponding to the target user, the risk level of the target user, the age of the target user, and the gender of the target user. That is, the electronic device can group each user or determine the user type of each user from multiple angles such as location information, perception type, risk level, age, and gender, and can comprehensively and accurately determine the user group (or customer group) to which each user belongs based on the labels that may cause porting / off-network, and then determine maintenance strategies with specific service values ​​for different user groups.

[0103] In a third aspect, a policy generation device is provided. The device may include: an acquisition module and a generation module; the acquisition module is used to acquire a behavior sequence of a target user, the behavior sequence of the target user is used to characterize the execution order of user events contained in the behavior sequence of the target user; the generation module is used to generate a target policy based on the behavior sequence of the target user, the target policy is a policy corresponding to a target user group, the target user group is a user group to which the target user belongs, each user included in the target user group has the same user type, and the user type of the target user is determined based on the user events contained in the behavior sequence of the target user.

[0104] Optionally, the user events included in the behavior sequence of the target user are determined based on user data of the target user.

[0105] Optionally, the user data of the above-mentioned target user includes at least one item of the business domain data of the target user, the operation domain data of the target user and the service domain data of the target user. The business domain data of the target user is used to characterize the consumption habits of the target user, the operation domain data of the target user is used to characterize the network quality corresponding to the target user, and the service domain data of the target user is used to characterize the user perception of the target user.

[0106] Optionally, the target user's behavior sequence includes multiple user events and respective timestamps of the multiple user events, and the target user's behavior sequence is obtained by sorting the multiple user events according to respective timestamps of the multiple user events.

[0107] Optionally, the behavior sequence of the above-mentioned target user is determined based on a user behavior history graph, which includes a user node, an event node, and an edge connecting the user node and the event node, the user node is used to represent the user, the event node is used to represent the user event, and the edge is used to represent the timestamp of the user executing the user event.

[0108] Optionally, the strategy generation device also includes a determination module and a sorting module; the acquisition module is specifically used to obtain the user identification of the target user; the determination module is used to query the user behavior history graph based on the user identification of the target user, and determine the target user node from the user behavior history graph, the node identification of the target user node is the same as the user identification of the target user, and the user behavior history graph includes a user node, an event node, and an edge connecting the user node and the event node, the user node is used to represent the user, the event node is used to represent the user event, and the edge is used to represent the timestamp of the user executing the user event; the determination module is also used to determine the user events represented by multiple event nodes as multiple user events included in the behavior sequence of the target user, and the multiple event nodes are event nodes with edges between the target user node; the determination module is also used to determine the timestamps represented by each of the multiple edges as the timestamps of each of the multiple user events, wherein one edge is used to connect the target user node and an event node among the multiple event nodes;

[0109] The sorting module is used to sort the multiple user events according to their respective timestamps to obtain the behavior sequence of the target user.

[0110] Optionally, the user events included in the above-mentioned target user's behavior sequence include negative perception events and / or subjective feedback events, wherein the negative perception event is used to characterize the passive consumption behavior corresponding to the target user, and the subjective feedback event is used to characterize the active complaint behavior corresponding to the target user.

[0111] Optionally, the target strategy is determined based on a common behavior sequence corresponding to the target user group, and the common behavior sequence corresponding to the target user group is determined based on a behavior sequence of each user included in the target user group.

[0112] Optionally, the target strategy is determined based on at least one business indicator, and the at least one business indicator is determined based on an event type of user events included in a common behavior sequence corresponding to the target user group.

[0113] Optionally, the event type of the user events included in the common behavior sequence corresponding to the target user group includes at least one of a marketing type, a wireless type, and a home broadband type.

[0114] Optionally, the above-mentioned target strategy is a strategy corresponding to a target value, and the target value is a value that matches at least one value in a numerical strategy relationship, and the at least one value is a value corresponding to the at least one business indicator. The numerical strategy relationship includes multiple values ​​and a strategy corresponding to each of the multiple values.

[0115] Optionally, the determination module is used to query a numerical policy relationship based on at least one numerical value, and determine a target numerical value that matches the at least one numerical value from the numerical policy relationship, the numerical policy relationship including multiple numerical values ​​and a policy corresponding to each of the multiple numerical values, the at least one numerical value being a numerical value corresponding to the at least one business indicator; the determination module is also used to determine the policy corresponding to the target numerical value as the target policy.

[0116] Optionally, the determination module is used to determine the number of users corresponding to each of the multiple behavior sequences, and the multiple behavior sequences are determined based on the behavior sequences of each of the multiple users included in the target user group; the determination module is also used to determine the behavior sequences in the multiple behavior sequences whose corresponding number of users is greater than or equal to a first quantity threshold as the common behavior sequences corresponding to the target user group.

[0117] Optionally, the policy generation module also includes an operation module; the acquisition module is further used to obtain the behavior sequence of each user among the multiple users included in the target user group; the operation module is used to perform a preset operation on at least one user event included in the behavior sequence of each user to obtain the multiple behavior sequences, the execution order of the user events included in each behavior sequence in the multiple behavior sequences remains unchanged, and the preset operation includes a deletion operation.

[0118] Optionally, the above-mentioned target strategy is a strategy corresponding to a first behavior sequence, which is determined from at least one behavior sequence based on the similarity between each behavior sequence in at least one behavior sequence and the behavior sequence of the target user, and the at least one behavior sequence is a behavior sequence included in the common behavior sequence corresponding to the target user group.

[0119] Optionally, the common behavior sequences corresponding to the above-mentioned target user group include at least one behavior sequence; the determination module is also used to determine the similarity between each behavior sequence in the at least one behavior sequence and the behavior sequence of the target user; the determination module is also used to determine the strategy corresponding to the first behavior sequence as the target strategy, and the first behavior sequence is the behavior sequence in the at least one behavior sequence that has the greatest similarity with the behavior sequence of the target user.

[0120] Optionally, the common behavior sequences corresponding to the above-mentioned target user group include at least one behavior sequence, each behavior sequence in the at least one behavior sequence has the same similarity with the behavior sequence of the target user, and the target strategy is a strategy corresponding to a second behavior sequence, which is determined from the at least one behavior sequence based on the event difference corresponding to each behavior sequence in the at least one behavior sequence, wherein the event difference corresponding to a behavior sequence is determined based on the number of user events between each user event included in the behavior sequence and the last user event included in the behavior sequence of the target user.

[0121] Optionally, the determination module is further used to determine the event difference corresponding to each behavior sequence in the at least one behavior sequence; the determination module is further used to determine the behavior sequence with the smallest corresponding event difference in the at least one behavior sequence as the second behavior sequence.

[0122] Optionally, the determination module is used to determine that the target user event is a key event if the number of users corresponding to the target user event is greater than or equal to a second number threshold, and the target user event is a user event included in the common behavior sequence corresponding to the target user group.

[0123] Optionally, the common behavior sequence corresponding to the target user group includes at least two behavior sequences, the target user event is a user event included in the converged behavior sequence corresponding to the target user group, and the converged behavior sequence corresponding to the target user group is determined based on the at least two behavior sequences.

[0124] Optionally, the policy generating device further includes a processing module; the processing module is used to aggregate the same user events included in the at least two behavior sequences; the sorting module is used to sort the different user events included in the at least two behavior sequences in the order of timestamps to obtain the aggregated behavior sequence corresponding to the target user group.

[0125] Optionally, the number of users corresponding to the above-mentioned target user event is determined based on a common behavior history graph, which includes at least two event nodes and an edge connecting the at least two event nodes, one event node is used to represent a user event, and the edge is used to represent the number of users corresponding to the downstream event node connected to the edge.

[0126] Optionally, the acquisition module is used to obtain the event identifier of the target user event; the determination module is also used to query the common behavior history graph based on the event identifier of the target user event, and determine the target event node from the common behavior history graph, the node identifier of the target event node is the same as the event identifier of the target user event, the common behavior history graph includes at least two event nodes and an edge connecting the at least two event nodes, one event node is used to represent a user event, and the edge is used to represent the number of users corresponding to the downstream event node connected to the edge; the determination module is also used to determine the number of users represented by the target edge as the number of users corresponding to the target user event, and the downstream event node connected to the target edge is the target event node.

[0127] Optionally, the user type of the target user is used to characterize the grouping information of the target user, and the grouping information of the target user includes one or more of the location information of the target user, the perception type corresponding to the target user, the risk level of the target user, the age of the target user and the gender of the target user.

[0128] In a fourth aspect, a policy application device is provided. The device may include: an acquisition module and an execution module; the acquisition module is used to acquire a target policy, the target policy includes a target measure, the target policy is a policy corresponding to a target user group, the target user group is a user group to which a target user belongs, each user included in the target user group has the same user type, the user type of the target user is determined based on a user event included in a behavior sequence of the target user, and the behavior sequence of the target user is used to characterize the execution order of the user event included in the behavior sequence of the target user; the execution module is used to execute the target measure on the target user based on the target policy, so that the target user is in a stable state.

[0129] Optionally, the user events included in the behavior sequence of the target user are determined based on user data of the target user.

[0130] Optionally, the user data of the above-mentioned target user includes at least one item of the business domain data of the target user, the operation domain data of the target user and the service domain data of the target user. The business domain data of the target user is used to characterize the consumption habits of the target user, the operation domain data of the target user is used to characterize the network quality corresponding to the target user, and the service domain data of the target user is used to characterize the user perception of the target user.

[0131] Optionally, the target user's behavior sequence includes multiple user events and respective timestamps of the multiple user events, and the target user's behavior sequence is obtained by sorting the multiple user events according to respective timestamps of the multiple user events.

[0132] Optionally, the behavior sequence of the above-mentioned target user is determined based on a user behavior history graph, which includes a user node, an event node, and an edge connecting the user node and the event node, the user node is used to represent the user, the event node is used to represent the user event, and the edge is used to represent the timestamp of the user executing the user event.

[0133] Optionally, the policy application device also includes a determination module and a sorting module; the acquisition module is specifically used to obtain the user identifier of the target user; the determination module is used to query the user behavior history graph based on the user identifier of the target user, and determine the target user node from the user behavior history graph, the node identifier of the target user node is the same as the user identifier of the target user, the user behavior history graph includes a user node, an event node and an edge connecting the user node and the event node, the user node is used to represent the user, the event node is used to represent the user event, and the edge is used to represent the timestamp of the user executing the user event; the determination module is also used to determine the user events represented by multiple event nodes as multiple user events included in the behavior sequence of the target user, and the multiple event nodes are event nodes with edges between the target user node; the determination module is also used to determine the timestamps represented by each of the multiple edges as the timestamps of each of the multiple user events, wherein one edge is used to connect the target user node and an event node among the multiple event nodes; the sorting module is used to sort the multiple user events according to their respective timestamps to obtain the behavior sequence of the target user.

[0134] Optionally, the user events included in the above-mentioned target user's behavior sequence include negative perception events and / or subjective feedback events, wherein the negative perception event is used to characterize the passive consumption behavior corresponding to the target user, and the subjective feedback event is used to characterize the active complaint behavior corresponding to the target user.

[0135] Optionally, the target strategy is determined based on a common behavior sequence corresponding to the target user group, and the common behavior sequence corresponding to the target user group is determined based on a behavior sequence of each user included in the target user group.

[0136] Optionally, the target strategy is determined based on at least one business indicator, and the at least one business indicator is determined based on an event type of user events included in a common behavior sequence corresponding to the target user group.

[0137] Optionally, the event type of the user events included in the common behavior sequence corresponding to the target user group includes at least one of a marketing type, a wireless type, and a home broadband type.

[0138] Optionally, the above-mentioned target strategy is a strategy corresponding to a target value, and the target value is a value that matches at least one value in a numerical strategy relationship, and the at least one value is a value corresponding to the at least one business indicator. The numerical strategy relationship includes multiple values ​​and a strategy corresponding to each of the multiple values.

[0139] Optionally, the determination module is used to query a numerical policy relationship based on at least one numerical value, and determine a target numerical value that matches the at least one numerical value from the numerical policy relationship, the numerical policy relationship including multiple numerical values ​​and a policy corresponding to each of the multiple numerical values, the at least one numerical value being a numerical value corresponding to the at least one business indicator; the determination module is also used to determine the policy corresponding to the target numerical value as the target policy.

[0140] Optionally, the determination module is used to determine the number of users corresponding to each of the multiple behavior sequences, and the multiple behavior sequences are determined based on the behavior sequences of each of the multiple users included in the target user group; the determination module is also used to determine the behavior sequences in the multiple behavior sequences whose corresponding number of users is greater than or equal to a first quantity threshold as the common behavior sequences corresponding to the target user group.

[0141] Optionally, the policy application module also includes an operation module; the acquisition module is also used to obtain the behavior sequence of each user among the multiple users included in the target user group; the operation module is used to perform a preset operation on at least one user event included in the behavior sequence of each user to obtain the multiple behavior sequences, the execution order of the user events included in each behavior sequence in the multiple behavior sequences remains unchanged, and the preset operation includes a deletion operation.

[0142] Optionally, the above-mentioned target strategy is a strategy corresponding to a first behavior sequence, which is determined from at least one behavior sequence based on the similarity between each behavior sequence in at least one behavior sequence and the behavior sequence of the target user, and the at least one behavior sequence is a behavior sequence included in the common behavior sequence corresponding to the target user group.

[0143] Optionally, the common behavior sequences corresponding to the above-mentioned target user group include at least one behavior sequence; the determination module is also used to determine the similarity between each behavior sequence in the at least one behavior sequence and the behavior sequence of the target user; the determination module is also used to determine the strategy corresponding to the first behavior sequence as the target strategy, and the first behavior sequence is the behavior sequence in the at least one behavior sequence that has the greatest similarity with the behavior sequence of the target user.

