WO2024087752A1

WO2024087752A1 - User preference analysis method and apparatus

Info

Publication number: WO2024087752A1
Application number: PCT/CN2023/108058
Authority: WO
Inventors: 朱永军; 谭耀斌
Original assignee: 中兴通讯股份有限公司
Priority date: 2022-10-24
Filing date: 2023-07-19
Publication date: 2024-05-02
Also published as: CN117972184A

Abstract

The embodiments of the present application disclose a user preference analysis method and apparatus. The method comprises: in response to an execution instruction from a target user with regard to a target event, determining a target user type of the target user; matching the target user type with a pre-created preference database, and determining target event preference data corresponding to the target user type so as to execute the target event according to the target event preference data; wherein the preference database comprises corresponding relationships between a plurality of user types and event preference data; and the event preference data comprises intention preference data and policy preference data of an execution event.

Description

User preference analysis method and device

CROSS-REFERENCE TO RELATED APPLICATIONS

This application claims the priority of the Chinese patent application filed with the China Patent Office on October 24, 2022, with application number 202211304560.7 and invention name “User Preference Analysis Method and Device”. The entire contents of the Chinese patent application are incorporated herein by reference.

Technical Field

The present invention relates to the field of data analysis technology, and in particular to a method and device for analyzing user preferences.

Background technique

Intent-Based Network (IBN) is a closed-loop network architecture that is built and operated based on human business intent while mastering its own "holographic state". It realizes the automatic conversion from user intent to specific infrastructure, and can monitor the overall performance of the network, identify problems in the network and automatically solve the problems without human intervention. IBN includes functions such as intent translation and verification, automatic implementation, perception of network status, assurance, and dynamic optimization/repair. Among them, intent translation realizes the conversion of the user's natural language expression of intent into network-recognizable intent, which is a key link to ensure IBN. Therefore, how to accurately analyze user intent (i.e. user preference) is a major problem in the current field.

In the related art, when using IBN to execute related events, specific problems are usually solved based on the same logical operations without considering user intent (i.e., user preference), resulting in a mismatch between the event execution results and the user's intent/preference, which in turn causes the user to be dissatisfied with the event execution results.

Summary of the invention

The purpose of the embodiments of the present application is to provide a user preference analysis method and device to solve the problem in the prior art that user intentions cannot be accurately analyzed when using an intent network.

To solve the above technical problems, the embodiments of the present application are implemented as follows.

On the one hand, the embodiment of the present application provides a user preference analysis method, comprising: in response to an execution instruction of a target user for a target event, determining a target user type of the target user; The target user type is matched with a pre-created preference database to determine the target event preference data corresponding to the target user type, so as to execute the target event according to the target event preference data; the preference database includes a correspondence between multiple user types and event preference data; the event preference data includes intention preference data and strategy preference data for executing the event.

On the other hand, an embodiment of the present application provides a user preference analysis device, comprising: a first determination module, used to determine the target user type of the target user in response to the target user's execution instruction for the target event; a second determination module, used to match the target user type with a pre-created preference database, and determine the target event preference data corresponding to the target user type, so as to execute the target event according to the target event preference data; the preference database includes a correspondence between multiple user types and event preference data; the event preference data includes intention preference data and strategy preference data for executing the event.

On the other hand, an embodiment of the present application provides an electronic device, including a processor and a memory electrically connected to the processor, the memory storing a computer program, and the processor being used to call and execute the computer program from the memory to implement the above-mentioned user preference analysis method.

On the other hand, an embodiment of the present application provides a storage medium for storing a computer program, wherein the computer program can be executed by a processor to implement the above-mentioned user preference analysis method.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to more clearly illustrate one or more embodiments of this specification or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in one or more embodiments of this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

FIG1 is a schematic flow chart of a method for analyzing user preferences according to an embodiment of the present specification;

FIG2 is a schematic flow chart of a method for analyzing event preference data according to an embodiment of this specification;

FIG3 is a schematic flow chart of executing an event based on a user preference analysis method according to an embodiment of this specification;

FIG4 is a schematic block diagram of a user preference analysis device according to an embodiment of this specification;

FIG5 is a schematic block diagram of an electronic device according to an embodiment of this specification.

Detailed ways

In order to enable those skilled in the art to better understand the technical solutions in the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work should fall within the scope of protection of the present application.

The embodiments of the present application provide a user preference analysis method and device to solve the problem in the prior art that user intent cannot be accurately analyzed when using an intent network.

Taking the communication network scenario as an example, in the planning, construction, maintenance, optimization and operation process of the communication network, the application intention network architecture interacts with the operator users. Different regions and operators have different investment and construction strategies for the network, and there are also role divisions with different intentions for the construction and development of the network within the same operator, such as marketing personnel focusing on the return on investment of the network, and network optimization personnel paying more attention to the completion of the network (such as network coverage performance indicators, user complaints, etc.). These roles have different intentional needs for the network, so it is not suitable to use the same intention network process to deal with all users. It is necessary to give matching intention preferences and policy preferences to these user roles in the intention network process to help improve the efficiency of interaction using the intention network, as well as user satisfaction with the final landing plan. The intention preference here refers to the user's tendency to the intention target, such as the network construction target and construction scale in the communication network scenario. Policy preference refers to the different methods that different user roles expect to use when achieving the same goal. The user preference analysis method provided in the embodiment of the present application is described in detail below.

FIG1 is a schematic flow chart of a method for analyzing user preferences according to an embodiment of the present application. As shown in FIG1 , the method includes the following steps.

S102: In response to an execution instruction of a target event by a target user, determining a target user type of the target user.

Among them, user types can be divided based on different classification dimensions, and the classification dimensions may include at least one of the user's region, user identity, user personal information, user's business position, and user's business development plan. Taking the communication network scenario as an example, user types can be divided according to at least one of the user's network region, operator attributes, job position, and network development strategy. For example, by classifying users based on information such as the user's network region, user's department, and job position, the user type can be determined as: wireless network planning engineer in area A, communication network optimization engineer in area B, and C. Local market sales personnel, etc.

S104, matching the target user type with a pre-created preference database, determining the target event preference data corresponding to the target user type, so as to execute the target event according to the target event preference data; the preference database includes a correspondence between multiple user types and event preference data; the event preference data includes intention preference data and strategy preference data for executing the event.

Among them, the intention preference data may include: the first contribution of each preference influencing factor to the intention preference; the strategy preference data includes: the second contribution of each preference influencing factor to the strategy preference. Preference influencing factors refer to factors that may affect event preference data, which can be determined based on the user's execution intention for the event (referred to as event execution intention) and/or event scenario. The creation method of the preference database will be described in detail in the following embodiments and will not be repeated here.

In this embodiment, after the target event preference data corresponding to the target user type is determined, the target event may be executed immediately according to the target event preference data, or the target event may not be executed temporarily.

Optionally, the execution instruction for the target event carries the event execution time, and after determining the target event preference data corresponding to the target user type, the target event is executed according to the event execution time. Optionally, after determining the target event preference data corresponding to the target user type, the target event is not executed, and after obtaining the target user's confirmation information on the target event preference data, the target event is executed.

