Self-adaptive service division method and device for user and computer equipment

Abstract

The invention relates to a user adaptive service division method and device and computer equipment. The method comprises the following steps: acquiring interaction record information and order record information of each user, and identifying order demand information and product dependency association information of each user based on the order record information of each user; based on the interaction record information of each user, identifying interaction participation information and service demand information of each user, and based on the product dependency association information and the interaction participation information of each user, identifying user quality information of each user through a user analysis model; and on the basis of the order demand information and the service demand information of each user, through a user demand prediction model, predicting instant service demand information of each user, and on the basis of the instant service demand information of each user and the user quality information of each user, generating target service classification information of the user. By adopting the method, the corresponding service division adaptability can be improved.

Description

Technical Field

[0001] The present application relates to the fields of user classification and big data technology, and in particular to a method, apparatus, and computer device for adaptively dividing user services. Background Art

[0002] In the modern business environment, customer service quality has become a key factor in corporate competition. In the field of intelligent liquid dispensers, in particular, improving customer experience through intelligent control systems, customer relationship management systems, and optimization algorithms is an important research direction.

[0003] Existing solutions primarily use CRM systems to collect and analyze customer data, then categorize and manage customers based on this data. For example, customers can be categorized into different levels, such as VIP, regular, and potential, based on their purchase volume, reviews, and interactions with the platform. Different services and offers are then provided based on these customer levels. However, existing customer analysis techniques are often one-sided, and the real-time response to customer needs after categorization is poor. This results in limited flexibility in user service categorization, leading to poor adaptability. Summary of the Invention

[0004] Based on this, it is necessary to provide a method, apparatus, computer device, computer-readable storage medium and computer program product for adaptive service partitioning of users in response to the above technical problems.

[0005] In a first aspect, the present application provides a method for adaptively partitioning services for a user, comprising:

[0006] Obtaining interaction record information of each user and order record information of each user, and identifying order demand information of each user and product dependency association information of each user based on the order record information of each user;

[0007] Based on each user's interaction record information, identify each user's interactive participation information and each user's service demand information, and based on each user's product dependency association information and each user's interactive participation information, identify each user's user quality information through the user analysis model;

[0008] Based on each user's order demand information and each user's service demand information, the user demand prediction model is used to predict each user's immediate service demand information, and based on each user's immediate service demand and each user's user quality information, the user's target service classification information is generated.

[0009] Optionally, identifying each user's order demand information and each user's product dependency association information based on the order record information of each user includes:

[0010] For each user, split the user's order record information into individual order information, and identify the sub-order requirements corresponding to each individual order information, as well as the order product information corresponding to each individual order information;

[0011] Based on each sub-order requirement, identify the order content corresponding to each single order information and the special requirement content corresponding to each single order information, and use the order content corresponding to all single order information and the special requirement content corresponding to all single order information as the order requirement information of the user;

[0012] Based on each order product information, the product characteristics of each order product information and the order characteristics of each order product information are identified, and the product characteristics of all order product information and the order characteristics of all order product information are used as the product dependency association information of the user.

[0013] Optionally, identifying each user's interactive participation information and each user's service demand information based on each user's interaction record information includes:

[0014] For each user, based on the user's interaction record information, identifying the interaction content of each interaction type of the user and the user's interaction participation information in each interaction type;

[0015] Based on the user's interaction participation information in each interaction type, extracting the interaction preference feature of each interaction type through a feature extraction network, and using the interaction preference features of all interaction types as the user's service demand information;

[0016] Based on the interaction content of each interaction type of the user, the interaction feature information of the user and the interaction behavior information of the user are identified, and the interaction feature information of the user and the interaction behavior information of the user are used as the interaction participation information of the user.

[0017] Optionally, identifying user quality information of each user through a user analysis model based on the product dependency association information of each user and the interactive participation information of each user includes:

[0018] For each user, based on the product features of each order product information of the user and the order features of each order product information, an order quality evaluation value of each order evaluation indicator type of the user is identified through the order quality evaluation network of the user analysis model;

[0019] Based on each interaction feature information in the user's interaction participation information and the interaction behavior information in the user's interaction participation information, identifying the interaction quality evaluation value of each interaction evaluation indicator type of the user through the interaction quality evaluation network of the user analysis model;

[0020] Based on the order quality evaluation value of each order evaluation indicator type and the interaction quality evaluation value of each interaction evaluation indicator type, identifying the user quality type to which the user quality feature of the user belongs through the user quality analysis network of the user analysis model;

[0021] The user quality type to which the user quality feature belongs is used as the user quality information of the user.

[0022] Optionally, the predicting of each user's instant service demand information based on each user's order demand information and each user's service demand information by using a user demand prediction model includes:

[0023] For each user, based on the order content corresponding to all single order information and the special demand content corresponding to all single order information, the order preference information and the order preference range of the user are identified through the order preference identification network;

[0024] Based on the interaction preference characteristics of each interaction type in the user's service demand information, predicting the demand content of each service demand type of the user through the user demand prediction model;

[0025] Based on the user's order preference information and the user's order preference range, predicting the user's target order demand information through the user demand prediction model;

[0026] Based on the demand content of each service demand type of the user and the target order demand information of the user, the target service information of the user is generated, and the target service information is used as the instant service demand information of the user.

