Method and device for locating product customer groups, electronic device, and storage medium

Abstract

The present application relates to the field of computer technology, and discloses a method for locating a product customer group, including: obtaining text information corresponding to a target product, and obtaining a user tag of a user corresponding to the text information; the user tag includes one or more of the user's age, gender, occupation, and hobbies; inputting the text information and the user tag into a preset sentiment classification model to obtain the target product and the user's preference for the target product; obtaining the correlation between the input features and the output features of the sentiment classification model; determining alternative user tags based on the correlation; and determining customer group positioning based on the alternative user tags. In this way, by analyzing the correlation between the input features and the output features of the sentiment classification model, the customer group of the target product can be located based on the correlation, thereby improving the degree of automation of customer group positioning. The present application also discloses a device, electronic device, and storage medium for locating a product customer group.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and for example, to a method and device, an electronic device, and a storage medium for locating product customer groups. Background Art

[0002] How to clearly define the customer base for a product is an important issue in the marketing field. At present, in order to clearly define products and analyze audience needs, to clarify the direction of product operations and to effectively use operational resources, companies need to clearly define the customer base of their products.

[0003] In the process of implementing the embodiments of the present disclosure, it is found that there are at least the following problems in the related art:

[0004] In the existing technology, the customer positioning of a product is usually determined through manual research, discussion and analysis, and the degree of automation is low. Summary of the invention

[0005] In order to provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. The summary is not an extensive review, nor is it intended to identify key / critical components or delineate the scope of protection of these embodiments, but rather serves as a prelude to the detailed description that follows.

[0006] The embodiments of the present disclosure provide a method and device, an electronic device, and a storage medium for locating a product customer group, so as to improve the automation level of customer group positioning.

[0007] In some embodiments, the method for locating a product customer group includes: obtaining text information corresponding to a target product, and obtaining a user tag of a user corresponding to the text information; the user tag includes one or more of the user's age, gender, occupation, and hobbies; inputting the text information and the user tag into a preset sentiment classification model to obtain the target product and the user's degree of liking for the target product; obtaining the correlation between the input features and output features of the sentiment classification model; determining alternative user tags based on the correlation; and determining customer group positioning based on the alternative user tags.

[0008] In some embodiments, the device for locating product customer groups includes: a first acquisition module, configured to acquire text information corresponding to a target product, and acquire a user tag of a user corresponding to the text information; the user tag includes one or more of the user's age, gender, occupation, and hobbies; a classification module, configured to input the text information and the user tag into a preset sentiment classification model to obtain the target product and the user's degree of liking for the target product; a second acquisition module, configured to acquire the correlation between input features and output features of the sentiment classification model; a first determination module, configured to determine alternative user tags based on the correlation; and a second determination module, configured to determine customer group positioning based on the alternative user tags.

[0009] In some embodiments, the device for locating a product customer group includes a processor and a memory storing program instructions, and the processor is configured to execute the method for locating a product customer group as described above when running the program instructions.

[0010] In some embodiments, the electronic device includes the above-mentioned device for locating product customer groups.

[0011] In some embodiments, the storage medium stores program instructions, and when the program instructions are run, the above-mentioned method for locating product customer groups is executed.

[0012] The method and device, electronic device, and storage medium for locating product customer groups provided by the embodiments of the present disclosure can achieve the following technical effects: by obtaining text information corresponding to the target product and obtaining the user tag of the user corresponding to the text information; the user tag includes one or more of the user's age, gender, occupation, and hobbies; inputting the text information and user tag into a preset sentiment classification model to obtain the target product and the user's preference for the target product; obtaining the correlation between the input features and the output features of the sentiment classification model; determining the candidate user tags based on the correlation; and determining the customer group positioning based on the candidate user tags. In this way, the user's preference for the target product can be determined through the sentiment classification model, and by analyzing the correlation between the input features and the output features of the sentiment classification model, the target product's customer group can be located based on the correlation, thereby improving the degree of automation of customer group positioning.