Adopting the technical solution of the embodiment of the present application, when receiving the execution instruction of the target event from the target user, by determining the target user type and matching the target user type with the pre-created preference database, the target event preference data corresponding to the target user type is determined, so as to execute the target event according to the target event preference data. Among them, the preference database includes the correspondence between multiple user types and event preference data, and the event preference data includes the intention preference data and strategy preference data of the execution event. Since the user type is used to determine the event preference data of the user, the event preference data of different user types can be analyzed in a targeted manner for different types of users, so that the determination result of the event preference data is more accurate. Furthermore, when executing the target event according to the event preference data of the target user, not only the event execution efficiency is improved, but also the strategy adopted when executing the event can be more matched with the event preference data (including intention preference and strategy preference) of the target user, so that the event execution result can achieve the user's satisfaction to the greatest extent.

In one embodiment, in the preference database, the correspondence between user type and event preference data includes: a first correspondence between user type and intention preference data, and a second correspondence between intention preference data and strategy preference data. Based on this, the target user type is matched with the pre-created preference database to determine the target event preference data corresponding to the target user type. When, the target user type and the first corresponding relationship are matched first to determine the target intention preference data corresponding to the target user type; secondly, the target intention preference data and the second corresponding relationship are matched to determine the target strategy preference data corresponding to the target intention preference data, wherein the target event preference data includes target intention preference data and target strategy preference data.

In this embodiment, the first correspondence between the user type and the intention preference data is used to characterize the intention preference of the user of the user type when executing the event, that is, the intention target to be achieved when executing the event. The second correspondence between the intention preference data and the strategy preference data is used to characterize the execution strategy that the user tends to when he wants to achieve his intention target (i.e., intention preference) when executing the event. Therefore, by first matching the target user type with the first correspondence, the intention preference data of the target user when executing the target event can be matched, that is, the intention target that the target user wants to achieve when executing the target event is determined, and then the matched intention preference data is matched with the second correspondence, and the execution strategy (i.e., strategy preference) that the target user tends to when he wants to achieve his intention target when executing the target event can be matched, so that according to the target user type of the target user, the intention preference and strategy preference of the target user for executing the target event can be analyzed in a targeted and accurate manner, and then, when executing the target event according to the event preference data of the target user, not only the event execution efficiency is improved, but also the strategy adopted when executing the event can be more matched with the event preference data of the target user, so that the event execution result can maximize the satisfaction of the target user.

In one embodiment, before determining the target user type in response to the target user's execution instruction for the target event, a preference database is created in advance, and event preference data corresponding to multiple user types are stored in the preference database, so that the preference database can be used to accurately analyze the target user's event preference data subsequently.

Optionally, the method for adding event preference data corresponding to a user type in a preference database may include steps S201 - S203 as shown in FIG. 2 .

S201, obtaining historical event information of sample users, the historical event information including at least one of the following: user information of the sample user, event influencing factors of historical events, event scenarios, event execution time, event execution intention, event execution strategy, event execution results, and initial satisfaction of the sample user with the event execution results.

The user information of the sample user may include at least one of the user identity, geographic location information, user personal information, user business position information, user business development plan information, etc. of the sample user. A historical event is an event that the sample user has completed, and the event execution result of the historical event is known. The event influencing factor of the historical event refers to the influence of the sample user on the event of the historical event. The factors that may affect the event preference data can be determined based on the sample user's execution intention for historical events (referred to as event execution intention) and/or the event scenario of the historical event. Event scenario refers to the scenario involved in executing an event. Event execution intention is the intended target of the sample user to execute the historical event, such as 5G outdoor coverage of 95%, existing high-speed rail coverage of 10%, etc. Event execution strategy is the strategy adopted by the sample user to execute historical events, such as site planning, macro site reuse, etc.; event execution strategy may include recommendation strategy and final selection strategy. In addition to the above information, historical event information may also include the execution plan adopted by the sample user when executing the historical event based on the final selection strategy. The execution plan matches the final selection strategy, and the execution plan is more specific and detailed than the final selection strategy. The sample user's initial satisfaction with the event execution result can be understood as the score given by the sample user to the event execution result from a subjective perspective, such as a value between 0 and 1.

Taking the communication network application scenario as an example, assuming that the sample user's event execution intention for network events is "5G outdoor coverage reaches 95%", the corresponding event influencing factors may include: improving network performance indicators, coverage, etc. The system sends policies (i.e., recommended policies) including site planning, macro station reuse or new macro station construction. The final selected policies are site planning and macro station reuse. The execution plan taken for executing historical events is: planning 3,000 macro stations. The event execution result is: the coverage rate is 80%, and the intended target is not achieved. The sample user's initial satisfaction with the event execution result is 0.

S202: Determine the user type of the sample user based on the historical event information, and analyze the event preference data of the sample user in executing the historical events.

Among them, the user type can be divided based on different classification dimensions, and the classification dimension may include at least one of the user area of the sample user, user identity, user personal information, user business position, user business development plan, etc. Taking the communication network scenario as an example, the user type of the sample user can be divided according to at least one of the user's network area, operator attributes, job position, network development strategy, etc. For example, the sample users can be classified according to information such as the user's network area, user department and job position, and the user type of the sample user can be determined as: wireless network planning engineer in A, communication network optimization engineer in B, market sales personnel in C, etc.

Event preference data includes intention preference data and strategy preference data. Intent preference data is used to characterize the intention goals that sample users want to achieve when executing historical events, and strategy preference data is used to characterize the execution strategies that sample users prefer to achieve their intention goals (i.e., intention preferences) when executing historical events.

S203: Store the user type and event preference data of the sample user in a preference database accordingly.

In one embodiment, the above S202 is performed, that is, the event of the sample user executing the historical event is analyzed. When preference data is selected, the following steps A1-A3 may be specifically performed.

Step A1, determining the first target satisfaction of the sample user with the event execution result based on the sample user's initial satisfaction with the event execution result, the event execution intention and the event execution time; and determining the second target satisfaction of the sample user with the event execution result based on the sample user's initial satisfaction with the event execution result, the event execution strategy and the event execution time.

The purpose of converting the sample user's initial satisfaction with the event execution result into the first target satisfaction and the second target satisfaction is to make the satisfaction corresponding to multiple historical events more accurately serve as data basis, and more specifically, to more accurately serve as data basis for determining preference influencing factors. As can be seen from the following step A2, the satisfaction corresponding to the historical event is one of the data used to determine the preference influencing factors, while the initial satisfaction is only the satisfaction provided subjectively by the sample user. Therefore, by converting the initial satisfaction corresponding to the historical event into the more objective first target satisfaction and second target satisfaction, the subsequent determination of the preference influencing factors can be made more accurate.

Optionally, if the first contribution of the preference influencing factor to the intended preference is to be calculated, the following expression (1a) may be used to calculate the first target satisfaction.

First goal satisfaction = initial satisfaction * relevant value of event execution intention * weight corresponding to event execution time (1a)

If the second contribution of the preference influencing factor to the strategy preference is to be calculated, the following expression (1b) can be used to calculate the second target satisfaction.