[0027] Optionally, generating target service classification information of each user based on the instant service demand of each user and the user quality information of each user includes:

[0028] For each user, based on the user's instant service demand information, identify the user's instant demand content for each service type, and based on the user's user quality type, query the user service database to obtain the service optimization range of each target service type corresponding to the user quality type;

[0029] Based on the service optimization scope of each target service type, performing service optimization processing on the instant service demand content of each target service type to obtain the target instant demand content of each target service type;

[0030] The target instant service demand content of each target service type and the instant service demand content of each non-target service type are used as the target service classification information of the user.

[0031] In a second aspect, the present application further provides a user adaptive service division device, comprising:

[0032] An acquisition module, configured to acquire interaction record information of each user and order record information of each user, and identify order demand information of each user and product dependency association information of each user based on the order record information of each user;

[0033] An identification module is used to identify each user's interactive participation information and service demand information based on each user's interaction record information, and to identify each user's user quality information based on each user's product dependency association information and each user's interactive participation information through a user analysis model;

[0034] The prediction module is used to predict each user's immediate service demand information based on each user's order demand information and each user's service demand information through a user demand prediction model, and generate the user's target service classification information based on each user's immediate service demand and each user's user quality information.

[0035] Optionally, the acquisition module is specifically configured to:

[0036] For each user, split the user's order record information into individual order information, and identify the sub-order requirements corresponding to each individual order information, as well as the order product information corresponding to each individual order information;

[0037] Based on each sub-order requirement, identify the order content corresponding to each single order information and the special requirement content corresponding to each single order information, and use the order content corresponding to all single order information and the special requirement content corresponding to all single order information as the order requirement information of the user;

[0038] Based on each order product information, the product characteristics of each order product information and the order characteristics of each order product information are identified, and the product characteristics of all order product information and the order characteristics of all order product information are used as the product dependency association information of the user.

[0039] Optionally, the identification module is specifically configured to:

[0040] For each user, based on the user's interaction record information, identifying the interaction content of each interaction type of the user and the user's interaction participation information in each interaction type;

[0041] Based on the user's interaction participation information in each interaction type, extracting the interaction preference feature of each interaction type through a feature extraction network, and using the interaction preference features of all interaction types as the user's service demand information;

[0042] Based on the interaction content of each interaction type of the user, the interaction feature information of the user and the interaction behavior information of the user are identified, and the interaction feature information of the user and the interaction behavior information of the user are used as the interaction participation information of the user.

[0043] Optionally, the identification module is specifically configured to:

[0044] For each user, based on the product features of each order product information of the user and the order features of each order product information, an order quality evaluation value of each order evaluation indicator type of the user is identified through the order quality evaluation network of the user analysis model;

[0045] Based on each interaction feature information in the user's interaction participation information and the interaction behavior information in the user's interaction participation information, identifying the interaction quality evaluation value of each interaction evaluation indicator type of the user through the interaction quality evaluation network of the user analysis model;

[0046] Based on the order quality evaluation value of each order evaluation indicator type and the interaction quality evaluation value of each interaction evaluation indicator type, identifying the user quality type to which the user quality feature of the user belongs through the user quality analysis network of the user analysis model;

[0047] The user quality type to which the user quality feature belongs is used as the user quality information of the user.

[0048] Optionally, the prediction module is specifically used to:

[0049] For each user, based on the order content corresponding to all single order information and the special demand content corresponding to all single order information, the order preference information and the order preference range of the user are identified through the order preference identification network;

[0050] Based on the interaction preference characteristics of each interaction type in the user's service demand information, predicting the demand content of each service demand type of the user through the user demand prediction model;

[0051] Based on the user's order preference information and the user's order preference range, predicting the user's target order demand information through the user demand prediction model;

[0052] Based on the demand content of each service demand type of the user and the target order demand information of the user, the target service information of the user is generated, and the target service information is used as the instant service demand information of the user.

[0053] Optionally, the prediction module is specifically used to:

[0054] For each user, based on the user's instant service demand information, identify the user's instant demand content for each service type, and based on the user's user quality type, query the user service database to obtain the service optimization range of each target service type corresponding to the user quality type;

[0055] Based on the service optimization scope of each target service type, performing service optimization processing on the instant service demand content of each target service type to obtain the target instant demand content of each target service type;

[0056] The target instant service demand content of each target service type and the instant service demand content of each non-target service type are used as the target service classification information of the user.

[0057] In a third aspect, the present application provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any one of the methods described in the first aspect when executing the computer program.

[0058] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of any one of the methods in the first aspect.

[0059] In a fifth aspect, the present application provides a computer program product, wherein the computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of any one of the methods in the first aspect are implemented.

