Service recommendation method and device, storage medium and electronic equipment

Abstract

The invention discloses a service recommendation method and device, a storage medium and electronic equipment, and the method comprises the steps: obtaining target consumption data of a target user based on a service recommendation triggering operation of the target user; determining target consumption scene features of the target consumption data; determining a target extended service in a plurality of candidate extended services based on the target consumption scene feature and a pre-constructed matching relationship between the extended service and the consumption scene feature; binding the target extended service with the basic service to obtain a to-be-recommended service; and recommending the to-be-recommended service to the target user. The consumption data of the user is associated with the consumption scene, and the consumption scene is associated with the candidate extended service related to subsequent basic service recommendation, so that the service recommendation effect is improved. Moreover, manual recommendation is avoided, and the labor cost is saved.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a service recommendation method, apparatus, storage medium, and electronic device. Background Technology

[0002] To improve user experience, additional extended services can be recommended alongside basic services, such as those that the user might be interested in. Currently, service recommendations are generally selected manually, resulting in poor recommendation effectiveness.

[0003] Based on this, this specification provides a service recommendation method. Summary of the Invention

[0004] This application specification provides a service recommendation method, apparatus, storage medium, and electronic device to at least partially solve the aforementioned problems existing in the prior art.

[0005] The technical solution adopted in this application specification is as follows: This application provides a service recommendation method, which is applied to a first service provider, and the method includes: In response to a service recommendation trigger operation for a target user, the target user's target consumption data is obtained; Determine the target consumption scenario characteristics of the target consumption data; Based on the target consumption scenario characteristics and the matching relationship between the pre-built extended services and the consumption scenario characteristics, the target extended service is determined from several candidate extended services. Bind the target extended service with the basic service to obtain the service to be recommended; The service to be recommended is recommended to the target user.

[0006] This application provides a service recommendation method, which is applied to a third-party service provider, and the method includes: The system receives an electronic credential acquisition request from a first service provider. The electronic credential acquisition request includes a target extended service identifier. The electronic credential acquisition request is sent by the first service provider to the third service provider in response to the target user's recommended service usage operation. The first service provider recommends the service to be recommended to the target user based on the matching relationship between the pre-built extended service and the consumption scenario characteristics. Based on the target extended service identifier, obtain the target electronic credential of the target extended service; The target electronic credential is returned to the first service provider so that the first service provider can display the target electronic credential to the target user.

[0007] This application specification provides a service recommendation system, the system comprising a first service providing module, a second service providing module, and a third service providing module, wherein: The first service providing module is configured to, in response to a service recommendation triggering operation by a target user, acquire the target consumption data of the target user, determine the target consumption scenario characteristics of the target consumption data, determine a target extended service from several candidate extended services based on the target consumption scenario characteristics and a pre-built matching relationship between extended services and consumption scenario characteristics, bind the target extended service with a basic service to obtain a service to be recommended, recommend the service to be recommended to the target user, and, in response to a recommended service usage operation by the target user, send an electronic voucher acquisition request to the third service providing module and a basic service usage request to the second service providing module. The second service providing module is used to receive the basic service usage request and send the basic service interface to the first service providing module; The third service providing module is configured to receive the electronic credential acquisition request, acquire the target electronic credential of the target extended service according to the target extended service identifier included in the electronic credential acquisition request, and return the target electronic credential to the first service providing module. The first service providing module is further configured to receive the target electronic credential returned by the third service providing module, display the target electronic credential to the target user, receive the basic service interface sent by the second service providing module, and display the basic service page based on the basic service interface.

[0008] This application specification provides a service recommendation device, which is applied to a first service provider, and the device includes: The target consumption data acquisition module is used to acquire the target consumption data of the target user in response to the service recommendation trigger operation of the target user. The target consumption scenario feature determination module is used to determine the target consumption scenario features of the target consumption data; The target extended service determination module is used to determine the target extended service from several candidate extended services based on the target consumption scenario characteristics and the pre-built matching relationship between extended services and consumption scenario characteristics. The module for determining the service to be recommended is used to bind the target extended service with the basic service to obtain the service to be recommended. The recommendation module is used to recommend the services to be recommended to the target user.

[0009] This application specification provides a service recommendation device, which is applied to a third-party service provider, and the device includes: The request receiving module is used to receive an electronic credential acquisition request sent by a first service provider. The electronic credential acquisition request includes a target extended service identifier. The electronic credential acquisition request is sent by the first service provider to the third service provider in response to the target user's recommended service usage operation, after the first service provider recommends the service to be recommended to the target user. The target electronic credential acquisition module is used to acquire the target electronic credential of the target extended service based on the target extended service identifier. The target electronic credential return module is used to return the target electronic credential to the first service provider so that the first service provider can display the target electronic credential to the target user.

[0010] This application specification provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described service recommendation method.

[0011] This application specification provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the above-mentioned service recommendation method.

