Method and device for determining promotion information and electronic equipment

Abstract

The invention discloses a promotion information determination method and apparatus, and an electronic device. Relates to the big data field. The method comprises the following steps: collecting product use information of M users of a target group using a target business product to obtain M groups of product use information, M being a positive integer; obtaining product information of the target business product, and determining a target portrait of the target group according to the product information and the M groups of product use information; generating an expected portrait of the target group, and comparing the expected portrait with the target portrait to obtain a comparison result; and determining at least one abnormal feature of the target portrait according to the comparison result, determining at least one current demand of the target group according to the at least one abnormal feature, and determining product promotion information sent to the target group according to the at least one current demand. Through the application, the problem that the accuracy of determining the promotion information through the historical business information of the user is low in the related technology is solved.

Description

Technical Field

[0001] The present application relates to the field of big data, and more specifically, to a method, device and electronic device for determining promotional information. Background Art

[0002] As the types of services provided by operators increase, in order to enable users to understand the new services, operators usually push the new services to users, so that users can handle the services according to their own needs after understanding the new services, so that the operator's services can operate normally.

[0003] Since there are many types of services and different users prefer to handle different services, different services need to be pushed to different users when pushing services. Currently, when determining to push services to a certain user, since most services are handled by a single person and used by a single person, the new service to be pushed to the user can be determined based on the user's historical service information, such as historical service handling, service consultation, etc.

[0004] However, there are currently services that are handled by one person and used by multiple people. For such services, when using the above method to determine the services that need to be pushed, since the services are used by multiple people, it is impossible to obtain accurate services to be pushed, which leads to low accuracy and efficiency of the service push operation, affecting the handling of the services and user experience.

[0005] With respect to the problem of low accuracy in determining promotion information through historical business information of users in related technologies, no effective solution has been proposed so far. Summary of the invention

[0006] The present application provides a method, device and electronic device for determining promotion information to solve the problem of low accuracy in determining promotion information through historical business information of a user in the related art.

[0007] According to one aspect of the present application, a method for determining promotion information is provided. The method includes: collecting product usage information of M users of a target group who use a target business product to obtain M groups of product usage information, where M is a positive integer; obtaining product information of the target business product, and determining a target portrait of the target group based on the product information and the M groups of product usage information; generating an expected portrait of the target group, and comparing the expected portrait with the target portrait to obtain a comparison result; determining at least one abnormal feature of the target portrait based on the comparison result, determining at least one current demand of the target group based on the at least one abnormal feature, and determining product promotion information to be sent to the target group based on the at least one current demand.

[0008] Optionally, each group of product usage information includes multiple sub-usage information at different times, and collecting product usage information of M users in the target group who use the target business product includes: for each user, obtaining the user's communication resource usage information within the target time period, wherein the communication resource usage information includes at least one of the following: traffic usage information, call duration, and wireless network usage information; obtaining the user's location information within the target time period, and obtaining the user's application usage information within the target time period; combining the communication resource usage information, call duration, and application usage information into sub-usage information within the target time period; and combining the sub-usage information under each target time period to obtain the user's product usage information.

[0009] Optionally, determining the target portrait of the target group based on the product information and M groups of product usage information includes: determining the features included in the target portrait to obtain multiple target features; inputting the multiple target features and the M groups of product usage information into a target classification model to obtain a feature value of each target feature, wherein the target classification model is used to extract target usage information belonging to the same target feature in the M groups of product usage information, and determine the feature value of the target feature based on the target usage information; updating the feature value of each target feature based on the product information to obtain an updated feature value, and combining the multiple target features and the updated feature values ​​to obtain a target portrait.

[0010] Optionally, the target portrait includes attribute characteristics of the target group, and generating an expected portrait of the target group includes: inputting characteristic values ​​of the attribute characteristics into a target prediction model to obtain the expected portrait, wherein the target prediction model is trained by multiple first sample data, and the first sample data includes historical attribute characteristics and historical expected portraits associated with the historical attribute characteristics.

[0011] Optionally, the expected portrait and the target portrait are compared to obtain a comparison result, including: obtaining the characteristic value of each target feature in the expected portrait to obtain multiple first characteristic values; obtaining the characteristic value of each target feature in the target portrait to obtain multiple second characteristic values; comparing the first characteristic value and the second characteristic value with the same target feature to obtain multiple sub-comparison results; and determining the multiple sub-comparison results as the comparison result.

[0012] Optionally, determining at least one abnormal feature of the target portrait based on the comparison result includes: for any target feature, when the feature value of the target feature is a numerical value, calculating the difference between the first feature value and the second feature value, and judging whether the difference is greater than a preset difference; when the difference is greater than the preset difference, determining that the target feature is an abnormal feature; when the feature value of the target feature is a non-numerical value, determining whether the first feature value and the second feature value are the same, and when the first feature value and the second feature value are not the same, determining that the target feature is an abnormal feature.