[0060] The above-mentioned user adaptive service division method, device and computer equipment obtain the interaction record information of each user and the order record information of each user, and identify the order demand information of each user and the product dependency association information of each user based on the order record information of each user; identify the interaction participation information of each user and the service demand information of each user based on the interaction record information of each user, and identify the user quality information of each user through the user analysis model based on the product dependency association information of each user and the interaction participation information of each user; predict the immediate service demand information of each user through the user demand prediction model based on the order demand information of each user and the service demand information of each user, and generate the target service classification information of the user based on the immediate service demand of each user and the user quality information of each user. This solution identifies the user's product dependency information, order demand information, interactive participation information, and service demand information from the user's interaction records, order records and other recorded information, and thus conducts a comprehensive analysis of the user's user quality and immediate service needs from the perspectives of the customer's product order habits, order demand, interactive information, and service demand. This can not only comprehensively evaluate the user's quality, but also predict the user's needs in advance, avoiding the problem of one-sided customer analysis and poor real-time response to customer needs after customer classification. Then, this solution comprehensively combines the user's immediate needs and user quality to adaptively classify users, thereby improving the accuracy of user classification and comprehensively improving the adaptability of the corresponding service division. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0062] Figure 1 A flowchart of a method for adaptively dividing user services in one embodiment is shown;

[0063] Figure 2 A flowchart of an example of adaptive service division for users in one embodiment;

[0064] Figure 3 A structural block diagram of an apparatus for adaptively dividing user services in one embodiment;

[0065] Figure 4 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0066] In order to make the purpose, technical solutions and advantages of this application more clearly understood, the present application is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0067] The user adaptive service division method provided in the embodiment of the present application can be applied to the application environment of user adaptive service division. Among them, the control module can be a terminal, and the terminal can be but not limited to various personal computers, laptops, mid-range computers, etc. Among them, the terminal identifies the user's product dependency association information, order demand information, interactive participation information, and service demand information from the user's interaction records, order records and other recorded information, thereby comprehensively analyzing the user's user quality and immediate service demand from the perspectives of the customer's product order habits, order demand, interactive information, and service demand, so as to comprehensively evaluate the user's quality and predict the user's needs in advance, avoiding the problem of one-sided customer analysis and poor real-time response to customer needs after customer classification. Then, this solution comprehensively combines the user's immediate needs and user quality to adaptively classify users, improves the accuracy of user classification, and thus comprehensively improves the adaptability of the corresponding service division.

[0068] In an exemplary embodiment, Figure 1 As shown, a method for adaptive service division of users is provided, which is described by taking the application of the method to a terminal as an example, and includes the following steps S101 to S103.

[0069] in:

[0070] Step S101 : acquiring interaction record information of each user and order record information of each user, and identifying order demand information of each user and product dependency association information of each user based on the order record information of each user.

[0071] In this embodiment, the terminal obtains the content of each interaction record between each user and the enterprise through official accounts, mini-programs, apps, and offline activity collection to obtain the interaction record information of each user. The terminal then obtains the content of each user's order record from the order information of order platforms of types such as POS order types (i.e., on-site scan code payment orders), mini-program / APP order types (i.e., internal link orders), and takeout order types (delivery orders from third-party or internal platforms) to obtain the order record information of each user. Among them, the interaction record content includes but is not limited to activity participation records, evaluation records, questionnaire response records, offline opinion provision records, service quality evaluation records, and user satisfaction feedback records, while the order record information includes the quantity of each product type for each order, additional demand information for each product type, and order time requirements, order delivery requirements, and other order note requirements. Then, the terminal identifies each user's order demand information and each user's product dependency association information from the order record information of each user. Among them, the product dependency association information includes the product characteristics of the order product information corresponding to each order record for the user, as well as the order characteristics. Order requirement information includes the user's order content, product information, and special requirements for each order record. The order content includes the quantity of each product type, additional requirements for each product type, order time requirements, and order delivery requirements. Special requirements include any additional notes for each order. The specific identification process will be explained in detail later.

[0072] Step S102: Based on the interaction record information of each user, identify the interactive participation information of each user and the service demand information of each user, and based on the product dependency association information of each user and the interactive participation information of each user, identify the user quality information of each user through the user analysis model.

[0073] In this embodiment, the terminal identifies each user's interactive participation information and service demand information based on each user's interaction record information. Furthermore, based on each user's product dependency information and interactive participation information, the terminal uses a user analysis model to identify each user's user quality information. The user analysis model includes an order quality evaluation network, an interaction quality evaluation network, and a user quality analysis network. Each of these networks is a classifier neural network based on a reinforcement learning neural network. The user quality information represents the user quality type to which the user's user quality characteristics belong, including but not limited to high-quality purchase volume, high-quality review, and high-quality platform interaction. The user's interactive participation information includes information about each user's interaction characteristics and their interactive behavior, while the user's service demand information includes the user's interaction preference characteristics for each interaction type. The interaction preference characteristics represent the user's preferred interaction method and content during the interaction process. The specific identification process will be described in detail later.