[0013] The above general description and the following description are exemplary and explanatory only and are not intended to limit the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] One or more embodiments are exemplarily described by corresponding drawings, which do not limit the embodiments. Elements with the same reference numerals in the drawings are shown as similar elements, and the drawings do not constitute a scale limitation, and wherein:

[0015] Figure 1 is a schematic diagram of a method for locating product customer groups provided by an embodiment of the present disclosure;

[0016] Figure 2 is a schematic diagram of a method for obtaining a sentiment classification model provided by an embodiment of the present disclosure;

[0017] Figure 3 is a schematic diagram of another method for locating product customer groups provided by an embodiment of the present disclosure;

[0018] Figure 4 is a schematic diagram of another method for locating product customer groups provided by an embodiment of the present disclosure;

[0019] Figure 5 is a schematic diagram of a device for locating product customer groups provided by an embodiment of the present disclosure;

[0020] Figure 6 It is a schematic diagram of another device for locating product customer groups provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0021] In order to be able to understand the features and technical contents of the embodiments of the present disclosure in more detail, the implementation of the embodiments of the present disclosure is described in detail below in conjunction with the accompanying drawings. The attached drawings are for reference only and are not used to limit the embodiments of the present disclosure. In the following technical description, for the convenience of explanation, a full understanding of the disclosed embodiments is provided through multiple details. However, one or more embodiments can still be implemented without these details. In other cases, to simplify the drawings, well-known structures and devices can be simplified for display.

[0022] The terms "first", "second", etc. in the specification and claims of the embodiments of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchanged where appropriate, so that the embodiments of the embodiments of the present disclosure described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions.

[0023] Unless otherwise stated, the term "plurality" means two or more.

[0024] In the embodiment of the present disclosure, the character " / " indicates that the preceding and following objects are in an "or" relationship. For example, A / B indicates: A or B.

[0025] The term "and / or" is a description of the association relationship between objects, indicating that three relationships can exist. For example, A and / or B means: A or B, or, A and B.

[0026] The term "correspondence" may refer to an association relationship or a binding relationship. The correspondence between A and B means that there is an association relationship or a binding relationship between A and B.

[0027] Combination Figure 1 As shown, the embodiment of the present disclosure provides a method for locating a product customer group, including:

[0028] Step S101, obtaining text information corresponding to the target product, and obtaining a user tag of the user corresponding to the text information; the user tag includes one or more of the user's age, gender, occupation and hobbies.

[0029] Step S102, inputting the text information and the user tag into a preset sentiment classification model to obtain the target product and the user's preference for the target product.

[0030] Step S103, obtaining the correlation between the input features and the output features of the sentiment classification model.

[0031] Step S104: determining candidate user tags according to the correlation.

[0032] Step S105: determining customer group positioning according to the candidate user tags.

[0033] The method for locating a product customer group provided by the embodiment of the present disclosure is adopted, by obtaining text information corresponding to the target product and obtaining a user tag of the user corresponding to the text information; the user tag includes one or more of the user's age, gender, occupation and hobbies; the text information and the user tag are input into a preset sentiment classification model to obtain the target product and the user's preference for the target product; the correlation between the input features and the output features of the sentiment classification model is obtained; the candidate user tags are determined based on the correlation; and the customer group positioning is determined based on the candidate user tags. In this way, the user's preference for the target product can be determined through the sentiment classification model, and the customer group of the target product can be located based on the correlation by analyzing the correlation between the input features and the output features of the sentiment classification model, thereby improving the automation of customer group positioning.

[0034] Optionally, the target product includes the product to be positioned and / or a competing product corresponding to the product to be positioned.

[0035] Optionally, the text information is articles or comment information posted by the user on a social platform or a shopping platform.

[0036] In some embodiments, the text information and user tags are input into a preset sentiment classification model, and when the text information is an article or review information related to the target product, the target product and the user's preference for the target product are obtained.

[0037] In some embodiments, the text information and the user tag are input into a preset sentiment classification model, and when the text information is an article or comment information irrelevant to the target product, the text information is obtained as invalid text information.

