Service recommendation method and device, electronic equipment and storage medium

Abstract

The invention discloses a service recommendation method, belongs to the field of data processing, and is used for improving the accuracy of service recommendation for users. The method comprises the steps that the user type of a target user is obtained, service recommendation is carried out on the target user based on the user type of the target user and a preset service recommendation table, and the service recommendation table comprises multiple to-be-recommended services corresponding to the user type and first recommendation probabilities corresponding to all the to-be-recommended services; after a recommendation selection result of the target user is received, updating the first recommendation probability of each to-be-recommended service based on the recommendation selection result to obtain a second recommendation probability; and performing service recommendation on the target user based on the second recommendation probability.

Description

Technical Field

[0001] The present application belongs to the field of data processing, and specifically relates to a business recommendation method, device, electronic device and storage medium. Background Art

[0002] The traditional service recommendation method is mainly through manual outbound calls. The manual recommendation of service packages relies on the personal experience and subjective judgment of customer service personnel, which can easily lead to unstable recommendation accuracy and cannot guarantee that the recommended users always get the package recommendation that best suits their consumption needs and preferences.

[0003] Therefore, a business recommendation method that can improve the accuracy of business recommendations is needed. Summary of the invention

[0004] The embodiment of the present application provides a service recommendation method, which can improve the accuracy of service recommendation to users.

[0005] In a first aspect, an embodiment of the present application provides a service recommendation method, the method comprising: obtaining a user type of a target user, and making service recommendations to the target user based on the user type of the target user and a preset service recommendation table, the service recommendation table comprising a plurality of to-be-recommended services corresponding to the user type and a first recommendation probability corresponding to each of the to-be-recommended services; after receiving a recommendation selection result of the target user, updating the first recommendation probability of each of the to-be-recommended services based on the recommendation selection result to obtain a second recommendation probability; and making service recommendations to the target user based on the second recommendation probability.

[0006] In a second aspect, an embodiment of the present application provides a service recommendation device, which includes: a first recommendation module, used to obtain a user type of a target user, and make service recommendations to the target user based on the user type of the target user and a preset service recommendation table, wherein the service recommendation table includes multiple services to be recommended corresponding to the user type and a first recommendation probability corresponding to each of the services to be recommended; a first update module, used to update the first recommendation probability of each of the services to be recommended based on the recommendation selection result after receiving the recommendation selection result of the target user, to obtain a second recommendation probability; a second recommendation module, used to make service recommendations to the target user based on the second recommendation probability.

[0007] In a third aspect, an embodiment of the present application provides an electronic device, which includes a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of the method described in the first aspect.

[0008] In a fourth aspect, an embodiment of the present application provides a readable storage medium, on which a program or instruction is stored, and when the program or instruction is executed by a processor, the steps of the method described in the first aspect are implemented.

[0009] In a fifth aspect, an embodiment of the present application provides a chip, comprising a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run a program or instruction to implement the method described in the first aspect.

[0010] In an embodiment of the present application, by obtaining the user type of the target user, and making service recommendations to the target user based on the user type of the target user and a preset service recommendation table, the service recommendation table includes multiple to-be-recommended services corresponding to the user type and a first recommendation probability corresponding to each of the to-be-recommended services; after receiving the recommendation selection result of the target user, the first recommendation probability of each of the to-be-recommended services is updated based on the recommendation selection result to obtain a second recommendation probability; making service recommendations to the target user based on the second recommendation probability can improve the accuracy of service recommendations to users. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 It is a flowchart of a service recommendation method provided in an embodiment of the present application; Figure 2 It is a flowchart of the second service recommendation method provided in the embodiment of the present application; Figure 3 This is a flowchart of a third service recommendation method provided in an embodiment of the present application; Figure 4 It is a swimming lane diagram of a service recommendation method provided in an embodiment of the present application; Figure 5 It is a structural diagram of a business recommendation device provided in an embodiment of the present application; Figure 6 It is a structural diagram of a business recommendation device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0012] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0013] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are generally of one type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0014] The following describes in detail the service recommendation method provided by the embodiment of the present application through specific embodiments and application scenarios in conjunction with the accompanying drawings.