[0074] Step S103, based on each user's order demand information and each user's service demand information, predict each user's immediate service demand information through the user demand prediction model, and generate the user's target service classification information based on each user's immediate service demand and each user's user quality information.

[0075] In this embodiment, the terminal uses a user demand prediction model to predict each user's immediate service demand information based on each user's order demand information and service demand information. Based on each user's immediate service demand and user quality information, the terminal generates the user's target service classification information. The user's immediate service demand information represents the immediate demand content for each service type that the user may generate in a future time period. The future time period is a time period preset by the terminal staff, with the current time as the starting point, the time period as the prediction range, and the time period resulting from the sum of the current time period and the current time as the end point. Service types include, but are not limited to, order service types, event service types, welfare service types, and preferential service types. The user demand prediction model is a convolutional neural network based on an attention mechanism. The user's target service classification information includes the immediate demand content obtained by optimizing the immediate demand content for each service type. The specific optimization process will be described in detail later.

[0076] Based on the above scheme, by identifying the user's product dependency information, order demand information, interactive participation information, and service demand information from the user's interaction records, order records and other recorded information, the user's user quality and immediate service needs are comprehensively analyzed from the perspectives of the customer's product order habits, order demand, interactive information, and service demand. This can not only comprehensively evaluate the user's quality, but also predict the user's needs in advance, avoiding the problem of one-sided customer analysis and poor real-time response to customer needs after customer classification. Then, this scheme comprehensively combines the user's immediate needs and user quality to adaptively classify users, thereby improving the accuracy of user classification, thereby comprehensively improving the adaptability of the corresponding service division.

[0077] Optionally, based on the order record information of each user, the order demand information of each user and the product dependency association information of each user are identified, including: for each user, the user's order record information is split into single order information, and the sub-order demand corresponding to each single order information and the order product information corresponding to each single order information are identified; based on each sub-order demand, the order content corresponding to each single order information and the special demand content corresponding to each single order information are identified, and the order content corresponding to all single order information and the special demand content corresponding to all single order information are used as the user's order demand information; based on each order product information, the product characteristics of each order product information and the order characteristics of each order product information are identified, and the product characteristics of all order product information and the order characteristics of all order product information are used as the user's product dependency association information.

[0078] In this embodiment, the terminal divides each user's order record information into individual order information and identifies the sub-order requirements corresponding to each individual order information, as well as the order product information corresponding to each individual order information. The individual order information refers to the order information for each order placed by the user. The order product information includes product description information for each product type in the order information, as well as description information for each type of additive added by the user.

[0079] Then, based on each sub-order requirement, the terminal identifies the order content corresponding to each single order information and the special requirement content corresponding to each single order information, and uses the order content corresponding to all single order information and the special requirement content corresponding to all single order information as the user's order requirement information.

[0080] Next, the terminal uses a large language model based on natural language processing technology to perform semantic feature extraction based on each order product information. This extracts the product feature content corresponding to the product description information for each product type, and the additive feature content corresponding to the additive description information for each additive type. The terminal then uses the product feature content of each order product information as the product feature of each order product information, the additive feature content of each order product information as the order feature of each order product information, and the product features of all order product information, as well as the order features of all order product information, as the user's product dependency association information.

[0081] Based on the above solution, after splitting the order information into individual order information, the order requirement content, special requirement content, product characteristics, and order characteristics of each individual order information are split and analyzed, thereby improving the comprehensiveness and precision of the analysis of each order information.

[0082] Optionally, based on the interaction record information of each user, the interaction participation information of each user and the service demand information of each user are identified, including: for each user, based on the user's interaction record information, the interaction content of each interaction type of the user and the interaction participation information of the user in each interaction type are identified; based on the user's interaction participation information in each interaction type, the interaction preference features of each interaction type are extracted through a feature extraction network, and the interaction preference features of all interaction types are used as the user's service demand information; based on the interaction content of each interaction type of the user, the interaction feature information of the user and the interaction behavior information of the user are identified, and the interaction feature information of the user and the interaction behavior information of the user are used as the user's interaction participation information.

[0083] In this embodiment, the terminal identifies the interaction content of each user in each interaction type and the user's interaction participation information in each interaction type based on the user's interaction record information. The interaction types include, but are not limited to, activity interaction types, evaluation interaction types, opinion / questionnaire interaction types, discount interaction types, and welfare interaction types.

[0084] Then, based on the user's interaction participation information in each interaction type, the terminal extracts the interaction preference features of each interaction type through a feature extraction network, and uses the interaction preference features of all interaction types as the user's service demand information. Among them, the feature extraction network is a convolutional neural network (CNN) based on deep learning.

[0085] Afterwards, the terminal identifies the user's various interaction feature information and the user's interaction behavior information based on the interaction content of each interaction type of the user, and uses the user's various interaction feature information and the user's interaction behavior information as the user's interaction participation information. The terminal presets each interaction feature type and each interaction behavior type, and then, based on the interaction content of each interaction type, the terminal extracts the feature data of each interaction feature type and the behavior data of each interaction behavior type to obtain the user's various interaction feature information and the user's interaction behavior information. Among them, each interaction feature type includes but is not limited to interaction frequency features, interaction effect features, interaction quality features, and interaction effectiveness features, etc., and interaction behavior types include but are not limited to text interaction types, offline interaction types, image / table interaction types, action interaction types, task interaction types (task interaction types for completing tasks such as predetermined collection, acquisition, collection of likes, and activity processes), etc.