[0038] Optionally, the sentiment classification model is obtained in the following manner, including: obtaining sample text information and sample user labels corresponding to the sample products; obtaining training sample labels; the training sample labels are used to characterize the user's preference for the sample products; the sample text information and sample user labels are determined as training samples; the training samples with the training sample labels are input into a preset machine learning model for training to obtain the sentiment classification model.

[0039] Optionally, obtaining training sample labels includes: performing natural language processing on sample text information to obtain training sample labels.

[0040] Optionally, natural language processing is performed on the sample text information to obtain training sample labels, including: processing the sample text information through NER (Named Entity Recognition) technology to obtain training sample labels; or, processing the sample text information through ABSA (Aspect-Based Sentiment Analysis) technology to obtain training sample labels.

[0041] Optionally, the training sample label includes a first label and a second label.

[0042] Optionally, the first tag includes related to competing products, related to the product to be located, related to the product to be located and its competing products, and not related to the product to be located and its competing products. Optionally, the competing product is a competing product of the product to be located.

[0043] Optionally, the second label includes positive emotion, negative emotion and neutral emotion; positive emotion includes very like and generally like; negative emotion includes generally dislike and very dislike.

[0044] In some embodiments, the sample text information is "The sound quality of recording device A is very good, I like it very much", and the sample text information is entity recognized by NER technology to obtain the first label, that is, the product to be located is: recording device A; the second label is: positive emotion. In this way, by performing natural language processing on the sample text information, the training sample label can be determined more accurately.

[0045] Combination Figure 2 As shown, the embodiment of the present disclosure provides a method for obtaining a sentiment classification model, including:

[0046] Step S201, obtaining sample text information and sample user tags corresponding to sample products;

[0047] Step S202, obtaining training sample labels; the training sample labels are used to characterize the user's preference for the sample product; the sample text information and the sample user labels are determined as training samples; the training samples with the training sample labels are input into a preset machine learning model for training to obtain a sentiment classification model.

[0048] By adopting the method for obtaining a sentiment classification model provided in an embodiment of the present disclosure, a machine learning model is trained through deep learning technology using sample text information and sample user labels corresponding to acquired sample products and the user's preference for the sample products to obtain a sentiment classification model, so that the user can determine the user's possible emotional state, that is, the preference level, for the target product through text information, thereby improving the degree of automation in locating the target product customer group. At the same time, the method for obtaining a sentiment classification model provided in an embodiment of the present disclosure is replicable and can be easily trained for different products, thereby obtaining sentiment classification models for different products.

[0049] Optionally, the correlation between the input features and output features of the sentiment classification model is obtained, including: determining text information and user tags as input features of the model, and determining the user's preference for the target product as the output feature of the model; obtaining a first feature vector corresponding to the input feature and a second feature vector corresponding to the output feature; and obtaining the correlation between the first feature vector and the second feature vector.

[0050] Optionally, obtaining a first feature vector corresponding to the input feature includes: respectively obtaining a feature vector corresponding to the text information and a feature vector corresponding to the user tag; fusing and concatenating the feature vector corresponding to the text information and the feature vector corresponding to the user tag to obtain the first feature vector.

[0051] Optionally, obtaining the correlation between the first eigenvector and the second eigenvector includes: performing calculations using the first eigenvector and the second eigenvector according to a preset algorithm to obtain the correlation between the first eigenvector and the second eigenvector.

[0052] In some embodiments, the preset algorithm is a corrcoef correlation coefficient function based on Matlab.

[0053] In some embodiments, whether the input feature is important can be determined by the sentiment classification model, including: adjusting the input feature of the sentiment classification model by the control variable method, and inputting the adjusted input feature into the sentiment classification model to obtain the output feature; determining whether the adjusted input feature has an impact on the output feature; if the adjusted input feature has an impact on the output feature, determining that the adjusted feature in the input feature is important. In this way, by adjusting the input feature by the control variable method, the importance of the input feature can be analyzed more accurately, thereby facilitating the positioning of the target product's customer base.