[0144] Optionally, the common behavior sequences corresponding to the above-mentioned target user group include at least one behavior sequence, each behavior sequence in the at least one behavior sequence has the same similarity with the behavior sequence of the target user, and the target strategy is a strategy corresponding to a second behavior sequence, which is determined from the at least one behavior sequence based on the event difference corresponding to each behavior sequence in the at least one behavior sequence, wherein the event difference corresponding to a behavior sequence is determined based on the number of user events between each user event included in the behavior sequence and the last user event included in the behavior sequence of the target user.

[0145] Optionally, the determination module is further used to determine the event difference corresponding to each behavior sequence in the at least one behavior sequence; the determination module is further used to determine the behavior sequence with the smallest corresponding event difference in the at least one behavior sequence as the second behavior sequence.

[0146] Optionally, the determination module is used to determine that the target user event is a key event if the number of users corresponding to the target user event is greater than or equal to a second number threshold, and the target user event is a user event included in the common behavior sequence corresponding to the target user group.

[0147] Optionally, the common behavior sequence corresponding to the target user group includes at least two behavior sequences, the target user event is a user event included in the converged behavior sequence corresponding to the target user group, and the converged behavior sequence corresponding to the target user group is determined based on the at least two behavior sequences.

[0148] Optionally, the policy application device also includes a processing module; the processing module is used to aggregate the same user events included in the at least two behavior sequences; the sorting module is used to sort the different user events included in the at least two behavior sequences in the order of timestamps to obtain the aggregated behavior sequence corresponding to the target user group.

[0149] Optionally, the number of users corresponding to the above-mentioned target user event is determined based on a common behavior history graph, which includes at least two event nodes and an edge connecting the at least two event nodes, one event node is used to represent a user event, and the edge is used to represent the number of users corresponding to the downstream event node connected to the edge.

[0150] Optionally, the acquisition module is used to obtain the event identifier of the target user event; the determination module is also used to query the common behavior history graph based on the event identifier of the target user event, and determine the target event node from the common behavior history graph, the node identifier of the target event node is the same as the event identifier of the target user event, the common behavior history graph includes at least two event nodes and an edge connecting the at least two event nodes, one event node is used to represent a user event, and the edge is used to represent the number of users corresponding to the downstream event node connected to the edge; the determination module is also used to determine the number of users represented by the target edge as the number of users corresponding to the target user event, and the downstream event node connected to the target edge is the target event node.

[0151] Optionally, the user type of the target user is used to characterize the grouping information of the target user, and the grouping information of the target user includes one or more of the location information of the target user, the perception type corresponding to the target user, the risk level of the target user, the age of the target user and the gender of the target user.

[0152] In a fifth aspect, an electronic device is provided, which may include: a processor and a memory configured to store processor executable instructions; wherein the processor is configured to execute the instructions to implement any one of the optional policy generation methods in the above-mentioned first aspect, or to implement any one of the optional policy application methods in the above-mentioned second aspect.

[0153] In a sixth aspect, a computer-readable storage medium is provided, on which instructions are stored. When the instructions in the computer-readable storage medium are executed by an electronic device, the electronic device is enabled to execute any one of the optional policy generation methods in the first aspect above, or execute any one of the optional policy application methods in the second aspect above.

[0154] In a seventh aspect, a computer program product is provided, which includes computer instructions. When the computer instructions are executed on an electronic device, the electronic device executes any optional policy generation method as described in the first aspect, or executes any optional policy application method as described in the second aspect.

[0155] It should be noted that the above general description and the following detailed description are merely exemplary and explanatory and do not limit the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0156] Figure 1 A schematic diagram of a network architecture of a communication system provided in an embodiment of the present application is shown;

[0157] Figure 2 A schematic diagram of a process flow of a strategy generation method provided by an embodiment of the present application is shown;

[0158] Figure 3 A schematic diagram showing a principle of obtaining a user's behavior sequence provided by an embodiment of the present application is shown;

[0159] Figure 4 A schematic diagram of a process flow of another strategy generation method provided in an embodiment of the present application is shown;

[0160] Figure 5 A user behavior history diagram provided by an embodiment of the present application is shown;

[0161] Figure 6 A schematic diagram showing a principle of obtaining a user's behavior sequence based on the user's original behavior sequence provided by an embodiment of the present application;

[0162] Figure 7 A schematic diagram showing a principle of obtaining a corresponding strategy based on a common behavior sequence provided by an embodiment of the present application;

[0163] Figure 8 A schematic diagram showing the principle of allocating a maintenance strategy to a user based on the user's priority provided in an embodiment of the present application is shown;

[0164] Fig. 9 A schematic diagram showing a principle of obtaining multiple behavior sequences provided by an embodiment of the present application is shown;

[0165] Fig.10 A schematic diagram showing a principle of determining a first behavior sequence provided by an embodiment of the present application is shown;

[0166] Fig.11 A schematic diagram showing a principle of obtaining a convergence behavior sequence provided by an embodiment of the present application is shown;

[0167] Fig.12 A schematic diagram showing a principle of determining a user type provided by an embodiment of the present application is shown;

[0168] Fig.13 A schematic diagram showing the principle of screening users who transfer or leave the network provided in an embodiment of the present application is shown;

[0169] Fig.14 A schematic diagram of a process for identifying a transferred user provided in an embodiment of the present application is shown;

[0170] Fig.15 A schematic diagram showing a principle of obtaining a portability probability of each user provided by an embodiment of the present application is shown;

[0171] Fig.16 A schematic diagram of a process flow of a strategy application method provided in an embodiment of the present application is shown;

[0172] Fig.17A schematic diagram of a process of generating a target strategy and using a target strategy provided by an embodiment of the present application is shown;

[0173] Fig.18 A schematic diagram of a display interface of an electronic device provided in an embodiment of the present application is shown;

[0174] Fig.19 A schematic diagram of the structure of a strategy generation device provided in an embodiment of the present application is shown;

[0175] Fig. 20 A schematic diagram showing the structure of another strategy generation device provided in an embodiment of the present application is shown;

[0176] Fig.21 A schematic diagram of the structure of a strategy application device provided in an embodiment of the present application is shown;

[0177] Fig. 22 A structural schematic diagram of another strategy application device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0178] In order to enable ordinary persons in the art to better understand the technical solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0179] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the attached claims.

[0180] It should also be understood that the term “comprising” indicates the presence of described features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements and / or components.

[0181] As described in the background technology, since the number of users of operators is over 10 million, the process of formulating a maintenance strategy after receiving user complaint information (or complaint information) may not be able to quickly identify user pain points and provide effective solutions, resulting in user loss. Based on this, the embodiment of the present application provides a policy generation method and a policy application method. The electronic device determines the policy corresponding to the target user group as the target policy to be generated, and can implement the process of dynamically allocating corresponding maintenance strategies to different users based on the user types of different users. It can quickly and effectively generate (or determine) the maintenance strategy corresponding to each user to avoid user loss.

[0182] The policy generation method, policy application method, device, electronic device, and storage medium provided in the embodiments of the present application are applied to customer satisfaction repair scenarios (specifically, they may include scenarios for maintaining and retaining users who have switched / left the network, and scenarios for predicting declining satisfaction (such as upgrade complaint predictions, home broadband disassembly predictions, etc.)). Specifically, in the scenario for maintaining and retaining users who have switched / left the network, when the electronic device obtains the behavior sequence of the target user, it may generate a target policy based on the behavior sequence of the target user according to the method provided in the embodiments of the present application, thereby improving the success rate of maintenance.

[0183] The following is an exemplary description of the strategy generation method and strategy application method provided in the embodiments of the present application in conjunction with the accompanying drawings:

[0184] The policy generation method, policy application method, device and electronic device provided in the embodiments of the present application can be applied to Figure 1 The communication system shown in FIG. 1 includes a big data platform 101, an application server 102, and an electronic device 103. Generally, in practical applications, the connection between the above-mentioned devices can be a wireless connection. In order to conveniently and intuitively represent the connection relationship between the devices, Figure 1 Solid lines are used to indicate this.

[0185] Specifically, the big data platform 101 is used to collect and store user data of users, including the user's business domain data, operation domain data, and service domain data.

[0186] The application server 102 has a market management application 1021 installed therein, and the application server 102 is used to obtain user data of related users from the big data platform 101 at regular intervals.

[0187] After receiving the scheduled task indicated by the application server 102, the electronic device 103 will request to obtain the user data of the corresponding period from the application server 102, and generate the user's behavior sequence, the common behavior sequence corresponding to the user group to which the user belongs, and match the corresponding maintenance strategy based on the user data.

[0188] Finally, the front-end interface of the market management application 1021 displays the user's behavior sequence, the common behavior sequence corresponding to the user group to which the user belongs, and the corresponding maintenance strategy.

[0189] Exemplarily, the electronic device that executes the policy generation method and policy application method provided in the embodiment of the present application can be a mobile phone, a tablet computer, a desktop, a laptop, a handheld computer, a notebook computer, an ultra-mobile personal computer (ultra-mobile personal computer, UMPC), a netbook, a cellular phone, a personal digital assistant (personal digital assistant, PDA), an augmented reality (augmented reality, AR) / virtual reality (virtual reality, VR) device, etc. The present application does not impose any special restrictions on the specific form of the electronic device. It can interact with the user through one or more methods such as a keyboard, a touchpad, a touch screen, a remote control, voice interaction or a handwriting device.

[0190] Optionally, the electronic device can also be a server, which can be an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, network acceleration services (content delivery network, CDN), as well as big data and artificial intelligence platforms.

[0191] Based on the above Figure 1 The electronic device shown in the embodiment of the present application provides a policy generation method that can act on the electronic device to implement the process of generating relevant policies. Specifically, Figure 2 As shown, the strategy generation method provided in the embodiment of the present application may include S101-S102.

[0192] S101. The electronic device obtains a behavior sequence of a target user.

[0193] The behavior sequence of the target user is used to represent the execution order of the user events contained in the behavior sequence of the target user.

[0194] It is worth noting that the user events included in the target user's behavior sequence are events experienced by the target user in the process of performing telecommunication services, and all events experienced by the target user in the process of performing telecommunication services are arranged in the target user's behavior sequence according to the above execution order. In addition, a user event included in the target user's behavior sequence can represent the state of the target user in the telecommunication service at the time corresponding to the user event.

[0195] Exemplarily, a user event may be network access, number portability (hereinafter referred to as number portability), or network leaving.

[0196] S102: The electronic device generates a target strategy based on the behavior sequence of the target user.

[0197] The target policy is a policy corresponding to a target user group, the target user group is a user group to which the target user belongs, each user included in the target user group has the same user type, and the user type of the target user is determined based on user events included in the behavior sequence of the target user.

[0198] Specifically, the electronic device can determine the user type of the target user based on the user events contained in the target user's behavior sequence, and determine the user group to which the target user belongs (i.e., the target user group) from multiple user groups, and finally determine the policy corresponding to the target user group as the target policy, that is, the target policy can be obtained.

[0199] It is worth noting that the strategies (including target strategies) in the embodiments of the present application can be understood as maintenance strategies (or retention strategies), which are used to achieve the purpose of maintaining / retaining the corresponding users, so as to avoid the user from switching / leaving the network, etc., and to improve the service experience of existing users.

[0200] In the embodiment of the present application, the electronic device can also use the target policy after generating the target policy. Specifically, the electronic device can execute the specific content included in the target policy on the target user based on the target policy, thereby improving the user experience of the target user and effectively retaining the target user.

[0201] The technical solution provided by the above embodiment can at least bring the following beneficial effects: As can be seen from S101-S102, after acquiring the behavior sequence of the target user, the electronic device can determine the user type of the target user based on the user events contained in the behavior sequence of the target user, and determine the user group to which the target user belongs (i.e., the target user group) based on the user type of the target user; finally, the electronic device determines the policy corresponding to the target user group as the target policy, that is, the process of generating the target policy based on the behavior sequence of the target user can be realized. In the embodiment of the present application, the electronic device can realize the process of dynamically allocating corresponding maintenance policies to different users based on the user types of different users by determining the policy corresponding to the target user group as the target policy to be generated, and can quickly and effectively generate (or determine) the maintenance policy corresponding to each user to avoid user loss.

[0202] In an implementation manner of the embodiment of the present application, the user events included in the behavior sequence of the target user are determined based on the user data of the target user.

[0203] It is worth noting that the user data of the target user includes the data generated by the target user in the process of performing telecommunication services, and the user data can also be understood as the user experience data of the target user, which can reflect the behavior habits, hobbies and needs of the target user. In the embodiment of the present application, the electronic device can accurately and effectively determine the user events included in the behavior sequence of the target user based on the user data of the target user, so that the electronic device can accurately and effectively generate a strategy adapted to the target user based on the behavior sequence of the target user, that is, the target strategy.

[0204] In an optional implementation, the user data of the above-mentioned target user includes at least one of the business domain data of the target user, the operation domain data of the target user, and the service domain data of the target user. The business domain data of the target user is used to characterize the consumption habits of the target user, the operation domain data of the target user is used to characterize the network quality corresponding to the target user, and the service domain data of the target user is used to characterize the user perception of the target user.

[0205] It can be understood that the network quality corresponding to the target user is the network quality of the network where the terminal corresponding to (or used by) the target user is located.

[0206] Specifically, the business domain data (or B-domain data (business support system)) of a user may include product tariff data and consumption attribute data related to the user, including voice low saturation, traffic low saturation, voice over-package, traffic over-package, speed limit, main tariff upgrade and main tariff downgrade, etc.