Second target satisfaction = initial satisfaction * relevant value of event execution strategy * weight corresponding to event execution time (1b)

In expressions (1a) and (1b), the initial satisfaction can be a value between 0 and 1, and the relevant value of the event execution intention can be a value involved in the event execution intention. For example, in the communication network scenario listed above, the relevant value of the event execution intention can be the number of sites involved in the planning optimization. For example, if the event execution intention is "planning and optimizing 2000 macro sites", the relevant value of the event execution intention is 2000.

The relevant value of the event execution strategy may be the value involved in the event execution strategy. For example, in the communication network scenario listed above, the relevant value of the event execution strategy may be the number of sites involved in the planning and the number of sites involved in the optimization. For example, if the event execution strategy is "planning 3000 macro sites", the relevant value of the event execution strategy is 3000.

In expressions (1a) and (1b), the weight corresponding to the event execution time is related to the early or late event execution time. Generally, the earlier the event execution time (i.e., the farther from the current time), the better the event execution time. The lower the importance of the corresponding historical event, the lower the weight can be assigned to the event execution time. Conversely, the later the event execution time (i.e., the closer to the current time), the higher the importance of the corresponding historical event, and the higher the weight can be assigned to the event execution time.

Of course, the above expressions (1a) and (1b) are only exemplary ways to determine the first target satisfaction and the second target satisfaction. In other embodiments, other ways may be used to determine the first target satisfaction and the second target satisfaction, and this embodiment does not limit this. For example, the initial satisfaction may be directly determined as the first target satisfaction and the second target satisfaction. For another example, the first target satisfaction and the second target satisfaction are determined based on one or two of the sample user's initial satisfaction with the event execution result, the event execution strategy/event execution intention, and the weight corresponding to the event execution time. For example, the product of the initial satisfaction and the weight corresponding to the event execution time is determined as the first target satisfaction or the second target satisfaction.

Step A2, determining preference influencing factors related to event execution results based on event execution intention, event scenario and/or event influencing factors.

The preference influencing factors related to the event execution result may include one or more. If the preference influencing factors related to the event execution result include multiple preference influencing factors, the multiple preference influencing factors may be combined as a preference influencing factor combination corresponding to the historical event, and the preference influencing factor combination includes multiple preference influencing factors.

Optionally, when executing step A2, the event keywords of the historical event can be first determined based on the event execution intention and/or event scenario, and then the event influencing factors corresponding to the event keywords of the historical event can be determined as the preference influencing factors based on the correspondence between the preset event keywords and the event influencing factors; or, the event keywords corresponding to the historical event can be determined as the preference influencing factors.

Step A3, determining the first contribution of each preference influencing factor to the intention preference based on the preference influencing factor and the first target satisfaction; and determining the second contribution of each preference influencing factor to the strategy preference based on the preference influencing factor and the second target satisfaction.

Optionally, when determining the first contribution of each preference influencing factor to the intended preference according to the preference influencing factor and the first target satisfaction, the following steps B1-B2 may be specifically performed.

Step B1, for any preference influencing factor, determine the first target satisfaction corresponding to the preference influencing factor and the preference influencing factor combination including the preference influencing factor, and determine the first target satisfaction corresponding to the preference influencing factor combination not including the preference influencing factor, and use the determined first target satisfaction as the first satisfaction.

For any preference influencing factor, determine the preference influencing factor and the factors that include the preference influencing factor. The second target satisfaction levels corresponding to the preference influencing factor combinations of the preference influencing factors are determined, and the second target satisfaction levels corresponding to the preference influencing factor combinations that do not include the preference influencing factors are determined, and the determined second target satisfaction levels are used as the second satisfaction levels.

In step B1, there is no time limit for determining the first satisfaction level and the second satisfaction level.

Step B2, calculating the first contribution of the preference influencing factors to the intention preference according to the total number of preference influencing factors and the first satisfaction level; and calculating the second contribution of the preference influencing factors to the strategy preference according to the total number of preference influencing factors and the second satisfaction level.

In one embodiment, the preference database further includes: event preference data corresponding to sample users of the same user type in different event scenarios. Based on this, when determining the event preference data corresponding to different user types, for sample users of each user type and their corresponding historical event information, the historical event information of the sample users can be classified according to the event scenario to obtain the historical event information corresponding to the sample users in different event scenarios. Then, based on the historical event information corresponding to the sample users in each event scenario, the event preference data of the sample users is analyzed to obtain the event preference data corresponding to the sample users in different event scenarios.

Among them, when analyzing the event preference data of sample users, the method steps adopted are the same as those in the above embodiment and will not be repeated here.

In this embodiment, since the preference database stores the event preference data corresponding to sample users in different event scenarios, when matching the target user type with the pre-created preference database to determine the target event preference data corresponding to the target user type, the event scenario of the target event can be determined first, and then the target user type, the event scenario of the target event and the preference database can be matched to obtain the target event preference data corresponding to the target user type and the event scenario of the target event.

The event scene of the target event may be provided by the user or automatically determined by the system, for example, by locating the current geographical location and then determining the scene to which the geographical location belongs.

In one embodiment, after determining the target event preference data corresponding to the target user type, the target event can be executed according to the target event preference data to obtain the event execution result of the target event, and the target user's satisfaction with the event execution result can be obtained; then, the preference database can be optimized according to the target user's satisfaction with the event execution result.

Optionally, after obtaining the target user's satisfaction with the event execution result, the event preference data of the target user may be re-determined in accordance with the method of determining the event preference data of the sample user in the above embodiment. According to the re-determined event preference data, the event preference data corresponding to the user type of the target user in the preference database is updated, thereby optimizing the preference database.

The following uses a communication network scenario as an example to explain in detail how the user preference analysis method provided by the present application is implemented.

In the communication network scenario, the intentional network is usually used to manage the planning, construction, maintenance, optimization and operation of the network. This management mode is integrated into the planning, construction, maintenance and operation system. The system that implements the user preference analysis method can use the existing planning, construction, maintenance and operation system, or it can build a user system. First, it explains how to create a preference database based on the historical event information of sample users.

First, historical event information of multiple sample users is obtained, and the sample users are classified according to the historical event information to determine the user type of the sample users. The historical event information includes at least one of the following: user information of the sample user, event influencing factors of the historical event, event scenario, event execution time, event status (such as the current status of the event), event execution intention, event execution strategy, event execution result, and the sample user's initial satisfaction with the event execution result.

Among them, the user information of the sample user may include at least one of the user identity, geographic location information, user personal information, user business position information, user business development plan information, etc. of the sample user. A historical event is an event that the sample user has completed, and the event execution result of the historical event is known. The event influencing factors of the historical event refer to the factors that may affect the event preference data of the sample user for the historical event, which can be determined based on the sample user's execution intention for the historical event (referred to as event execution intention) and/or the event scenario of the historical event. The event scenario refers to the scenario involved in executing the event. The event execution intention is the intended target of the sample user to execute the historical event, such as 5G outdoor coverage reaching 95%, the existing network high-speed rail coverage rate of 10%, etc. The event execution strategy is the strategy adopted by the sample user to execute the historical event, such as site planning, macro site reuse, etc.; the event execution strategy may include a recommended strategy and a final selection strategy. In addition to the above information, the historical event information may also include the execution plan adopted by the sample user based on the final selection strategy when executing the historical event. The execution plan matches the final selection strategy, and the execution plan is more specific and detailed than the final selection strategy. The sample users' initial satisfaction with the event execution results can be understood as the score given by the sample users to the event execution results from a subjective perspective, such as a value between 0 and 1.