[0012] This application discloses a computer program product, which includes a computer program that, when executed by a processor, implements the aforementioned service recommendation method.

[0013] The above-described technical solution adopted in this application specification can achieve the following beneficial effects: In the service recommendation method provided in this application, the application obtains the target user's target consumption data by triggering a service recommendation operation based on the target user; determines the target consumption scenario characteristics of the target consumption data; based on the target consumption scenario characteristics and the matching relationship between pre-built extended services and consumption scenario characteristics, determines the target extended service from several candidate extended services; binds the target extended service with the basic service to obtain the service to be recommended; and recommends the service to be recommended to the target user. By associating the user's consumption data with the consumption scenario, and associating the consumption scenario with the candidate extended services related to the subsequent basic service recommendation, the service recommendation effect is improved. Furthermore, it eliminates the need for manual recommendation, saving labor costs. Attached Figure Description

[0014] The accompanying drawings, which are included to provide a further understanding of this application specification and form part of this specification, illustrate exemplary embodiments and their descriptions, serving to explain this application specification and do not constitute an undue limitation thereof. In the drawings: Figure 1A flowchart illustrating a service recommendation method provided in this application specification; Figure 2 A schematic diagram of a service recommendation device provided in this application specification; Figure 3 The corresponding specification provided in this application is Figure 1 A schematic diagram of an electronic device. Detailed Implementation

[0015] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments described in this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments in this application without creative effort are within the scope of protection of this application.

[0016] It should be noted that the acquisition, storage, use, and processing of data in the technical solution of this application comply with the relevant provisions of national laws and regulations.

[0017] Service recommendations are an effective way to improve user experience. Generally, while providing basic services, additional extended services can be recommended. For example, when providing navigation services, users can be advised on nearby restaurants and activities. However, current service recommendations are generally selected manually, with a low level of intelligence, resulting in poor recommendation effectiveness.

[0018] To address the aforementioned issues, this application provides a service recommendation method. This method involves obtaining target consumption data from a target user through a service recommendation trigger operation; determining the target consumption scenario characteristics of the target consumption data; identifying a target extended service from several candidate extended services based on the target consumption scenario characteristics and a pre-built matching relationship between extended services and consumption scenario characteristics; binding the target extended service with a basic service to obtain a service to be recommended; and recommending the service to be recommended to the target user. By associating user consumption data with consumption scenarios and linking consumption scenarios with candidate extended services related to subsequent basic service recommendations, the service recommendation effect is improved. Furthermore, this application eliminates the need for manual recommendations, saving labor costs.

[0019] The implementing entities of this application may include a first service provider, a second service provider, and a third service provider. Each service provider can be any electronic device, such as a server, personal computer, tablet, etc., and this application does not impose any restrictions. The second service provider provides resources and basic services, while the third service provider provides candidate extended services. The first service provider can utilize the resources provided by the second service provider to obtain several extended services from multiple third service providers. It is understood that the first service provider can be understood as an intermediary, used to interact with the second and third service providers, and with the user's terminal, to recommend services to the user.

[0020] It should be noted that both basic and extended services can be any type of service. For example, a basic service could be a membership service, while an extended service could be a product discount service. A basic service could be an online video viewing service, while an extended service could be a movie ticket discount service, etc.

[0021] The technical solutions provided by the various embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0022] Figure 1 This is a flowchart illustrating a service recommendation method provided in this application specification, specifically including steps S101 to S105.

[0023] S101: In response to the service recommendation trigger operation of the target user, obtain the target user's target consumption data.

[0024] Users can interact with the first service provider through a terminal. This terminal can be deployed with application software or other triggering programs to initiate service recommendations. When a user clicks on the application software installed on the terminal, the service recommendation service is triggered. Of course, the service recommendation service can also be triggered automatically by the terminal pushing information to the user; this application specification does not impose any limitations on this. After the target user triggers the service recommendation through the terminal, the first service provider can obtain the target user's target consumption data. This target consumption data can be obtained with the target user's authorization, and the consumption data can be consumption data generated from the user's purchase of any type of goods.

[0025] S102: Determine the target consumption scenario characteristics of the target consumption data.

[0026] In this application specification, the first service provider may identify consumption scenarios in target consumption data based on a preset clustering algorithm; generate target profiles of target users based on consumption scenarios; and construct the association between consumption scenarios and target profiles of target users to obtain target consumption scenario features.

