Customer obtaining method, digital intelligent marketing system, terminal equipment and storage medium

Abstract

The invention discloses a customer obtaining method, a digital intelligent marketing system, terminal equipment and a storage medium, and the method comprises the steps: obtaining at least one piece of historical delivery information meeting a preset matching condition with to-be-delivered information of a product; determining a non-target user of the to-be-released information according to the negative evaluation of each piece of historical released information; determining a non-target user group according to the number of the non-target users in each user group; according to the clustering condition set of the non-target user group, determining each target user group from the user groups, wherein a common clustering condition does not exist between the target user group and the clustering condition set of the non-target user group, or at least one clustering condition is mutually exclusive to a certain clustering condition in the clustering condition set of the non-target user group; and determining each target user of the to-be-released information from each target user group. By implementing the method, the memory consumption when the target user is acquired can be reduced, and the efficiency of acquiring the target user is improved.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a customer acquisition method, a digital marketing system, a terminal device and a storage medium. Background Art

[0002] In the field of marketing, delivering product information to users is a very important means of product dissemination. In order to increase the marketing success rate of products, the target users of products are usually selected through digital marketing systems for information delivery.

[0003] In the related art, the method of acquiring target users through the digital marketing system is to filter the user data matching the product characteristics from the user data according to the product characteristics, so as to determine the target users for product information delivery. However, this method requires traversing and converting all user data, resulting in a large amount of memory consumption when acquiring target users, increasing hardware costs and affecting the efficiency of acquiring target users. Summary of the invention

[0004] Embodiments of the present invention provide a customer acquisition method, a digital marketing system, a terminal device, and a storage medium, which can reduce memory consumption when acquiring target users and improve the efficiency of acquiring target users.

[0005] An embodiment of the present invention provides a customer acquisition method, comprising: obtaining at least one historical delivery information that meets a preset matching condition with the product's to-be-delivered information; Determining non-target users of the information to be delivered according to the negative evaluations of each of the historical delivery information; Determine a non-target user group according to the number of the non-target users in each user group; According to the clustering condition set of the non-target user group, determining from the user groups the target user groups that have no common clustering condition with the clustering condition set of the non-target user group, or at least one clustering condition is mutually exclusive with a clustering condition in the clustering condition set of the non-target user group; Determining each target user to whom the information is to be delivered from each target user group; Each of the user groups is provided with a corresponding clustering condition set, and users meeting the clustering condition set are divided into the corresponding user group; the clustering condition set includes at least one clustering condition.

[0006] Furthermore, it also includes: determining at least one common clustering condition according to the clustering condition set of each user group; Determining a user set that meets the common clustering condition according to the user data of each user; In the case where the clustering condition set of the user group includes the common clustering condition, determining each user belonging to the user group according to the user set of the common clustering condition and the user sets meeting each independent clustering condition of the user group; The independent clustering condition is a clustering condition in the clustering condition set of the user group except the common clustering condition.

[0007] Furthermore, it also includes: determining that the independent clustering conditions of any two of the user groups are mutually opposed conditions, and obtaining the user set of the independent clustering condition of the other user group based on the user set of the independent clustering condition of one of the user groups.

[0008] Furthermore, the user data belonging to any of the user groups is recorded with a unique identifier corresponding to the user group, and the user group to which the non-target user belongs is determined according to the user data of the non-target user.

[0009] Further, determining non-target users of the information to be delivered according to the negative evaluations of each of the historical delivery information includes: Determining a candidate user who publishes the negative evaluation according to any negative evaluation of the historical delivery information; When the number of positive evaluations by the candidate users on each of the historical delivery information is less than a preset number, the candidate users are determined to be non-target users of the information to be delivered.

[0010] Further, determining the non-target user group according to the number of the non-target users in each user group includes: Obtaining a candidate user group in which the number of non-target users in each of the user groups reaches a preset ratio; It is determined that the number of users in the candidate user group who have published positive comments on at least one of the historical delivery information is less than a preset number, and the candidate user group is determined as a non-target user group.

[0011] Furthermore, it also includes: determining that the historical delivery information does not exist, and obtaining a target clustering condition set whose matching degree with the information feature reaches a preset matching degree according to the information feature of the information to be delivered; According to the target clustering condition set, users in each user group having an intersection between the clustering condition set and the target clustering condition set are determined as target users to which information is to be delivered.