The user types of sample users can be divided according to at least one of the network area where the user is located, operator attributes, job position, network development strategy, etc. For example, by classifying the sample users according to the network area where the user is located, the department to which the user belongs, and the job position, the user types of the sample users can be determined as: wireless network planning engineer in area A, communication network optimization engineer in area B, marketing salesperson in area C, etc. Members, etc.

Table 1 below exemplarily shows the historical event information of multiple sample users in a communication network scenario. Table 1 lists the historical event information of multiple sample users whose user type is "Wireless Network Planning Engineer in Location A". Among them, the intended target (network construction target) is the event execution intention. The event execution strategy includes the recommended strategy sent by the system to the sample user, such as the first and second strategies, and also includes the final selection strategy, that is, the solution to the historical event selected based on the recommended strategy.

Table 1

After the historical event information is acquired, the event preference data of the sample users who executed the historical events are analyzed according to the historical event information.

The initial satisfaction feedback from sample users is an evaluation of a single historical event. The system can directly use the initial satisfaction to analyze the event preference data corresponding to the sample users, or convert the initial satisfaction feedback from sample users into a more objective satisfaction (which can also be understood as the satisfaction customized within the system), including the sample users' first target satisfaction or second target satisfaction with the event execution results. For example, according to the importance of different historical events, historical events with higher importance can be given higher weights. Generally speaking, the closer the event execution time is, the higher the importance of the historical event. Therefore, different time weights (i.e., the weight corresponding to the event execution time) can be given according to the order of the event execution time of the historical events.

Assume that the following expression (2) is used to calculate the first goal satisfaction of sample users with the event execution results.

First target satisfaction = initial satisfaction * number of sites involved in planning optimization * time weight (2)

Among them, the number of sites involved in planning optimization is the relevant value of the event execution intention. For the wireless network planning engineer in place A in Table 1, the "number of sites involved in planning optimization" can be statistically obtained from the "final selection strategy" in Table 1, which can be the sum of the number of macro stations, indoor stations and micro stations, reflecting the event scale of historical events. The calculation of time weight is to sort all historical events in order from early to late according to the event execution time. The time weight corresponding to the starting event (that is, the historical event with the earliest event execution time) is 1, and it is increased by 1 every six months, reflecting the impact of time on the importance of historical events. Table 2 is the result of the first target satisfaction calculated based on the above expression (2) for the data in Table 1.

Table 2

The following expression (3) can be used to calculate the second goal satisfaction of sample users with the event execution results.

Second target satisfaction = initial satisfaction * (number of sites involved in planning and/or number of sites involved in optimization) * time weight (3)

The number of sites involved in planning and/or the number of sites involved in optimization are the relevant values of the event execution strategy. The specific calculation method is similar to the first goal satisfaction, and will not be repeated here.

It should be noted that the calculation method of the first target satisfaction and the second target satisfaction is not limited to the above expressions (2) and (3), and can also be positioned as other methods, such as replacing the "number of sites involved in planning optimization" with "the cost of planning and optimization", "the return on investment of planning and optimization", etc. Since the cost and return on investment are related to the type of site, they can better reflect the importance of historical events than the simple number of sites. In addition, since there is generally a deviation between the planning estimate and the actual implementation results, after obtaining the exact implementation data, the corresponding relevant values can be modified and recalculated, or the calculated contribution (including the first contribution or the second contribution) can be corrected according to the implementation data. Of course, the original calculated value can also be retained, and the a posteriori supplementary field can be added at the same time, and the corrected data can be added to the position corresponding to the a posteriori supplementary field.

After calculating the first target satisfaction and the second target satisfaction, determine the preference influencing factors related to the event execution result according to the event execution intention (i.e., the intended target), the event scenario and/or the event influencing factors, that is, determine which factors (or combinations of factors) will affect the sample user's satisfaction with the historical event. Among them, the preference influencing factors related to the event execution result may include one or more. If there are multiple preference influencing factors related to the event execution result, the multiple preference influencing factors can be combined as a combination of preference influencing factors corresponding to the historical event, and the combination of preference influencing factors includes multiple preference influencing factors. When determining the preference influencing factors, the event keywords of the historical event can be determined first according to the event execution intention and/or the event scenario, and then according to the correspondence between the preset event keywords and the event influencing factors, the event influencing factors corresponding to the event keywords of the historical event are determined as the preference influencing factors; or, the event keywords corresponding to the historical event are determined as the preference influencing factors.

For example, in Table 1, at least one key field of the event scene is extracted from the "intent target" as the event keyword corresponding to the historical event. For example, the event keywords extracted from "the indoor coverage rate of the brand area reaches 90%" include: brand area, indoor, coverage rate. The event keywords extracted from "the outdoor coverage rate of the main roads reaches 98%" include: main roads, coverage rate. Then, the event keywords corresponding to the historical event can be directly determined as preference influencing factors, for example, preference influencing factors include: brand area, indoor, coverage rate, main roads, etc.

Alternatively, it is also possible to determine the event influencing factors corresponding to the event keywords of historical events as preference influencing factors based on the correspondence between preset event keywords and event influencing factors. Among them, event keywords may include intent keywords and scenario keywords, and intent keywords and scenario keywords may correspond to their own independent preference influencing factors, or a combination of intent keywords and scenario keywords may correspond to one preference influencing factor. In this correspondence, event influencing factors can be customized by users, so that customized event influencing factors are closer to the general cognition of users, such as improving network performance indicators, improving reputation and market position, focusing on value areas and users, improving existing network user perception, ROI indicators, competing to seize users of competing operators, expanding 2B business, etc.

Taking the event influencing factors "improving network performance indicators, improving reputation and market position, and focusing on value areas and users" as an example, the system matches the "intent target" in Table 1 to obtain a list of time influencing factors such as Tables 3 and 4. Among them, Table 3 defines the correspondence between some event influencing factors and event keywords. In the process of intent analysis, the corresponding intent keywords and scene keywords are extracted. As long as they appear in the intent keywords or scene keywords corresponding to the event influencing factors, the historical event corresponds to the corresponding event influencing factors. Table 4 defines the event influencing factors corresponding to some keyword combinations. In this example, although the two keywords "college" and "coverage rate" are extracted from the intent target "the indoor coverage rate of colleges and universities reaches 95%", according to the remarks, only the event influencing factor "improving reputation and market position" corresponding to "colleges and universities" can be taken as the preferred influencing factor. In addition, priorities can be set for different keywords, so that each historical event only retains the event influencing factors corresponding to some keywords with higher priorities.

table 3

Table 4

For Table 3 and Table 4, corresponding priorities can be set. For example, the priority of the keyword combination is set higher than the priority corresponding to a single keyword (intent keyword or scene keyword). Then, the priority of the corresponding relationship in Table 4 is higher than the priority of the corresponding relationship in Table 3.