[0013] Optionally, determining the product promotion information to be sent to the target group based on at least one current demand includes: acquiring business products for solving each current demand from a product library, obtaining at least one target business product, and generating initial promotion information for each target business product; judging whether the initial promotion information has been pushed to the target group; if the initial promotion information has not been pushed to the target group, determining the initial promotion information as promotion information for the target group; if the promotion information has been pushed to the target group, judging whether the number of promotions is greater than a preset number; if the number of promotions is less than a preset number, determining the initial promotion information as promotion information for the target group; if the number of promotions is greater than a preset number, determining that the initial promotion information is not promotion information for the target group.

[0014] According to another aspect of the present application, a device for determining promotion information is provided. The device includes: a collection unit, which is used to collect product usage information of M users of a target group who use a target business product, and obtain M groups of product usage information, where M is a positive integer; a first determination unit, which is used to obtain product information of the target business product, and determine a target portrait of the target group based on the product information and the M groups of product usage information; a comparison unit, which is used to generate an expected portrait of the target group, and compare the expected portrait with the target portrait to obtain a comparison result; a second determination unit, which is used to determine at least one abnormal feature of the target portrait based on the comparison result, determine at least one current demand of the target group based on the at least one abnormal feature, and determine the product promotion information to be sent to the target group based on the at least one current demand.

[0015] According to another aspect of the present invention, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, a method for determining promotion information provided in the aforementioned embodiment of the present application is implemented.

[0016] According to another aspect of the present invention, there is also provided an electronic device comprising one or more processors and a memory; the memory stores computer-readable instructions, and the processor is used to execute the computer-readable instructions, wherein when the computer-readable instructions are executed, a method for determining promotion information provided in the aforementioned embodiment is executed.

[0017] Through this application, the following steps are adopted: collect product usage information of M users of the target group who use the target business product, and obtain M groups of product usage information, where M is a positive integer; obtain product information of the target business product, and determine the target portrait of the target group according to the product information and the M groups of product usage information; generate the expected portrait of the target group, and compare the expected portrait with the target portrait to obtain the comparison result; determine at least one abnormal feature of the target portrait according to the comparison result, determine at least one current demand of the target group according to the at least one abnormal feature, and determine the product promotion information sent to the target group according to the at least one current demand. The problem of low accuracy in determining promotion information through the user's historical business information in the related art is solved. By collecting the product usage information of each user in the target group, generating the target portrait of the target group according to the product usage information, and comparing the target portrait with the expected portrait, and then determining the abnormal features existing in the target portrait according to the comparison result, the needs of users in the target group are determined according to the abnormal features, and the promotion information is determined according to the needs, thereby achieving the effect of improving the accuracy of selecting promotion information. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0019] Figure 1 is a flow chart of a method for determining promotion information provided in an embodiment of the present application;

[0020] Figure 2 is a flowchart of an optional method for determining promotion information provided according to an embodiment of the present application;

[0021] Figure 3 is a schematic diagram of a device for determining promotion information provided in an embodiment of the present application;

[0022] Figure 4 It is a schematic diagram of an electronic device provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0023] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0024] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the 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 this field without creative work should fall within the scope of protection of the present application.

[0025] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0026] It should be noted that the method, device and electronic device for determining the promotional information determined in the present disclosure can be used in the field of big data, and can also be used in any field other than the field of big data. The application field of the method, device and electronic device for determining the promotional information determined in the present disclosure is not limited.

[0027] It should be noted that the collected information, user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) used in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of relevant data are in compliance with the relevant laws, regulations and standards of the relevant regions, necessary confidentiality measures are taken, and public order and good customs are not violated. Corresponding operation portals are provided for users to choose to authorize or refuse to use. For example, an interface is set up between this system and relevant users or organizations. Before obtaining relevant information, it is necessary to send an acquisition request to the aforementioned user or organization through the interface, and obtain relevant information after receiving the consent information fed back by the aforementioned user or organization.

[0028] The embodiments or examples of the present disclosure are not exhaustive, but are only illustrative of some embodiments or examples, and are not intended to be specific limitations on the scope of protection of the present disclosure. In the absence of contradiction, each step in a certain embodiment or example can be implemented as an independent example, and the steps can be combined arbitrarily. For example, the scheme after removing some steps in a certain embodiment or example can also be implemented as an independent example, and the order of the steps in a certain embodiment or example can be arbitrarily exchanged. In addition, the optional methods or optional examples in a certain embodiment or example can be combined arbitrarily; in addition, the various embodiments or examples can be combined arbitrarily, for example, some or all steps of different embodiments or examples can be combined arbitrarily, and a certain embodiment or example can be combined arbitrarily with the optional methods or optional examples of other embodiments or examples.

[0029] According to an embodiment of the present application, a method for determining promotion information is provided.