[0012] Based on the above method embodiment, the present invention provides a corresponding device embodiment; An embodiment of the present invention provides a digital marketing system, including: an information matching module, a first processing module, a second processing module, a user screening module, and a user acquisition module; The information matching module is used to obtain at least one piece of historical delivery information that meets a preset matching condition with the product's to-be-delivered information; The first processing module is used to determine non-target users of the information to be delivered according to the negative evaluations of each of the historical delivery information; The second processing module is used to determine the non-target user group according to the number of the non-target users in each user group; The user screening module is used to determine, from the user groups, according to the clustering condition set of the non-target user group, target user groups that do not have a common clustering condition with the clustering condition set of the non-target user group, or at least one clustering condition is mutually exclusive with a clustering condition in the clustering condition set of the non-target user group; The user acquisition module is used to determine each target user to which the information is to be delivered from each target user group; Each of the user groups is provided with a corresponding clustering condition set, and users meeting the clustering condition set are divided into the corresponding user group; the clustering condition set includes at least one clustering condition.

[0013] Based on the above method embodiment, the present invention provides another embodiment; Another embodiment of the present invention provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, it implements the customer acquisition method provided by any one of the above method embodiments of the present application.

[0014] Based on the method embodiment of the present invention, another embodiment is provided: Another embodiment of the present invention provides a storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the storage medium is located is controlled to execute the customer acquisition method provided by any one of the above-mentioned method embodiments of the present invention.

[0015] The following beneficial effects are achieved by implementing the embodiments of the present invention: The embodiment of the present invention provides a customer acquisition method, apparatus, terminal device and storage medium. The method obtains at least one historical delivery information that meets preset matching conditions with the information to be delivered of a product, determines non-target users of the information to be delivered according to negative comments of each historical delivery information, determines the non-target user groups according to the number of non-target users in each user group, and then determines, from each user group, according to the clustering condition set of the non-target user group, each target user group that does not have a common clustering condition with the clustering condition set of the non-target user group, or at least one clustering condition is mutually exclusive with a clustering condition in the clustering condition set of the non-target user group, so as to determine each target user of the information to be delivered from each target user group, thereby only needing to screen each user group through the non-target users of the information to be delivered, so as to screen out the target user group from each user group to determine each target user of the information to be delivered, without traversing and converting the user data of all users, thereby reducing the memory consumption when acquiring the target users and improving the efficiency of acquiring the target users. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a flowchart of a customer acquisition method provided by an embodiment of the present invention.

[0017] Figure 2 It is a flowchart of a customer acquisition method provided by another embodiment of the present invention.

[0018] Figure 3 It is a flowchart of a customer acquisition method provided by another embodiment of the present invention.

[0019] Figure 4 It is a structural diagram of a digital marketing system provided by one embodiment of the present invention.

[0020] Figure 5 It is a structural diagram of a digital marketing system provided by another embodiment of the present invention. DETAILED DESCRIPTION

[0021] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0022] See also Figure 1 , is a flow chart of a customer acquisition method provided by an embodiment of the present invention, including: Step S101: Obtain at least one piece of historical delivery information that meets a preset matching condition with the product's to-be-delivered information.

[0023] The information to be released for a product may be advertising information or introduction information to be released for the product, which may include characteristic information used to represent product characteristics, such as the product's name, type, applicable population, function, features, and price, etc. The information to be released may be presented in text, video, or voice formats.

[0024] For the information to be released, the information content of the information to be released can be matched with each piece of information that has been released. Among them, the released information can be the advertising information or introduction information of a certain product that has been released, and it can also include characteristic information used to represent the characteristics of the product, such as the name, type, applicable population, function, characteristics and price of the product. By matching the information content of the information to be released with each piece of information that has been released, the released information that meets the preset matching conditions, such as the content matching degree reaching the preset matching degree, can be obtained from each piece of information that has been released as the historical release information that meets the preset matching conditions with the information to be released of the product.

[0025] Step S102: Determine non-target users of the information to be delivered according to the negative evaluations of each of the historical delivery information.