[0015] Figure 1 A service recommendation method provided by an embodiment of the present invention is shown. The method can be executed by an electronic device, and the electronic device may include: a server and / or a terminal device, wherein the terminal device may be, for example, a vehicle-mounted terminal or a mobile phone terminal. In other words, the method can be executed by software or hardware installed in the service recommendation device, and the method includes the following steps: Step 102: Obtain the user type of the target user, and recommend services to the target user based on the user type of the target user and a preset service recommendation table.

[0016] The service recommendation table includes a plurality of services to be recommended corresponding to the user type and a first recommendation probability corresponding to each of the services to be recommended.

[0017] The service recommendation system obtains the user type of the target user, wherein the target user is the user for whom service recommendation is required, and the user type is the type to which the target user belongs. Further, the user type information of the target user may be pre-stored in a database, or may be determined based on the attribute information of the target user.

[0018] After determining the user type corresponding to the target user, the service recommendation system recommends services or service packages to the target user based on the user type of the target user and a preset service recommendation table, wherein the service recommendation table includes multiple services to be recommended corresponding to various user types and a first recommendation probability corresponding to each service to be recommended, and the first recommendation probability is used to characterize the recommendation probability of the service to be recommended.

[0019] That is to say, the business recommendation system pre-stores in the business recommendation table multiple businesses to be recommended corresponding to each user type and the first recommendation probability of each business to be recommended. In this way, after determining the user type of the target user, the business recommendation system can determine the multiple businesses to be recommended corresponding to the type and the first recommendation probability of each business to be recommended according to the user type of the target user.

[0020] When recommending services to a target user based on a plurality of services to be recommended corresponding to the user type and a first recommendation probability corresponding to each service to be recommended, the service recommendation system can recommend a preset number of services to be recommended with the highest service recommendation probability to the target user, wherein the preset number may be one or more. After determining the services to be recommended to the target user, the service recommendation system sends the recommended services to the target user.

[0021] Step 104: After receiving the recommendation selection result of the target user, the first recommendation probability of each of the services to be recommended is updated based on the recommendation selection result to obtain a second recommendation probability.

[0022] After the recommended services are sent to the target user, the target user selects a target recommended service suitable for him / herself from the multiple services to be recommended according to his / her own situation, and sends the recommendation selection result to the service recommendation system. The service recommendation system receives the recommendation selection result sent by the target user, and updates the first recommendation probability of the multiple services to be recommended corresponding to the user type based on the recommendation selection result to obtain a second recommendation probability.

[0023] Specifically, when the service recommendation system updates the first probability based on the recommendation selection result, it can increase the recommendation probability of the target recommended service selected by the target user, that is, increase the first recommendation probability corresponding to the target recommended service, thereby obtaining the second recommendation probability corresponding to the target recommended service. For the recommended services that the target user has not selected for recommendation, the corresponding first recommendation probability can remain unchanged or can be decreased. Furthermore, when increasing or decreasing the first recommendation probability, the first recommendation probability can be increased or decreased based on a preset fixed increase or fixed decrease value, or can be processed based on a preset first recommendation probability increase or decrease algorithm.

[0024] Step 106: Recommend a service to the target user based on the second recommendation probability.

[0025] After determining the second recommendation probability corresponding to each to-be-recommended service, the service recommendation system recommends services to the target user based on the second recommendation probability corresponding to each to-be-recommended service.

[0026] Specifically, after making a business recommendation to the target user based on the second recommendation probability and receiving the recommendation selection result returned by the user for the second time, the business recommendation system can update the second recommendation probability corresponding to each business to be recommended based on the recommendation selection result returned for the second time. In this way, it can be continuously updated according to the user's recommendation selection results, thereby not only providing personalized business recommendation services to the target user, but also improving the accuracy of business recommendations to the target user.