After determining the preference influencing factors corresponding to the historical events according to the correspondence between the preset event keywords and the event influencing factors, it is assumed that each preference influencing factor is simplified into a different digital identifier, among which the preference influencing factors "improve network performance indicators", "improve reputation and market position", and "focus on value areas and users" are simplified into digital identifiers 1, 2, and 3 respectively. Then the historical event information, preference influencing factors, and the first goal satisfaction corresponding to the historical events can be listed in the following Table 5. The simplified identification set of preference influencing factors is the set of identifications of all preference influencing factors corresponding to the historical events, that is, the identification set corresponding to the preference influencing factor combination.

table 5

After determining the preference influencing factor or the combination of preference influencing factors corresponding to each historical event, determine the first contribution of each preference influencing factor to the intention preference and the second contribution to the strategy preference. Each preference influencing factor may be a single preference influencing factor corresponding to a historical event or a preference influencing factor included in the combination of preference influencing factors corresponding to a historical event.

The following formula (4) shows an optional way of calculating the first contribution and the second contribution corresponding to the preference influencing factor.

Among them, i represents the preference influencing factor, Indicates the first contribution or second contribution corresponding to preference influencing factor i. n represents the total number of preference influencing factors, N represents various sets composed of all preference influencing factors, S represents preference influencing factor i and all preference influencing factor combinations containing preference influencing factor i, and S\{i} represents all preference influencing factor combinations that do not contain preference influencing factor i. For example, different preference influencing factors are represented by numbers. Assuming there are three preference influencing factors 1, 2, and 3, then n = 3 and N = [1,2,3]. [1,2,3] represents all sets that can be composed of preference influencing factors 1, 2, and 3, including {1}, {2}, {3}, {1,2}, {1,3}, {2,3}, and {1,2,3}.

Take the calculation of the first contribution corresponding to the preference influencing factor "1" as an example. S is the preference influencing factor "1" and all preference influencing factor combinations including 1: {1}, {1,2}, {1,3}, {1,2,3}. S\{i} is all preference influencing factor combinations that do not include the preference influencing factor "1": {2}, {3}, {2,3}. c(S) represents the first target satisfaction corresponding to the set S, and v(S\{i}) represents the first target satisfaction corresponding to S\{i}. |S| represents the number of elements in the set S. By combining the first target satisfactions in Table 5, the first target satisfactions corresponding to each preference influencing factor or preference influencing factor combination can be obtained, as shown in Table 6 below.

Table 6

The preference influencing factors or preference influencing factor combinations not shown in Table 6 indicate that the corresponding first target satisfaction is 0.

Table 7 below shows the first contribution of the calculated preference influencing factors. the process of.

Table 7

In Table 7, v(S) can be obtained by querying Table 6. If the first target satisfaction corresponding to S cannot be found in Table 6, the default first target satisfaction corresponding to S is 0. v(S\{1}) can be obtained by querying the first target satisfaction corresponding to the set S\{1} after deleting "1" from S in Table 6. For example, the set after deleting "1" from {1,2} is {2}, and the corresponding first target satisfaction is 735. According to the calculation sequence listed in Table 7, it can be concluded that the first contribution corresponding to the preference influencing factor "1" is 8229.17. The calculation method of the first contribution corresponding to other preference influencing factors "2" and "3" is the same as that of the preference influencing factor "1", which will not be repeated. According to the calculation method of the first contribution corresponding to the preference influencing factor "1", it can be calculated that the first contribution corresponding to the preference influencing factor "2" is 611.67, and the first contribution corresponding to the preference influencing factor "3" is 5311.67.

It can be seen that the first contribution calculated in this way is in the form of a score. Optionally, the first contribution can also be in the form of a percentage. By dividing each first contribution by all first contributions, the percentage value corresponding to each contribution can be obtained. For example, the sum of the first contributions corresponding to the preference influencing factors "1", "2", and "3" is: 8229.17+611.67+5311.67=14152.51. Dividing the first contribution corresponding to the preference influencing factor "1" by the sum of the first contributions, the first contribution corresponding to the preference influencing factor "1" can be obtained as 0.59; dividing the first contribution corresponding to the preference influencing factor "2" by the sum of the first contributions can be obtained as 0.04; dividing the first contribution corresponding to the preference influencing factor "3" by the sum of the first contributions can be obtained as 0.37.

The calculation method of the first contribution degree corresponding to each preference influencing factor is described in detail above. The calculation method of the second contribution degree corresponding to each preference influencing factor is similar to the first contribution degree, and will not be repeated here. The only difference between the two is that the first target satisfaction is replaced by the second target satisfaction.

When calculating the second contribution corresponding to each preference influencing factor, since the first and second delivery strategies shown in Table 1 are slightly different, this will result in different extracted keywords, that is, different event keywords corresponding to historical events, resulting in different preference influencing factors determined based on event keywords. Therefore, for different delivery strategies, even if the same contribution calculation method is used, the calculated contribution will be different.

Table 8 below shows the second contribution and the second contribution ratio calculated for one of the delivery strategies.

Table 8

In Table 8, a posteriori supplementary content is introduced as a note. For example, since the operator in area A has not introduced a new frequency band plan, the policy preference of the newly added frequency band is 0. This information can be filled in the "Post-A posteriori supplementary" field. For the second delivery strategy in Table 1, the corresponding second contribution and second contribution ratio can be calculated in the same way, which will not be repeated here.

In one embodiment, the intention preference data and strategy preference data corresponding to the sample users can be determined by scene. In this way, the preference database can include the preferences of different user objects in different scenes. The event scene of a historical event can be a certain scene or a combination of multiple scenes. First, the historical event information of the sample users is classified according to the event scene to obtain the historical event information corresponding to the sample users in different event scenes. Then, according to the historical event information corresponding to each event scene of the sample users, the event preference data of the sample users is analyzed to obtain the event preference data corresponding to the sample users in different event scenes.

Taking the historical event information shown in Table 1 as an example, if the event preference data corresponding to the historical event analysis with the event scene being "outdoors" is analyzed, the event preference data includes the first contribution and the second contribution corresponding to the preference influencing factors. First, the matching historical event information is filtered out according to the event scene "outdoors", and then the filtered historical event information is analyzed to obtain the event preference data under the event scene "outdoors". Table 9 shows the first contribution corresponding to each preference influencing factor under the event scene "outdoors".

Table 9

It can be seen from Table 9 that for wireless network planning engineers in site A, the outdoor scenario mainly focuses on improving network performance indicators.

Similarly, the calculation method of the second contribution degree corresponding to each preference influencing factor is similar to the first contribution degree, and the only difference is that the first target satisfaction degree used in the calculation process is replaced by the second target satisfaction degree. Other detailed processes are not repeated here.

After calculating the event preference data (including the first contribution of the preference influencing factors to the intention preference and the second contribution to the strategy preference), the event preference data and the corresponding user type can be associated and stored in the preference database. After the target user issues an execution instruction for the target event and executes the target event based on the execution instruction, the event preference data corresponding to the target user type can be re-determined based on the event execution result, the initial satisfaction of the target user with the event execution result feedback, and other data, so as to utilize the event preference data to determine the event preference data corresponding to the target user type. Optimize the preference database with event preference data corresponding to the target user type.