[0027] When identifying consumption scenarios, the target consumption data can first be converted into feature vectors. The goal is to allow clustering algorithms to automatically construct cluster trees based on the similarity between data points. Next, a distance metric is selected, such as Euclidean distance or Manhattan distance, to measure the difference between two consumption behaviors. Then, a linking criterion is chosen to define how the distance between two consumption behaviors is calculated. Linking criteria can include full linking, single linking, and average linking. Full linking uses the distance between the two least similar points in two clusters as the inter-cluster distance, tending to form compact, similarly sized clusters. Single linking uses the distance between the two most similar points in two clusters as the inter-cluster distance. Average linking takes the average of the distances between all pairs of points between two clusters. The clustering algorithm then outputs a dendrogram. The bottom of the dendrogram represents each individual consumption scenario. From the root to the top, similar consumption scenarios are merged together, eventually converging at the top into a single consumption scenario containing all data. Finally, the dendrogram is segmented to determine the individual consumption scenarios. Examples include: high-value purposeful shopping, daily dining, and weekend entertainment and socializing.

[0028] For example, in the mining of credit card consumption scenarios, hierarchical clustering algorithms are used to identify scenario categories such as nighttime food delivery clusters and cross-border consumption clusters from target consumption data, and to filter out incidental transactions.

[0029] Subsequently, when generating the target profile, the user's target profile can be determined by factors such as the consumption time, resources consumed, channels consumed, and the category of the consumed items. Then, the correlation between the consumption scenario and the target profile is established, yielding the characteristics of the target consumption scenario.

[0030] This application utilizes a clustering algorithm to achieve adaptive parameter optimization. Furthermore, for non-uniform density data, it can automatically determine the neighborhood radius threshold and the minimum number of core points required through K-nearest neighbor distance sorting or Gaussian distribution estimation, avoiding the limitations of manual parameter tuning. Additionally, it improves the clustering performance on non-uniform datasets by assigning local parameters to different density regions using density hierarchy partitioning or clustering effect indices.

[0031] S103: Based on the target consumption scenario characteristics and the matching relationship between the pre-built extended services and the consumption scenario characteristics, determine the target extended service from several candidate extended services.

[0032] In this application specification, the first service provider may first identify several candidate extended services that match the characteristics of the target consumption scenario from the matching relationship, and then identify the target extended service from the several candidate extended services. The first service provider may identify all candidate extended services as the target extended service, or may select one candidate extended service as the target extended service; this application embodiment does not impose any restrictions on this.

[0033] S104: Bind the target extended service with the basic service to obtain the service to be recommended.

[0034] S105: Recommend the service to be recommended to the target user.

[0035] Specifically, the first service provider sends the service to be recommended to the terminal used by the target user, so that the service to be recommended can be displayed through the terminal's display device, audio playback device, etc.

[0036] based on Figure 1 The service recommendation method described herein involves obtaining target consumption data of the target user through a service recommendation trigger operation based on the target user; determining the target consumption scenario characteristics of the target consumption data; determining a target extended service from several candidate extended services based on the target consumption scenario characteristics and the pre-built matching relationship between extended services and consumption scenario characteristics; binding the target extended service with the basic service to obtain the service to be recommended; and recommending the service to be recommended to the target user. By associating the user's consumption data with the consumption scenario, and associating the consumption scenario with the candidate extended services related to subsequent basic service recommendations, the service recommendation effect is improved. Furthermore, the service recommendation method provided in this application eliminates manual recommendation, saving labor costs.

[0037] Before executing S101, the first service provider may select a target third service provider from among the various third service providers based on the resources provided by the second service provider; and determine the candidate extended services from the extended services provided by the target third service provider. The candidate extended services can be set as needed, for example, extended services can be various promotional activities, various physical goods vouchers, and various electronic vouchers for daily necessities, etc.

[0038] By utilizing resources provided by a second service provider, the first service provider selects the desired candidate extended services within that resource range, rather than choosing a third service provider directly from the second service provider. When multiple second service providers exist, they can all use the same batch of candidate extended services, reducing the steps required for each second service provider to select extended services independently. Furthermore, after identifying candidate extended services, the first service provider can match them based on the user's consumption characteristics. Therefore, the matched candidate extended services better meet the user's needs, improving the effectiveness of the recommendation service.

[0039] Of course, various existing extended services can also be obtained as candidate extended services, and this application specification does not limit this. For example, airport VIP lounge access and points rules.

[0040] It should be further noted that when selecting a target third-party service provider, multiple third-party service providers can be selected, or only one can be selected; this application specification does not impose any restrictions on this. Specifically, before selecting a target third-party service provider, a consumption dataset can be obtained, which includes consumption data from several users; based on the consumption dataset, the consumption scenario characteristics of several users can be determined; based on several candidate extended services, an extended service knowledge graph can be constructed, where nodes in the extended service knowledge graph represent candidate extended services, and an edge represents the correlation between two candidate extended services; according to the extended service knowledge graph and the characteristics of each consumption scenario, the matching relationship between each candidate extended service and the characteristics of the consumption scenario can be determined.