[0207] The operation domain data (or O domain data (operation support system)) of a user may include network perception data and network performance data related to the user, including base station engineering parameter table, home broadband resource service topology, resident base station level value, and optical line terminal (OLT) / broadband remote access server (BRAS) faults.

[0208] The above-mentioned base station engineering parameter table may include the longitude and latitude of the cell to which the user belongs, the name, the district and county where the user is located, the grid information of the service center, the maintenance manufacturer, status and construction time of the base station, etc. The above-mentioned home broadband resource service topology may include the upstream link information of the user's bandwidth number, such as the primary splitter, secondary splitter and local area network (LAN) port information. The above-mentioned resident base station level value is used to determine the stability and signal quality of the resident base station.

[0209] The service domain data of a user may include information related to the user's complaints, including business consultation, business handling, complaints, and post-use reviews.

[0210] Optionally, the electronic device may convert a recording file of customer service related to a certain user into a text file, and then perform keyword extraction to obtain the service domain data of the user.

[0211] In the embodiment of the present application, since the user data of the target user includes at least one of the business domain data of the target user, the operation domain data of the target user, and the service domain data of the target user, the electronic device can determine the user events contained in the behavior sequence of the target user based on the data of the at least one item. That is, the behavior sequence of each user can reflect the actual situation of each user when performing telecommunications services from multiple angles (including the consumption habits of each user, the network quality of each user, and the user perception of each user), and can fully portray the experience of each user. Thereby, in the subsequent process of generating the target strategy, the accuracy of the target strategy can be improved.

[0212] In one implementation of the embodiment of the present application, the behavior sequence of the target user includes multiple user events and respective timestamps of the multiple user events, and the behavior sequence of the target user is obtained by sorting the multiple user events according to respective timestamps of the multiple user events.

[0213] In combination with the description of the above embodiment, the electronic device can determine the user events (ie, the multiple user events) included in the behavior sequence of the target user based on the user data of the target user and can also determine the timestamps of the multiple user events based on the user data.

[0214] In an embodiment of the present application, after determining (or obtaining) multiple user events and respective timestamps of the multiple user events, the electronic device sorts the multiple user events according to respective timestamps of the multiple user events, and can accurately and effectively reflect the user events that occur (or are executed) in chronological order when the target user is performing telecommunications services, that is, a correct and relevant behavior sequence that can effectively reflect the user behavior of each user can be obtained.

[0215] For example, Figure 3 As shown, the user data of a user may include the user's O-domain data, B-domain data and service domain data. The user's O-domain data includes the user's network perception data and network performance data, specifically including base station engineering parameter table, home broadband resource service topology, resident base station level value and OLT / BRAS faults.

[0216] The user's B-domain data includes product tariff data and consumption attribute data related to the user, including voice / traffic undersaturation, voice / traffic over-package, speed limit, and main tariff upgrade / downgrade.

[0217] The user's service domain data includes the user's contact service data, including business consultation, business processing, complaints and post-use reviews, etc.

[0218] After the electronic device obtains the user data of the user (that is, including the above-mentioned O domain data, B domain data and service domain data), it can obtain the behavior sequence of the user based on the user data of the user.

[0219] Continue as Figure 3 As shown, the user's behavior sequence includes 7 user events, namely, network access, voice over-coverage, measurement report (MR) low coverage, complaint about wireless Internet access, speed limit, processing of phone bill contract, and number portability. The times corresponding to the 7 user events are 2021-02-01 12:59:01, 2021-03-31 08:00:00, 2021-04-30 12:00:01, 2021-06-01 14:08:11, 2021-08-2009:20:11, 2021-10-02 16:24:02, and 2022-01-01 19:07:09. That is, joining the network → voice coverage exceeding the limit → low MR coverage → complaining about wireless Internet access issues → speed limit → applying for a phone bill contract → number portability can be understood as a user's behavior sequence, and each user event included in the behavior sequence has a corresponding timestamp.

[0220] In one implementation of an embodiment of the present application, the behavior sequence of the above-mentioned target user is determined based on a user behavior history graph, which includes a user node, an event node, and an edge connecting the user node and the event node. The user node is used to represent the user, the event node is used to represent the user event, and the edge is used to represent the timestamp of the user executing the user event.

[0221] Specifically, for a certain user (for example, a target user), the electronic device can determine the user node corresponding to the target user from the user behavior history graph, and determine the event node that has an edge (or connection relationship) with the user node as the event node corresponding to the above-mentioned multiple user events, and determine the timestamp represented by the edge between the user node and the event nodes corresponding to the multiple user events as the timestamp of each of the multiple user events, so that the behavior sequence of the target user can be obtained.

[0222] In an embodiment of the present application, since the user behavior history graph includes user nodes for representing users, event nodes for representing user events, and edges for representing timestamps of users executing user events, the electronic device can conveniently and quickly determine the behavior sequence of each user based on the user behavior history graph, thereby improving the rate of generating corresponding strategies for each user.

[0223] Combination Figure 2 ,like Figure 4 As shown, the electronic device obtains the behavior sequence of the target user, which may specifically include S1011-S1015.

[0224] S1011. The electronic device obtains a user ID of a target user.

[0225] S1012: The electronic device queries a user behavior history graph based on the user identification of the target user, and determines a target user node from the user behavior history graph.

[0226] Among them, the node identifier of the target user node is the same as the user identifier of the target user, and the user behavior history graph includes a user node, an event node, and an edge connecting the user node and the event node. The user node is used to represent the user, the event node is used to represent the user event, and the edge is used to represent the timestamp of the user executing the user event.

[0227] Specifically, the user behavior history graph includes multiple user nodes, and the electronic device (or the user behavior history graph) stores the respective identifiers of the multiple user nodes. The electronic device can determine the target user node from the multiple user nodes based on the user identifier of the target user, and the target user node is used to characterize the target user.

[0228] S1013: The electronic device determines the user events represented by the multiple event nodes as the multiple user events included in the behavior sequence of the target user.

[0229] The multiple event nodes are event nodes that have edges with the target user node.

[0230] It should be understood that there are edges between the multiple event nodes and the target user node, indicating that the user represented by the target user node has executed the user events represented by the multiple event nodes. Since the user represented by the target user node is the target user, the user events represented by the multiple event nodes are user events executed by the target user, so it can be concluded that the user events represented by the multiple event nodes are multiple user events included in the behavior sequence of the target user.

[0231] S1014. The electronic device determines the timestamps represented by the multiple edges as the timestamps of the multiple user events respectively.

[0232] Among them, one edge is used to connect the above-mentioned target user node and one event node among multiple event nodes.

[0233] In combination with the description of the above embodiment, the edge connecting a user node and an event node is used to represent the timestamp of the user represented by the user node executing the user event represented by the event node. In this way, after the electronic device determines the multiple edges between the multiple event nodes and the target user node, the timestamps represented by each of the multiple edges can be determined as the timestamps of each of the multiple user events included in the behavior sequence of the target user. At this point, the electronic device can obtain the multiple user events and the timestamps of each of the multiple user events.

[0234] S1015. The electronic device sorts the multiple user events according to their respective timestamps to obtain a behavior sequence of the target user.

[0235] In an embodiment of the present application, after obtaining the user identification of the target user, the electronic device can determine the target user node from the user behavior history graph, the node identification of the target user node is the same as the user identification of the target user, and the target user node is used to characterize the target user; then the electronic device can determine the user events represented by multiple event nodes in the user behavior history graph that have edges (or connection relationships) with the target user node as multiple user events included in the behavior sequence of the target user, and determine the timestamps represented by the multiple edges between the target user node and the multiple event nodes in the user behavior history graph as the timestamps of the multiple user events; finally, the electronic device can sort the multiple user events according to the timestamps of the multiple user events to obtain the behavior sequence of the target user. That is, the electronic device can conveniently and quickly determine the user events performed by each user and the timestamps of the user events performed by each user based on the user identification of each user and the user behavior history graph, which can improve the efficiency of obtaining the behavior sequence of each user.

[0236] Optionally, the electronic device may store the behavior sequence of the target user in the form of a user behavior history map.

[0237] For example, Figure 5 As shown, for a single user (for example, user A), user node A can represent user A, and there are 6 event nodes with edges (or connection relationships) between user node A, including event node 201, event node 202, event node 203, event node 204, event node 205 and event node 206. The timestamps of the 6 user events represented by the 6 event nodes are timestamp 1, timestamp 2, timestamp 3, timestamp 4, timestamp 5 and timestamp 6 respectively. The 6 user events are speed limit 2-4 times, voice package exceeding, traffic package exceeding, package cancellation, complaint about network migration and query of transcoding in the order of timestamps.

[0238] Continue as Figure 5 As shown, for multiple users (including user A and user B), user node B can represent user B, and there are four event nodes with edges (or connection relationships) between user node B, including event node 204, event node 205, event node 207, and event node 208. The timestamps corresponding to the four user events represented by the four event nodes are timestamp 1, timestamp 2, timestamp 3, and timestamp 4, respectively. The four user events are package cancellation, low traffic saturation, complaint about home broadband, and complaint about network migration in the order of timestamps. Since the user events executed by user A and user B both include package cancellation and complaint about network migration, that is, there are edges between user node A and user node B and event node 204 and event node 205.

[0239] If the number of user nodes is m and the number of event nodes is n, then the user behavior history graph contains a total of m+n nodes, and the number of edges (or association relationships) is less than m*n, where m is an integer greater than or equal to 1, and n is an integer greater than or equal to 1.

[0240] For user A and user B, the behavior sequence of user A determined by the electronic device based on user A's user identification and user behavior history graph is: speed limit 2-4 times → voice exceeding package → data exceeding package → cancel package → complain about mobile network → query portability transcoding. The behavior sequence of user B determined by the electronic device based on user B's user identification and user behavior history graph is: cancel package → low data saturation → complain about home broadband → complain about mobile network.

[0241] In one implementation of an embodiment of the present application, the user events contained in the behavior sequence of the above-mentioned target user include negative perception events and / or subjective feedback events, wherein the negative perception event is used to characterize the passive consumption behavior corresponding to the target user, and the subjective feedback event is used to characterize the active complaint behavior corresponding to the target user.

[0242] Specifically, passive consumption behaviors may include voice overage, traffic overage, voice undersaturation, traffic undersaturation, and speed limit, etc. Active complaint behaviors may include complaints and complaints, etc.

[0243] In the embodiment of the present application, since the user events included in the target user's behavior sequence include negative perception events and / or subjective feedback events, that is, the electronic device can characterize the user behavior of each user in the process of performing telecommunications services in the form of passive consumption behavior corresponding to each user and active complaint behavior corresponding to each user, and can comprehensively and completely obtain the behavior sequence of each user.

[0244] Optionally, the electronic device can subdivide negative perception events into long-term negative perception events and short-term severe perception events. Long-term negative perception events are used to characterize that a negative perception event occurs a large number of times (or frequency) within a preset time period, while short-term severe perception events are used to characterize that a negative perception event has a large range of changes during a single occurrence.

[0245] For example, long-term negative perception events may be speed limit 2-4 times, speed limit greater than 4 times, and voice overage greater than 4 times, etc. Short-term serious perception events may be voice overage (for example, voice exceeds the package by 1 times) and traffic overage.

[0246] In an optional implementation, the electronic device may classify the above-mentioned long-term negative perception events as long-term negative perception modes, and classify the above-mentioned subjective feedback events and short-term severe perception events as short-term severe mutation modes, and use the user events included in the two modes to form a user's behavior sequence.

[0247] In another optional implementation, porting and leaving the network can also be understood as a landmark event that occurs (or is performed) by the user in the process of carrying out telecommunications services. In the process of carrying out telecommunications services, the user can also perform a bundled event that is closely related to (or has a collateral effect on) the landmark event, and the electronic device can delete the bundled event to avoid the negative impact of the bundled event on the user's behavior sequence.

[0248] Exemplarily, bundling events may include user complaints after querying the code portability, broadband machine disassembly before portability, network withdrawal before portability, and package withdrawal before portability, etc.

[0249] Optionally, the electronic device can determine the original behavior sequence of the target user based on the user data of the above-mentioned target user, and then identify the user events included in the above-mentioned long-term negative perception pattern and the user events included in the short-term severe mutation pattern from all user events included in the original behavior sequence, and delete the bundled events from the original behavior sequence to obtain the behavior sequence of the target user.

[0250] It is worth noting that a user's original behavior sequence can be understood as the user's original service history, and the user's behavior sequence can be understood as the user's personalized service history.

[0251] For example, Figure 6 As shown, the user's original behavior sequence includes 3 speed limits, 6 voice over-packages, 1 serious voice over-package, 1 package cancellation, 1 complaint about network migration, 1 package withdrawal before porting, and 1 porting.

[0252] The three speed limits and the six voice over-sets correspond to a long-term negative perception event respectively. The corresponding user events are speed limits 2-4 times and voice over-sets more than 4 times. The two long-term negative perception events belong to the long-term negative perception mode.

[0253] This severe voice overshoot corresponds to a short-term severe perception event, and the specific corresponding user event is severe voice overshoot.

[0254] The cancellation of the package and the complaint about the network migration each correspond to a subjective feedback event, and the specific corresponding user events are cancellation of the package and complaint about the network migration. The short-term severe perception event and the two subjective feedback events belong to the short-term severe mutation mode.

[0255] This one package cancellation before transfer corresponds to a bundling event, and this one package transfer corresponds to a landmark event.

[0256] That is, the user events included in the behavior sequence of the user obtained by the electronic device are: speed limit 2-4 times, voice over limit more than 4 times, voice over limit seriously, package cancellation, complaint about network migration, and portability.