[0030] Figure 1 1 is a flow chart of a method for determining promotion information provided in an embodiment of the present application. Figure 1 As shown, the method comprises the following steps:

[0031] Step S101 , collecting product usage information of M users of a target group who use a target business product, to obtain M groups of product usage information, where M is a positive integer.

[0032] Specifically, the target service product may be a service product that a user has subscribed to and is using, for example, user 1 subscribes to a package service launched by operator A, which can be used for Internet access or calls. The target group may be a group consisting of multiple users who use the target service product, for example, a family subscribes to a communication service product, which includes 5 numbers that can be used by 5 users.

[0033] Furthermore, since different users use the service product at different times, locations, and other contents, it is necessary to obtain the product usage information of each user respectively, so as to obtain the product usage information of each user, that is, M sets of product usage information.

[0034] For example, the target service product may be a communication service product, and the contents included are as shown in Table 1:

[0035] Table 1

[0036]

[0037]

[0038] The user's product usage information may be shown in Table 2, wherein Table 2 only contains part of the product usage information of some users, which is only used as an example for explanation:

[0039] Table 2

[0040]

[0041] Table 2 can be used to determine the time when the user uses the service product, the content of use (traffic usage, calls, etc.), and the matters performed using the service product (calls, browsing applications, etc.), so that the user profile can be determined based on the user's product usage information.

[0042] Step S102, obtaining product information of the target business product, and determining the target profile of the target group based on the product information and M groups of product usage information.

[0043] Furthermore, after obtaining the user's product usage information, the target portrait of the target group can be determined based on the product usage information and product information. When determining the target portrait, a preset model can be used to analyze the product information and product usage information to determine the user's habit of using the product and obtain the target portrait shown in Table 3.

[0044] Table 3

[0045]

[0046]

[0047] After obtaining the above-mentioned portrait, the user's living habits and the applications that the user frequently browses can be determined based on the portrait, and business information can be further pushed to the user based on the living habits and application browsing situation.

[0048] It should be noted that the above Table 3 only contains some features and corresponding feature values, not all the contents.

[0049] It should be noted that after obtaining the data in Tables 1 and 2 above, the acquired data needs to be cleaned, junk data removed, and formatted in a unified format for subsequent analysis and processing. The name, ID number, address, mobile phone number, etc. involving sensitive customer information are encrypted. If the data needs to be displayed at the front desk, the key parts of the data are desensitized, such as only displaying the customer's surname, ID number or mobile phone number only displaying the first and last parts, address information hiding the building number and unit information, etc., so as to ensure the user's information security.

[0050] It should be noted that since the product usage information obtained in Table 2 is the product usage information of each user, and business promotion needs to be carried out for the entire target group, it is necessary to infer the product usage characteristics of the target group based on the product usage information of each user, and then determine the characteristic values ​​of each feature in Table 3 based on the product usage characteristics.

[0051] For example, according to the usage characteristics of mobile network users, each mobile service user can obtain the information of the APP (Application) used by the user based on the traffic flow, collect the APPs used by all mobile phone users in the target group, and then perform union and intersection operations. The purpose of the union operation is to obtain the overall picture of the APPs used in the target group, and to obtain the ranking of the APPs of each mobile service user based on the frequency and duration of APP use. Furthermore, the intersection operation is performed based on the ranking to obtain the common characteristics of the APPs used in the target group. For example: 1. All members of a certain target group frequently use a short video platform APP, and the commonly used APP label is: audio and video entertainment-a short video APP, so it can be added to the target portrait; 2. There are 4 mobile service users in a certain target group, and only 1 of them uses a homework tutoring APP. The commonly used APP label is: family education-a homework tutoring APP, so it does not need to be added to the target portrait, so that the target portrait is more closely aligned with the target group, so that each feature in the target portrait is the feature corresponding to the target group, not the feature of a certain user.

[0052] Furthermore, the preset model can infer the work and rest time of each user by analyzing the active time period, and can further use the work and rest time period to infer the age segmentation of the members of the target group, where the active time period can be defined as: a natural day is segmented into 1-hour segments, starting at the hour, with a total of 24 time periods in a day, and the starting time period is 0-1 hours. If there is activity during the time period, the time period is recorded as an active time period. By analyzing the active time period and the corresponding active range, the most intuitive result is whether the target group is gathered. Then, taking into account factors such as working days and weekends, the activity range of users in the target group can be inferred, and the user portrait of the user can be determined through the user's product usage information.

[0053] Step S103, generating an expected portrait of the target group, and comparing the expected portrait with the target portrait to obtain a comparison result.

[0054] Specifically, after obtaining the expected portrait of the target group, the attribute information in the expected portrait can be obtained, such as the number of users included in the group, the product usage of each user, etc., so as to generate the expected portrait of the target group based on the attribute information, wherein the expected portrait is used to represent the usage of the target business product by the target group under normal circumstances.