[0026] Specifically, for any historical delivery information, all evaluation information for the historical delivery information can be obtained from a database storing evaluation information of any historical delivery information through an API interface. For any evaluation information, the evaluation information can be determined to be a negative evaluation or a non-negative evaluation according to the grade evaluation information corresponding to the evaluation information. Exemplarily, when commenting on the historical delivery information, the grade evaluation information for the historical delivery information is usually attached, such as the grade evaluation information of 1-5 stars. The grade evaluation information can be used to reflect the user's negative evaluation or non-negative evaluation of the historical delivery information, such as the grade evaluation information of 3-5 stars is a non-negative evaluation; the grade evaluation information of 1-2 stars is a negative evaluation. Alternatively, the evaluation information can be determined to be a negative evaluation or a non-negative evaluation according to the keywords extracted from the evaluation information, such as matching the extracted keywords with each preset negative evaluation entry. Alternatively, the evaluation information can also be subjected to semantic analysis to determine whether the evaluation information is a negative evaluation or a non-negative evaluation. For any negative evaluation in the evaluation information of each historical delivery information, the user who posted the negative evaluation can be determined to determine the user as a non-target user of the information to be delivered.

[0027] Step S103: Determine a non-target user group according to the number of non-target users in each user group.

[0028] Each user group is provided with a corresponding clustering condition set, and users meeting the clustering condition set are divided into the corresponding user group, and the clustering condition set includes at least one clustering condition.

[0029] Specifically, before determining the target user, each user can be clustered according to the user data of each user, and each user can be assigned to a corresponding user group. For any user group, a corresponding clustering condition set is set, and the clustering condition set includes at least one clustering condition, such as a combination of multiple clustering conditions, or a single clustering condition. The clustering condition can be a compound condition or a single condition, and the compound condition can be a logical combination of multiple single conditions. Exemplarily, the clustering condition set can be (A AND B) OR C, A AND B is a compound condition composed of single condition A and single condition B, and C is a single condition. The single condition can be set according to the actual situation, such as annual income greater than a preset value, annual income less than a preset value, age less than a preset age, age greater than a preset age or occupation requirements, etc.

[0030] Through the pre-stored user data of each user, the user data of each user can be matched with the clustering condition set of the user group to classify each user into the corresponding user group. The user data can be uploaded by the user himself or obtained through a publicly available data acquisition channel. The user data can include the user's annual income, occupation, age, and fixed assets, etc.

[0031] For any user group, non-target users can be searched from all users in the user group to determine the number of non-target users in the user group. To facilitate the subsequent determination of the user group to which a user belongs, each user group is provided with a unique identifier corresponding to the user group. After each user is divided into a corresponding user group, the unique identifier of the user group is written into the user data of the user, so that the user data belonging to the user group is recorded with the unique identifier corresponding to the user group. At this time, by identifying the unique identifier in the user data of the non-target user, the user group to which the non-target user belongs can be determined, without traversing all users in the user group, thereby improving the efficiency of finding the number of non-target users in the user group.

[0032] After determining the number of non-target users in any user group, it can be determined whether the number of non-target users in the user group reaches a preset number, or whether the proportion of non-target users in the user group reaches a preset ratio. If so, the user group can be determined to be a non-target user group.

[0033] Step S104: According to the clustering condition set of the non-target user group, target user groups are determined from the user groups, which have no common clustering condition with the clustering condition set of the non-target user group, or have at least one clustering condition that is mutually exclusive with a clustering condition in the clustering condition set of the non-target user group.

[0034] Among them, the common clustering condition refers to the clustering condition in which at least two clustering condition sets exist at the same time. Specifically, the rules of each user group are compared in pairs to obtain the common clustering condition. For example, the clustering condition set of user group 1 is (A AND B) OR C, and the clustering condition set of user group 2 is (A AND B) OR D. By comparing user group 1 and user group 2, it can be determined that the common clustering condition is (A AND B). Clustering conditions are mutually exclusive, which means that there is no intersection between clustering conditions. For example, the clustering condition set of user group 1 is (A AND B) OR C, and the clustering condition set of user group 2 is (A AND B) OR D. Clustering condition C is occupational demand, and clustering condition D is that annual income is greater than a preset value. By comparing the clustering conditions of user group 1 and user group 2, it can be determined that clustering condition C and clustering condition D are mutually exclusive.

[0035] The clustering condition set of the non-target user group is compared with the clustering condition set of any user group to determine whether there are common clustering conditions between the two clustering condition sets, or whether there are mutually exclusive clustering conditions. If there are no common clustering conditions between the two clustering condition sets, the user group can be determined as the target user group; or if there are mutually exclusive clustering conditions between the two clustering condition sets, the user group can be determined as the target user group.