[0257] In an implementation of the embodiment of the present application, the above-mentioned target strategy is determined based on a common behavior sequence corresponding to a target user group, and the common behavior sequence corresponding to the target user group is determined based on a behavior sequence of each user included in the target user group.

[0258] In combination with the description of the above embodiment, the target user group is the user group to which the above target user belongs, and each user included in the target user group has the same user type.

[0259] It is worth noting that the common behavior sequence corresponding to the target user group can characterize the most common behavior pattern with time series characteristics for each user included in the target user group (or the user type corresponding to the target user group). After determining the target user group, the electronic device can determine the common behavior sequence corresponding to the target user group based on the behavior sequence of each user included in the target user group, and accurately and effectively determine the target strategy based on the common behavior sequence corresponding to the target user group. That is, the electronic device can accurately and effectively determine the maintenance strategy corresponding to each user based on the most common behavior pattern with time series characteristics corresponding to the user group to which each user belongs, thereby reducing the portability / off-network situation of each user.

[0260] In an optional implementation, the target strategy is determined based on at least one business indicator, and the at least one business indicator is determined based on the event type of the user event included in the common behavior sequence corresponding to the target user group.

[0261] Specifically, an event type can correspond to one or more business indicators. After determining the common behavior sequence corresponding to the target user group, the electronic device can accurately and effectively determine at least one business indicator related to the target user group based on the event type of the user event included in the common behavior sequence, and finally determine the target strategy based on the at least one business indicator. That is, the electronic device can accurately and effectively determine the maintenance strategy corresponding to each user based on the business indicators related to the user group to which each user belongs, which can improve the accuracy of strategy generation.

[0262] In an optional implementation manner, the event type of the user events included in the common behavior sequence corresponding to the target user group includes at least one of a marketing type, a wireless type, and a home broadband type.

[0263] Optionally, market user events may include average revenue per user (ARPU) increase, ARPU decrease, and serious over-accounting, etc. Wireless user events may include speed limit, wireless complaints, wireless complaints, and slow wireless speed, etc. Home broadband user events may include home broadband disconnection and home broadband complaints, etc.

[0264] Specifically, for a common behavior sequence corresponding to a user group, the electronic device may perform scenario-based classification on each user event included in the common behavior sequence to obtain the event type of each user event.

[0265] Optionally, the event type of a user event may also be survey or comprehensive perception.

[0266] Optionally, for market user events, the corresponding service indicators may include ARPU, etc. For wireless user events, the corresponding service indicators may include monthly Internet traffic (dataflow of usage, DOU) and monthly talk time (minutes of usage, MOU), etc. For home broadband user events, the corresponding service indicators may include home broadband DOU, etc.

[0267] In an embodiment of the present application, a common behavior sequence corresponding to a user group can also be understood as a common service history corresponding to the user group. By performing scenario-based classification on each user event included in the common behavior sequence and obtaining the event type of each user event included in the common behavior sequence, a common behavior sequence with scenario-based business meaning can be formed, so that a maintenance strategy with scenario-based business meaning can be assigned to each user, thereby improving the practicality of the strategy.

[0268] In one implementation of an embodiment of the present application, the above-mentioned target strategy is a strategy corresponding to a target value, and the target value is a value that matches at least one value in a numerical strategy relationship, and the at least one value is a value corresponding to the above-mentioned at least one business indicator, and the numerical strategy relationship includes multiple values ​​and a strategy corresponding to each of the multiple values.

[0269] Specifically, the numerical policy relationship is a correspondence between multiple numerical values ​​and multiple policies, specifically one numerical value corresponds to one policy. The target numerical value is a numerical value that matches at least one numerical value in the numerical policy relationship, which can also be understood as the target numerical value being the same as the at least one numerical value, that is, the policy corresponding to the target numerical value is the policy corresponding to at least one numerical value (or at least one business indicator). The electronic device can easily and quickly determine the maintenance strategy related to the business indicator corresponding to the user group to which each user belongs in the numerical policy relationship, thereby improving the efficiency of strategy generation.

[0270] In an optional implementation, the above numerical strategy relationship may be pre-stored in the electronic device. Based on this, the strategy generation method provided in the embodiment of the present application may also include step A-step B.

[0271] Step A: The electronic device queries a numerical value strategy relationship based on at least one numerical value, and determines a target numerical value matching the at least one numerical value from the numerical value strategy relationship.

[0272] The numerical strategy relationship includes multiple numerical values ​​and a strategy corresponding to each of the multiple numerical values, and the at least one numerical value is a numerical value corresponding to the at least one business indicator.

[0273] Specifically, a business indicator may correspond to a numerical value.

[0274] Step B: The electronic device determines the strategy corresponding to the target value as the target strategy.

[0275] In the embodiment of the present application, the electronic device can determine a target value that matches (or is the same as) the at least one value from the value policy relationship based on at least one value (i.e., the value corresponding to at least one business indicator), and determine the policy corresponding to the target value as the target policy. It is possible to quickly output a personalized maintenance policy corresponding to the business indicator related to the user group corresponding to each user, thereby ensuring the improvement of user service experience perception from the source and increasing user satisfaction.

[0276] It is worth noting that, for a user, the common behavior sequence corresponding to the user group to which the user belongs can also be understood as the common behavior sequence corresponding to the user. The electronic device can identify the current scenario shortcomings of the user based on the event type of each user event included in the common behavior sequence corresponding to the user, thereby generating (or allocating) a corresponding maintenance strategy for the user.

[0277] For example, Figure 7 As shown, it is assumed that the common behavior sequence corresponding to user A is network access → ARPU decreases → serious over-package → speed limit → query of portability code → portability, the common behavior sequence corresponding to user B is network access → ARPU increases → complain about wireless → complain about wireless → slow wireless speed → query of portability code → portability, and the common behavior sequence corresponding to user C is network access → serious over-package → home broadband disconnection → complain about home broadband → query of portability code → portability.

[0278] For user A, the electronic device identifies that the corresponding common behavior sequence includes 2 market user events, 1 wireless user event, and 0 home broadband user events, that is, the electronic device determines that the current scenario shortcoming of user A is market perception. At this time, the electronic device can determine the corresponding maintenance strategy for user A based on the business indicator corresponding to the market category (i.e. ARPU).

[0279] For user B, the electronic device identifies that the corresponding common behavior sequence includes 1 market user event, 3 wireless user events, and 0 home broadband user events, that is, the electronic device determines that the current scenario shortcoming of user B is the wireless perception type. At this time, the electronic device can determine the corresponding maintenance strategy for user B through the business indicators corresponding to the wireless type (i.e., DOU and MOU).

[0280] For user C, the electronic device identifies that the corresponding common behavior sequence includes 1 market user event, 0 wireless user events, and 2 home broadband user events, that is, the electronic device determines that the current scenario shortcoming of user C is the home broadband perception category. At this time, the electronic device determines the corresponding maintenance strategy for user C through the business indicators corresponding to the home broadband category (i.e., home broadband DOU).

[0281] Optionally, for relevant business indicators (such as ARPU) of a certain user (such as user A) within a preset time interval, the preset time interval can be divided into an early period and a late period, and the ARPU level of user A in the early period and the ARPU level of user A in the late period can be determined respectively.

[0282] Continue as Figure 7 As shown in Figure 1, the ARPU level of user A in the early stage shows a sharp decline, and the ARPU level of user A in the later stage shows a sharp increase. In this way, the electronic device can be based on these two features from Figure 7 The corresponding policy is found in the policy table shown in , that is, the electronic device determines that the policy corresponding to user A is that the installation and maintenance team will come to the site.

[0283] Optionally, Figure 7 The strategy table shown in the figure may also include a root cause analysis, which may instruct the relevant departments and personnel to promptly discover and handle existing problems or defects.

[0284] Optionally, the electronic device can also assign different priorities to different users, and the priority is used to characterize the user's potential off-network expectation. That is, if a user's priority is higher, it means that the user's potential off-network expectation is higher. For high-priority users, the electronic device can assign them customized maintenance strategies.

[0285] Specifically, the operator can regularly send satisfaction survey questionnaires to users, and users can rate their telecommunications services, and define users with lower scores as high-priority users. Or if a user has a behavior of querying transcoding, the electronic device can determine that the user is a high-priority user.

[0286] For example, Figure 8 As shown, user A and user B are high-priority users, and the electronic device can allocate customized maintenance strategies to user A and user B. User C is a low-priority user, and the electronic device can allocate a common maintenance strategy to user C.

[0287] The strategy generation method provided in the embodiment of the present application may also include steps C to D.

[0288] Step C: The electronic device determines the number of users corresponding to each of the plurality of behavior sequences.

[0289] The multiple behavior sequences are determined based on the respective behavior sequences of the multiple users included in the target user group.

[0290] Specifically, after the electronic device determines the target user group to which the target user belongs, it can determine the above-mentioned multiple behavior sequences from the behavior sequences of the multiple users included in the target user group. For a behavior sequence (for example, a first behavior sequence) among the multiple behavior sequences, if the behavior sequence of a certain user is the same as the first behavior sequence and / or the user events included in the behavior sequence of the user include the user events included in the first behavior sequence, it means that the user is the user corresponding to the first behavior sequence.

[0291] Step D: The electronic device determines the behavior sequences whose corresponding user numbers among the multiple behavior sequences are greater than or equal to the first number threshold as the common behavior sequences corresponding to the target user group.

[0292] Optionally, the electronic device may also determine K behavior sequences corresponding to the largest number of users among the multiple behavior sequences as common behavior sequences corresponding to the target user group, where K is an integer greater than or equal to 1.

[0293] It is worth noting that, since the multiple behavior sequences are determined based on the behavior sequences of the multiple users included in the target user group, the multiple behavior sequences can comprehensively reflect the behavior habits of each user in the target user group in performing telecommunication services (or user events performed in the process of performing telecommunication services). The behavior sequences corresponding to the number of users in the multiple behavior sequences being greater than or equal to the first quantity threshold can reflect the behavior habits of a large number (or majority) of users in the target user group, and thus can reflect the behavior characteristics of the target user group as a whole, that is, can accurately and effectively characterize the behavior characteristics of the user type corresponding to the target user group, and can then allocate appropriate maintenance strategies to the target users based on the behavior characteristics.

[0294] Before the electronic device determines the number of users corresponding to each of the plurality of behavior sequences, the strategy generation method provided in the embodiment of the present application may further include steps E to F.

[0295] Step E: The electronic device obtains a behavior sequence of each user among the multiple users included in the target user group.

[0296] Step F: The electronic device performs a preset operation on at least one user event included in the behavior sequence of each user to obtain multiple behavior sequences.

[0297] The execution order of the user events included in each behavior sequence in the multiple behavior sequences remains unchanged, and the preset operation includes a deletion operation.

[0298] Optionally, the electronic device may perform frequent pattern mining on the behavior sequence of each user based on a time series mining algorithm (prefixspan) to obtain the above-mentioned multiple behavior sequences.

[0299] Exemplarily, assuming that a behavior sequence of a user included in the target user group is network access→speed limit→exceeding the package→querying the portability code→portability, the behavior sequence obtained by the electronic device based on the behavior sequence of the user may include network access→speed limit, network access→exceeding the package, and network access→speed limit→exceeding the package, etc. In the behavior sequence of the user, the super-package is located after the network access, so in the behavior sequence generated based on the behavior sequence of the user, the super-package is also located after the network access.

[0300] In the embodiment of the present application, the electronic device can obtain the behavior sequence of each user among the multiple users included in the target user group, and perform a preset operation on at least one user event included in the behavior sequence of each user, that is, multiple behavior sequences can be obtained. That is, the electronic device can accurately and effectively determine multiple behavior sequences that can fully reflect the behavior habits of each user in the target user group in the process of performing telecommunications services based on the behavior habits of each user included in the target user group in the process of performing telecommunications services, and then accurately determine the common behavior sequence corresponding to each user group, so as to formulate a customized strategy for each user group, guide market personnel to complete maintenance, and improve service efficiency.

[0301] For example, Fig. 9 As shown, it is assumed that the target user group includes 3 users, namely user A, user B and user C. The behavior sequence of user A is E1 (network access) → E2 (speed limit) → E3 (exceeding the package) → E4 (low saturation) → E5 (querying the portability code) → E6 (portability), the behavior sequence of user B is E1 (network access) → E3 (exceeding the package) → E4 (low saturation) → E7 (complaining about wireless) → E5 (querying the portability code) → E6 (portability), and the behavior sequence of user C is E1 (network access) → E3 (exceeding the package) → E4 (low saturation) → E8 (cancelling the package) → E5 (querying the portability code) → E6 (portability).

[0302] The electronic device determines that after the user event E1 in the target user group, there will be two branches, namely, user event E2 and user event E3, and there is also a process of executing user event E3 after the user event E2.

[0303] The electronic device can determine multiple behavior sequences through the behavior sequences of the three users, and determine the three behavior sequences with the largest number of users from the multiple behavior sequences, which are behavior sequence 1, behavior sequence 2, and behavior sequence 3 in descending order of the number of users. The three behavior sequences are E1→E2 (i.e., network access→speed limit), E1→E4 (i.e., network access→low saturation), and E1→E2→E4 (i.e., network access→speed limit→low saturation).

[0304] Continue as Fig. 9As shown, the electronic device can also perform scenario-based classification on the user events included in each of the above-mentioned multiple behavior sequences, that is, divide the multiple behavior sequences according to the event type (including market, wireless, home broadband, and research, etc.), and determine some behavior sequences with scenario-based categories, including E1→E2→E4 (i.e., network access→speed limit→low saturation) and E1→E3→E7 (i.e., network access→exceeding the limit→complaining about wireless).