[0027] The service recommendation method provided by the embodiment of the present invention obtains the service usage data of the target user, and determines the user type of the target user based on comparing the service usage data with a preset type classification table; obtains the user type of the target user, and recommends services to the target user based on the user type of the target user and a preset service recommendation table, wherein the service recommendation table includes multiple services to be recommended corresponding to the user type and a first recommendation probability corresponding to each of the services to be recommended; after receiving the recommendation selection result of the target user, updates the first recommendation probability of each of the services to be recommended based on the recommendation selection result to obtain a second recommendation probability; recommends services to the target user based on the second recommendation probability, thereby improving the accuracy of service recommendations to users.

[0028] In one implementation, before obtaining the user type of the target user (step 102), steps A1-A2 may also be performed: Step A1: Acquire the service usage data of the target user, wherein the service usage data includes the usage data of the Subscriber Identity Module (SIM) card.

[0029] The service recommendation system obtains the service usage data of the target user, where the target user is the user for whom the service recommendation is required, and the service usage data is the target user's use of the service, which may include the user's SIM card usage data and may also include usage data of other services. When the service usage data includes SIM card usage data, the user's SIM card usage data may be one or more of the user's call duration, the user's data traffic usage, and the user's text message usage.

[0030] Specifically, when the business recommendation system obtains the business usage data of the target user, it can not only obtain it directly from the target user, but also obtain it from other data acquisition sources, such as a preset database.

[0031] Step A2: Determine the user type of the target user based on comparing the service usage data with a preset type classification table.

[0032] After the service recommendation system obtains the service usage data of the target user, the service recommendation system compares the service usage data of the target user with a preset type classification table to determine the user type of the target user.

[0033] Specifically, the business recommendation system pre-stores business usage data corresponding to multiple user types. After obtaining the business usage data of the target user, the business usage data of the target user can be compared with the business usage data corresponding to multiple user types to determine the user type corresponding to the target user.

[0034] Furthermore, the service usage data may include a plurality of service usage sub-data, and the service recommendation system may compare each service usage sub-data with each data in the preset type classification table, thereby determining the user type of the target user.

[0035] More specifically, when the service usage data of the target user is the user's SIM card usage data, the service recommendation system can determine the user type of the target user based on the service usage data of the target user, such as the user's call duration, user data usage, user text message usage, etc., and determine, based on the user type, multiple services to be recommended corresponding to the user type and a first recommendation probability corresponding to each service to be recommended, and then make service recommendations to the target user based on the first recommendation probability.

[0036] In one implementation, the step of obtaining the service usage data of the target user (step A1) may include executing steps B1-B2: Step B1: Send a first acquisition request to the blockchain.

[0037] The first acquisition request is used to request the blockchain to send the business usage data of the target user to the business recommendation system.

[0038] When the business recommendation system obtains the business usage data of the target user, it can not only obtain it directly from the target user, but also from other data acquisition sources, such as blockchain. When the business system obtains the business usage data of the target user through blockchain, the business recommendation system generates a first acquisition request and sends the first acquisition request to the blockchain, wherein the first acquisition request is used to request the blockchain to send the business usage data of the target user to the business recommendation system.

[0039] In other words, the target user can interact with the blockchain smart contract through the interactive interface and submit his or her own public key for registration. After the registration is completed, the target user's business usage data can be recorded. In this way, the access source of the business usage data can be recorded through the blockchain, so that the target user can clearly understand the access source of the business usage data.

[0040] Step B2: Receive the business usage data of the target user sent by the blockchain.

[0041] After the service recommendation system sends the first acquisition request to the blockchain, the blockchain sends the service usage data of the target user to the service recommendation system. After the blockchain sends the service usage data of the target user, the service recommendation system receives the service usage data of the target user.

[0042] In one implementation, the sending of the first acquisition request to the blockchain (step B1) may execute steps C1-C2: Step C1: Obtain first address information.

[0043] Wherein, the first address information is the address information of the business recommendation system.