[0036] Step S105: Determine the target users to whom the information is to be delivered from the target user groups.

[0037] Specifically, all users in each user group may be determined as target users to which information is to be delivered; or, all users in each user group except non-target users may be determined as target users to which information is to be delivered.

[0038] By acquiring at least one historical delivery information that meets preset matching conditions with the product's information to be delivered, non-target users of the information to be delivered are determined based on negative comments of each historical delivery information, and after the non-target user groups are determined based on the number of non-target users in each user group, target user groups that do not have a common clustering condition with the clustering condition set of the non-target user group, or at least one clustering condition is mutually exclusive with a clustering condition in the clustering condition set of the non-target user group, are determined from each user group, so as to determine each target user of the information to be delivered from each target user group. Thus, each user group only needs to be screened through the non-target users of the information to be delivered, so as to screen out the target user groups from each user group to determine each target user of the information to be delivered, without traversing and converting the user data of all users, thereby reducing the memory consumption when acquiring the target users and improving the efficiency of acquiring the target users.

[0039] In addition, since users who are interested in the product may not comment on the product's launch information, non-target users who post negative comments are usually users who clearly have no interest in the product. Therefore, using non-target users to reversely screen the target user group can more comprehensively screen out users who may be interested in the product.

[0040] like Figure 2 As shown, in a preferred embodiment, the division of the user groups to which each user belongs may include step S1011: determining at least one common clustering condition according to the clustering condition sets of each user group.

[0041] Specifically, the rules of each user group are compared in pairs to obtain the common clustering condition. For example, the clustering condition set of user group 1 is (A AND B) OR C, and the clustering condition set of user group 2 is (A AND B) OR D. By comparing user group 1 and user group 2, it can be determined that the common clustering condition is (A AND B).

[0042] Step S1012: Determine a user set that meets the common clustering condition based on the user data of each user.

[0043] Specifically, for each common clustering condition, all user data meeting the common clustering condition may be determined based on the user data of each user stored in the database, so that all users corresponding to the user data are grouped into a user set meeting the common clustering condition.

[0044] Step S1013: when the clustering condition set of the user group contains the common clustering condition, determine the users belonging to the user group according to the user set of the common clustering condition and the user sets meeting the independent clustering conditions of the user group.

[0045] The independent clustering condition is a clustering condition in the clustering condition set of the user group except the common clustering condition.

[0046] Specifically, when determining each user belonging to a certain user group, if the clustering condition set of the user group includes a certain common clustering condition, such as the clustering condition set of the user group is (A AND B) OR C, which includes the common clustering condition A AND B, then the user set of the common clustering condition A AND B can be obtained. At the same time, based on the user data of each user stored in the database, the user set that meets the independent clustering condition C can be searched from each user, so as to logically combine the user set of the common clustering condition and the user set that meets the independent clustering condition to obtain each user belonging to the user group. When determining each user belonging to a certain user group, since the user set that meets the common clustering condition has been determined in advance, if the user group has a common clustering condition, the corresponding user set can be directly obtained through the common clustering condition, without traversing and converting the user data in the database, thereby improving the processing efficiency when determining each user belonging to a certain user group.

[0047] In a preferred embodiment, the method for determining each user belonging to a certain user group further includes: It is determined that the independent clustering conditions of any two of the user groups are mutually opposed conditions, and the user set of the independent clustering condition of one of the user groups is obtained based on the user set of the independent clustering condition of the other user group.

[0048] Specifically, when determining the users belonging to a certain user group, if the independent clustering condition of a certain user group is opposite to the independent clustering condition of another user group, after obtaining the user set of the independent clustering event of a certain user group, the user set composed of the remaining users can be directly determined as the user set of the independent clustering condition of the other user group, without traversing and converting the user data in the database, thereby improving processing efficiency.

[0049] Among them, if there is no intersection between two independent clustering conditions and their union covers all users, it can be determined that the two independent clustering conditions are mutually opposed events. For example, if independent clustering condition D is age less than N and independent clustering condition E is age greater than or equal to N, it can be determined that the two independent clustering conditions are mutually opposed events.

[0050] In a preferred embodiment, determining non-target users of the information to be delivered according to the negative evaluations of each of the historical delivery information includes: Determining a candidate user who publishes the negative evaluation according to any negative evaluation of the historical delivery information; When the number of positive evaluations by the candidate users on each of the historical delivery information is less than a preset number, the candidate users are determined to be non-target users of the information to be delivered.