[0086] Based on the above solution, by splitting and analyzing each different interaction type and analyzing the interaction preference characteristics, interaction feature information, and interaction behavior information of each interaction type, the comprehensiveness and accuracy of the analysis of interaction information are improved.

[0087] Optionally, based on each user's product dependency association information and each user's interactive participation information, the user quality information of each user is identified through a user analysis model, including: for each user, based on the product characteristics of each order product information of the user and the order characteristics of each order product information, the order quality evaluation value of each order evaluation indicator type of the user is identified through the order quality evaluation network of the user analysis model; based on each interaction feature information in the user's interactive participation information and the interactive behavior information in the user's interactive participation information, the interaction quality evaluation value of each interaction evaluation indicator type of the user is identified through the interaction quality evaluation network of the user analysis model; based on the order quality evaluation value of each order evaluation indicator type and the interaction quality evaluation value of each interaction evaluation indicator type, the user quality type to which the user's user quality characteristics belong is identified through the user quality analysis network of the user analysis model; and the user quality type to which the user quality characteristics belong is used as the user quality information of the user.

[0088] In this embodiment, the terminal identifies, for each user, an order quality evaluation value for each order evaluation indicator type based on the product characteristics of each order product information and the order characteristics of each order product information, using the order quality evaluation network of the user analysis model. Each order evaluation indicator type is used to evaluate a user's purchase behavior, product support, and ordering of high-value products. These order evaluation indicator types include, but are not limited to, purchase quantity evaluation indicator types, product range evaluation indicator types, product value range evaluation indicator types, product usage frequency evaluation indicator types, and product usage trend evaluation indicator types.

[0089] Then, based on the interaction feature information and interaction behavior information in the user's interactive participation information, the terminal uses the interaction quality evaluation network of the user analysis model to identify the user's interaction quality evaluation value for each interaction evaluation indicator type. Interaction evaluation indicator types include, but are not limited to, opinion availability evaluation indicator types, engagement evaluation indicator types, interaction frequency evaluation indicator types, interaction scope evaluation indicator types, and interaction cost-effectiveness evaluation indicator types. These are used to evaluate information such as participation, usage, recognition, and follow-up of various activities, discounts, services, reviews, and opinions related to the enterprise.

[0090] Next, the terminal identifies the user quality type to which the user's user quality characteristics belong, based on the order quality evaluation values of each order evaluation indicator type and the interaction quality evaluation values of each interaction evaluation indicator type, through the user quality analysis network of the user analysis model. Finally, the terminal uses the user quality type to which the user quality characteristics belong as the user quality information of the user. The user quality analysis network includes the correspondence between the order evaluation indicator type, the evaluation value ranges of each interaction evaluation indicator type, and user quality. Each user quality type corresponds to one or more user quality characteristics, for example, the purchase volume quality type corresponds to the new product purchase volume quality characteristic, the classic product purchase volume quality characteristic, the comprehensive product purchase volume quality characteristic, etc.

[0091] Based on the above solution, by evaluating the order quality and interaction quality separately, the user quality type of the user is analyzed, which improves the comprehensiveness and accuracy of the analysis of the user quality type.

[0092] Optionally, based on each user's order demand information and each user's service demand information, a user demand prediction model is used to predict each user's instant service demand information, including: for each user, based on the order content corresponding to all single order information and the special demand content corresponding to all single order information, an order preference identification network is used to identify the user's order preference information and the user's order preference range; based on the interaction preference characteristics of each interaction type in the user's service demand information, a user demand prediction model is used to predict the user's demand content of each service demand type; based on the user's order preference information and the user's order preference range, a user demand prediction model is used to predict the user's target order demand information; based on the user's demand content of each service demand type and the user's target order demand information, the user's target service information is generated, and the target service information is used as the user's instant service demand information.

[0093] In this embodiment, the terminal uses an order preference recognition network to identify the user's order preference information and order preference range for each user based on the order content and special needs content corresponding to all single order information. The order preference recognition network is a neural network corresponding to a prediction algorithm based on a gray neural network.

[0094] Then, the terminal predicts the user's demand content for each service demand type based on the interaction preference characteristics of each interaction type in the user's service demand information through the user demand prediction model.

[0095] Then, based on the user's order preference information and the user's order preference range, the terminal uses the user demand prediction model to predict the user's target order demand information. Finally, based on the user's demand content for each service demand type and the user's target order demand information, the terminal generates the user's target service information and uses the target service information as the user's immediate service demand information. The target service information is the service information corresponding to the demand content of each service demand type and the user's target order demand information, and includes the immediate demand content of each service type.