[0044] The business recommendation system obtains the address information of the business recommendation system and uses it as the first address information.

[0045] Step C2: Generate a first acquisition request based on the first address information, and send the first acquisition request to the blockchain, so that the blockchain determines whether the business recommendation system has the authority to obtain the business usage data based on the first address information and the access permission information pre-set by the target user.

[0046] After obtaining the first address information, the business recommendation system generates a first acquisition request based on the obtained first address information, and sends the first acquisition request to the blockchain. After receiving the first acquisition request, the blockchain can obtain the access permission information pre-set by the target user, and then determine whether the business recommendation system has the permission to obtain the business usage data based on the first address information and access permission information in the first acquisition request.

[0047] That is to say, the target user not only sends his or her own business usage data to the blockchain for storage, but also pre-sets the access rights to the business usage data in the blockchain. The blockchain will only send the target user's business usage data to the access source after determining that it has access rights based on the access source's address information, thereby ensuring that only the access source authorized by the target user can obtain the target user's business usage data. This can not only improve the accuracy of business recommendations to users, but also increase the protection of users' private data.

[0048] In one implementation, before comparing the service usage data with a preset type classification table to determine the user type of the target user (step B2), steps D1-D4 may also be performed: Step D1: Obtain service usage data of multiple sample users.

[0049] Before comparing the target user's business usage data with the preset type classification table, the business recommendation system first needs to set up a type classification table to clarify the user type corresponding to various business usage data. When determining the user type corresponding to various business usage data, the business recommendation system can first obtain the business usage data of multiple sample users, where the business usage data of the sample users is the business usage data of multiple users obtained when determining the user type.

[0050] Step D2: performing cluster analysis on the plurality of sample users based on the service usage data of the plurality of sample users to obtain a first number of classifications of the plurality of sample users and a classification to which each of the sample users belongs.

[0051] After obtaining the business usage data of multiple users, the business recommendation system performs cluster analysis on the multiple users based on the business usage data of the multiple users, so as to determine the number of categories of the multiple users (i.e., the first number) and the category to which each sample user belongs (or the users corresponding to each category), i.e., determine the number of categories of the multiple users and the sample users corresponding to each type after classification.

[0052] Specifically, when clustering multiple users based on the service usage data of multiple sample users, the service usage data of each sample user can be first processed into coordinates, so as to represent the service usage data of each sample user in a unified coordinate system, and then cluster analysis can be performed based on the distribution of the service usage data of each sample user in the coordinate system, so as to determine the number of sample users to be classified (such as classifying multiple sample users into three or four categories), and the corresponding users in each category. For example, when the service usage data is the user's SIM card usage data, the sample users can be clustered based on the user's call duration, user traffic usage, and user text message usage in the SIM card usage data, so as to classify multiple sample users according to the user's call duration, user traffic usage, and user text message usage.

[0053] Step D3: Determine the user type of each of the sample users based on the category to which each of the sample users belongs.

[0054] After determining the number of user categories and the category to which each user belongs, the service recommendation system determines the user type of each user based on the category to which each user belongs. For example, it can classify users with longer call duration but less data usage and text message usage as high call duration users, users with more data usage but less call duration and text message usage as high data usage users, and users with more text message usage but less data usage and call usage as high text message usage users.

[0055] Step D4: Setting the service recommendation table according to the user type of each of the sample users.

[0056] After determining the user type of each sample user, the service recommendation system sets up different service recommendation tables for different user types. For example, when setting up a service recommendation table for users with high data usage, multiple recommended services with high data usage and low SMS usage and call usage can be set, and the first recommendation probability corresponding to each recommended service can be set according to the actual content of each recommended service and the user's service usage data volume.

[0057] In one implementation, cluster analysis is performed on the service usage data of the plurality of sample users to obtain a first number of classifications of the plurality of sample users and a classification to which each sample user belongs (step D2), and steps E1-E2 may be performed: Step E1: Obtain a preset number of clusters.