[0051] Specifically, for any negative evaluation in the evaluation information of the historical delivery information, the user who posted the negative evaluation may be determined to determine the user as a candidate user.

[0052] For any candidate user, all evaluation information of the candidate user for each historical delivery information can be obtained, and the number of positive evaluations in each evaluation information can be detected to be less than the preset number. If the number of positive evaluations in each evaluation information is greater than or equal to the preset number, if there is a positive evaluation in each evaluation information, it means that the user is not interested in a specific historical delivery information, so the candidate user can be ignored; if the number of positive evaluations in each evaluation information is less than the preset number, if it is detected that there is no positive evaluation in each evaluation information, it means that the user is not interested in delivery information similar to the historical delivery information, and at this time, the candidate user can be determined as a non-target user of the information to be delivered.

[0053] In a preferred embodiment, determining the non-target user group according to the number of the non-target users in each user group includes: Obtaining a candidate user group in which the number of non-target users in each of the user groups reaches a preset ratio; It is determined that the number of users in the candidate user group who have published positive comments on at least one of the historical delivery information is less than a preset number, and the candidate user group is determined as a non-target user group.

[0054] Specifically, for any user group, non-target users can be searched from all users of the user group to determine the number of non-target users in the user group. After determining the number of non-target users in any user group, it can be determined whether the proportion of non-target users in the user group reaches a preset ratio. If so, the user group can be determined as a candidate user group.

[0055] For any candidate user group, the evaluation information published by each user in the candidate user group for each historical delivery information can be detected to determine the number of users in the candidate user group who have published positive evaluations on at least one historical delivery information. If the number of users is less than the preset number, it can be determined that all users in the candidate user group are most likely not interested in delivery information similar to the historical delivery information, and the candidate user group can be determined as a non-target user group. The preset number can be set according to actual conditions.

[0056] In a preferred embodiment, the customer acquisition method further includes: Step S106: determining that the historical delivery information does not exist, and obtaining a target clustering condition set whose matching degree with the information feature reaches a preset matching degree according to the information feature of the information to be delivered.

[0057] Specifically, when obtaining historical delivery information that meets the preset matching conditions with the information to be delivered, if no historical delivery information that meets the preset matching conditions with the information to be delivered is found, such as the information to be delivered is the first time the advertising information is delivered, then the information features of the information to be delivered can be obtained to match the information features of the information to be delivered with the clustering condition set of each user group. Among them, the information features can be descriptive features of the information to be delivered, such as keywords that reflect the name, type, applicable population, functions, features, and price of the product. Matching the information features of the information to be delivered with the clustering condition set can be to determine whether a certain information feature of the information to be delivered meets a certain clustering condition of the clustering condition set. If so, it can be determined that the matching degree between the information features of the information to be delivered and the clustering condition set reaches the preset matching degree.

[0058] If the matching degree between the information characteristics of the information to be delivered and a certain clustering condition set reaches a preset matching degree, the clustering condition set can be determined as the target clustering condition set.

[0059] Step S107: according to the target clustering condition set, users in each user group having an intersection between the clustering condition set and the target clustering condition set are determined as target users to which the information is to be delivered.

[0060] Specifically, for any clustering condition set, it is possible to detect whether at least one clustering condition of the clustering condition set has an intersection with at least one clustering condition in the target clustering condition set. For example, if a clustering condition in the clustering condition set is that the age is less than 30 years old, and a clustering condition in the target clustering condition set is that the age is less than 40 years old, it can be determined that the clustering condition set has an intersection with the target clustering condition set. If at least one clustering condition of the clustering condition set has an intersection with at least one clustering condition in the target clustering condition set, it can be determined that the clustering condition set has an intersection with the target clustering condition set, so that the users in the user group corresponding to the clustering condition set are determined as the target users of the information to be delivered. Therefore, even if the historical delivery information is not found, the target users can be determined from the user group through the clustering condition set that matches the information characteristics of the information to be delivered, without traversing and converting the user data of all users, thereby reducing the memory consumption when acquiring the target users and improving the efficiency of acquiring the target users.