[0096] Based on the above solution, by combining the demand content of each service demand type of the user and the target order demand information, the user's target service information is generated, thereby improving the comprehensiveness and accuracy of the target service information.

[0097] Optionally, based on each user's instant service needs and each user's user quality information, the user's target service classification information is generated, including: for each user, based on the user's instant service demand information, identifying the user's instant demand content of each service type, and based on the user's user quality type, querying the user service database to obtain the service optimization range of each target service type corresponding to the user quality type; based on the service optimization range of each target service type, performing service optimization processing on the instant service demand content of each target service type to obtain the target instant service content of each target service type; using the target instant service demand content of each target service type and the instant service demand content of each non-target service type as the user's target service classification information.

[0098] In this embodiment, the terminal identifies the immediate service needs of each user for each service type based on the user's immediate service demand information, and queries the user service database based on the user's user quality type to obtain the service optimization range of each target service type corresponding to the user quality type. In the user service database, different user quality types correspond to one or more target service types, as well as a service optimization range corresponding to each target service type. For example, the target service types corresponding to the purchase volume quality type include, but are not limited to, order service types, preferential service types, and welfare service types. The service optimization range of the order service type is the reduction or exemption ratio value for different order volumes, the service optimization range of the preferential service type is the preferential degree value for each product, and the service optimization range of the welfare service type is the welfare level range, etc.

[0099] Then, based on the service optimization range of each target service type, the terminal performs service optimization processing on the instant service demand content of each target service type to obtain the target instant service demand content of each target service type. The service optimization processing method is as follows: based on the instant service demand content of each target service type, the terminal uses the service optimization range of each target service type as the range interval. If the instant service demand content does not exceed the range interval, the instant service demand content is used as the target instant service demand content. If the instant service demand content exceeds the range interval, the target instant service demand content is used as the boundary value of the range interval adjacent to the instant service demand content.

[0100] Finally, the terminal uses the target instant service demand content of each target service type and the instant service demand content of each non-target service type as the user's target service classification information.

[0101] Based on the above scheme, the instant service demand content of each service type is optimized and adjusted through each user quality type, so as to obtain the user's target service classification information, thereby improving the adaptability and service accuracy of the user's target service classification.

[0102] The application also provides an example of adaptive service partitioning for a user, such as Figure 2 As shown, the specific processing process includes the following steps:

[0103] Step S201: Acquire interaction record information of each user and order record information of each user.

[0104] Step S202 : For each user, the user's order record information is split into individual order information, and the sub-order requirements corresponding to each individual order information and the order product information corresponding to each individual order information are identified.

[0105] Step S203, based on each sub-order requirement, identifies the order content corresponding to each single order information and the special requirement content corresponding to each single order information, and uses the order content corresponding to all single order information and the special requirement content corresponding to all single order information as the user's order requirement information.

[0106] Step S204: Based on each order product information, identify the product features of each order product information and the order features of each order product information, and use the product features of all order product information and the order features of all order product information as the user's product dependency association information.

[0107] Step S205 : for each user, based on the user's interaction record information, identifying the user's interaction content of each interaction type and the user's interaction participation information in each interaction type.

[0108] Step S206 , based on the user's interaction participation information in each interaction type, the feature extraction network is used to extract the interaction preference features of each interaction type, and the interaction preference features of all interaction types are used as the user's service demand information.

[0109] Step S207 , based on the interaction content of each interaction type of the user, identifying each interaction feature information of the user and the interaction behavior information of the user, and using each interaction feature information of the user and the interaction behavior information of the user as the interaction participation information of the user.

[0110] Step S208 , for each user, based on the product features of each order product information of the user and the order features of each order product information, the order quality evaluation value of each order evaluation indicator type of the user is identified through the order quality evaluation network of the user analysis model.

[0111] Step S209 , based on the interaction feature information and the interaction behavior information in the user's interaction participation information, the interaction quality evaluation network of the user analysis model is used to identify the interaction quality evaluation value of each interaction evaluation indicator type of the user.

[0112] Step S210 , based on the order quality evaluation value of each order evaluation indicator type and the interaction quality evaluation value of each interaction evaluation indicator type, the user quality type to which the user quality feature of the user belongs is identified through the user quality analysis network of the user analysis model.

[0113] Step S211: taking the user quality type to which the user quality feature belongs as the user quality information of the user.

[0114] Step S212: for each user, based on the order content corresponding to all single order information and the special demand content corresponding to all single order information, the order preference information and the order preference range of the user are identified through the order preference identification network.

[0115] Step S213 : Based on the interaction preference features of each interaction type in the user's service demand information, the user's demand content of each service demand type is predicted using a user demand prediction model.

[0116] Step S214 , based on the user's order preference information and the user's order preference range, the user's target order demand information is predicted through the user demand prediction model.

[0117] Step S215 , based on the user's demand content of each service demand type and the user's target order demand information, the user's target service information is generated, and the target service information is used as the user's instant service demand information.

[0118] Step S216: for each user, based on the user's instant service demand information, identify the user's instant demand content for each service type, and based on the user's user quality type, query the user service database to obtain the service optimization range of each target service type corresponding to the user quality type.