[0041] The consumption dataset includes consumption data from various users and may also include data across multiple dimensions, such as merchant type, amount, frequency, and geographical location. Therefore, based on this dataset, the consumption scenario characteristics of various users can be determined. These scenarios can include various real-world consumption scenarios, such as food delivery, travel, and cross-border consumption. When determining these consumption scenario characteristics, a pre-defined clustering algorithm, such as Density-Based Spatial Clustering of Applications with Noise (DBSCAN), can be used to identify the consumption scenarios in the dataset. Based on these scenarios, user profiles for various users can be generated, and the association between consumption scenarios and user profiles can be established to obtain the consumption scenario characteristics. Subsequently, based on the resources provided by the second service provider and the users' consumption scenario characteristics, multiple candidate extended services can be selected to construct an extended service knowledge graph.

[0042] This application specification uses a constructed knowledge graph to reflect the correlation between different extended services, so that when determining matching relationships in the future, matching can be performed based on features of the same consumption scenario that are highly correlated.

[0043] When constructing the knowledge graph, a service feature vector is determined for each candidate extended service based on preset service characteristics. These service characteristics include at least one of extended service type, consumption scenario, and user profile. Based on the service feature vector of each candidate extended service, the correlation between any two candidate extended services is determined. An extended service knowledge graph is constructed using each correlation as an edge, each candidate extended service as a node, and the service feature vector of each candidate extended service as a node feature. The correlation can be determined by assessing the similarity between the service feature vectors of two candidate extended services; this application does not restrict how the similarity between the service feature vectors of two candidate extended services is determined. This application does not restrict how the service feature vectors of candidate extended services are determined; if predefined, they can be determined based on the weights corresponding to the candidate extended service type, applicable scenario, audience profile, and resource threshold.

[0044] This application specification constructs a knowledge graph that, through relevance edges, can quickly discover extended services related to a user's current service, enabling accurate recommendations. Furthermore, node feature vectors allow for the consideration of multi-dimensional information, such as service type, scenario, and user profile, avoiding the limitations of single-dimensional recommendations and thus improving the diversity and personalization of recommendations. Moreover, when a new extended service is added, only its feature vector and its relevance to existing services need to be calculated, and then it can be added to the graph, facilitating updates.

[0045] When determining the matching relationship between each candidate extended service and the consumption scenario feature, the first service provider can use a collaborative filtering algorithm to determine the scenario similarity and feature vector similarity between each node in the extended service knowledge graph and each consumption scenario feature; based on the scenario similarity and feature vector similarity, determine the matching score between each candidate extended service in the extended service knowledge graph and each consumption scenario feature; and based on each matching score, determine the matching relationship between each candidate extended service and the consumption scenario feature.

[0046] Collaborative filtering (CF) is a recommendation algorithm based on group behavior, mainly divided into two categories: User-based CF, which calculates user similarity and recommends items liked by similar users; and Item-based CF, which calculates item similarity and recommends items similar to users' historical preferences.

[0047] Specifically, the first approach involves determining the similarity between users, identifying the K users most similar to the target user, and recommending items liked or highly rated by these K users that the target user has not yet accessed. The second approach involves determining the similarity between items, identifying the K items most similar to the target user's historically liked items, and recommending these similar items to the target user.

[0048] Collaborative filtering is primarily implemented through similarity calculation, sparsity and cold-start optimization, and distributed processing. For similarity, Pearson correlation coefficient and cosine similarity can be chosen. Pearson correlation coefficient is suitable for rating data, measuring the linear correlation between users / items. Cosine similarity is suitable for implicit feedback, such as click behavior.

[0049] Sparsity and cold start optimization include matrix factorization, which reduces dimensionality through latent factor models to address data sparsity. Hybrid methods, such as combining K-nearest neighbors with gradient boosting decision trees, can also be used to improve recommendation accuracy through ensemble learning. Introducing user behavior weights, such as click duration and purchase frequency, enhances the interpretability of sparse data. The distributed implementation is based on the Spark platform. For large-scale data, the Spark-based hierarchical collaborative filtering scheme includes steps such as user interest modeling, parallel clustering, and clustered collaborative filtering. User interest modeling can be based on time-series behaviors, such as clicks and purchases, to construct user feature vectors. Parallel clustering can use a resilient distributed dataset to cluster users, reducing computational complexity. Clustered collaborative filtering involves running Item-CF in parallel within each user cluster, improving real-time performance.

[0050] In this embodiment, scene similarity is similar to User-CF, calculating the similarity between two scenes. Feature vector similarity is similar to Item-CF, calculating the similarity between extended services based on their service feature vectors. Therefore, when determining matching relationships, a scene-service interaction matrix can be constructed first: rows represent scenes, columns represent services, and values ​​represent the performance of the service in that scene, such as usage frequency and conversion rate. Then, Pearson correlation coefficient or cosine similarity is used to calculate the similarity between scenes. Next, based on the service feature vector of each node, the cosine similarity between every two service feature vectors is determined. Then, for each consumption scene feature, similar consumption scene features are found through scene similarity, and then recommended extended services for similar scenes are obtained. Alternatively, one extended service corresponding to each consumption scene feature can be determined first, and other services similar to the extended service can be determined based on feature vector similarity as extended services matching the consumption scene feature. Finally, the extended services corresponding to each consumption scene feature determined by the two methods can be fused to obtain the matching score between each candidate extended service and each consumption scene feature.