[0061] Based on the above method embodiment, a corresponding device embodiment is provided; like Figure 4 As shown, another embodiment of the present invention provides a digital marketing system, including: an information matching module, a first processing module, a second processing module, a user screening module and a user acquisition module; The information matching module is used to obtain at least one piece of historical delivery information that meets a preset matching condition with the product's to-be-delivered information; The first processing module is used to determine non-target users of the information to be delivered according to the negative evaluations of each of the historical delivery information; The second processing module is used to determine the non-target user group according to the number of the non-target users in each user group; The user screening module is used to determine, from the user groups, according to the clustering condition set of the non-target user group, target user groups that do not have a common clustering condition with the clustering condition set of the non-target user group, or at least one clustering condition is mutually exclusive with a clustering condition in the clustering condition set of the non-target user group; The user acquisition module is used to determine each target user to which the information is to be delivered from each target user group; Each of the user groups is provided with a corresponding clustering condition set, and users meeting the clustering condition set are divided into the corresponding user group; the clustering condition set includes at least one clustering condition.

[0062] like Figure 5 As shown, another embodiment of the present invention provides a digital marketing system, further including a user clustering module, wherein the user clustering module is used to determine a user set that meets the common clustering condition based on user data of each user; when the common clustering condition exists in the clustering condition set of the user group, determine each user belonging to the user group based on the user set with the common clustering condition and the user set that meets each independent clustering condition of the user group; wherein the independent clustering condition is a clustering condition in the clustering condition set of the user group, excluding the common clustering condition.

[0063] In a preferred embodiment, the user clustering module is further used to: determine that the independent clustering conditions of any two user groups are mutually opposed conditions, and obtain the user set of the independent clustering conditions of the other user group based on the user set of the independent clustering conditions of one of the user groups.

[0064] In a preferred embodiment, the user data belonging to any of the user groups is recorded with a unique identifier corresponding to the user group, and the user group to which the non-target user belongs is determined based on the user data of the non-target user.

[0065] In a preferred embodiment, the first processing module is specifically used to: determine an alternative user who posted the negative evaluation based on any negative evaluation of the historical delivery information; and determine that the alternative user is a non-target user of the information to be delivered when the number of positive evaluations of the alternative user for each of the historical delivery information is less than a preset number.

[0066] In a preferred embodiment, the second processing module is specifically used to: obtain a candidate user group in which the number of non-target users in each of the user groups reaches a preset ratio; determine that the number of users in the candidate user group who have posted positive comments on at least one of the historical delivery information is less than a preset number, and determine the candidate user group as a non-target user group.

[0067] In a preferred embodiment, the user acquisition module is also used to: determine that the historical delivery information does not exist, and obtain a target clustering condition set whose matching degree with the information characteristics reaches a preset matching degree based on the information characteristics of the information to be delivered; and according to the target clustering condition set, determine the users in each user group where the clustering condition set and the target clustering condition set have an intersection as the target users of the information to be delivered.

[0068] It can be understood that the above-mentioned device item embodiments correspond to the method item embodiments of the present invention, and can implement the customer acquisition method provided by any of the above-mentioned method item embodiments of the present invention.

[0069] It should be noted that the device embodiments described above are merely schematic, wherein the units / modules described as separate components may or may not be physically separated, and the components displayed as units / modules may or may not be physical units / modules, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which can be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art can understand and implement it without paying any creative labor. The schematic diagram is only an example of a digital marketing system and does not constitute a limitation on the digital marketing system. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components.

[0070] Based on the above method embodiment, another embodiment is provided; Another embodiment of the present invention provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, it implements the customer acquisition method provided by any one of the above method embodiments of the present invention.

[0071] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program in the terminal device.

[0072] The terminal device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The terminal device may include, but is not limited to, a processor and a memory. Those skilled in the art may understand that, for example, the terminal device may also include an input / output device, a network access device, a bus, etc.

[0073] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the terminal device, and uses various interfaces and lines to connect various parts of the entire terminal device.

[0074] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the terminal device by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound display function, an image display function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0075] Based on the above-mentioned embodiments of the invention, a corresponding storage medium embodiment is provided; Another embodiment of the present invention provides a storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the storage medium is located is controlled to execute the customer acquisition method provided by any one of the above-mentioned method embodiments of the present invention.