[0054] Optionally, determining candidate user tags according to the correlation includes: determining user tags corresponding to the correlations within a first preset range as candidate user tags.

[0055] Optionally, the first preset range is 0.5-1.

[0056] In some embodiments, the larger the value of the correlation is, the more important the input feature corresponding to the first feature vector is.

[0057] Optionally, the user tags corresponding to the correlations within the second preset range are determined to be in a swinging state. Optionally, the second preset range is -0.5 to 0.5.

[0058] In this way, by determining which user tags are in a swinging state and analyzing the users corresponding to the user tags in the swinging state, it is convenient for enterprises to improve the products to be positioned, thereby making key breakthroughs in the products to be positioned so that the products to be positioned can satisfy the users corresponding to the user tags in the swinging state.

[0059] Combination Figure 3 As shown, the embodiment of the present disclosure provides a method for locating a product customer group, including:

[0060] Step S301, obtaining text information corresponding to the target product, and obtaining a user tag of the user corresponding to the text information; the user tag includes one or more of the user's age, gender, occupation and hobbies.

[0061] Step S302: input the text information and user tags into a preset sentiment classification model to obtain the target product and the user's preference for the target product.

[0062] Step S303, obtaining the correlation between the input features and the output features of the sentiment classification model.

[0063] Step S304: Determine the user tags corresponding to the correlations within the first preset range as candidate user tags.

[0064] Step S305: determining customer group positioning according to the candidate user tags.

[0065] By adopting the method for locating product customer groups provided by the embodiments of the present disclosure, the degree of user preference for a target product can be determined through a sentiment classification model, and by analyzing the correlation between input features and output features of the sentiment classification model, user tags corresponding to correlations within a first preset range are determined as candidate user tags, thereby locating the customer groups for the target product based on the candidate user tags, thereby improving the degree of automation of customer group positioning.

[0066] Optionally, determining the customer group positioning according to the candidate user tags includes: determining all users who meet the candidate user tags as the customer group positioning corresponding to the target product.

[0067] Combination Figure 4 As shown, the embodiment of the present disclosure provides a method for locating a product customer group, including:

[0068] Step S401, obtaining text information corresponding to the target product, and obtaining a user tag of the user corresponding to the text information; the user tag includes one or more of the user's age, gender, occupation and hobbies.

[0069] Step S402: input the text information and the user tag into a preset sentiment classification model to obtain the target product and the user's preference for the target product.

[0070] Step S403, obtaining the correlation between the input features and the output features of the sentiment classification model.

[0071] Step S404: Determine the user tags corresponding to the correlations within the first preset range as candidate user tags.

[0072] Step S405: All users meeting the candidate user tags are determined as the customer group corresponding to the target product.

[0073] By adopting the method for locating product customer groups provided by the embodiments of the present disclosure, the degree of user preference for a target product can be determined through a sentiment classification model, and by analyzing the correlation between input features and output features of the sentiment classification model, user tags corresponding to correlations within a first preset range are determined as candidate user tags, and users with candidate user tags are determined as customer groups for the target product, thereby improving the degree of automation in customer group positioning.

[0074] In some embodiments, after the target product is positioned for the customer group, the profitability of the target product within a preset time period is obtained. If the profitability does not reach the preset expected value, the text information and user tags corresponding to the target product are re-obtained, and the user's preference for the target product is obtained based on the sentiment classification model. The target product positioning is adjusted based on the relevance, and repeated iterations are performed to continuously adjust the target product positioning and expand the product's influence.

[0075] Combination Figure 5 As shown, an embodiment of the present disclosure provides a device for locating a product customer group, including: a first acquisition module 501, a classification module 502, a second acquisition module 503, a first determination module 504 and a second determination module 505; the first acquisition module 501 is configured to acquire text information corresponding to a target product, and acquire a user tag of a user corresponding to the text information; the user tag includes one or more of the user's age, gender, occupation and hobbies; the classification module 502 is configured to input the text information and the user tag into a preset sentiment classification model to obtain the target product and the user's degree of liking for the target product; the second acquisition module 503 is configured to acquire the correlation between the input features and the output features of the sentiment classification model; the first determination module 504 is configured to determine alternative user tags based on the correlation; the second determination module 505 is configured to determine customer group positioning based on the alternative user tags.