[0058] The number of clusters is the number of categories that the sample users can be divided into when performing cluster analysis.

[0059] The business recommendation system obtains a preset number of clusters, where the number of clusters is the number of categories that multiple sample users can be divided into when performing cluster analysis, where the number of clusters can be three, four, or other numbers. In other words, the business recommendation system determines the number of categories determined by cluster analysis of sample users, such as clustering sample users into three categories or four categories according to the preset number of clusters.

[0060] Step E2: determining the first number for classifying the plurality of sample users and the category to which each sample user belongs from the plurality of cluster numbers based on the elbow rule.

[0061] After determining the number of clusters, the business recommendation system determines the optimal number of categories (i.e., the first number) for classifying multiple sample users and the category to which each sample user belongs from the multiple numbers of clusters. The elbow rule determines the optimal K value (i.e., the first number) by calculating the cost function (i.e., the sum of the squares of the distances from each point to its centroid) for different K values ​​(i.e., the number of clusters). When increasing the number of clusters no longer significantly reduces the value of the cost function, the K value is the best choice.

[0062] Specifically, when determining the K value based on the elbow rule, K centroids are initialized, and then the following steps are repeated until convergence: each point is assigned to the nearest centroid to form K clusters; the mean of all points in each cluster is calculated, and the centroid is updated to the mean.

[0063] Among them, the objective function of the clustering method is:

[0064] in, represents the ith data point, is the number of data points in cluster k, is the centroid of cluster k, is the centroid The distance to its nearest cluster centroid is used to ensure that there is sufficient separation between clusters. This can be calculated using any distance metric function, such as the Euclidean distance, is the distance from all data points in cluster k to the centroid The standard deviation of the distance is used to evaluate the uniformity of the distribution within the cluster. is a weight parameter used to adjust the relative importance of the three items.

[0065] In one implementation, after determining the number of categories for classifying the plurality of sample users and the category to which each sample user belongs from the plurality of cluster numbers based on the elbow rule (step E2), steps F1-F2 may also be performed: Step F1: Based on a preset silhouette coefficient function, determine the silhouette coefficient value when the number of categories for classifying the sample user is the first number.

[0066] After determining the first number, the business recommendation system can directly determine the first number as the optimal number of clusters, and can further verify the optimality of the first number, and determine the first number as the optimal number of clusters after the optimality verification passes.

[0067] When the business recommendation system verifies the optimality of the first number, the business recommendation system can determine the silhouette coefficient value when the number of classifications for classifying sample users is the first number based on a preset silhouette coefficient function, wherein the silhouette coefficient function is a pre-set function for determining the quality of clustering effect.

[0068] Step F2: when it is determined that the silhouette coefficient value is greater than a preset threshold, determining the first number as the number of categories for classifying the sample users.

[0069] After determining the silhouette coefficient value corresponding to the first number, the business recommendation system can determine that the first number is the number of categories for classifying sample users, that is, the optimal number of categories when the silhouette coefficient value is greater than a preset threshold, wherein the preset threshold is a pre-set threshold.

[0070] Specifically, when verifying the optimality of the first number, not only can the first number be determined as the number of categories for classifying sample users when the silhouette coefficient value is greater than a preset threshold, but the first number can also be determined as the number of categories for classifying sample users when the silhouette coefficient value is greater than or equal to a target silhouette coefficient value, wherein the target silhouette value is a plurality of silhouette coefficient values ​​corresponding to a plurality of cluster numbers. In other words, the recommendation system can determine the silhouette coefficient value corresponding to each cluster number when the number of categories for classifying sample users is a plurality of cluster numbers, and then determine whether the silhouette coefficient value corresponding to the first number is greater than or equal to the silhouette coefficient values ​​corresponding to other cluster numbers. If so, the first number is determined to be the number of categories for classifying sample users, i.e., the optimal number of categories.

[0071] In one implementation, the first recommendation probability of each of the services to be recommended is updated based on the recommendation selection result to obtain a second recommendation probability (step 104), and steps G1 and G2 may be executed: Step G1: determining a first influencing factor when updating the first recommendation probability based on the recommendation selection result.