In one embodiment, before the target user issues an execution instruction for the target event, he needs to log in to the system, for example, by entering login information (such as account number, password, user information, etc.). The system will authenticate the target user based on the login information entered by the target user, and then execute subsequent steps after the authentication is passed. If the target user logs in to the system for the first time, he needs to select his corresponding user type, or create a user type by himself, and register the login information at the same time.

FIG3 is a schematic flow chart of an event execution method according to an embodiment of the present application. As shown in FIG3 , the method includes the following steps.

S301, obtaining login information input by a target user, and authenticating the target user based on the login information; wherein the login information includes a target user type of the target user.

S302: If the authentication is successful, then according to the target user type, the event preference data corresponding to the target user type is obtained from the preference database, and the intention preference data in the event preference data is displayed to the target user.

Among them, the event preference data includes intention preference data and strategy preference data. The intention preference data includes the first contribution of each preference influencing factor to the intention preference, and the strategy preference data includes the second contribution of each preference influencing factor to the strategy preference. The preference database includes: the first correspondence between user type and intention preference data, and the second correspondence between intention preference data and strategy preference data. The first contribution can be in the form of a score or a percentage.

In this step, the intention preference data may be first displayed to the target user, specifically, the first contribution of each preference influencing factor to the intention preference may be displayed to the target user for reference. By displaying the intention preference data to the target user, the intention goal of recommending the target event to be executed for the target user is achieved.

Optionally, the system may recommend the preference influencing factor with the highest first contribution or the intent keyword corresponding to the preference influencing factor as the intent target to the target user based on the first contribution of each preference influencing factor to the intent preference in the intent preference data. Continuing with the above example, assuming that the target user type is "wireless network planning engineer in location A", the preference influencing factor with the highest contribution ratio in the intent preference data corresponding to the target user type is "improving network performance indicators". It can be seen from Table 3 above that the intent keyword corresponding to the preference influencing factor is "coverage", and the intent keyword "coverage" can be displayed to the target user as the intent target. Of course, the system can also adopt other methods that include multiple intent targets, such as setting a minimum contribution ratio threshold, so as to recommend intent targets to the target user based on the preference influencing factor corresponding to the first contribution ratio that is not lower than the minimum contribution ratio threshold.

Alternatively, the target user may also input an event scenario first, so that the system can recommend intent targets for the target user based on the event scenario. For example, if the event scenario input by the target user is "outdoor", the system will first query the intent preference data corresponding to the target user type and under the event scenario "outdoor" based on the event scenario "outdoor", and then recommend intent targets for the target user based on the query intent preference data.

In addition, if the target user logs in to the system multiple times, the system can also recommend the target user's intended target based on the target user's historical selected intended targets.

S303, determining the final intention selected by the target user.

Optionally, the system provides a front-end interactive interface for the target user, and the target user can select the final intent through the front-end interactive interface. The intent here can be applied to the confirmation and issuance of NOP intent-NOP in the 3GPP (Third Generation Partnership Project) protocol.

Optionally, the target user can modify the intended target recommended by the system, such as rejecting the intended target recommended by the system, to trigger the system to re-recommend other different intended targets. Alternatively, the system is triggered to display all the intended targets, so that the intended target is selected from all the intended targets.

S304: Use the final intention as the intention preference data for this time, determine the strategy preference data corresponding to the intention preference data, and display the strategy preference data to the target user.

S305, determining the final strategy selected by the target user, and sending the final strategy to the corresponding platform.

Among them, the final strategy is used to execute the target event on the corresponding platform, thereby obtaining the event execution result of the target event.

S306, obtaining the target user's satisfaction with the event execution result feedback.

In this step, if the corresponding platform has completed the target event and obtained the event execution result, the user can give feedback on the satisfaction of the event execution result. If the target event has not been implemented yet, or is in the process of implementation (such as the implementation time of the planned plan is long), you can first give a subjective approximate satisfaction, and then modify the satisfaction according to the actual execution result after the target event is executed. If the target user does not ultimately select the final strategy using the strategy preference data recommended by the system, the satisfaction can be 0.

In this embodiment, after obtaining the target user's satisfaction with the event execution result feedback, the target event can be used as a historical event, and the relevant information of the target event can be used as the corresponding historical event information, so as to optimize the preference database based on the new historical event information.

It can be seen that, by adopting the technical solution of this embodiment, when receiving the execution instruction of the target user for the target event, by determining the target user type and combining the target user type and the pre-created preference data The target event preference data corresponding to the target user type is matched with the database to determine the target event preference data, so as to execute the target event according to the target event preference data. Among them, the preference database includes the correspondence between multiple user types and event preference data, and the event preference data includes the intention preference data and strategy preference data for executing the event. Since the event preference data of the user is determined based on the target user type of the target user, the event preference data of the target user can be analyzed in a targeted manner according to the target user type, so that the determination result of the event preference data is more accurate. Furthermore, when executing the target event according to the event preference data of the target user, not only the event execution efficiency is improved, but also the strategy adopted when executing the event can be more matched with the event preference data (including intention preference and strategy preference) of the target user, so that the event execution result can maximize the satisfaction of the target user.

In summary, specific embodiments of the present subject matter have been described. Other embodiments are within the scope of the appended claims. In some cases, the actions recorded in the claims can be performed in a different order and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing can be advantageous.

The above is a user preference analysis method provided in an embodiment of the present application. Based on the same idea, an embodiment of the present application also provides a user preference analysis device.

FIG4 is a schematic block diagram of a user preference analysis device according to an embodiment of the present application. As shown in FIG4 , the user preference analysis device includes the following modules.

The first determining module 41 is configured to determine a target user type of the target user in response to an execution instruction of the target user for the target event.

The second determination module 42 is used to match the target user type with a pre-created preference database to determine the target event preference data corresponding to the target user type, so as to execute the target event according to the target event preference data; the preference database includes a correspondence between multiple user types and event preference data; the event preference data includes intention preference data and strategy preference data for executing the event.

In one embodiment, the intention preference data includes: a first contribution degree of each preference influencing factor to the intention preference; and the strategy preference data includes: a second contribution degree of each preference influencing factor to the strategy preference.

In one embodiment, the correspondence between the user type and the event preference data includes: a first correspondence between the user type and the intention preference data, and a second correspondence between the intention preference data and the strategy preference data.

The second determination module 42 includes: a first determination unit, used to match the target user type with the first corresponding relationship, and determine the target intention preference data corresponding to the target user type; a second determination unit, used to match the target intention preference data with the second corresponding relationship, and determine the target strategy preference data corresponding to the target intention preference data; wherein the target event preference data includes the target intention preference data and the target strategy preference data.

In one embodiment, the device also includes: a first acquisition module, which is used to obtain historical event information of sample users before determining the target user type of the target user in response to the target user's execution instruction for the target event; the historical event information includes at least one of the following: user information of the sample user, event influencing factors of historical events, event scenarios, event execution time, event execution intentions, event execution strategies, event execution results, and the sample user's initial satisfaction with the event execution results; a third determination module, which is used to determine the user type of the sample user based on the historical event information, and analyze the event preference data of the sample user executing historical events; a storage module, which is used to store the user type of the sample user and the event preference data in the preference database accordingly.