[0055] Furthermore, after obtaining the expected portrait and the target portrait, the expected portrait and the target portrait may be compared to determine abnormal features in the target portrait, and then push information may be determined based on the abnormal features.

[0056] Step S104, determining at least one abnormal feature of the target portrait according to the comparison result, determining at least one current demand of the target group according to the at least one abnormal feature, and determining product promotion information to be sent to the target group according to the at least one current demand.

[0057] Specifically, after comparing the target portrait with the expected portrait, the differences between the target portrait and the expected portrait, that is, the difference characteristics, can be determined based on the comparison results. The difference characteristics are the differentiated product usage habits of the target group, and then the differentiated needs of the target group can be inferred. Based on the needs, the product promotion information to be sent to the target group can be determined, thereby achieving the technical effect of accurately determining the product promotion information to be sent to the target group.

[0058] It should be noted that after obtaining the abnormal features, the user needs can be determined according to the abnormal features. At this time, it is necessary to comprehensively analyze the relationship between the various abnormal features, and determine the user needs according to the relationship between the various abnormal features. That is, the user needs can be analyzed separately according to each abnormal feature, and multiple abnormal features can also be comprehensively analyzed to determine the user needs.

[0059] For example, when the characteristic value of the abnormal feature is: traffic consumption is higher than the in-suite traffic and traffic is used from 19:00 to 21:00, since the characteristic value in the expected portrait is: traffic consumption is lower than the in-suite traffic and wifi is used from 19:00 to 21:00, it can be determined that the wifi signal of the target group is poor during the period of 19:00-21:00, causing users to use traffic, which in turn causes traffic consumption to be higher than the in-suite traffic. At this time, the current needs of the target group can be determined by combining the abnormal features, and then the promotion information can be determined based on the current needs.

[0060] The method for determining promotion information provided by the embodiment of the present application collects product usage information of M users of the target group using the target business product to obtain M groups of product usage information, where M is a positive integer; obtains product information of the target business product, and determines the target portrait of the target group according to the product information and the M groups of product usage information; generates an expected portrait of the target group, and compares the expected portrait with the target portrait to obtain a comparison result; determines at least one abnormal feature of the target portrait according to the comparison result, determines at least one current demand of the target group according to the at least one abnormal feature, and determines the product promotion information sent to the target group according to the at least one current demand. The problem of low accuracy in determining promotion information through the user's historical business information in the related art is solved. By collecting product usage information of each user in the target group, generating a target portrait of the target group according to the product usage information, and comparing the target portrait with the expected portrait, and then determining the abnormal features existing in the target portrait according to the comparison result, the needs of users in the target group are determined according to the abnormal features, and the promotion information is determined according to the needs, thereby achieving the effect of improving the accuracy of selecting promotion information.

[0061] Optionally, in the method for determining promotional information provided in an embodiment of the present application, each group of product usage information includes multiple sub-usage information at different times, and collecting product usage information of M users of a target group who use a target business product includes: for each user, obtaining the user's communication resource usage information within a target time period, wherein the communication resource usage information includes at least one of the following: traffic usage information, call duration, and wireless network usage information; obtaining the user's location information within the target time period, and obtaining the user's application usage information within the target time period; combining the communication resource usage information, call duration, and application usage information into sub-usage information within the target time period; and combining the sub-usage information under each target time period to obtain the user's product usage information.

[0062] Specifically, when obtaining the user's product usage information, you can obtain usage information in multiple dimensions, including: communication resource usage information, call duration and application usage information. When obtaining the usage information, you can obtain it according to time periods. For example, divide a day into 24 time periods, and obtain sub-usage information for each time period, and combine the sub-usage information of multiple time periods to obtain the product usage information of one user, and combine the product usage information of multiple users in the target group into the product usage information of the target group.

[0063] For example, Table 4 may be some product usage information:

[0064] Table 4

[0065]

[0066] Through Table 2, it can be determined that the main user uses traffic to browse application B during the time period of 7:00-8:00, thereby obtaining product usage information of each user.

[0067] This embodiment achieves the technical effect of accurately obtaining the user's product usage information by obtaining the user's product usage information in multiple usage dimensions, and obtaining and combining the product usage information in multiple dimensions according to time periods.

[0068] Optionally, in the method for determining promotional information provided in an embodiment of the present application, determining the target portrait of the target group based on product information and M groups of product usage information includes: determining the features contained in the target portrait to obtain multiple target features; inputting the multiple target features and the M groups of product usage information into a target classification model to obtain a feature value of each target feature, wherein the target classification model is used to extract target usage information belonging to the same target feature in the M groups of product usage information, and determine the feature value of the target feature based on the target usage information; updating the feature value of each target feature according to the product information to obtain an updated feature value, and combining the multiple target features and the updated feature values ​​to obtain a target portrait.