[0072] After the service recommendation system receives the recommendation selection result sent by the target user, the service recommendation system determines the first influencing factor when updating the first recommendation probability corresponding to each service to be recommended based on the recommendation selection result, that is, the first influencing factor is used to characterize the degree of influence of the user selection result on the update of the first recommendation probability.

[0073] Specifically, when determining the first recommendation probability based on the recommendation selection result, the service recommendation system can determine the service to be recommended selected by the target user, that is, the target recommended service, based on the recommendation selection result, and determine the first recommendation probability and the first impact factor of the target recommended service. The first impact factor can be a fixed value (that is, the impact degree on the first recommendation probability corresponding to the target recommended service is the same each time the target user selects the target recommended service), or it can be a non-fixed value. When the determined first impact factor is not a fixed value, the service recommendation system can determine the first impact factor according to the number of times the user selects the service to be recommended. After the target user selects the target recommended service each time, the size of the first impact factor is determined according to the number of times the user has selected the target recommended service in history. For example, the more times the user selects the target recommended service, the larger the first impact factor will be when the first recommendation probability corresponding to the target recommended service is updated.

[0074] Step G2: Determine the second recommendation probability based on the first recommendation probability, the first influencing factor and a preset second influencing factor.

[0075] The second influencing factor is used to characterize the retention degree of the preset first recommendation probability.

[0076] After determining the first influencing factor, the business recommendation system determines the second recommendation probability corresponding to each business to be recommended according to the first recommendation probability, the first influencing factor and the second influencing factor, wherein the second influencing factor is used to characterize the degree of retention of the first recommendation probability when determining the second recommendation probability.

[0077] Specifically, when determining the second influencing factor of the first recommendation probability corresponding to each service to be recommended, the second influencing factors of each first recommendation probability can be set to be the same, or the second influencing factors of each first recommendation probability can be different. For example, the second influencing factor of the first recommendation probability of the target recommended service can be set to be smaller, so that when the second recommendation probability is determined based on the first recommendation probability, the first influencing factor and the second influencing factor, the degree of influence of the user's selection result on the second recommendation probability can be highlighted.

[0078] Figure 2 is a flow chart of a second service recommendation method provided in an embodiment of this specification, such as Figure 2 As shown, the schematic diagram includes: Step 202: Obtain service usage data of multiple sample users.

[0079] Step 204: Obtain a preset number of clusters.

[0080] The number of clusters is the number of categories that the sample users can be divided into when performing cluster analysis.

[0081] Step 206: Determine a first number of classifications for the plurality of sample users and a classification to which each of the sample users belongs from the plurality of cluster numbers based on the elbow rule. Step 208: Based on a preset silhouette coefficient function, determine a silhouette coefficient value when the number of categories for classifying the sample user is the first number.

[0082] Step 210: When it is determined that the silhouette coefficient value is greater than a preset threshold, the first number is determined as the number of categories for classifying the sample user.

[0083] Step 212: Determine the user type of each of the sample users based on the category to which each of the sample users belongs.

[0084] Step 214: Setting the service recommendation table according to the user type of each of the sample users.

[0085] Step 216: Obtain the service usage data of the target user, and determine the user type of the target user based on comparing the service usage data with a preset type classification table.

[0086] Step 218: Recommend services to the target user based on the user type and a preset service recommendation table.

[0087] The service recommendation table includes a plurality of services to be recommended corresponding to the user type and a first recommendation probability corresponding to each of the services to be recommended.

[0088] Step 220: After receiving the recommendation selection result of the target user, the first recommendation probability of each of the services to be recommended is updated based on the recommendation selection result to obtain a second recommendation probability.

[0089] Step 222: Recommend a service to the target user based on the second recommendation probability.