In one embodiment, the third determination module includes: a third determination unit, used to determine the first target satisfaction of the sample user with the event execution result based on the initial satisfaction, the event execution intention and the event execution time; determine the second target satisfaction of the sample user with the event execution result based on the initial satisfaction, the event execution strategy and the event execution time; a fourth determination unit, used to determine the preference influencing factors related to the event execution result based on the event execution intention, the event scenario and/or the event influencing factors; a fifth determination unit, used to determine the first contribution of each preference influencing factor to the intention preference based on the preference influencing factors and the first target satisfaction; and, determine the second contribution of each preference influencing factor to the strategy preference based on the preference influencing factors and the second target satisfaction.

In one embodiment, the fourth determination unit is specifically used to: determine the event keywords of the historical event according to the event execution intention and/or the event scenario; determine the event influencing factors corresponding to the event keywords of the historical event as the preference influencing factors according to the correspondence between preset event keywords and event influencing factors; or, determine the event keywords corresponding to the historical event as the preference influencing factors.

In one embodiment, the fifth determining unit is specifically configured to: for any one of the preference influencing factors, determine the preference influencing factor and the preference influencing factors including the preference influencing factor. The first target satisfaction levels respectively corresponding to the preference influence factor combinations, and the first target satisfaction levels corresponding to the preference influence factor combinations excluding the preference influence factors, are taken as the first satisfaction levels; for any one of the preference influence factors, the second target satisfaction levels respectively corresponding to the preference influence factor and the preference influence factor combinations including the preference influence factor, and the second target satisfaction levels corresponding to the preference influence factor combinations excluding the preference influence factor are determined as the second satisfaction levels; based on the total number of the preference influence factors and the first satisfaction levels, the first contribution of the preference influence factors to the intention preference is calculated; and based on the total number of the preference influence factors and the second satisfaction levels, the second contribution of the preference influence factors to the strategy preference is calculated.

In one embodiment, the preference database further includes: event preference data corresponding to sample users of the same user type in different event scenarios; the device further includes the following modules.

The classification module is used to classify the historical event information of the sample users of each user type according to the event scenarios, so as to obtain the historical event information corresponding to the sample users in different event scenarios.

The analysis module is used to analyze the event preference data of the sample users according to the historical event information corresponding to each event scenario of the sample users, so as to obtain the event preference data corresponding to the sample users in different event scenarios.

In one embodiment, the second determination module 42 includes: a sixth determination unit, used to determine the event scene of the target event; a matching unit, used to match the target user type, the event scene of the target event and the preference database to obtain the target event preference data corresponding to the target user type and the event scene of the target event.

In one embodiment, the device also includes: an execution module, which is used to execute the target event according to the target event preference data after determining the target event preference data corresponding to the target user type, and obtain the event execution result of the target event; a second acquisition module, which is used to obtain the target user's satisfaction with the event execution result; and an optimization module, which is used to optimize the preference database according to the target user's satisfaction with the event execution result.

When the device of the embodiment of the present application receives the execution instruction of the target event from the target user, it determines the target user type and matches the target user type with the pre-created preference database to determine the target event preference data corresponding to the target user type, so as to execute the target event according to the target event preference data. Among them, the preference database includes the correspondence between multiple user types and event preference data, and the event preference data includes the intention preference data and strategy preference data of executing the event. Since the event preference data of the user is determined based on the user type, it is possible For different types of users, the event preference data of different user types are analyzed in a targeted manner, so that the determination result of the event preference data is more accurate. Furthermore, when executing the target event according to the event preference data of the target user, not only the event execution efficiency is improved, but also the strategy adopted when executing the event can be more closely matched with the event preference data of the target user (including intention preference and strategy preference), so that the event execution result can achieve the user's satisfaction to the greatest extent.

Those skilled in the art should understand that the user preference analysis device in FIG. 4 can be used to implement the user preference analysis method described above, and the detailed description thereof should be similar to that described in the method section above, and will not be further described here to avoid redundancy.

Based on the same idea, an embodiment of the present application also provides an electronic device, as shown in FIG5 . The electronic device may have relatively large differences due to different configurations or performances, and may include one or more processors 501 and a memory 502, and the memory 502 may store one or more storage applications or data. Among them, the memory 502 may be a short-term storage or a persistent storage. The application stored in the memory 502 may include one or more modules (not shown in the figure), and each module may include a series of computer executable instructions in the electronic device. Furthermore, the processor 501 may be configured to communicate with the memory 502 and execute a series of computer executable instructions in the memory 502 on the electronic device. The electronic device may also include one or more power supplies 503, one or more wired or wireless network interfaces 504, one or more input and output interfaces 505, and one or more keyboards 506.

Specifically in this embodiment, the electronic device includes a memory, and one or more programs, wherein the one or more programs are stored in the memory, and the one or more programs may include one or more modules, and each module may include a series of computer executable instructions in the electronic device, and is configured to be executed by one or more processors. The one or more programs include the following computer executable instructions: in response to the target user's execution instruction for the target event, determine the target user type of the target user; match the target user type with a pre-created preference database to determine the target event preference data corresponding to the target user type, so as to execute the target event according to the target event preference data; the preference database includes a correspondence between multiple user types and event preference data; the event preference data includes intention preference data and strategy preference data for executing the event.

By adopting the technical solution of the embodiment of the present application, when receiving the execution instruction of the target user for the target event, by determining the target user type and matching the target user type with the pre-created preference database, the target event preference data corresponding to the target user type is determined, so as to The target event is executed according to the event preference data. Among them, the preference database includes a correspondence between multiple user types and event preference data, and the event preference data includes intention preference data and strategy preference data for executing events. Since the user's event preference data is determined based on the user's user type, it is possible to analyze the event preference data of different user types in a targeted manner for different types of users, thereby making the determination result of the event preference data more accurate. Furthermore, when executing the target event according to the event preference data of the target user, not only the event execution efficiency is improved, but also the strategy adopted when executing the event can be more matched with the event preference data (including intention preference and strategy preference) of the target user, so that the event execution result can maximize the user's satisfaction.

An embodiment of the present application also proposes a storage medium, which stores one or more computer programs, which include instructions. When the instructions are executed by an electronic device including multiple applications, the electronic device can execute the various processes of the above-mentioned user preference analysis method embodiment, and are specifically used to execute: in response to the target user's execution instruction for the target event, determine the target user type of the target user; match the target user type with a pre-created preference database to determine the target event preference data corresponding to the target user type, so as to execute the target event according to the target event preference data; the preference database includes the correspondence between multiple user types and event preference data; the event preference data includes intention preference data and strategy preference data for executing the event.

By adopting the technical solution of the embodiment of the present application, when receiving the execution instruction of the target event from the target user, the target event preference data corresponding to the target user type is determined by determining the target user type and matching the target user type with the pre-created preference database, so as to execute the target event according to the target event preference data. Among them, the preference database includes the correspondence between multiple user types and event preference data, and the event preference data includes the intention preference data and strategy preference data of the execution event. Since the user type is used to determine the event preference data of the user, the event preference data of different user types can be analyzed in a targeted manner for different types of users, so that the determination result of the event preference data is more accurate. Furthermore, when executing the target event according to the event preference data of the target user, not only the event execution efficiency is improved, but also the strategy adopted when executing the event can be more matched with the event preference data (including intention preference and strategy preference) of the target user, so that the event execution result can achieve the user's satisfaction to the greatest extent.