[0119] Step S217 : Based on the service optimization scope of each target service type, service optimization processing is performed on the instant service demand content of each target service type to obtain the target instant demand content of each target service type.

[0120] Step S218: The target instant service demand content of each target service type and the instant service demand content of each non-target service type are used as the user's target service classification information.

[0121] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0122] Based on the same inventive concept, embodiments of the present application also provide a user adaptive service partitioning device for implementing the aforementioned user adaptive service partitioning method. The implementation solution provided by this device is similar to the implementation solution described in the aforementioned method. Therefore, the specific limitations of the embodiments of the user adaptive service partitioning device provided below can be found in the above-mentioned limitations of the user adaptive service partitioning method, and will not be repeated here.

[0123] In an exemplary embodiment, Figure 3 As shown, a user adaptive service division device is provided, including: an acquisition module 310, an identification module 320 and a prediction module 330, wherein:

[0124] An acquisition module 310 is configured to acquire interaction record information of each user and order record information of each user, and identify order demand information of each user and product dependency association information of each user based on the order record information of each user;

[0125] Identification module 320, for identifying each user's interactive participation information and service demand information based on each user's interaction record information, and identifying each user's user quality information based on each user's product dependency association information and each user's interactive participation information using a user analysis model;

[0126] The prediction module 330 is used to predict each user's immediate service demand information based on each user's order demand information and each user's service demand information through a user demand prediction model, and generate the user's target service classification information based on each user's immediate service demand and each user's user quality information.

[0127] Optionally, the acquisition module 310 is specifically configured to:

[0128] For each user, split the user's order record information into individual order information, and identify the sub-order requirements corresponding to each individual order information, as well as the order product information corresponding to each individual order information;

[0129] Based on each sub-order requirement, identify the order content corresponding to each single order information and the special requirement content corresponding to each single order information, and use the order content corresponding to all single order information and the special requirement content corresponding to all single order information as the order requirement information of the user;

[0130] Based on each order product information, the product characteristics of each order product information and the order characteristics of each order product information are identified, and the product characteristics of all order product information and the order characteristics of all order product information are used as the product dependency association information of the user.

[0131] Optionally, the identification module 320 is specifically configured to:

[0132] For each user, based on the user's interaction record information, identifying the interaction content of each interaction type of the user and the user's interaction participation information in each interaction type;

[0133] Based on the user's interaction participation information in each interaction type, extracting the interaction preference feature of each interaction type through a feature extraction network, and using the interaction preference features of all interaction types as the user's service demand information;

[0134] Based on the interaction content of each interaction type of the user, the interaction feature information of the user and the interaction behavior information of the user are identified, and the interaction feature information of the user and the interaction behavior information of the user are used as the interaction participation information of the user.

[0135] Optionally, the identification module 320 is specifically configured to:

[0136] For each user, based on the product features of each order product information of the user and the order features of each order product information, an order quality evaluation value of each order evaluation indicator type of the user is identified through the order quality evaluation network of the user analysis model;

[0137] Based on each interaction feature information in the user's interaction participation information and the interaction behavior information in the user's interaction participation information, identifying the interaction quality evaluation value of each interaction evaluation indicator type of the user through the interaction quality evaluation network of the user analysis model;

[0138] Based on the order quality evaluation value of each order evaluation indicator type and the interaction quality evaluation value of each interaction evaluation indicator type, identifying the user quality type to which the user quality feature of the user belongs through the user quality analysis network of the user analysis model;

[0139] The user quality type to which the user quality feature belongs is used as the user quality information of the user.

[0140] Optionally, the prediction module 330 is specifically configured to:

[0141] For each user, based on the order content corresponding to all single order information and the special demand content corresponding to all single order information, the order preference information and the order preference range of the user are identified through the order preference identification network;

[0142] Based on the interaction preference characteristics of each interaction type in the user's service demand information, predicting the demand content of each service demand type of the user through the user demand prediction model;

[0143] Based on the user's order preference information and the user's order preference range, predicting the user's target order demand information through the user demand prediction model;

[0144] Based on the demand content of each service demand type of the user and the target order demand information of the user, the target service information of the user is generated, and the target service information is used as the instant service demand information of the user.

[0145] Optionally, the prediction module 330 is specifically configured to:

[0146] For each user, based on the user's instant service demand information, identify the user's instant demand content for each service type, and based on the user's user quality type, query the user service database to obtain the service optimization range of each target service type corresponding to the user quality type;

[0147] Based on the service optimization scope of each target service type, performing service optimization processing on the instant service demand content of each target service type to obtain the target instant demand content of each target service type;

[0148] The target instant service demand content of each target service type and the instant service demand content of each non-target service type are used as the target service classification information of the user.

[0149] Each module in the above-mentioned user adaptive service partitioning device can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the corresponding operations of each module.

[0150] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 4 As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface, the display unit and the input device are connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a method for adaptive service division of users is implemented. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device casing, or an external keyboard, touchpad or mouse.