[0090] In the embodiments of the specification, by obtaining the business usage data of multiple sample users, performing cluster analysis on the multiple sample users based on the business usage data of the multiple sample users, and then determining the user type of each sample user and the recommended business corresponding to each user type based on the cluster analysis results, the user types can be better divided, thereby providing suitable recommended businesses for various types of users, thereby improving the accuracy of business recommendations to users.

[0091] In one implementation, the determining the second recommendation probability based on the first recommendation probability, the first influencing factor, and a preset second influencing factor (step G2) may include executing steps H1-H2: Step H1: determining a third influencing factor based on the service usage data of the target user and a preset time variation function.

[0092] The third impact factor is used to characterize changes in the service usage data of the target user over time.

[0093] When the business recommendation system determines the second recommendation probability, it can also determine a third influencing factor based on the target user's business usage data and a preset time change function. The third influencing factor is used to characterize the change of the target user's business usage data over time to determine whether the business recommendation system can use the change of the target user's behavior.

[0094] Specifically, the third impact factor can be determined by a time sensitivity function, such as dt is determined to take into account the temporal variation of user behavior. It is a function that adjusts the Q value update rate according to the state s and time t to ensure that the system can adapt to changes in user behavior. Specifically:

[0095]

[0096] Where g(s) is a function that calculates the behavior complexity based on the user state s, T represents the time range for considering the user behavior change, λ is a positive constant representing the rate of time decay, s1, s2, s3 represent the current values ​​of call duration, data usage, and number of text messages in the user state s, respectively, and S1, S2, and S3 represent the value ranges of call duration, data usage, and number of text messages among all users, respectively, which are used for normalization processing.

[0097] Step H2: Determine the second recommendation probability based on the first recommendation probability, the first influencing factor, the second influencing factor and the third influencing factor.

[0098] After determining the third influencing factor, the service recommendation system determines the second recommendation probability corresponding to each service to be recommended according to the first recommendation probability, the first influencing factor and the third influencing factor.

[0099] When the business recommendation system updates the first recommendation probability corresponding to each business to be recommended, the first recommendation probability can be updated through the Q-learning algorithm to determine the second recommendation probability corresponding to each business to be recommended. Specifically, the business recommendation system initializes the Q table: create a Q table to store the value (Q value) of the state-action pair, where each state-action corresponds to an estimated long-term reward. Initially, all values ​​in the Q table can be set to 0 or other numerical probabilities, and then perform actions and observe rewards: perform the selected action (recommend the business to be recommended), observe user feedback as a reward, and then update the Q table based on user feedback. The Q value update method can be:

[0100] Among them, st is the current state, at is the currently executed action, rt+1 is the reward observed after executing the action, α is the learning rate (which determines the degree of fusion of new and old information), and γ is the discount factor (which determines the current value of future rewards).

[0101] Figure 3 FIG. 1 is a flow chart of a second service recommendation method provided in an embodiment of the present specification. Figure 3 As shown, the schematic diagram includes: Step 302: Obtain the service usage data of the target user, and determine the user type of the target user based on comparing the service usage data with a preset type classification table.

[0102] Step 304: Recommend services to the target user based on the user type and a preset service recommendation table.

[0103] The service recommendation table includes a plurality of services to be recommended corresponding to the user type and a first recommendation probability corresponding to each of the services to be recommended.

[0104] Step 306: After receiving the recommendation selection result of the target user, determine a first influencing factor when updating the first recommendation probability based on the recommendation selection result.

[0105] Step 308: Determine a third impact factor based on the service usage data of the target user and a preset time variation function.

[0106] The third impact factor is used to characterize changes in the service usage data of the target user over time.

[0107] Step 310: Determine the second recommendation probability based on the first recommendation probability, the first influencing factor, the second influencing factor, and the third influencing factor.

[0108] The second influencing factor is used to characterize the retention degree of the preset first recommendation probability.

[0109] Step 312: Recommend a service to the target user based on the second recommendation probability.

[0110] In the embodiments of the specification, the first recommendation probability corresponding to each service to be recommended is continuously updated based on the recommendation selection result of the target user, thereby determining the second recommendation probability of each service to be recommended, and more suitable services can be recommended to the target user based on the time dimension and the user's historical selection situation.