[0051] In this application specification, in addition to traditional user similarity, scenario similarity is introduced, such as the co-occurrence probability of food delivery scenarios and travel scenarios, to further improve the service recommendation effect.

[0052] Once the matching relationship between each candidate extended service and the characteristics of the consumption scenario is determined, it can be put into practical application, that is, S103 is executed, and the target extended service is determined.

[0053] As one example, basic services can be credit card processing services, while extended services can be preferential services such as electronic vouchers for free appliances, food delivery vouchers, and car wash vouchers.

[0054] After recommending the services to be recommended to the target user, if the target user uses the basic services, the target extended services in the services to be recommended can be sent to the target user.

[0055] Specifically, in response to the target user's recommended service usage operation, the first service provider sends an electronic credential acquisition request to the third service provider and a basic service usage request to the second service provider; the third service provider receives the electronic credential acquisition request sent by the first service provider.

[0056] It is understood that the electronic credential acquisition request includes a target extended service identifier. The electronic credential acquisition request is sent by the first service provider to the third service provider in response to the target user's recommended service usage operation, after the first service provider recommends the service to be recommended to the target user based on the matching relationship between the pre-built extended service and the consumption scenario characteristics.

[0057] Subsequently, the third service provider obtains the target electronic credential for the target extended service based on the target extended service identifier; it then returns the target electronic credential to the first service provider, enabling the first service provider to display the target electronic credential to the target user. In other words, the first service provider receives the target electronic credential returned by the third service provider and displays it to the target user. The second service provider receives the basic service usage request sent by the first service provider and sends the basic service interface to the first service provider. The first service provider receives the basic service interface sent by the second service provider and displays the basic service page based on the basic service interface.

[0058] It's understandable that electronic credentials for using targeted extended services would be sent to the target user when or after they use the basic service. For example, a food delivery coupon might be sent to a user after they apply for a credit card. By recommending extended services that users might be interested in, thus encouraging them to use the basic service, the likelihood of users using the basic service is increased, and the effectiveness of recommending the basic service is enhanced.

[0059] Subsequently, in response to the target user's electronic credential usage, extended services corresponding to the electronic credential are provided to the target user.

[0060] Specifically, the target user can click on the electronic voucher stored on the terminal to use it. In response to the target user's use of the electronic voucher, the terminal sends a usage request to the third-party service provider, which can then provide the target user with extended services corresponding to the electronic voucher. For example, if the extended service is a free air fryer, the third-party service provider can send an air fryer purchase link to the target user's terminal, enabling the target user to initiate a purchase, with the final purchase amount set to 0.

[0061] After executing S105, the first service provider can update the candidate extended services based on the frequency of use of the target extended service by several target users, ensuring that the candidate extended services identified using the resources of the second service provider are fully utilized. Alternatively, when selecting candidate extended services, the value weight of each extended service in a specific scenario can be determined based on historical usage data. Candidate extended services are then selected based on this weight. Subsequently, when users use candidate extended services, the value weight of each candidate extended service is updated according to the frequency of use of the target extended service, achieving dynamic weight allocation to improve service recommendation effectiveness.

[0062] This application specification describes a shift from traditional manual, static scenario labeling to dynamic scenario clustering automatically by a large model, achieved through the construction of a consumer scenario graph. This relies on a large model to establish a consumer scenario graph and its associated user tags adapted to basic services. By establishing a rights and benefits feature library and using it in conjunction with intelligent supply, the approach shifts from traditional second-party service providers offering fixed extended services or relying on industry expert experience to customize extended services. This transitions to algorithm-controlled intelligent extended services and customized extended services through interfaces with third-party service providers. Based on the matching relationship between extended services and consumer scenario features, a self-built extended service library maximizes the coverage of scenarios within the system. Through interfaces, the matching results of extended services and consumer scenario features are synchronized with second-party service providers, supporting their targeted development of extended services. Dynamic optimization is also possible; if the usage rate or user click-through rate of a particular extended service is low, it is automatically eliminated to ensure effective service recommendations.

[0063] The above describes one or more embodiments of the service recommendation method provided in this application specification. Based on the same idea, this application specification also provides corresponding service recommendation devices, such as... Figure 2 As shown, the device is applied to a first service provider, and the device includes: The target consumption data acquisition module 200 is used to acquire the target consumption data of the target user in response to the service recommendation trigger operation of the target user. The target consumption scenario feature determination module 202 is used to determine the target consumption scenario features of the target consumption data. The target extended service determination module 204 is used to determine the target extended service from several candidate extended services based on the target consumption scenario characteristics and the pre-built matching relationship between extended services and consumption scenario characteristics. The service to be recommended module 206 is used to bind the target extended service with the basic service to obtain the service to be recommended; The recommendation module 208 is used to recommend the service to be recommended to the target user.