[0076] Wherein, the storage medium is a computer storage medium, and the module / unit integrated in the device / terminal equipment can be stored in a computer-readable storage medium if it is implemented in the form of a software functional unit and sold or used as an independent product. Based on such an understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium can include: any entity or device that can carry the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0077] The above is a preferred embodiment of the present invention. It should be pointed out that a person skilled in the art can make several improvements and modifications without departing from the principle of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A customer acquisition method, characterized in that: include: Obtain at least one piece of historical delivery information that meets a preset matching condition with the product's to-be-delivered information; Determining non-target users of the information to be delivered according to the negative evaluations of each of the historical delivery information; Determine a non-target user group according to the number of the non-target users in each user group; According to the clustering condition set of the non-target user group, determining from the user groups the target user groups that have no common clustering condition with the clustering condition set of the non-target user group, or at least one clustering condition is mutually exclusive with a clustering condition in the clustering condition set of the non-target user group; Determining each target user to whom the information is to be delivered from each target user group; Each of the user groups is provided with a corresponding set of clustering conditions, and users meeting the set of clustering conditions are divided into corresponding user groups; The clustering condition set includes at least one clustering condition.

2. The customer acquisition method according to claim 1, characterized in that: Also includes: Determining at least one common clustering condition according to the clustering condition sets of each of the user groups; Determining a user set that meets the common clustering condition according to the user data of each user; In the case where the clustering condition set of the user group includes the common clustering condition, determining each user belonging to the user group according to the user set of the common clustering condition and the user sets meeting each independent clustering condition of the user group; The independent clustering condition is a clustering condition in the clustering condition set of the user group except the common clustering condition.

3. The customer acquisition method according to claim 2, characterized in that: Also includes: It is determined that the independent clustering conditions of any two of the user groups are mutually opposed conditions, and the user set of the independent clustering condition of one of the user groups is obtained based on the user set of the independent clustering condition of the other user group.

4. The customer acquisition method according to any one of claims 1 to 3, characterized in that: The user data belonging to any of the user groups is recorded with a unique identifier corresponding to the user group, and the user group to which the non-target user belongs is determined according to the user data of the non-target user.

5. The customer acquisition method according to claim 1, characterized in that: Determining non-target users of the information to be delivered based on the negative evaluations of each of the historical delivery information includes: Determining a candidate user who publishes the negative evaluation according to any negative evaluation of the historical delivery information; When the number of positive evaluations by the candidate users on each of the historical delivery information is less than a preset number, the candidate users are determined to be non-target users of the information to be delivered.

6. The customer acquisition method according to claim 1, characterized in that: According to the number of non-target users in each user group, the non-target user group is determined, including: Obtaining a candidate user group in which the number of non-target users in each of the user groups reaches a preset ratio; It is determined that the number of users in the candidate user group who have published positive comments on at least one of the historical delivery information is less than a preset number, and the candidate user group is determined as a non-target user group.

7. The customer acquisition method according to any one of claims 1 to 3 or 5 to 6, characterized in that: Also includes: Determining that the historical delivery information does not exist, and obtaining, based on the information features of the information to be delivered, a target clustering condition set whose matching degree with the information features reaches a preset matching degree; According to the target clustering condition set, users in each user group having an intersection between the clustering condition set and the target clustering condition set are determined as target users to which information is to be delivered.

8. A digital marketing system, characterized in that: include: An information matching module, a first processing module, a second processing module, a user screening module, and a user acquisition module; The information matching module is used to obtain at least one piece of historical delivery information that meets a preset matching condition with the product's to-be-delivered information; The first processing module is used to determine non-target users of the information to be delivered according to the negative evaluations of each of the historical delivery information; The second processing module is used to determine the non-target user group according to the number of the non-target users in each user group; The user screening module is used to determine, from the user groups, according to the clustering condition set of the non-target user group, target user groups that do not have a common clustering condition with the clustering condition set of the non-target user group, or at least one clustering condition is mutually exclusive with a clustering condition in the clustering condition set of the non-target user group; The user acquisition module is used to determine each target user to which the information is to be delivered from each target user group; Each of the user groups is provided with a corresponding set of clustering conditions, and users meeting the set of clustering conditions are divided into corresponding user groups; The clustering condition set includes at least one clustering condition.

9. A terminal device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements the customer acquisition method described in any one of claims 1 to 7 when executing the computer program.

10. A storage medium, characterized in that: The storage medium includes a stored computer program, wherein when the computer program is running, the device where the storage medium is located is controlled to execute the customer acquisition method described in any one of claims 1 to 7.

Images