[0069] Specifically, since it is necessary to use the product usage information of each user to generate a group portrait of the target group when generating the target portrait, it is necessary to classify and summarize the product usage information of each user through a target classification model, so as to determine the target features and the feature values ​​under the target features in the product usage information.

[0070] It should be noted that the target feature can be a preset feature or a target feature determined based on product usage information. For example, if users 1 to 5 all use application A, application A can be the target feature, and the feature value of the feature is 5, so that the product usage of the target group can be determined based on the product usage of the users, and then the target profile can be obtained.

[0071] Table 5 may be a comparison table of target features and corresponding feature values, as shown in Table 5:

[0072] Table 5

[0073]

[0074] After obtaining the comparison table in Table 5, the product information of the target business product can be obtained, and the characteristic values ​​in the comparison table can be modified according to the product information, changing the characteristic values ​​to comparison results with the product information. The modified comparison table is shown in Table 6. After obtaining Table 6, Table 6 can be determined as the target portrait of the target group.

[0075] Table 6

[0076]

[0077] This embodiment generates a target portrait of the target group, thereby laying a foundation for subsequently determining push information based on the target portrait.

[0078] In order to obtain an accurate expected portrait, optionally, in the method for determining promotion information provided in an embodiment of the present application, the target portrait includes attribute characteristics of the target group, and generating the expected portrait of the target group includes: inputting the characteristic values ​​of the attribute characteristics into a target prediction model to obtain the expected portrait, wherein the target prediction model is trained by multiple first sample data, and the first sample data includes historical attribute characteristics and historical expected portraits associated with the historical attribute characteristics.

[0079] Specifically, when generating an expected portrait, a target prediction model can be used to generate an expected portrait corresponding to the target group under general circumstances corresponding to the attribute information based on the attribute features in the target portrait, wherein the attribute features can be related information such as the number of people in the target group, age distribution, working hours, etc.

[0080] It should be noted that the target prediction model is trained with historical attribute features and historical expected portraits associated with the historical attribute features as sample data, so that a conventional portrait under the attribute features can be generated based on the attribute features, that is, the expected portrait. For example, for the usage of application A, the target portrait may show that 5 people actively use it during time period A-time period B, but the expected portrait may show that 2 people for this group use it during time period C-time period D, where the duration of time period A-time period B is greater than that of time period C-time period D. At this time, it can be determined that the target group prefers to use application A, so that the promotional information to be pushed to the target group can be determined based on the comparison between the target portrait and the expected portrait.

[0081] In order to accurately determine the abnormal characteristics, optionally, in the method for determining the promotion information provided in the embodiment of the present application, the expected portrait and the target portrait are compared to obtain a comparison result including: obtaining the characteristic value of each target feature in the expected portrait to obtain a plurality of first characteristic values; obtaining the characteristic value of each target feature in the target portrait to obtain a plurality of second characteristic values; comparing the first characteristic value and the second characteristic value with the same target feature to obtain a plurality of sub-comparison results; and determining the plurality of sub-comparison results as the comparison result.

[0082] Specifically, when comparing the target portrait with the expected portrait, the feature value of each target feature in the expected portrait can be obtained, and compared with the feature value of the same target feature in the target portrait, thereby obtaining multiple sub-comparison results, and the multiple sub-comparison results are combined into a comparison result between the target portrait and the expected portrait.

[0083] For example, the target feature in the target portrait: the number of members, the feature value of which is 5, is obtained, and the target feature in the expected portrait: the number of members, the feature value of which is 5, is obtained. At this time, the above two feature values ​​are compared to obtain a sub-comparison result.

[0084] This embodiment lays a foundation for subsequently determining promotion information based on abnormal features by comparing the target portrait with the expected portrait.

[0085] In order to accurately determine abnormal features, optionally, in the method for determining promotion information provided in an embodiment of the present application, determining at least one abnormal feature of the target portrait based on the comparison result includes: for any target feature, when the feature value of the target feature is a numerical value, calculating the difference between the first feature value and the second feature value, and judging whether the difference is greater than a preset difference; when the difference is greater than the preset difference, determining that the target feature is an abnormal feature; when the feature value of the target feature is a non-numerical value, determining whether the first feature value and the second feature value are the same, and when the first feature value and the second feature value are not the same, determining that the target feature is an abnormal feature.

[0086] Specifically, when determining the abnormal feature according to the comparison result, since each sub-comparison result corresponds to a target feature, the feature whose sub-comparison result is abnormal can be determined as the abnormal feature.

[0087] When determining whether the sub-comparison result is abnormal, it is necessary to determine the processing method of the comparison result according to the type of feature value. In the case where the feature value of the target feature is a numerical value, the difference between the first feature value and the second feature value can be calculated, and whether it is an abnormal feature can be determined based on the difference. For example, the target feature is: the number of users using APP1. The feature value of this feature in the target portrait is 5, and the feature value in the expected portrait is 2. The difference is 150%. At this time, it can be determined that the target feature is an abnormal feature.