[0064] Optionally, the second service provider is used to provide basic services, and the third service provider is used to provide candidate extended services; The device further includes: The candidate extended service determination module is used to select a target third service provider from among several candidate extended services before determining the target extended service based on the target consumption scenario characteristics and the pre-built matching relationship between extended services and consumption scenario characteristics; Among the extended services provided by the target third-party service provider, each candidate extended service is determined; The device further includes: The candidate extended service update module is used to update the candidate extended services based on the frequency of use of the target extended service by several target users.

[0065] Optionally, the target consumption scenario feature determination module 202 is specifically used to identify the consumption scenario in the target consumption data based on a preset clustering algorithm; Based on the aforementioned consumption scenario, a target user profile is generated; The association between the consumption scenario and the target user's target profile is constructed to obtain the target consumption scenario characteristics.

[0066] Optionally, the device further includes: The matching relationship construction module is used to obtain the consumption dataset, which includes the consumption data of several users; Based on the aforementioned consumer dataset, the consumption scenario characteristics of several users are determined. Based on several candidate extended services, an extended service knowledge graph is constructed, where nodes in the extended service knowledge graph are candidate extended services and an edge represents the correlation between two candidate extended services. Based on the knowledge graph of the extended services and the characteristics of each consumption scenario, the matching relationship between each candidate extended service and the characteristics of the consumption scenario is determined.

[0067] Optionally, the matching relationship construction module is specifically used to determine the service feature vector of each candidate extended service based on preset service features, wherein the service features include at least one of extended service type, consumption scenario, and user profile; Based on the service feature vector of each candidate extended service, the correlation between every two candidate extended services is determined. An extended service knowledge graph is constructed using each correlation as an edge, each candidate extended service as a node, and the service feature vector of each candidate extended service as a node feature.

[0068] Optionally, the matching relationship construction module is specifically used to determine the scene similarity and feature vector similarity between each node in the extended service knowledge graph and each consumption scenario feature based on the collaborative filtering algorithm; Based on the scene similarity and the feature vector similarity, the matching score between each candidate extended service in the extended service knowledge graph and each of the consumption scene features is determined; Based on each matching score, the matching relationship between each candidate extended service and the consumption scenario feature is determined.

[0069] Optionally, the device further includes: The extended service usage module is used to respond to the recommended service usage operation of the target user by sending an electronic credential acquisition request to the third service provider and a basic service usage request to the second service provider; Receive the basic service interface sent by the second service provider, and display the basic service page based on the basic service interface; Receive the target electronic credential returned by the third service provider and display the target electronic credential to the target user.

[0070] This application specification also provides another service recommendation device, which is applied to a third service provider, and the device includes: The request receiving module is used to receive an electronic credential acquisition request sent by a first service provider. The electronic credential acquisition request includes a target extended service identifier. The electronic credential acquisition request is sent by the first service provider to the third service provider in response to the target user's recommended service usage operation, after the first service provider recommends the service to be recommended to the target user. The target electronic credential acquisition module is used to acquire the target electronic credential of the target extended service based on the target extended service identifier. The target electronic credential return module is used to return the target electronic credential to the first service provider so that the first service provider can display the target electronic credential to the target user.

[0071] Optionally, the device further includes: The extended service module is used to respond to the target user's electronic credential usage operation and provide the target user with extended services corresponding to the electronic credential.

[0072] This application also provides a computer-readable storage medium storing a computer program that can be used to execute the above-described... Figure 1 Recommended service methods.

[0073] This application also provides a service recommendation system, which includes a first service providing module, a second service providing module, and a third service providing module, wherein: The first service providing module is configured to, in response to a service recommendation triggering operation by a target user, acquire the target consumption data of the target user, determine the target consumption scenario characteristics of the target consumption data, determine a target extended service from several candidate extended services based on the target consumption scenario characteristics and a pre-built matching relationship between extended services and consumption scenario characteristics, bind the target extended service with a basic service to obtain a service to be recommended, recommend the service to be recommended to the target user, and, in response to a recommended service usage operation by the target user, send an electronic voucher acquisition request to the third service providing module and a basic service usage request to the second service providing module. The second service providing module is used to receive the basic service usage request and send the basic service interface to the first service providing module; The third service providing module is configured to receive the electronic credential acquisition request, acquire the target electronic credential of the target extended service according to the target extended service identifier included in the electronic credential acquisition request, and return the target electronic credential to the first service providing module. The first service providing module is further configured to receive the target electronic credential returned by the third service providing module, display the target electronic credential to the target user, receive the basic service interface sent by the second service providing module, and display the basic service page based on the basic service interface.