[0076] The device for locating the customer group of a product provided by the embodiment of the present disclosure is adopted, and the text information corresponding to the target product is obtained through the first acquisition module, and the user tag of the user corresponding to the text information is obtained; the classification module inputs the text information and the user tag into the preset sentiment classification model to obtain the target product and the user's preference for the target product; the second acquisition module obtains the correlation between the input features and the output features of the sentiment classification model; the first determination module determines the candidate user tag according to the correlation; and the second determination module determines the customer group positioning according to the candidate user tag. In this way, the user's preference for the target product can be determined through the sentiment classification model, and by analyzing the correlation between the input features and the output features of the sentiment classification model, the customer group of the target product can be located according to the correlation, thereby improving the degree of automation of customer group positioning.

[0077] Optionally, the classification module is also configured to obtain a sentiment classification model in the following manner: obtaining sample text information and sample user labels corresponding to sample products; obtaining training sample labels; the training sample labels are used to characterize the user's preference for the sample products; determining the sample text information and sample user labels as training samples; and inputting the training samples with the training sample labels into a preset machine learning model for training to obtain a sentiment classification model.

[0078] Optionally, obtaining training sample labels includes: performing natural language processing on sample text information to obtain training sample labels.

[0079] Optionally, the second acquisition module is configured to obtain the correlation between the input features and output features of the sentiment classification model in the following manner: determining text information and user tags as input features of the model, and determining the user's preference for the target product as the output features of the model; obtaining a first feature vector corresponding to the input feature and a second feature vector corresponding to the output feature; and obtaining the correlation between the first feature vector and the second feature vector.

[0080] Optionally, the first determining module is configured to determine the candidate user tags according to the correlation in the following manner: determining the user tags corresponding to the correlations within the first preset range as the candidate user tags.

[0081] Optionally, the second determination module is configured to determine the customer group positioning according to the candidate user tags in the following manner: all users meeting the candidate user tags are determined as the customer group positioning corresponding to the target product.

[0082] In this way, the sample text information is processed by natural language processing technology to obtain training sample labels, and the machine learning model is trained using the training samples and training sample labels through deep learning technology to obtain a sentiment classification model; the collected text information and user labels are determined as the input features of the model and input into the sentiment classification model to obtain the user's possible emotional state towards the target product, that is, the degree of liking, which facilitates the automatic mining of customer groups for the products to be positioned from a large amount of network information and improves the degree of automation of customer positioning.

[0083] Combination Figure 6 As shown, an embodiment of the present disclosure provides a device for locating a product customer group, including a processor (processor) 600 and a memory (memory) 601. Optionally, the device may also include a communication interface (Communication Interface) 602 and a bus 603. Among them, the processor 600, the communication interface 602, and the memory 601 can communicate with each other through the bus 603. The communication interface 602 can be used for information transmission. The processor 600 can call the logic instructions in the memory 601 to execute the method for locating a product customer group of the above embodiment.

[0084] The device for locating the customer group of a product provided by the embodiment of the present disclosure is adopted, by obtaining the text information corresponding to the target product and the user tag of the user corresponding to the text information; the user tag includes one or more of the user's age, gender, occupation and hobbies; the text information and the user tag are input into a preset sentiment classification model to obtain the target product and the user's preference for the target product; the correlation between the input features and the output features of the sentiment classification model is obtained; the candidate user tags are determined based on the correlation; and the customer group positioning is determined based on the candidate user tags. In this way, the user's preference for the target product can be determined through the sentiment classification model, and the customer group of the target product can be located based on the correlation by analyzing the correlation between the input features and the output features of the sentiment classification model, thereby improving the automation of customer group positioning.

[0085] In addition, the logic instructions in the memory 601 described above can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product.