[0088] Furthermore, when the feature value of the target feature is non-numeric, the feature value representing the feature is text. In this case, whether the feature is an abnormal feature can be determined by determining whether the text is completely consistent. When the first feature value and the second feature value are exactly the same, the feature is not an abnormal feature. When the first feature value and the second feature value are different, the feature value is different from the expected feature value. In this case, the feature can be determined to be an abnormal feature.

[0089] For example, when the target feature is traffic consumption, the feature value in the target portrait can be: the traffic used is higher than the traffic in the suite, and the feature value in the expected portrait can be: the traffic used is lower than the traffic in the suite. In this case, the feature characterizing traffic consumption is an abnormal feature, and all abnormal features in the target portrait are obtained through the above operations.

[0090] This embodiment determines the abnormal feature according to the comparison result of the feature value, thereby laying a foundation for subsequently determining the promotion information according to the abnormal feature.

[0091] In order to ensure the accuracy and rationality of the promotional information sent to the target group, optionally, in the method for determining the promotional information provided in the embodiment of the present application, determining the product promotion information to be sent to the target group based on at least one current demand includes: obtaining business products for solving each current demand from a product library, obtaining at least one target business product, and generating initial promotion information for each target business product; judging whether the initial promotion information has been pushed to the target group; if the initial promotion information has not been pushed to the target group, determining the initial promotion information as the promotion information of the target group; if the promotion information has been pushed to the target group, judging whether the number of promotions is greater than a preset number; if the number of promotions is less than a preset number, determining the initial promotion information as the promotion information of the target group; if the number of promotions is greater than the preset number, determining that the initial promotion information is not the promotion information of the target group.

[0092] Specifically, Figure 2 is a flowchart of an optional method for determining promotion information provided in an embodiment of the present application, such as Figure 2 As shown, after the current needs of the target group are determined, business products for solving each current need can be obtained from the product library, and initial promotion information can be generated based on the business products.

[0093] Furthermore, after generating the initial promotion information, it is also necessary to determine whether the initial promotion information has been pushed before, that is, to determine whether the initial promotion information has been pushed to the target group. If the initial promotion information has not been pushed to the target group, the initial promotion information can be sent to the target group. If the promotion information has been pushed to the target group, it is necessary to determine whether the initial promotion information can be sent to the target group based on the number of promotions.

[0094] When the number of promotions is less than the preset number, it means that the number of times the initial promotion information is sent to the target group is small. At this time, the initial promotion information can be sent to the target group. When the number of promotions is greater than the preset number, it means that the number of promotions is too many and the user has not yet purchased or processed the product service. At this time, it can be determined that the initial promotion information does not need to be promoted to the target group, thereby completing the screening operation of the initial promotion information and ensuring the accuracy and rationality of the promotion information sent to the target group.

[0095] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0096] The present application also provides a device for determining promotion information. It should be noted that the device for determining promotion information in the present application can be used to execute the method for determining promotion information provided in the present application. The following introduces the device for determining promotion information provided in the present application.

[0097] Figure 3 Schematic diagram of a device for determining promotion information provided in an embodiment of the present application. Figure 3 As shown, the device includes: a collecting unit 31 , a first determining unit 32 , a comparing unit 33 , and a second determining unit 34 .

[0098] The collecting unit 31 is used to collect product usage information of M users of a target group who use a target service product, and obtain M groups of product usage information, where M is a positive integer.

[0099] The first determination unit 32 is used to obtain product information of the target business product, and determine the target profile of the target group according to the product information and M groups of product usage information.

[0100] The comparison unit 33 is used to generate an expected profile of the target group, and compare the expected profile with the target profile to obtain a comparison result.

[0101] The second determination unit 34 is used to determine at least one abnormal feature of the target portrait according to the comparison result, determine at least one current demand of the target group according to the at least one abnormal feature, and determine the product promotion information to be sent to the target group according to the at least one current demand.

[0102] The promotion information determination device provided in the embodiment of the present application collects product usage information of M users of the target group who use the target business product through the collection unit 31, and obtains M groups of product usage information, wherein M is a positive integer; the first determination unit 32 obtains the product information of the target business product, and determines the target portrait of the target group according to the product information and the M groups of product usage information; the comparison unit 33 generates the expected portrait of the target group, compares the expected portrait with the target portrait, and obtains the comparison result; the second determination unit 34 determines at least one abnormal feature of the target portrait according to the comparison result, determines at least one current demand of the target group according to the at least one abnormal feature, and determines the product promotion information sent to the target group according to the at least one current demand. The problem of low accuracy in determining promotion information through the historical business information of the user in the related art is solved, by collecting the product usage information of each user in the target group, generating the target portrait of the target group according to the product usage information, and comparing the target portrait with the expected portrait, and then determining the abnormal features existing in the target portrait according to the comparison result, thereby determining the needs of the users in the target group according to the abnormal features, and determining the promotion information according to the needs, thereby achieving the effect of improving the accuracy of selecting promotion information.