[0305] In one implementation of an embodiment of the present application, the above-mentioned target strategy is a strategy corresponding to a first behavior sequence, which is determined from at least one behavior sequence based on the similarity between each behavior sequence in at least one behavior sequence and the behavior sequence of the target user, and the at least one behavior sequence is a behavior sequence included in the common behavior sequence corresponding to the target user group.

[0306] Specifically, one behavior sequence in the at least one behavior sequence corresponds to one strategy, and the electronic device can determine the similarity between each behavior sequence in the at least one behavior sequence and the behavior sequence of the target user, thereby determining a first behavior sequence from the at least one behavior sequence and determining the strategy corresponding to the first behavior sequence as the target strategy. That is, the electronic device can determine a first behavior sequence similar to the behavior sequence of the target user based on a similarity algorithm, and the first behavior sequence can, to a certain extent, characterize the behavior habits similar to those of the target user when performing telecommunications services, thereby being able to quickly assign an effective target strategy to the target user, which helps to support low-cost and efficient user retention.

[0307] In an optional implementation, the common behavior sequence corresponding to the target user group includes at least one behavior sequence. The strategy generation method provided in the embodiment of the present application may also include steps G to H.

[0308] Step G: The electronic device determines the similarity between each behavior sequence in at least one behavior sequence and the behavior sequence of the target user.

[0309] Step H: The electronic device determines the policy corresponding to the first behavior sequence as the target policy.

[0310] The first behavior sequence is a behavior sequence having the greatest similarity with the behavior sequence of the target user among the at least one behavior sequence.

[0311] Combined with the description of the above embodiment, one behavior sequence in the at least one behavior sequence corresponds to one strategy. The similarity between the first behavior sequence and the behavior sequence of the target user is the greatest, indicating that the first behavior sequence is most similar to the behavior sequence of the target user. It can also be understood that the behavioral habits represented by the first behavior sequence are most similar to the behavioral habits of the target user in conducting telecommunications services. At this time, the electronic device determines the strategy corresponding to the first behavior sequence as the target strategy, that is, it can accurately and effectively assign the corresponding maintenance strategy to the target user, so that the maintenance and retention strategy for each potential porting / off-network user can be accurately formulated.

[0312] For example, Fig.10 As shown, it is assumed that the behavior sequence of the target user is network access→ARPU reduction→speed limit for more than 5 times→query for portability code→portability. The common behavior sequence corresponding to the target user group includes 3 behavior sequences, including behavior sequence 1, behavior sequence 2 and behavior sequence 3.

[0313] Among them, behavior sequence 1 is network access → ARPU increases → complaint → query the portability code → portability, behavior sequence 2 is network access → ARPU decreases → speed limit 2-4 times → query the portability code → portability, and behavior sequence 3 is network access → serious over-coverage → home broadband disconnection → query the portability code → portability.

[0314] The electronic device determines that the behavior sequence 2 is the first behavior sequence, and determines the policy corresponding to the behavior sequence 2 as the target policy.

[0315] In one implementation of the embodiment of the present application, the common behavior sequence corresponding to the above-mentioned target user group includes at least one behavior sequence, and each behavior sequence in the at least one behavior sequence has the same similarity with the behavior sequence of the target user. The above-mentioned target strategy is a strategy corresponding to a second behavior sequence, and the second behavior sequence is determined from the at least one behavior sequence based on the event difference corresponding to each behavior sequence in the at least one behavior sequence, wherein the event difference corresponding to a behavior sequence is determined based on the number of user events between each user event included in the behavior sequence and the last user event included in the behavior sequence of the target user.

[0316] It is worth noting that since the similarity between each behavior sequence in the at least one behavior sequence and the behavior sequence of the target user is the same, it may not be possible to determine a unique strategy for the target user based on the similarity algorithm. At this time, the electronic device can determine the event difference corresponding to each behavior sequence. Since the event difference corresponding to a behavior sequence is determined based on the number of user events between each user event included in the behavior sequence and the last user event (also understood as a landmark event) included in the behavior sequence of the target user, the event difference corresponding to the behavior sequence can accurately characterize the degree of association between each user event included in the behavior sequence and portability (or off-grid). In this way, an effective maintenance strategy can be determined for the target user based on the degree of association, thereby improving the effectiveness of user maintenance.

[0317] The strategy generation method provided in the embodiment of the present application may also include steps I to J.

[0318] Step I: The electronic device determines an event difference corresponding to each behavior sequence in at least one behavior sequence.

[0319] In combination with the description of the above embodiment, the event difference corresponding to a behavior sequence is determined based on the number of user events between each user event included in the behavior sequence and the last user event included in the behavior sequence of the target user.

[0320] Optionally, for a certain behavior sequence among the at least one behavior sequence, the electronic device may determine the sum of the number of user events between each user event included in the behavior sequence and the last user event included in the behavior sequence of the target user as the event difference corresponding to the behavior sequence.

[0321] Step J: The electronic device determines the behavior sequence with the smallest corresponding event difference in at least one behavior sequence as the second behavior sequence.

[0322] It is worth noting that if the event difference corresponding to a certain behavior sequence in the at least one behavior sequence is the smallest, it means that the correlation between each user event included in the behavior sequence and the portability (or off-network) is greater (the closer the correlation is), and the behavior sequence can accurately reflect the real reason why the user may portability (or off-network). In this way, the electronic device determines the behavior sequence as the second behavior sequence, and then determines the strategy corresponding to the second behavior sequence as the target strategy, which can accurately identify the user behavior characteristics based on the user events with a greater degree of correlation, and generate personalized and highly accurate maintenance strategies.

[0323] For example, it is assumed that the target user's behavior sequence is network access→ARPU reduction→voice over-package→speed limit more than 5 times→query portability code→portability. The common behavior sequence corresponding to the target user group includes 3 behavior sequences, namely, behavior sequence A, behavior sequence B and behavior sequence C.

[0324] Among them, behavior sequence A is network access → voice over-package → speed limit more than 5 times. Behavior sequence B is network access → speed limit more than 5 times → query portability. Behavior sequence C is network access → ARPU reduction → voice over-package.

[0325] The electronic device determines that the event difference corresponding to behavior sequence A is 10 (5+3+2), the event difference corresponding to behavior sequence B is 8 (5+2+1), and the event difference corresponding to behavior sequence C is 12 (5+4+3).

[0326] That is, the electronic device determines that the behavior sequence B is the second behavior sequence, and determines the policy corresponding to the behavior sequence B as the target policy.

[0327] The strategy generation method provided in the embodiment of the present application may further include step K.

[0328] Step K: If the number of users corresponding to the target user event is greater than or equal to the second number threshold, the electronic device determines that the target user event is a key event.

[0329] The target user event is a user event included in the common behavior sequence corresponding to the target user group.

[0330] Specifically, for each user event included in a common behavior sequence, the electronic device can determine the number of users corresponding to each user event. The number of users corresponding to a user event is the number of users who execute the user event.

[0331] It is worth noting that if the number of users corresponding to the target user event is greater than or equal to the second number threshold, it means that the number of users corresponding to the target user event is large, that is, a large number of users have executed the target user event. At this time, the electronic device can determine that the target user event is a key event. While identifying the key event, it conducts a retrospective analysis of the root cause of the key event to formulate a maintenance strategy that can effectively retain users who transfer / leave the network, thereby improving the success rate of maintenance.

[0332] In an optional implementation, the common behavior sequence corresponding to the target user group includes at least two behavior sequences, the target user event is a user event included in the converged behavior sequence corresponding to the target user group, and the converged behavior sequence corresponding to the target user group is determined based on the at least two behavior sequences.

[0333] Specifically, the electronic device can converge the at least two behavior sequences to obtain a converged behavior sequence corresponding to the target user group, and the converged behavior sequence includes the user events included in each of the at least two behavior sequences. In an embodiment of the present application, since the converged behavior sequence corresponding to a user group converges all common behavior sequences corresponding to the user group, the converged behavior sequence can reflect the behavioral habits corresponding to the user group as a whole. And since the target user event is the user event included in the converged behavior sequence corresponding to the target user group, the electronic device can accurately screen out the key events associated with the user type corresponding to the target user group, thereby improving the retention success rate of each type of user.

[0334] Optionally, the strategy generation method provided in the embodiment of the present application may further include step L.

[0335] Step L: The electronic device aggregates the same user events included in at least two behavior sequences, and sorts the different user events included in at least two behavior sequences in the order of timestamps to obtain an aggregated behavior sequence corresponding to the target user group.

[0336] It is worth noting that for all user events included in at least two behavior sequences included in the common service sequence corresponding to the target user group, the electronic device aggregates the same user events, that is, the same user events can be merged and deduplicated, reducing the size of the behavior sequence (specifically the converged behavior sequence) and saving storage resources. The electronic device sorts different user events in the order of timestamps, which can fully cover every user event included in the common service sequence corresponding to the target user group, ensuring the integrity of the common service sequence.

[0337] In one implementation of an embodiment of the present application, the number of users corresponding to the above-mentioned target user event is determined based on a common behavior history graph, which includes at least two event nodes and an edge connecting the at least two event nodes. An event node is used to represent a user event, and the edge is used to represent the number of users corresponding to the downstream event node connected to the edge.

[0338] Specifically, the electronic device can determine the event node used to characterize the target user event from the common behavior history graph, and determine the direct upstream event node of the event node (specifically, the upstream node that has a connection relationship with the event node). Finally, the number of users represented by the edge between the direct upstream event node and the event node is determined as the number of users corresponding to the target user event. In the embodiment of the present application, since the common behavior history graph can characterize multiple user events and the number of users corresponding to each of the multiple user events, the electronic device can accurately and effectively determine the number of users corresponding to the target user event from the common behavior history graph, thereby improving the efficiency of determining the number of users corresponding to each user event.

[0339] In an optional implementation, the common behavior history diagram may be pre-stored in an electronic device. Based on this, the strategy generation method provided in the embodiment of the present application may further include step M-step O.

[0340] Step M: The electronic device obtains the event identifier of the target user event.

[0341] Step N: the electronic device queries the common behavior history graph based on the event identifier of the target user event, and determines the target event node from the common behavior history graph.

[0342] Among them, the node identifier of the target event node is the same as the event identifier of the target user event, the common behavior history diagram includes at least two event nodes and an edge connecting the at least two event nodes, one event node is used to represent a user event, and the edge is used to represent the number of users corresponding to the downstream event node connected to the edge.

[0343] Step O: The electronic device determines the number of users represented by the target edge as the number of users corresponding to the target user event.

[0344] Among them, the downstream event node connected by the target edge is the target event node.

[0345] In an embodiment of the present application, after obtaining the event identifier of the target user event, the electronic device can determine the target event node from the common behavior history graph, the node identifier of the target event node is the same as the event identifier of the target user event, and the target event node can represent the target user event; then the electronic device can determine the target edge from the common behavior history graph, and the downstream event node connected to the target edge is the target event node; finally, the electronic device can determine the number of users represented by the target edge as the number of users corresponding to the target user event. That is, the electronic device can conveniently and quickly determine the number of users corresponding to each user event from the common behavior history graph based on the event identifier of each user event, thereby improving the rate at which the electronic device identifies key events and further improving the success rate of maintaining (off-network) users.

[0346] Optionally, the electronic device may use a graph multi-hop query technology to query at least two behavior sequences included in the common behavior history graph (specifically, the common behavior sequences corresponding to the target user group), thereby obtaining a converged behavior sequence corresponding to the target user group.

[0347] For example, Fig.11 As shown, the common behavior sequences corresponding to the target user group include two behavior sequences, namely, behavior sequence 1 and behavior sequence 2. Specifically, behavior sequence 1 is: network access → speed limit 2-4 times → cancel package → complain about network migration → query portability and transcoding, and behavior sequence 2 is: network access → speed limit 2-4 times → cancel package → low traffic saturation → complain about wireless.

[0348] Based on the graph multi-hop query technology, the electronic device determines from the common behavior history graph that the same user events in the two behavior sequences include network access, speed limit 2-4 times and package cancellation, and different user events include complaints about network migration, querying portability and transcoding, low traffic saturation and complaints about wireless.

[0349] Therefore, the converged behavior sequence corresponding to the target user group obtained by the electronic device is network access → speed limit 2-4 times → cancel package → complain about network migration / low traffic saturation → query portability / complain about wireless. Among them, the two sides of / represent two branches.

[0350] It is worth noting that for the same user event in the two behavior sequences (eg, speed limit 2-4 times), the number of users corresponding to the same user event is the sum of the number of users corresponding to the user event in the two behavior sequences.

[0351] In one implementation of an embodiment of the present application, the user type of the above-mentioned target user is used to characterize the grouping information of the target user, and the grouping information of the target user includes one or more of the location information of the target user, the perception type corresponding to the target user, the risk level of the target user, the age of the target user, and the gender of the target user.

[0352] In the embodiment of the present application, the user type of the target user may also be understood as the user type corresponding to the user group to which the target user belongs (ie, the target user group), and a user group may also be understood as a customer group.

[0353] Prior knowledge shows that location information, perception type, risk level, age, and gender are important factors that may determine whether a user is likely to switch or leave the network. Therefore, based on information entropy gain, we can identify the grouping information (or important tags) that affect user switching or leaving the network, and use this to distinguish user groups (or groups).

[0354] Specifically, the electronic device can group users according to the importance of each piece of information included in the grouping information, first according to the most important information (or label), and then continue to group based on the second most important information, until the user type of each user can be obtained by grouping based on each piece of information. Through a hierarchical grouping strategy, similar users can be grouped into specific user groups (or specific customer groups), which facilitates the subsequent determination of the common behavior sequence corresponding to the user group.