[0074] This application discloses a computer program product, which includes a computer program that, when executed by a processor, implements the aforementioned service recommendation method.

[0075] This application specification also provides Figure 3 The diagram shows the structure of an electronic device, which could be smart glasses. Figure 3As shown, at the hardware level, this electronic device includes a processor, internal bus, network interface, memory, and non-volatile memory, and may also include other hardware required for business operations. The processor reads the corresponding computer program from the non-volatile memory into memory and then runs it to achieve the above. Figure 1 The service recommendation method described above. Of course, in addition to software implementation, this application specification does not exclude other implementation methods, such as logic devices or a combination of hardware and software, etc. That is to say, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0076] In the 1990s, improvements to a technology could be clearly distinguished as either hardware improvements (e.g., improvements to the circuit structure of diodes, transistors, switches, etc.) or software improvements (improvements to the methodology). However, with technological advancements, many methodological improvements today can be considered direct improvements to the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved methodology into the hardware circuit. Therefore, it cannot be said that a methodological improvement cannot be implemented using hardware physical modules. For example, a Programmable Logic Device (PLD) (such as a Field Programmable Gate Array (FPGA)) is such an integrated circuit whose logic function is determined by the user programming the device. Designers can program and "integrate" a digital system onto a PLD themselves, without needing chip manufacturers to design and manufacture dedicated integrated circuit chips. Furthermore, nowadays, instead of manually manufacturing integrated circuit chips, this programming is mostly implemented using "logic compiler" software. Similar to the software compiler used in program development, the original code before compilation must also be written in a specific programming language, called a Hardware Description Language (HDL). There are many HDLs, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, and RHDL (Ruby Hardware Description Language). Currently, the most commonly used are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also understand that by simply performing some logic programming on the method flow using one of these hardware description languages ​​and programming it into an integrated circuit, the hardware circuit implementing the logical method flow can be easily obtained.

[0077] The controller can be implemented in any suitable manner. For example, it can take the form of a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro)processor, logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers, and embedded microcontrollers. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicon Labs C8051F320. A memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art will also recognize that, in addition to implementing the controller in purely computer-readable program code form, the same functionality can be achieved by logically programming the method steps to make the controller take the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers. Therefore, such a controller can be considered a hardware component, and the means included therein for implementing various functions can also be considered as structures within the hardware component. Alternatively, the means for implementing various functions can be considered as both software modules implementing the method and structures within the hardware component.

[0078] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0079] For ease of description, the above devices are described separately by function as various units. Of course, in implementing this application specification, the functions of each unit can be implemented in one or more software and / or hardware.

[0080] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0081] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0082] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0083] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0084] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0085] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0086] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0087] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0088] Those skilled in the art will understand that the embodiments of this application specification can be provided as methods, systems, or computer program products. Therefore, this application specification can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application specification can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0089] This specification can be described in the general context of computer-executable instructions that are executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. This specification can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0090] The various embodiments in this application specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0091] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims.

Claims

1. A service recommendation method, the method being applied to a first service provider, the method comprising: In response to a service recommendation trigger operation for a target user, the target user's target consumption data is obtained; Determine the target consumption scenario characteristics of the target consumption data; Based on the target consumption scenario characteristics and the matching relationship between the pre-built extended services and the consumption scenario characteristics, the target extended service is determined from several candidate extended services. Bind the target extended service with the basic service to obtain the service to be recommended; The service to be recommended is recommended to the target user.

2. The method as described in claim 1, wherein the second service provider is used to provide basic services, and the third service provider is used to provide candidate extended services; Based on the target consumption scenario characteristics and the pre-built matching relationship between extended services and consumption scenario characteristics, before determining the target extended service from several candidate extended services, the method further includes: Based on the resources provided by the second service provider, a target third service provider is selected from among the third service providers; Among the extended services provided by the target third-party service provider, each candidate extended service is determined; The method further includes: The candidate extended services are updated based on the frequency with which several target users use the target extended service.

3. The method as described in claim 1, wherein determining the target consumption scenario characteristics of the target consumption data specifically includes: Based on a preset clustering algorithm, the consumption scenarios in the target consumption data are identified; Based on the aforementioned consumption scenario, a target user profile is generated; The association between the consumption scenario and the target user's target profile is constructed to obtain the target consumption scenario characteristics.

4. The method as described in claim 2, wherein constructing the matching relationship between extended services and consumption scenario characteristics specifically includes: Obtain a consumer dataset, which includes consumer data from several users; Based on the aforementioned consumer dataset, the consumption scenario characteristics of several users are determined. Based on several candidate extended services, an extended service knowledge graph is constructed, where nodes in the extended service knowledge graph are candidate extended services and an edge represents the correlation between two candidate extended services. Based on the knowledge graph of the extended services and the characteristics of each consumption scenario, the matching relationship between each candidate extended service and the characteristics of the consumption scenario is determined.