[0151] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0152] In an exemplary embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps of the method for adaptively dividing user services when executing the computer program.

[0153] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method for adaptively dividing user services are implemented.

[0154] In one embodiment, a computer program product is provided, comprising a computer program, which implements the steps of the method for adaptive service partitioning of users when executed by a processor.

[0155] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0156] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processor involved in the various embodiments provided herein may be, but are not limited to, a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, and the like.

[0157] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0158] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A method for adaptive service partitioning of users, characterized in that: The method comprises: Obtaining interaction record information of each user and order record information of each user, and identifying order demand information of each user and product dependency association information of each user based on the order record information of each user; Based on each user's interaction record information, identify each user's interactive participation information and each user's service demand information, and based on each user's product dependency association information and each user's interactive participation information, identify each user's user quality information through a user analysis model; Based on each user's order demand information and each user's service demand information, the user demand prediction model is used to predict each user's immediate service demand information, and based on each user's immediate service demand and each user's user quality information, the user's target service classification information is generated.

2. The method according to claim 1, characterized in that The step of identifying each user's order demand information and each user's product dependency association information based on the order record information of each user includes: For each user, split the user's order record information into individual order information, and identify the sub-order requirements corresponding to each individual order information, as well as the order product information corresponding to each individual order information; Based on each sub-order requirement, identify the order content corresponding to each single order information and the special requirement content corresponding to each single order information, and use the order content corresponding to all single order information and the special requirement content corresponding to all single order information as the order requirement information of the user; Based on each order product information, the product characteristics of each order product information and the order characteristics of each order product information are identified, and the product characteristics of all order product information and the order characteristics of all order product information are used as the product dependency association information of the user.

3. The method according to claim 1, characterized in that The identification of each user's interactive participation information and each user's service demand information based on each user's interaction record information includes: For each user, based on the user's interaction record information, identifying the interaction content of each interaction type of the user and the user's interaction participation information in each interaction type; Based on the user's interaction participation information in each interaction type, extracting the interaction preference features of each interaction type through a feature extraction network, and using the interaction preference features of all interaction types as the user's service demand information; Based on the interaction content of each interaction type of the user, the interaction feature information of the user and the interaction behavior information of the user are identified, and the interaction feature information of the user and the interaction behavior information of the user are used as the interaction participation information of the user.

4. The method according to claim 2, characterized in that The user quality information of each user is identified through a user analysis model based on the product dependency association information of each user and the interactive participation information of each user, including: For each user, based on the product features of each order product information of the user and the order features of each order product information, an order quality evaluation value of each order evaluation indicator type of the user is identified through the order quality evaluation network of the user analysis model; Based on each interaction feature information in the user's interaction participation information and the interaction behavior information in the user's interaction participation information, identifying the interaction quality evaluation value of each interaction evaluation indicator type of the user through the interaction quality evaluation network of the user analysis model; Based on the order quality evaluation value of each order evaluation indicator type and the interaction quality evaluation value of each interaction evaluation indicator type, identifying the user quality type to which the user quality feature of the user belongs through the user quality analysis network of the user analysis model; The user quality type to which the user quality feature belongs is used as the user quality information of the user.

5. The method according to claim 3, characterized in that The method of predicting each user's instant service demand information based on the order demand information and service demand information of each user through a user demand prediction model includes: For each user, based on the order content corresponding to all single order information and the special demand content corresponding to all single order information, the order preference information and the order preference range of the user are identified through the order preference identification network; Based on the interaction preference characteristics of each interaction type in the user's service demand information, predicting the demand content of each service demand type of the user through the user demand prediction model; Based on the user's order preference information and the user's order preference range, predicting the user's target order demand information through the user demand prediction model; Based on the demand content of each service demand type of the user and the target order demand information of the user, the target service information of the user is generated, and the target service information is used as the instant service demand information of the user.

6. The method according to claim 4, characterized in that The generating of target service classification information of each user based on the instant service demand of each user and the user quality information of each user includes: For each user, based on the user's instant service demand information, identify the user's instant demand content for each service type, and based on the user's user quality type, query the user service database to obtain the service optimization range of each target service type corresponding to the user quality type; Based on the service optimization scope of each target service type, performing service optimization processing on the instant service demand content of each target service type to obtain the target instant demand content of each target service type; The target instant service demand content of each target service type and the instant service demand content of each non-target service type are used as the target service classification information of the user.

7. A user's adaptive service division device, characterized in that: The device comprises: An acquisition module, configured to acquire interaction record information of each user and order record information of each user, and identify order demand information of each user and product dependency association information of each user based on the order record information of each user; An identification module is used to identify each user's interactive participation information and service demand information based on each user's interaction record information, and to identify each user's user quality information based on each user's product dependency association information and each user's interactive participation information through a user analysis model; The prediction module is used to predict each user's immediate service demand information based on each user's order demand information and each user's service demand information through a user demand prediction model, and generate the user's target service classification information based on each user's immediate service demand and each user's user quality information.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images