[0086] The memory 601 is a computer-readable storage medium that can be used to store software programs and computer executable programs, such as program instructions / modules corresponding to the method in the embodiment of the present disclosure. The processor 600 executes the function application and data processing by running the program instructions / modules stored in the memory 601, that is, the method for locating product customer groups in the above embodiment is implemented.

[0087] The memory 601 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application required for at least one function; the data storage area may store data created according to the use of the terminal device, etc. In addition, the memory 601 may include a high-speed random access memory and may also include a non-volatile memory.

[0088] Optionally, an embodiment of the present disclosure provides an electronic device, comprising the above-mentioned device for locating product customer groups.

[0089] Optionally, the electronic device includes a server, a computer, a tablet computer, etc.

[0090] The electronic device provided by the embodiment of the present disclosure is used to obtain text information corresponding to the target product and the user tag of the user corresponding to the text information; the user tag includes one or more of the user's age, gender, occupation and hobbies; the text information and the user tag are input into a preset sentiment classification model to obtain the target product and the user's preference for the target product; the correlation between the input features and the output features of the sentiment classification model is obtained; the candidate user tags are determined based on the correlation; and the customer group positioning is determined based on the candidate user tags. In this way, the user's preference for the target product can be determined through the sentiment classification model, and the customer group of the target product can be positioned based on the correlation by analyzing the correlation between the input features and the output features of the sentiment classification model, thereby improving the automation of customer group positioning.

[0091] The embodiment of the present disclosure provides a storage medium storing program instructions, which, when run, execute the above method for locating product customer groups.

[0092] An embodiment of the present disclosure provides a computer program product, which includes a computer program stored on a computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer executes the above-mentioned method for locating product customers.

[0093] The computer-readable storage medium mentioned above may be a transient computer-readable storage medium or a non-transitory computer-readable storage medium.

[0094] The technical solution of the embodiment of the present disclosure can be embodied in the form of a software product, which is stored in a storage medium and includes one or more instructions for enabling a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in the embodiment of the present disclosure. The aforementioned storage medium may be a non-transient storage medium, including: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes, or a transient storage medium.

[0095] The above description and the accompanying drawings fully illustrate the embodiments of the present disclosure so that those skilled in the art can practice them. Other embodiments may include structural, logical, electrical, process and other changes. The embodiments represent only possible changes. Unless explicitly required, separate components and functions are optional, and the order of operation may vary. The parts and features of some embodiments may be included in or replace the parts and features of other embodiments. Moreover, the words used in this application are only used to describe the embodiments and are not used to limit the claims. As used in the description of the embodiments and the claims, unless the context clearly indicates, the singular forms of "a", "an" and "the" are intended to include plural forms as well. Similarly, the term "and / or" as used in this application refers to any and all possible combinations of listings containing one or more associated ones. In addition, when used in the present application, the term "comprise" and its variants "comprises" and / or comprising refer to the presence of stated features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or groups thereof. In the absence of further restrictions, the elements defined by the sentence "comprising a ..." do not exclude the presence of other identical elements in the process, method or device comprising the elements. In this article, each embodiment may focus on the differences from other embodiments, and the same and similar parts between the various embodiments may refer to each other. For the methods, products, etc. disclosed in the embodiments, if they correspond to the method part disclosed in the embodiments, then the relevant parts can refer to the description of the method part.

[0096] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software may depend on the specific application and design constraints of the technical solution. The technicians may use different methods for each specific application to implement the described functions, but such implementations should not be considered to exceed the scope of the embodiments of the present disclosure. The technicians may clearly understand that, for the convenience and simplicity of description, the specific working processes of the systems, devices and units described above may refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here.

[0097] In the embodiments disclosed herein, the disclosed methods and products (including but not limited to devices, equipment, etc.) can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units can be only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between each other shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms. The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to implement this embodiment. In addition, each functional unit in the embodiment of the present disclosure may be integrated in a processing unit, or each unit may exist physically alone, or two or more units may be integrated in one unit.