5. The method as described in claim 4, wherein an extended service knowledge graph is constructed based on a plurality of candidate extended services, specifically including: Based on preset service characteristics, a service feature vector is determined for each candidate extended service, wherein the service characteristics include at least one of extended service type, consumption scenario, and user profile; Based on the service feature vector of each candidate extended service, the correlation between every two candidate extended services is determined. An extended service knowledge graph is constructed using each correlation as an edge, each candidate extended service as a node, and the service feature vector of each candidate extended service as a node feature.

6. The method as described in claim 4, wherein determining the matching relationship between each candidate extended service and the consumption scenario feature based on the extended service knowledge graph and the characteristics of each consumption scenario specifically includes: Based on the collaborative filtering algorithm, the scene similarity and feature vector similarity between each node and each consumption scenario feature in the extended service knowledge graph are determined. Based on the scene similarity and the feature vector similarity, the matching score between each candidate extended service in the extended service knowledge graph and each of the consumption scene features is determined; Based on each matching score, the matching relationship between each candidate extended service and the consumption scenario feature is determined.

7. The method of claim 1, further comprising: In response to the target user's recommended service usage operation, an electronic credential acquisition request is sent to the third service provider, and a basic service usage request is sent to the second service provider; Receive the basic service interface sent by the second service provider, and display the basic service page based on the basic service interface; Receive the target electronic credential returned by the third service provider and display the target electronic credential to the target user.

8. A service recommendation method, the method being applied to a third-party service provider, the method comprising: The system receives an electronic credential acquisition request from a first service provider. The electronic credential acquisition request includes a target extended service identifier. The electronic credential acquisition request is sent by the first service provider to the third service provider in response to the target user's recommended service usage operation. The first service provider recommends the service to be recommended to the target user based on the matching relationship between the pre-built extended service and the consumption scenario characteristics. Based on the target extended service identifier, obtain the target electronic credential of the target extended service; The target electronic credential is returned to the first service provider so that the first service provider can display the target electronic credential to the target user.

9. The method of claim 8, further comprising: In response to a target user's electronic credential usage operation, the system provides the target user with extended services corresponding to the electronic credential.

10. A service recommendation system, the system comprising a first service providing module, a second service providing module, and a third service providing module, wherein: The first service providing module is configured to, in response to a service recommendation triggering operation by a target user, acquire the target consumption data of the target user, determine the target consumption scenario characteristics of the target consumption data, determine a target extended service from several candidate extended services based on the target consumption scenario characteristics and a pre-built matching relationship between extended services and consumption scenario characteristics, bind the target extended service with a basic service to obtain a service to be recommended, recommend the service to be recommended to the target user, and, in response to a recommended service usage operation by the target user, send an electronic voucher acquisition request to the third service providing module and a basic service usage request to the second service providing module. The second service providing module is used to receive the basic service usage request and send the basic service interface to the first service providing module; The third service providing module is configured to receive the electronic credential acquisition request, acquire the target electronic credential of the target extended service according to the target extended service identifier included in the electronic credential acquisition request, and return the target electronic credential to the first service providing module. The first service providing module is further configured to receive the target electronic credential returned by the third service providing module, display the target electronic credential to the target user, receive the basic service interface sent by the second service providing module, and display the basic service page based on the basic service interface.

11. A service recommendation device, the device being applied to a first service provider, the device comprising: The target consumption data acquisition module is used to acquire the target consumption data of the target user in response to the service recommendation trigger operation of the target user. The target consumption scenario feature determination module is used to determine the target consumption scenario features of the target consumption data; The target extended service determination module is used to determine the target extended service from several candidate extended services based on the target consumption scenario characteristics and the pre-built matching relationship between extended services and consumption scenario characteristics. The module for determining the service to be recommended is used to bind the target extended service with the basic service to obtain the service to be recommended. The recommendation module is used to recommend the services to be recommended to the target user.

12. A service recommendation device, the device being applied to a third service provider, the device comprising: The request receiving module is used to receive an electronic credential acquisition request sent by a first service provider. The electronic credential acquisition request includes a target extended service identifier. The electronic credential acquisition request is sent by the first service provider to the third service provider in response to the target user's recommended service usage operation, after the first service provider recommends the service to be recommended to the target user. The target electronic credential acquisition module is used to acquire the target electronic credential of the target extended service based on the target extended service identifier. The target electronic credential return module is used to return the target electronic credential to the first service provider so that the first service provider can display the target electronic credential to the target user.

13. A computer-readable storage medium storing a computer program that, when executed by a processor, implements the method described in any one of claims 1 to 9.

14. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method described in any one of claims 1 to 9.

15. A computer program product comprising a computer program that, when executed by a processor, implements the method described in any one of claims 1-9.

Images