[0103] Optionally, in the device for determining promotion information provided in the embodiment of the present application, each group of product usage information includes multiple sub-usage information at different times, and the collection unit 31 includes: a first acquisition module, used to obtain the communication resource usage information of each user within the target time period, wherein the communication resource usage information includes at least one of the following: traffic usage information, call duration, wireless network usage information; a second acquisition module, used to obtain the user's location information within the target time period, and obtain the user's application usage information within the target time period; a first combination module, used to combine the communication resource usage information, call duration and application usage information into sub-usage information within the target time period; a second combination module, used to combine the sub-usage information under each target time period to obtain the user's product usage information.

[0104] Optionally, in the device for determining promotion information provided in the embodiment of the present application, the first determination unit 32 includes: a first determination module, used to determine the features included in the target portrait to obtain multiple target features; a first input module, used to input multiple target features and M groups of product usage information into a target classification model to obtain a feature value of each target feature, wherein the target classification model is used to extract target usage information belonging to the same target feature in the M groups of product usage information, and determine the feature value of the target feature based on the target usage information; an update module, used to update the feature value of each target feature according to the product information to obtain an updated feature value, and combine multiple target features and updated feature values ​​to obtain a target portrait.

[0105] Optionally, in the device for determining promotion information provided in the embodiment of the present application, the target portrait includes attribute characteristics of the target group, and the comparison unit 33 includes: a second input module, used to input the characteristic value of the attribute characteristic into the target prediction model to obtain an expected portrait, wherein the target prediction model is trained by multiple first sample data, and the first sample data includes historical attribute characteristics and historical expected portraits associated with the historical attribute characteristics.

[0106] Optionally, in the device for determining promotion information provided in the embodiment of the present application, the comparison unit 33 includes: a third acquisition module, used to obtain the characteristic values ​​of each target feature in the expected portrait, and obtain multiple first characteristic values; a fourth acquisition module, used to obtain the characteristic values ​​of each target feature in the target portrait, and obtain multiple second characteristic values; a comparison module, used to compare the first characteristic value and the second characteristic value with the same target feature, and obtain multiple sub-comparison results; a second determination module, used to determine the multiple sub-comparison results as the comparison result.

[0107] Optionally, in the device for determining promotion information provided in the embodiment of the present application, the second determination unit 34 includes: a first judgment module, for calculating the difference between the first eigenvalue and the second eigenvalue for any target feature when the eigenvalue of the target feature is a numerical value, and judging whether the difference is greater than a preset difference; a third determination module, for determining that the target feature is an abnormal feature when the difference is greater than a preset difference; and a fourth determination module, for determining whether the first eigenvalue and the second eigenvalue are the same when the eigenvalue of the target feature is a non-numeric value, and determining that the target feature is an abnormal feature when the first eigenvalue and the second eigenvalue are not the same.

[0108] Optionally, in the device for determining promotion information provided in the embodiment of the present application, the second determination unit 34 includes: a fifth acquisition module, used to acquire business products for solving various current needs from the product library, obtain at least one target business product, and generate initial promotion information for each target business product; a second judgment module, used to determine whether the initial promotion information has been pushed to the target group; a fifth determination module, used to determine the initial promotion information as the promotion information of the target group if the initial promotion information has not been pushed to the target group; a third judgment module, used to determine whether the number of promotions is greater than a preset number if the promotion information has been pushed to the target group; a sixth determination module, used to determine the initial promotion information as the promotion information of the target group if the number of promotions is less than a preset number; a seventh determination module, used to determine that the initial promotion information is not the promotion information of the target group if the number of promotions is greater than a preset number.

[0109] The above-mentioned promotion information determination device includes a processor and a memory. The above-mentioned collection unit 31, first determination unit 32, comparison unit 33, second determination unit 34, etc. are all stored in the memory as program units, and the processor executes the above-mentioned program units stored in the memory to realize corresponding functions.

[0110] The processor includes a kernel, which retrieves the corresponding program unit from the memory. One or more kernels can be set, and the problem of low accuracy in determining promotion information through historical business information of users in related technologies is solved by adjusting kernel parameters.

[0111] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0112] An embodiment of the present invention provides a computer-readable storage medium on which a program is stored. When the program is executed by a processor, the method for determining promotion information is implemented.

[0113] An embodiment of the present invention provides a processor, which is used to run a program, wherein the method for determining promotion information is executed when the program is running.

[0114] Figure 4 is a schematic diagram of an electronic device provided according to an embodiment of the present application, such as Figure 4 As shown, an embodiment of the present invention provides an electronic device, the electronic device 40 includes a processor, a memory, and a program stored in the memory and executable on the processor, and the processor implements the steps of the above-mentioned method for determining promotion information when executing the program. The device in this article can be a server, a PC, a PAD, a mobile phone, etc.