The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a The invention may include a mobile phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

For the convenience of description, the above device is described in terms of functions and is divided into various units and described separately. Of course, when implementing the present application, the functions of each unit can be implemented in the same or multiple software and/or hardware.

Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

The present application is described with reference to the flowchart and/or block diagram of the method, device (system) and computer program product according to the embodiment of the present application. It should be understood that each process and/or box in the flowchart and/or block diagram, and the combination of the process and/or box in the flowchart and/or block diagram can be realized by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce a device for realizing the function specified in one process or multiple processes in the flowchart and/or one box or multiple boxes in the block diagram.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device that implements the functions specified in one or more processes in the flowchart and/or one or more boxes in the block diagram.

These computer program instructions may also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more processes in the flowchart and/or one or more boxes in the block diagram.

In a typical configuration, a computing device includes one or more processors (CPU), input/output interfaces, network interfaces, and memory.

Memory may include non-permanent storage in a computer-readable medium, in the form of random access memory (RAM) and/or non-volatile memory, such as read-only memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.

Computer-readable media include permanent and non-permanent, removable and non-removable media that can be Any method or technology to achieve information storage. Information can be computer-readable instructions, data structures, modules of programs or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory media such as modulated data signals and carrier waves.

It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

The present application may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

A user preference analysis method, comprising:

In response to an execution instruction of a target user for a target event, determining a target user type of the target user;

The target user type is matched with a pre-created preference database to determine the target event preference data corresponding to the target user type, so as to execute the target event according to the target event preference data; the preference database includes a correspondence between multiple user types and event preference data; the event preference data includes intention preference data and strategy preference data for executing the event.
The method according to claim 1, wherein the intention preference data comprises: a first contribution of each preference influencing factor to the intention preference;

The strategy preference data includes: a second contribution degree of each preference influencing factor to the strategy preference.
The method according to claim 1, wherein the correspondence between the user type and the event preference data comprises: a first correspondence between the user type and the intention preference data, and a second correspondence between the intention preference data and the strategy preference data;

The step of matching the target user type with a pre-created preference database to determine the target event preference data corresponding to the target user type includes:

Matching the target user type with the first corresponding relationship to determine target intention preference data corresponding to the target user type;

Matching the target intention preference data with the second corresponding relationship to determine the target strategy preference data corresponding to the target intention preference data;

Wherein, the target event preference data includes the target intention preference data and the target strategy preference data.
The method according to claim 2, wherein, before determining the target user type of the target user in response to the target user's execution instruction for the target event, the method further comprises:

Acquire historical event information of sample users; the historical event information includes at least one of the following: user information of the sample user, event influencing factors of historical events, event scenarios, event execution time, event execution intention, event execution strategy, event execution results, and the sample user's initial satisfaction with the event execution results;

Determine the user type of the sample user according to the historical event information, and analyze the event preference data of the sample user in executing the historical events;

The user type of the sample user and the event preference data are stored in the preference database in correspondence.
The method according to claim 4, wherein the analyzing the event preference data of the sample user's execution of historical events comprises:

Determine the first target satisfaction of the sample user for the event execution result according to the initial satisfaction, the event execution intention and the event execution time; determine the second target satisfaction of the sample user for the event execution result according to the initial satisfaction, the event execution strategy and the event execution time;

Determining preference influencing factors related to the event execution result according to the event execution intention, the event scenario and/or the event influencing factors;

Based on the preference influencing factors and the first target satisfaction, determine the first contribution of each preference influencing factor to the intention preference; and based on the preference influencing factors and the second target satisfaction, determine the second contribution of each preference influencing factor to the strategy preference.
The method according to claim 5, wherein the determining the preference influencing factor related to the event execution result according to the event execution intention, the event scenario and/or the event influencing factor comprises:

Determining event keywords of the historical event according to the event execution intention and/or the event scenario;

According to the correspondence between preset event keywords and event influencing factors, the event influencing factor corresponding to the event keyword of the historical event is determined as the preference influencing factor; or, the event keyword corresponding to the historical event is determined as the preference influencing factor.
The method according to claim 5, wherein the determining the first contribution of each preference influencing factor to the intention preference according to the preference influencing factor and the first target satisfaction; and determining the second contribution of each preference influencing factor to the strategy preference according to the preference influencing factor and the second target satisfaction comprises:

For any one of the preference influencing factors, determine the first target satisfaction levels respectively corresponding to the preference influencing factor and the combination of preference influencing factors including the preference influencing factor, and the first target satisfaction level corresponding to the combination of preference influencing factors not including the preference influencing factor, as the first satisfaction level;

For any of the preference influencing factors, determine the preference influencing factors and the factors including the preference influencing factors. the second target satisfaction levels respectively corresponding to the preference influencing factor combinations of the preference influencing factors, and the second target satisfaction levels corresponding to the preference influencing factor combinations not including the preference influencing factors, as the second satisfaction levels;

Based on the total number of the preference influencing factors and the first satisfaction level, the first contribution of the preference influencing factors to the intention preference is calculated; and based on the total number of the preference influencing factors and the second satisfaction level, the second contribution of the preference influencing factors to the strategy preference is calculated.
The method according to claim 4, wherein the preference database further comprises: event preference data corresponding to sample users of the same user type in different event scenarios;

The method further comprises:

For each user type of sample user, classify the historical event information of the sample user according to the event scenario to obtain the historical event information corresponding to the sample user in different event scenarios;

According to the historical event information corresponding to the sample users in each event scenario, the event preference data of the sample users are analyzed to obtain the event preference data corresponding to the sample users in different event scenarios.
The method according to claim 8, wherein matching the target user type with a pre-created preference database to determine the target event preference data corresponding to the target user type comprises:

Determining an event scenario of the target event;

The target user type, the event scenario of the target event, and the preference database are matched to obtain the target event preference data corresponding to the target user type and the event scenario of the target event.
The method according to claim 1, wherein after determining the target event preference data corresponding to the target user type, the method further comprises:

Execute the target event according to the target event preference data to obtain an event execution result of the target event;

Obtaining the target user's satisfaction with the event execution result;

The preference database is optimized according to the target user's satisfaction with the event execution result.
A user preference analysis device, comprising:

A first determination module, configured to determine a target user type of the target user in response to an execution instruction of the target user for the target event;

The second determination module is used to match the target user type with a pre-created preference database to determine the target event preference data corresponding to the target user type, so as to execute the target event according to the target event preference data; the preference database includes a correspondence between multiple user types and event preference data; the event preference data includes intention preference data and strategy preference data for executing the event.
An electronic device comprises a processor and a memory electrically connected to the processor, the memory storing a computer program, and the processor being used to call and execute the computer program from the memory to implement the user preference analysis method as described in any one of claims 1 to 10.
A storage medium, wherein the storage medium is used to store a computer program, wherein the computer program can be executed by a processor to implement the user preference analysis method as described in any one of claims 1 to 10.