[0098] The flowchart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to the embodiment of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. In some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. In the description corresponding to the flowchart and the block diagram in the accompanying drawings, the operations or steps corresponding to different boxes can also occur in a different order from the order disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. Each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by a dedicated hardware-based system that performs the specified functions or actions, or may be implemented by a combination of dedicated hardware and computer instructions.

Claims

1. A method for locating a product customer group, characterized in that: include: Obtain text information corresponding to the target product, and obtain a user tag of a user corresponding to the text information; The user tag includes one or more of the user's age, gender, occupation and hobbies; Inputting the text information and the user tag into a preset sentiment classification model to obtain the target product and the user's preference for the target product; Obtaining the correlation between the input features and the output features of the sentiment classification model; Determine the user tags corresponding to the correlations within the first preset range as candidate user tags; Determine customer group positioning according to the candidate user tags; Wherein, when obtaining the correlation between the input features and the output features of the sentiment classification model, determining whether the input features are important through the sentiment classification model; adjusting the input features of the sentiment classification model through the control variable method, and inputting the adjusted input features into the sentiment classification model to obtain the output features; determining whether the adjusted input features have an impact on the output features; and in the case that the adjusted input features have an impact on the output features, determining that the adjusted features in the input features are important; Obtaining the correlation between the input features and the output features of the sentiment classification model, including: determining the text information and the user tag as the input features of the sentiment classification model, and determining the user's preference for the target product as the output feature of the sentiment classification model; obtaining a first feature vector corresponding to the input feature and a second feature vector corresponding to the output feature; and obtaining the correlation between the first feature vector and the second feature vector.

2. The method according to claim 1, characterized in that The sentiment classification model is obtained by: Obtain sample text information and sample user tags corresponding to sample products; Obtain training sample labels; the training sample labels are used to characterize the user's preference for the sample product; the sample text information and the sample user labels are determined as training samples; the training samples with the training sample labels are input into a preset machine learning model for training to obtain a sentiment classification model.

3. The method according to claim 2, characterized in that The step of obtaining training sample labels includes: Perform natural language processing on the sample text information to obtain the training sample label.

4. The method according to claim 1, characterized in that: Determining customer group positioning according to the candidate user tags includes: All users who meet the candidate user tags are determined as the customer group corresponding to the target product.

5. A device for locating product customer groups, characterized in that: include: A first acquisition module is configured to acquire text information corresponding to a target product and acquire a user tag of a user corresponding to the text information; The user tag includes one or more of the user's age, gender, occupation and hobbies; A classification module is configured to input the text information and the user tag into a preset sentiment classification model to obtain the target product and the user's preference for the target product; A second acquisition module is configured to obtain the correlation between the input features and the output features of the sentiment classification model; A first determining module is configured to determine the user tags corresponding to the correlations within a first preset range as candidate user tags; A second determination module is configured to determine customer group positioning according to the candidate user tags; Wherein, when obtaining the correlation between the input features and the output features of the sentiment classification model, determining whether the input features are important through the sentiment classification model; adjusting the input features of the sentiment classification model through the control variable method, and inputting the adjusted input features into the sentiment classification model to obtain the output features; determining whether the adjusted input features have an impact on the output features; and in the case that the adjusted input features have an impact on the output features, determining that the adjusted features in the input features are important; The second acquisition module is configured to obtain the correlation between the input features and the output features of the sentiment classification model in the following manner: determining the text information and the user tags as the input features of the model, and determining the user's preference for the target product as the output features of the model; obtaining the first feature vector corresponding to the input feature and the second feature vector corresponding to the output feature; and obtaining the correlation between the first feature vector and the second feature vector.

6. A device for locating product customer groups, comprising a processor and a memory storing program instructions, characterized in that: The processor is configured to perform the method according to any one of claims 1 to 4 when executing the program instructions.

7. An electronic device, characterized in that: It comprises the device for locating product customer groups as described in claim 6.

8. A storage medium storing program instructions, characterized in that: When the program instructions are executed, the method for locating product customer groups as described in any one of claims 1 to 4 is executed.

Images