[0115] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program that initializes the steps of the above-mentioned promotion information determination method.

[0116] 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.

[0117] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented 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 generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0118] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0119] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0120] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0121] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0122] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules 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 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 temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0123] 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.

[0124] The above are only embodiments of the present application and are 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 within the scope of the claims of the present application.

Claims

1. A method for determining promotion information, characterized in that: include: Collect product usage information of M users of a target group who use a target business product to obtain M groups of product usage information, where M is a positive integer; Acquire product information of the target business product, and determine the target profile of the target group according to the product information and the M group product usage information; Generate an expected profile of the target group, compare the expected profile with the target profile, and obtain a comparison result; At least one abnormal feature of the target portrait is determined based on the comparison result, at least one current demand of the target group is determined based on the at least one abnormal feature, and product promotion information to be sent to the target group is determined based on the at least one current demand.

2. The method according to claim 1, characterized in that: Each set of product usage information contains multiple sub-usage information at different times. The product usage information of M users in the target group who use the target business product is collected, including: For each user, obtaining the communication resource usage information of the user in the target time period, wherein the communication resource usage information includes at least one of the following: traffic usage information, call duration, and wireless network usage information; Acquire the location information of the user within the target time period, and acquire the application usage information of the user within the target time period; combining the communication resource usage information, the call duration, and the application usage information into sub-usage information within the target time period; The sub-usage information in each target time period is combined to obtain the product usage information of the user.

3. The method according to claim 1, characterized in that: Determining the target profile of the target group according to the product information and the M group product usage information includes: Determine the features included in the target portrait to obtain multiple target features; Inputting the multiple target features and the M groups of product usage information into a target classification model to obtain a feature value of each target feature, wherein the target classification model is used to extract target usage information belonging to the same target feature from the M groups of product usage information, and determine the feature value of the target feature according to the target usage information; The feature value of each target feature is updated according to the product information to obtain an updated feature value, and the multiple target features and the updated feature values ​​are combined to obtain the target portrait.

4. The method according to claim 1, characterized in that: The target profile includes attribute characteristics of the target group, and generating the expected profile of the target group includes: The characteristic value of the attribute feature is input into the target prediction model to obtain the expected portrait, wherein the target prediction model is trained by multiple first sample data, and the first sample data includes historical attribute features and historical expected portraits associated with the historical attribute features.

5. The method according to claim 1, characterized in that The expected profile and the target profile are compared to obtain the following comparison results: Acquire the feature value of each target feature in the desired portrait to obtain a plurality of first feature values; Acquire a feature value of each target feature in the target portrait to obtain a plurality of second feature values; Comparing the first characteristic value and the second characteristic value having the same target characteristic to obtain a plurality of sub-comparison results; The multiple sub-comparison results are determined as the comparison result.

6. The method according to claim 5, characterized in that Determining at least one abnormal feature of the target image according to the comparison result includes: For any target feature, when the feature value of the target feature is a numerical value, calculating the difference between the first feature value and the second feature value, and determining whether the difference is greater than a preset difference; When the difference is greater than the preset difference, determining the target feature as the abnormal feature; In the case where the characteristic value of the target feature is a non-numeric value, it is determined whether the first characteristic value and the second characteristic value are the same, and in the case where the first characteristic value and the second characteristic value are not the same, it is determined that the target feature is an abnormal feature.

7. The method according to claim 1, characterized in that Determining the product promotion information to be sent to the target group according to the at least one current demand includes: Acquire business products for solving various current needs from the product library, obtain at least one target business product, and generate initial promotion information for each target business product; Determining whether the initial promotion information has been pushed to the target group; In the case where the initial promotion information has not been pushed to the target group, determining the initial promotion information as the promotion information for the target group; In the case where the promotion information has been pushed to the target group, determining whether the number of promotions is greater than a preset number; When the number of promotions is less than the preset number of times, determining the initial promotion information as the promotion information for the target group; When the number of promotions is greater than the preset number of times, it is determined that the initial promotion information is not promotion information for the target group.

8. A device for determining promotion information, characterized in that: include: A collecting unit, used to collect product usage information of M users of a target group who use a target business product, to obtain M groups of product usage information, where M is a positive integer; A first determination unit is used to obtain product information of the target business product, and determine a target profile of the target group according to the product information and the M group product usage information; A comparison unit, used for generating an expected profile of the target group, comparing the expected profile with the target profile, and obtaining a comparison result; The second determination unit is used to determine at least one abnormal feature of the target portrait according to the comparison result, determine at least one current demand of the target group according to the at least one abnormal feature, and determine product promotion information to be sent to the target group according to the at least one current demand.

9. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for determining promotion information according to any one of claims 1 to 7 is implemented.

10. An electronic device, characterized in that: It includes one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method for determining promotion information as described in any one of claims 1 to 7.

Images