[0355] For example, Fig.12 As shown, assuming that the target user's grouping information includes the target user's location information, the target user's corresponding perception type, and the target user's risk level, the importance of the location information is greater than the importance of the perception type, and the importance of the perception type is greater than the importance of the risk level. Then the user type of the target user (or the specific customer group to which the target user belongs) can be Dazhou City-Market Category-Other Number Primary Card.

[0356] In the embodiment of the present application, since the user type of the target user is used to characterize the grouping information of the target user, the grouping information of the target user includes one or more of the location information of the target user, the perception type corresponding to the target user, the risk level of the target user, the age of the target user, and the gender of the target user. That is, the electronic device can group each user or determine the user type of each user from multiple perspectives such as location information, perception type, risk level, age, and gender, and can comprehensively and accurately determine the user group (or customer group) to which each user belongs based on the tags that may cause porting / offline, and then determine the maintenance strategies with specific service values ​​for different user groups.

[0357] In an optional implementation, the electronic device may also input the user events included in the behavior sequence of the target user into a pre-trained type prediction model to obtain the user type of the target user.

[0358] Optionally, the electronic device can construct a random forest model based on the user events included in the behavior sequence of historical portable (or off-network) users and the user events included in the behavior sequence of historical healthy users, and group the users according to the labels based on the importance of the labels output by the random forest model, so as to obtain the user type of each user. The random forest model is a specific form of the above-mentioned type prediction model.

[0359] In one implementation of the embodiment of the present application, the electronic device can also identify potential network porting / off-network users from a large number of operator users.

[0360] For example, Fig.13As shown, the number of users included in the operator user set is in the tens of millions. The electronic device can perform simple label filtering in the recall stage to reduce the tens of millions to the hundreds of thousands. Then, in the sorting stage, the electronic device determines the probability of each user in the hundreds of thousands by building a classification model, and sorts each user based on the probability of each user, and selects the thousands of users with a high willingness to carry / leave the network, that is, potential users who carry / leave the network can be obtained.

[0361] In an optional implementation, the electronic device may also predict whether the user to be identified is a mobile / offline user based on the service data of the user to be identified. Fig.14 As shown, the process may specifically include S201-S204.

[0362] S201. The electronic device obtains business data of multiple historical users, extracts behavior features of the multiple historical users based on attribute information of the multiple historical users, and clusters to obtain multi-dimensional feature classification data.

[0363] S202. The electronic device classifies the data according to the multi-dimensional features, performs weighted processing on the behavioral features of multiple historical users through a decision tree algorithm, and obtains feature data of the transferred user.

[0364] S203: The electronic device trains a neural network based on the characteristic data of the transferring user to obtain an analysis model.

[0365] S204: The electronic device inputs the business data of the user to be identified into the analysis model to obtain a prediction result.

[0366] The prediction result is used to characterize whether the user to be identified is a porting user.

[0367] Optionally, the above Fig.14 The process of predicting whether the user to be identified is a ported user shown in FIG. 1 can be further refined. The refinement process can be as follows: Fig.15 shown.

[0368] Specifically, the electronic device can first obtain multi-dimensional feature classification data, and then obtain the carry-over user feature data and user attribute threshold based on the multi-dimensional feature classification data; then the normal users and carry-over users identified by the neural network can obtain the first carry-over probability of the analysis model. The electronic device then compares and verifies the analysis model and calculates the matching degree to obtain the final weight of the classification model, and performs threshold calibration in the classification model to obtain the second threshold. Finally, the carry-over probability (i.e., the second carry-over probability) of each user is obtained based on the trained classification model.

[0369] In an embodiment of the present application, the electronic device can use the target policy after generating the target policy. Based on this, an embodiment of the present application provides a policy application method, such as Fig.16 As shown, the policy application method provided in the embodiment of the present application may include S301-S302.

[0370] S301, the electronic device obtains a target strategy.

[0371] Among them, the target strategy includes target measures, and the target strategy is a strategy corresponding to a target user group. The target user group is a user group to which the target user belongs. The user type of each user included in the target user group is the same. The user type of the target user is determined based on the user events included in the behavior sequence of the target user. The behavior sequence of the target user is used to characterize the execution order of the user events included in the behavior sequence of the target user.

[0372] For example, measures included in a strategy may include on-site installation and maintenance teams, increased traffic, additional broadband, reduced tariffs, and discounts for recharges.

[0373] S302: The electronic device executes the target policy on the target user based on the target policy, so that the target user is in a stable state.

[0374] It should be understood that the stable state is a healthy state in the telecommunications service, specifically the possibility of the user leaving the network / leaving the network.

[0375] The technical solution provided by the above embodiment can at least bring the following beneficial effects: As can be seen from S301-S302, after obtaining the target strategy, the electronic device can execute the target measures on the target user based on the target strategy, so that the target user is in a stable state. That is, the electronic device can obtain the maintenance strategy dynamically allocated to different users according to the user types of different users, and then maintain and retain each user based on the maintenance strategy, which can avoid the situation of each user switching / leaving the network, and improve the success rate of maintenance.

[0376] It is worth noting that the technical solutions or technical limitations related to the policy generation method described in the above embodiments (such as specific limitations on the target policy, the process of determining the user type of the target user, and the specific limitations on the behavior sequence of the target user, etc.) are still applicable in the policy application method provided in the embodiments of the present application and will not be repeated here.

[0377] The following is a complete example to illustrate the process of generating a target strategy and using a target strategy provided by an embodiment of the present application. Fig.17 As shown, the process specifically includes S401-S406.

[0378] S401. The electronic device obtains user data of each of a plurality of users.

[0379] The multiple users include a target user, and the user data of one user includes the B domain data of the user, the O domain data of the user, and the service domain data of the user.

[0380] S402: The electronic device constructs behavior sequences of the multiple users based on the user data of the multiple users.

[0381] Optionally, after constructing the respective behavior sequences of the multiple users, the electronic device may also display the respective behavior sequences of the multiple users.

[0382] For example, Fig.18 As shown, the electronic device can display the user ID of the target user, the behavior sequence of the target user, and the time interval corresponding to the behavior sequence on its display interface. Specifically, the behavior sequence of the target user is network access → speed limit 2-4 times → cancel package → complain about network migration → query portability code → portability.

[0383] S403: The electronic device classifies the multiple users and determines the user types of the multiple users.

[0384] S404: The electronic device constructs a common behavior sequence corresponding to the target user group based on the behavior sequence of at least one user.

[0385] The at least one user is a user included in the target user group, the target data group is a user group to which the target user belongs, and the user type of the at least one user is the same as the user type of the target user.

[0386] S405: The electronic device generates a target strategy based on the common behavior sequence corresponding to the target user group.

[0387] Among them, the target strategy includes target measures.

[0388] S406: The electronic device executes target measures on the target user based on the target policy to keep the target user in a stable state.

[0389] At this point, the electronic device has realized the process of generating and using the target policy.

[0390] It is worth noting that, in actual implementation, the electronic device described in the embodiment of the present application may include one or more hardware structures and / or software modules for implementing the aforementioned corresponding strategy generation method and strategy application method, and these execution hardware structures and / or software modules may constitute an electronic device. It should be easily appreciated by those skilled in the art that, in conjunction with the algorithm steps of each example described in the embodiment applied for herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present application.

[0391] Based on this understanding, the embodiment of the present application also provides a strategy generation device. Fig.19 FIG. 1 shows a schematic diagram of the structure of a strategy generation device provided in an embodiment of the present application. Fig.19 As shown, the strategy generating device 30 may include: an acquisition module 301 and a generation module 302 .

[0392] The acquisition module 301 is used to acquire the behavior sequence of the target user, where the behavior sequence of the target user is used to represent the execution order of the user events contained in the behavior sequence of the target user.

[0393] The generation module 302 is used to generate a target policy based on the behavior sequence of the target user. The target policy is a policy corresponding to a target user group. The target user group is a user group to which the target user belongs. The user type of each user included in the target user group is the same. The user type of the target user is determined based on the user events included in the behavior sequence of the target user.

[0394] Optionally, the user events included in the behavior sequence of the target user are determined based on user data of the target user.

[0395] Optionally, the user data of the above-mentioned target user includes at least one item of the business domain data of the target user, the operation domain data of the target user and the service domain data of the target user. The business domain data of the target user is used to characterize the consumption habits of the target user, the operation domain data of the target user is used to characterize the network quality corresponding to the target user, and the service domain data of the target user is used to characterize the user perception of the target user.

[0396] Optionally, the target user's behavior sequence includes multiple user events and respective timestamps of the multiple user events, and the target user's behavior sequence is obtained by sorting the multiple user events according to respective timestamps of the multiple user events.

[0397] Optionally, the behavior sequence of the above-mentioned target user is determined based on a user behavior history graph, which includes a user node, an event node, and an edge connecting the user node and the event node, the user node is used to represent the user, the event node is used to represent the user event, and the edge is used to represent the timestamp of the user executing the user event.

[0398] Optionally, the strategy generating device 30 further includes a determining module 303 and a sorting module 304 .

[0399] The acquisition module 301 is specifically used to acquire the user identification of the target user.

[0400] The determination module 303 is used to query the user behavior history graph based on the user identifier of the target user, and determine the target user node from the user behavior history graph, wherein the node identifier of the target user node is the same as the user identifier of the target user, and the user behavior history graph includes a user node, an event node, and an edge connecting the user node and the event node, wherein the user node is used to represent the user, the event node is used to represent the user event, and the edge is used to represent the timestamp of the user executing the user event.

[0401] The determination module 303 is further configured to determine the user events represented by the multiple event nodes as the multiple user events included in the behavior sequence of the target user, wherein the multiple event nodes are event nodes having edges with the target user node.

[0402] The determination module 303 is further configured to determine the timestamps represented by each of the multiple edges as the timestamps of each of the multiple user events, wherein one edge is used to connect the target user node and one of the multiple event nodes.

[0403] The sorting module 304 is used to sort the multiple user events according to their respective timestamps to obtain the behavior sequence of the target user.

[0404] Optionally, the user events included in the above-mentioned target user's behavior sequence include negative perception events and / or subjective feedback events, wherein the negative perception event is used to characterize the passive consumption behavior corresponding to the target user, and the subjective feedback event is used to characterize the active complaint behavior corresponding to the target user.

[0405] Optionally, the target strategy is determined based on a common behavior sequence corresponding to the target user group, and the common behavior sequence corresponding to the target user group is determined based on a behavior sequence of each user included in the target user group.

[0406] Optionally, the target strategy is determined based on at least one business indicator, and the at least one business indicator is determined based on an event type of user events included in a common behavior sequence corresponding to the target user group.

[0407] Optionally, the event type of the user events included in the common behavior sequence corresponding to the target user group includes at least one of a marketing type, a wireless type, and a home broadband type.

[0408] Optionally, the above-mentioned target strategy is a strategy corresponding to a target value, and the target value is a value that matches at least one value in a numerical strategy relationship, and the at least one value is a value corresponding to the at least one business indicator. The numerical strategy relationship includes multiple values ​​and a strategy corresponding to each of the multiple values.

[0409] Optionally, the determination module 303 is used to query a numerical policy relationship based on at least one numerical value, and determine a target numerical value that matches the at least one numerical value from the numerical policy relationship, the numerical policy relationship including multiple numerical values ​​and a policy corresponding to each of the multiple numerical values, and the at least one numerical value is a numerical value corresponding to the at least one business indicator.

[0410] The determination module 303 is further configured to determine the strategy corresponding to the target value as the target strategy.

[0411] Optionally, the determination module 303 is used to determine the number of users corresponding to each of a plurality of behavior sequences, where the plurality of behavior sequences are determined based on respective behavior sequences of a plurality of users included in the target user group.

[0412] The determination module 303 is further configured to determine the behavior sequences whose corresponding number of users among the multiple behavior sequences is greater than or equal to a first number threshold as the common behavior sequences corresponding to the target user group.

[0413] Optionally, the policy generating module 30 further includes an operating module 305 .

[0414] The acquisition module 301 is further used to acquire a behavior sequence of each user among the multiple users included in the target user group;

[0415] The operation module 305 is used to perform a preset operation on at least one user event included in the behavior sequence of each user to obtain the multiple behavior sequences, wherein the execution order of the user events included in each behavior sequence in the multiple behavior sequences remains unchanged, and the preset operation includes a deletion operation.

[0416] Optionally, the above-mentioned target strategy is a strategy corresponding to a first behavior sequence, which is determined from at least one behavior sequence based on the similarity between each behavior sequence in at least one behavior sequence and the behavior sequence of the target user, and the at least one behavior sequence is a behavior sequence included in the common behavior sequence corresponding to the target user group.

[0417] Optionally, the common behavior sequences corresponding to the target user group include at least one behavior sequence.

[0418] The determination module 303 is further used to determine the similarity between each behavior sequence in the at least one behavior sequence and the behavior sequence of the target user;

[0419] The determination module 303 is further configured to determine the strategy corresponding to the first behavior sequence as the target strategy, wherein the first behavior sequence is the behavior sequence with the greatest similarity with the behavior sequence of the target user among the at least one behavior sequence.

[0420] Optionally, the common behavior sequences corresponding to the above-mentioned target user group include at least one behavior sequence, each behavior sequence in the at least one behavior sequence has the same similarity with the behavior sequence of the target user, and the target strategy is a strategy corresponding to a second behavior sequence, which is determined from the at least one behavior sequence based on the event difference corresponding to each behavior sequence in the at least one behavior sequence, wherein the event difference corresponding to a behavior sequence is determined based on the number of user events between each user event included in the behavior sequence and the last user event included in the behavior sequence of the target user.

[0421] Optionally, the determination module 303 is further configured to determine an event difference corresponding to each behavior sequence in the at least one behavior sequence.

[0422] The determination module 303 is further configured to determine the behavior sequence with the smallest corresponding event difference in the at least one behavior sequence as the second behavior sequence.

[0423] Optionally, the determination module 303 is configured to determine that the target user event is a key event if the number of users corresponding to the target user event is greater than or equal to a second number threshold, and the target user event is a user event included in the common behavior sequence corresponding to the target user group.

[0424] Optionally, the common behavior sequence corresponding to the target user group includes at least two behavior sequences, the target user event is a user event included in the converged behavior sequence corresponding to the target user group, and the converged behavior sequence corresponding to the target user group is determined based on the at least two behavior sequences.

[0425] Optionally, the strategy generation method 30 further includes a processing module 306 .

[0426] The processing module 306 is used to perform aggregation processing on the same user events included in the at least two behavior sequences.

[0427] The sorting module 304 is used to sort the different user events included in the at least two behavior sequences according to the order of timestamps to obtain the aggregated behavior sequence corresponding to the target user group.

[0428] Optionally, the number of users corresponding to the above-mentioned target user event is determined based on a common behavior history graph, which includes at least two event nodes and an edge connecting the at least two event nodes, one event node is used to represent a user event, and the edge is used to represent the number of users corresponding to the downstream event node connected to the edge.

[0429] Optionally, the acquisition module 301 is used to acquire an event identifier of the target user event.

[0430] Determination module 303 is also used to query the common behavior history graph based on the event identifier of the target user event, and determine the target event node from the common behavior history graph, the node identifier of the target event node is the same as the event identifier of the target user event, and the common behavior history graph includes at least two event nodes and an edge connecting the at least two event nodes, one event node is used to represent a user event, and the edge is used to represent the number of users corresponding to the downstream event node connected to the edge.

[0431] The determination module 303 is further configured to determine the number of users represented by the target edge as the number of users corresponding to the target user event, and the downstream event node connected to the target edge is the target event node.

[0432] Optionally, the user type of the target user is used to characterize the grouping information of the target user, and the grouping information of the target user includes one or more of the location information of the target user, the perception type corresponding to the target user, the risk level of the target user, the age of the target user and the gender of the target user.

[0433] As described above, the embodiment of the present application can divide the functional modules of the policy generation device according to the above method example. Among them, the above integrated modules can be implemented in the form of hardware or in the form of software functional modules. In addition, it should be noted that the division of modules in the embodiment of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation. For example, each functional module can be divided according to each function, or two or more functions can be integrated into one processing module.

[0434] Regarding the strategy generating device in the above embodiment, the specific manner in which each module performs operations and the beneficial effects possessed have been described in detail in the above method embodiment and will not be repeated here.

[0435] Fig. 20 is a schematic diagram of the structure of another strategy generation device provided by the present application. Fig. 20 The strategy generating device 40 may include at least one processor 401 and a memory 403 for storing processor executable instructions. The processor 401 is configured to execute instructions in the memory 403 to implement the strategy generating method in the above embodiment.

[0436] In addition, the policy generating device 40 may further include a communication bus 402 and at least one communication interface 404 .

[0437] The processor 401 may be a central processing unit (CPU), a microprocessing unit, an ASIC, or one or more integrated circuits for controlling the execution of the program of the present application.

[0438] Communication bus 402 may include a pathway for transmitting information between the above-mentioned components.

[0439] The communication interface 404 uses any transceiver or other device for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.

[0440] The memory 403 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of an instruction or data structure and can be accessed by a computer, but is not limited thereto. The memory may exist independently and be connected to the processing unit through a bus. The memory may also be integrated with the processing unit.

[0441] The memory 403 is used to store instructions for executing the solution of the present application, and the execution is controlled by the processor 401. The processor 401 is used to execute the instructions stored in the memory 403, so as to realize the functions in the method of the present application.

[0442] In a specific implementation, as an embodiment, the processor 401 may include one or more CPUs, such as Fig. 20 CPU0 and CPU1 in.

[0443] In a specific implementation, as an embodiment, the strategy generating device 40 may include multiple processors, such as Fig. 20 401 and processor 407 in the embodiment of the present invention. Each of these processors may be a single-CPU processor or a multi-CPU processor. The processor herein may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0444] In a specific implementation, as an embodiment, the policy generation device 40 may further include an output device 405 and an input device 406. The output device 405 communicates with the processor 401 and may display information in a variety of ways. For example, the output device 405 may be a liquid crystal display (LCD), a light emitting diode (LED) display device, a cathode ray tube (CRT) display device, or a projector. The input device 406 communicates with the processor 401 and may receive user input in a variety of ways. For example, the input device 406 may be a mouse, a keyboard, a touch screen device, or a sensor device.

[0445] In an optional implementation, the embodiment of the present application further provides a policy application device. Fig.21 FIG. 1 shows a schematic diagram of the structure of the policy application device provided in an embodiment of the present application. Fig.21 As shown, the policy application device 50 may include: an acquisition module 501 and an execution module 502 .

[0446] The acquisition module 501 is used to acquire a target policy, which includes target measures. The target policy is a policy corresponding to a target user group. The target user group is a user group to which a target user belongs. Each user included in the target user group has the same user type. The user type of the target user is determined based on user events included in a behavior sequence of the target user. The behavior sequence of the target user is used to characterize the execution order of user events included in the behavior sequence of the target user.

[0447] The execution module 502 is used to execute the target measure on the target user based on the target strategy, so that the target user is in a stable state.

[0448] Optionally, the user events included in the behavior sequence of the target user are determined based on user data of the target user.

[0449] Optionally, the user data of the above-mentioned target user includes at least one item of the business domain data of the target user, the operation domain data of the target user and the service domain data of the target user. The business domain data of the target user is used to characterize the consumption habits of the target user, the operation domain data of the target user is used to characterize the network quality corresponding to the target user, and the service domain data of the target user is used to characterize the user perception of the target user.

[0450] Optionally, the target user's behavior sequence includes multiple user events and respective timestamps of the multiple user events, and the target user's behavior sequence is obtained by sorting the multiple user events according to respective timestamps of the multiple user events.

[0451] Optionally, the behavior sequence of the above-mentioned target user is determined based on a user behavior history graph, which includes a user node, an event node, and an edge connecting the user node and the event node, the user node is used to represent the user, the event node is used to represent the user event, and the edge is used to represent the timestamp of the user executing the user event.

[0452] Optionally, the policy application device 50 further includes a determination module 503 and a sorting module 504 .

[0453] The acquisition module 501 is specifically used to acquire the user identification of the target user.

[0454] Determination module 503 is used to query the user behavior history graph based on the user identifier of the target user, and determine the target user node from the user behavior history graph, the node identifier of the target user node is the same as the user identifier of the target user, and the user behavior history graph includes a user node, an event node, and an edge connecting the user node and the event node, the user node is used to represent the user, the event node is used to represent the user event, and the edge is used to represent the timestamp of the user executing the user event.

[0455] The determination module 503 is further configured to determine the user events represented by the multiple event nodes as the multiple user events included in the behavior sequence of the target user, wherein the multiple event nodes are event nodes having edges with the target user node.

[0456] The determination module 503 is further configured to determine the timestamps represented by each of the multiple edges as the timestamps of each of the multiple user events, wherein one edge is used to connect the target user node and one of the multiple event nodes.

[0457] The sorting module 504 is used to sort the multiple user events according to their respective timestamps to obtain the behavior sequence of the target user.

[0458] Optionally, the user events included in the above-mentioned target user's behavior sequence include negative perception events and / or subjective feedback events, wherein the negative perception event is used to characterize the passive consumption behavior corresponding to the target user, and the subjective feedback event is used to characterize the active complaint behavior corresponding to the target user.

[0459] Optionally, the target strategy is determined based on a common behavior sequence corresponding to the target user group, and the common behavior sequence corresponding to the target user group is determined based on a behavior sequence of each user included in the target user group.

[0460] Optionally, the target strategy is determined based on at least one business indicator, and the at least one business indicator is determined based on an event type of user events included in a common behavior sequence corresponding to the target user group.

[0461] Optionally, the event type of the user events included in the common behavior sequence corresponding to the target user group includes at least one of a marketing type, a wireless type, and a home broadband type.

[0462] Optionally, the above-mentioned target strategy is a strategy corresponding to a target value, and the target value is a value that matches at least one value in a numerical strategy relationship, and the at least one value is a value corresponding to the at least one business indicator. The numerical strategy relationship includes multiple values ​​and a strategy corresponding to each of the multiple values.

[0463] Optionally, the determination module 503 is used to query a numerical policy relationship based on at least one numerical value, and determine a target numerical value that matches the at least one numerical value from the numerical policy relationship, the numerical policy relationship including multiple numerical values ​​and a policy corresponding to each of the multiple numerical values, and the at least one numerical value is a numerical value corresponding to the at least one business indicator.

[0464] The determination module 503 is further configured to determine the strategy corresponding to the target value as the target strategy.

[0465] Optionally, the determination module 503 is used to determine the number of users corresponding to each of a plurality of behavior sequences, where the plurality of behavior sequences are determined based on respective behavior sequences of a plurality of users included in the target user group.

[0466] The determination module 503 is further configured to determine the behavior sequences whose corresponding number of users among the multiple behavior sequences is greater than or equal to a first number threshold as the common behavior sequences corresponding to the target user group.

[0467] Optionally, the policy application module 50 also includes an operation module 505 .

[0468] The acquisition module 501 is further configured to acquire a behavior sequence of each user among the multiple users included in the target user group.

[0469] The operation module 505 is used to perform a preset operation on at least one user event included in the behavior sequence of each user to obtain the multiple behavior sequences, wherein the execution order of the user events included in each behavior sequence in the multiple behavior sequences remains unchanged, and the preset operation includes a deletion operation.

[0470] Optionally, the above-mentioned target strategy is a strategy corresponding to a first behavior sequence, which is determined from at least one behavior sequence based on the similarity between each behavior sequence in at least one behavior sequence and the behavior sequence of the target user, and the at least one behavior sequence is a behavior sequence included in the common behavior sequence corresponding to the target user group.

[0471] Optionally, the common behavior sequences corresponding to the target user group include at least one behavior sequence.

[0472] The determination module 503 is further configured to determine the similarity between each behavior sequence in the at least one behavior sequence and the behavior sequence of the target user.

[0473] The determination module 503 is further configured to determine the strategy corresponding to the first behavior sequence as the target strategy, wherein the first behavior sequence is the behavior sequence with the greatest similarity with the behavior sequence of the target user among the at least one behavior sequence.

[0474] Optionally, the common behavior sequences corresponding to the above-mentioned target user group include at least one behavior sequence, each behavior sequence in the at least one behavior sequence has the same similarity with the behavior sequence of the target user, and the target strategy is a strategy corresponding to a second behavior sequence, which is determined from the at least one behavior sequence based on the event difference corresponding to each behavior sequence in the at least one behavior sequence, wherein the event difference corresponding to a behavior sequence is determined based on the number of user events between each user event included in the behavior sequence and the last user event included in the behavior sequence of the target user.

[0475] Optionally, the determination module 503 is further configured to determine an event difference corresponding to each behavior sequence in the at least one behavior sequence.

[0476] The determination module 503 is further configured to determine the behavior sequence with the smallest corresponding event difference in the at least one behavior sequence as the second behavior sequence.

[0477] Optionally, the determination module 503 is configured to determine that the target user event is a key event if the number of users corresponding to the target user event is greater than or equal to a second number threshold, and the target user event is a user event included in the common behavior sequence corresponding to the target user group.

[0478] Optionally, the common behavior sequence corresponding to the target user group includes at least two behavior sequences, the target user event is a user event included in the converged behavior sequence corresponding to the target user group, and the converged behavior sequence corresponding to the target user group is determined based on the at least two behavior sequences.

[0479] Optionally, the policy application device 50 also includes a processing module 506.

[0480] The processing module 506 is used to perform aggregation processing on the same user events included in the at least two behavior sequences.

[0481] The sorting module 504 is used to sort the different user events included in the at least two behavior sequences according to the order of timestamps to obtain a converged behavior sequence corresponding to the target user group.

[0482] Optionally, the number of users corresponding to the above-mentioned target user event is determined based on a common behavior history graph, which includes at least two event nodes and an edge connecting the at least two event nodes, one event node is used to represent a user event, and the edge is used to represent the number of users corresponding to the downstream event node connected to the edge.

[0483] Optionally, the acquisition module 501 is used to acquire an event identifier of the target user event.

[0484] Determination module 503 is also used to query the common behavior history graph based on the event identifier of the target user event, and determine the target event node from the common behavior history graph, the node identifier of the target event node is the same as the event identifier of the target user event, and the common behavior history graph includes at least two event nodes and an edge connecting the at least two event nodes, one event node is used to represent a user event, and the edge is used to represent the number of users corresponding to the downstream event node connected to the edge.

[0485] The determination module 503 is further configured to determine the number of users represented by the target edge as the number of users corresponding to the target user event, and the downstream event node connected to the target edge is the target event node.

[0486] Optionally, the user type of the target user is used to characterize the grouping information of the target user, and the grouping information of the target user includes one or more of the location information of the target user, the perception type corresponding to the target user, the risk level of the target user, the age of the target user and the gender of the target user.

[0487] Fig. 22 is a schematic diagram of the structure of another strategy application device provided by the present application. Fig. 22 The policy application device 60 may include at least one processor 601 and a memory 603 for storing processor executable instructions. The processor 601 is configured to execute instructions in the memory 603 to implement the policy generation method in the above embodiment.

[0488] In addition, the policy generating device 60 may further include a communication bus 602 and at least one communication interface 604 .

[0489] The processor 601 may be a central processing unit (CPU), a microprocessing unit, an ASIC, or one or more integrated circuits for controlling the execution of the program of the present application.

[0490] Communication bus 602 may include a pathway for transmitting information between the above-mentioned components.

[0491] The communication interface 604 uses any transceiver or other device for communicating with other devices or communication networks, such as Ethernet, RAN, WLAN, etc.

[0492] The memory 603 may be a ROM or other types of static storage devices that can store static information and instructions, a RAM or other types of dynamic storage devices that can store information and instructions, or an EEPROM, a CD-ROM or other optical disk storage, an optical disk storage (including a compressed optical disk, a laser disk, an optical disk, a digital versatile disk, a Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of an instruction or data structure and can be accessed by a computer, but is not limited thereto. The memory may exist independently and be connected to the processing unit via a bus. The memory may also be integrated with the processing unit.

[0493] The memory 603 is used to store instructions for executing the solution of the present application, and the execution is controlled by the processor 601. The processor 601 is used to execute the instructions stored in the memory 603, so as to realize the functions in the method of the present application.

[0494] In a specific implementation, as an embodiment, the processor 601 may include one or more CPUs, such as Fig. 22 CPU0 and CPU1 in.

[0495] In a specific implementation, as an embodiment, the strategy generating device 60 may include multiple processors, such as Fig. 22 601 and processor 607 in FIG. Each of these processors may be a single-CPU processor or a multi-CPU processor. A processor herein may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0496] In a specific implementation, as an embodiment, the policy generating device 60 may further include an output device 605 and an input device 606. The output device 605 communicates with the processor 601 and may display information in a variety of ways. For example, the output device 605 may be an LCD, LED display device, CRT display device, or a projector. The input device 606 communicates with the processor 601 and may receive user input in a variety of ways. For example, the input device 606 may be a mouse, a keyboard, a touch screen device, or a sensor device.

[0497] Those skilled in the art will understand that Fig. 20 The structure shown in the above does not constitute a limitation on the strategy generation device and Fig. 22 The structure shown in the figure does not constitute a limitation on the policy application device, and may include more or less components than those shown in the figure, or combine certain components, or adopt a different component arrangement.

[0498] In addition, the present application also provides a computer-readable storage medium, including instructions, which, when executed by an electronic device, enable the electronic device to execute the policy generation method and policy application method provided in the above embodiments.

[0499] In addition, the present application also provides a computer program product, including instructions, which, when executed by an electronic device, enable the electronic device to execute the policy generation method and policy application method provided in the above embodiments.

[0500] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the claims.

Claims

1. A strategy generation method, characterized in that: The method comprises: Acquire a behavior sequence of a target user, where the behavior sequence of the target user is used to represent an execution order of user events contained in the behavior sequence of the target user; Based on the behavior sequence of the target user, a target policy is generated, where the target policy is a policy corresponding to a target user group, where the target user group is a user group to which the target user belongs, where each user included in the target user group has the same user type, and where the user type of the target user is determined based on a user event included in the behavior sequence of the target user.

2. The strategy generation method according to claim 1, characterized in that: The user events included in the behavior sequence of the target user are determined based on the user data of the target user.

3. The strategy generation method according to claim 2, characterized in that: The user data of the target user includes at least one of the business domain data of the target user, the operation domain data of the target user, and the service domain data of the target user. The business domain data of the target user is used to characterize the consumption habits of the target user, the operation domain data of the target user is used to characterize the network quality corresponding to the target user, and the service domain data of the target user is used to characterize the user perception of the target user.

4. The strategy generation method according to any one of claims 1 to 3, characterized in that: The target user's behavior sequence includes multiple user events and respective timestamps of the multiple user events. The target user's behavior sequence is obtained by sorting the multiple user events according to respective timestamps of the multiple user events.

5. The strategy generation method according to any one of claims 1 to 4, characterized in that: The behavior sequence of the target user is determined based on a user behavior history graph, which includes a user node, an event node, and an edge connecting the user node and the event node. The user node is used to represent the user, the event node is used to represent the user event, and the edge is used to represent the timestamp of the user executing the user event.

6. The strategy generation method according to any one of claims 1 to 5, characterized in that: The step of obtaining the target user's behavior sequence includes: Obtaining a user ID of the target user; querying a user behavior history graph based on the user identifier of the target user, determining a target user node from the user behavior history graph, wherein the node identifier of the target user node is the same as the user identifier of the target user, and the user behavior history graph includes a user node, an event node, and an edge connecting the user node and the event node, wherein the user node is used to represent the user, the event node is used to represent the user event, and the edge is used to represent the timestamp of the user executing the user event; Determine user events represented by a plurality of event nodes as a plurality of user events included in the behavior sequence of the target user, wherein the plurality of event nodes are event nodes having edges with the target user node; Determine the timestamps represented by each of the multiple edges as the timestamps of each of the multiple user events, wherein one edge is used to connect the target user node and one of the multiple event nodes; The multiple user events are sorted according to their respective timestamps to obtain a behavior sequence of the target user.

7. The strategy generation method according to any one of claims 1 to 6, characterized in that: The user events included in the behavior sequence of the target user include negative perception events and / or subjective feedback events, wherein the negative perception events are used to characterize the passive consumption behavior corresponding to the target user, and the subjective feedback events are used to characterize the active complaint behavior corresponding to the target user.

8. The strategy generation method according to any one of claims 1 to 7, characterized in that: The target strategy is determined based on a common behavior sequence corresponding to the target user group, and the common behavior sequence corresponding to the target user group is determined based on a behavior sequence of each user included in the target user group.

9. The strategy generation method according to claim 8, characterized in that: The target strategy is determined based on at least one business indicator, and the at least one business indicator is determined based on an event type of user events included in a common behavior sequence corresponding to the target user group.

10. The strategy generation method according to claim 9, characterized in that: The event type of the user events included in the common behavior sequence corresponding to the target user group includes at least one of a marketing type, a wireless type, and a home broadband type.

11. The strategy generation method according to claim 9 or 10, characterized in that: The target strategy is a strategy corresponding to a target value, the target value is a value that matches at least one value in a value strategy relationship, the at least one value is a value corresponding to the at least one business indicator, and the value strategy relationship includes multiple values ​​and a strategy corresponding to each of the multiple values.

12. The strategy generation method according to any one of claims 9 to 11, characterized in that: The method further comprises: Querying a numerical policy relationship based on at least one numerical value, and determining a target numerical value matching the at least one numerical value from the numerical policy relationship, wherein the numerical policy relationship includes a plurality of numerical values ​​and a policy corresponding to each of the plurality of numerical values, and the at least one numerical value is a numerical value corresponding to the at least one business indicator; The strategy corresponding to the target value is determined as the target strategy.

13. The strategy generation method according to claim 8, characterized in that: The method further comprises: Determining the number of users corresponding to each of a plurality of behavior sequences, wherein the plurality of behavior sequences are determined based on the respective behavior sequences of a plurality of users included in the target user group; The behavior sequences corresponding to the number of users greater than or equal to the first number threshold among the multiple behavior sequences are determined as the common behavior sequences corresponding to the target user group.

14. The strategy generation method according to claim 13, characterized in that: The method further comprises: Acquire a behavior sequence of each user among a plurality of users included in the target user group; A preset operation is performed on at least one user event included in the behavior sequence of each user to obtain the multiple behavior sequences, wherein the execution order of the user events included in each behavior sequence in the multiple behavior sequences remains unchanged, and the preset operation includes a deletion operation.

15. The strategy generation method according to claim 13 or 14, characterized in that: The target strategy is a strategy corresponding to a first behavior sequence, and the first behavior sequence is determined from the at least one behavior sequence based on the similarity between each behavior sequence in the at least one behavior sequence and the behavior sequence of the target user, and the at least one behavior sequence is a behavior sequence included in the common behavior sequence corresponding to the target user group.

16. The strategy generation method according to any one of claims 13 to 15, characterized in that: The common behavior sequences corresponding to the target user group include at least one behavior sequence, and the method further includes: Determining a similarity between each behavior sequence in the at least one behavior sequence and a behavior sequence of the target user; The strategy corresponding to the first behavior sequence is determined as the target strategy, wherein the first behavior sequence is the behavior sequence with the greatest similarity to the behavior sequence of the target user among the at least one behavior sequence.

17. The strategy generation method according to any one of claims 13 to 16, characterized in that: The common behavior sequences corresponding to the target user group include at least one behavior sequence, each behavior sequence in the at least one behavior sequence has the same similarity with the behavior sequence of the target user, the target strategy is a strategy corresponding to a second behavior sequence, and the second behavior sequence is determined from the at least one behavior sequence based on the event difference corresponding to each behavior sequence in the at least one behavior sequence, wherein the event difference corresponding to a behavior sequence is determined based on the number of user events between each user event included in the behavior sequence and the last user event included in the behavior sequence of the target user.

18. The strategy generation method according to claim 17, characterized in that: The method further comprises: Determining an event difference corresponding to each behavior sequence in the at least one behavior sequence; The behavior sequence with the smallest corresponding event difference in the at least one behavior sequence is determined as the second behavior sequence.

19. The strategy generation method according to claim 8, characterized in that: The method further comprises: If the number of users corresponding to the target user event is greater than or equal to the second number threshold, the target user event is determined to be a key event, and the target user event is a user event included in the common behavior sequence corresponding to the target user group.

20. The strategy generation method according to claim 19, characterized in that: The common behavior sequence corresponding to the target user group includes at least two behavior sequences, the target user event is a user event included in the converged behavior sequence corresponding to the target user group, and the converged behavior sequence corresponding to the target user group is determined based on the at least two behavior sequences.

21. The strategy generation method according to claim 20, characterized in that: The method further comprises: The same user events included in the at least two behavior sequences are aggregated, and the different user events included in the at least two behavior sequences are sorted in chronological order of timestamps to obtain an aggregated behavior sequence corresponding to the target user group.

22. The strategy generation method according to any one of claims 19 to 21, characterized in that: The number of users corresponding to the target user event is determined based on a common behavior history graph, which includes at least two event nodes and an edge connecting the at least two event nodes. An event node is used to represent a user event, and the edge is used to represent the number of users corresponding to the downstream event node connected by the edge.

23. The strategy generation method according to any one of claims 19 to 22, characterized in that: The method further comprises: Obtaining an event identifier of the target user event; Based on the event identifier of the target user event, a common behavior history graph is queried, and a target event node is determined from the common behavior history graph, wherein the node identifier of the target event node is the same as the event identifier of the target user event, and the common behavior history graph includes at least two event nodes and an edge connecting the at least two event nodes, wherein one event node is used to represent one user event, and the edge is used to represent the number of users corresponding to the downstream event node connected by the edge; The number of users represented by the target edge is determined as the number of users corresponding to the target user event, and the downstream event node connected by the target edge is the target event node.

24. The strategy generation method according to any one of claims 1 to 23, characterized in that: The user type of the target user is used to characterize the grouping information of the target user, and the grouping information of the target user includes one or more of the location information of the target user, the perception type corresponding to the target user, the risk level of the target user, the age of the target user, and the gender of the target user.

25. A strategy application method, characterized in that: The method comprises: Acquire a target policy, wherein the target policy includes a target measure, the target policy is a policy corresponding to a target user group, the target user group is a user group to which a target user belongs, each user included in the target user group has the same user type, the user type of the target user is determined based on a user event included in a behavior sequence of the target user, and the behavior sequence of the target user is used to characterize an execution order of the user events included in the behavior sequence of the target user; The target measure is executed on the target user based on the target policy, so that the target user is in a stable state.

26. A strategy generating device, characterized in that: include: Get modules and generate modules; The acquisition module is used to acquire a behavior sequence of a target user, where the behavior sequence of the target user is used to represent an execution order of user events included in the behavior sequence of the target user; The generating module is used to generate a target policy based on the behavior sequence of the target user, where the target policy is a policy corresponding to a target user group, where the target user group is a user group to which the target user belongs, where each user included in the target user group has the same user type, and where the user type of the target user is determined based on a user event included in the behavior sequence of the target user.

27. A strategy application device, characterized in that: include: Get module and execute module; The acquisition module is used to acquire a target policy, wherein the target policy includes a target measure, and the target policy is a policy corresponding to a target user group, wherein the target user group is a user group to which the target user belongs, and each user included in the target user group has the same user type, and the user type of the target user is determined based on a user event included in a behavior sequence of the target user, and the behavior sequence of the target user is used to characterize an execution order of the user events included in the behavior sequence of the target user; The execution module is used to execute the target measure on the target user based on the target strategy, so that the target user is in a stable state.

28. An electronic device, characterized in that: The electronic device comprises: Memory; Communication interface; one or more processors; Wherein, one or more computer programs are stored in the memory, and the one or more computer programs include instructions. When the instructions are executed by the electronic device, the electronic device executes the policy generation method as described in any one of claims 1 to 24, or executes the policy application method as described in claim 25.

29. A computer-readable storage medium, characterized in that: It comprises computer instructions, which, when executed on an electronic device, enable the electronic device to execute the policy generation method as claimed in any one of claims 1 to 24, or execute the policy application method as claimed in claim 25.

30. A computer program product comprising instructions, characterized in that When the instruction is executed on an electronic device, the electronic device executes the policy generating method as described in any one of claims 1 to 24, or executes the policy applying method as described in claim 25.

Images