[0111] In one implementation, based on the second recommendation probability, a service is recommended to the target user (step 106), and steps I1-I2 may be performed: Step I1: based on the second recommendation probability, determine a first preset number of the services to be recommended from the plurality of the services to be recommended and recommend services to the target user.

[0112] After determining the second recommendation probability corresponding to each business to be recommended, the business recommendation system can determine a first preset number of businesses to be recommended from multiple businesses to be recommended according to the second recommendation probability corresponding to each business to be recommended, and recommend the determined businesses to be recommended to the target user, where the first preset number can be two or other numbers.

[0113] Specifically, when determining the recommended services to be recommended based on the second recommendation probability, a first preset number of recommended services with the highest second probability can be recommended, for example, the second recommendation probabilities corresponding to multiple recommended services are sorted, and the two recommended services with the highest second recommendation probability are recommended.

[0114] Step I2: Based on a preset random recommendation probability, determine a second preset number of the services to be recommended from the plurality of services to be recommended and recommend services to the target user.

[0115] After determining the second recommendation probability corresponding to each business to be recommended, the business recommendation system can determine a second preset number of businesses to be recommended from multiple businesses to be recommended according to the random recommendation probability corresponding to each business to be recommended, and recommend the determined businesses to be recommended to the target user, wherein the second preset number may be the same as or different from the first preset number, and may be two or other numbers.

[0116] Specifically, when determining the recommended services to be recommended based on the random recommendation probability, a second preset number (such as two or four) of the recommended services can be randomly selected from the multiple recommended services for recommendation according to the preset random recommendation probability, wherein the random recommendation probabilities corresponding to the services to be recommended can be the same or different. Further, when the random recommendation probabilities corresponding to the services to be recommended are different, the service recommendation system can determine the random recommendation probability based on the number of selections of each service to be recommended and the total number of recommendations, for example, determining the random recommendation probability as the ratio of the number of selections of each service to be recommended to the total number of recommendations.

[0117] The embodiment of the present application not only recommends services to the target user based on the second recommendation probability, but also recommends services to the target user based on the random recommendation probability, thereby not only ensuring that the service recommendation is based on the actual situation of the target user and improving the accuracy of the service recommendation, but also being able to recommend services to the target user through random probability, thereby increasing the diversity of the service recommendation.

[0118] In one implementation, after performing a service recommendation for the target user based on the second recommendation probability (step 106), steps J1-J2 may also be performed: Step J1: Obtain the target user's evaluation result on the service to be recommended.

[0119] After the service recommendation system recommends services to the target user based on the second recommendation probability, the service recommendation system can receive the evaluation result of the target user on the recommended service. That is, after the target user receives the recommended service, the service recommendation system can provide the target user with a simple and easy-to-use interface, allowing the user to quickly give feedback, i.e., the evaluation result. The feedback given by the user can be a simple "like" or "dislike" button, or a scoring option for the recommended service.

[0120] Specifically, the target user's evaluation results received by the business recommendation system can be obtained directly from the target user or from the blockchain. That is, the target user sends the evaluation results to the blockchain, and the business recommendation system obtains the target user's evaluation results from the blockchain. When the target user's evaluation results are recorded through the smart contract in the blockchain, the data structure can be defined in the smart contract to store user feedback, including user ID (anonymized), package ID, feedback type (such as like, dislike, score) and timestamp, and the business recommendation system can regularly obtain the target user's evaluation results from the blockchain.

[0121] Step J2: updating the strategy for updating the first recommendation probability based on the evaluation result and / or the recommendation selection result.

[0122] After obtaining the evaluation results, the business recommendation system updates the strategy for updating the first recommendation probability based on the evaluation results and / or the recommendation selection results. When updating the strategy for updating the first recommendation probability based on the evaluation results, the average score, the ratio of likes to dislikes, etc. of each package can be calculated based on the evaluation results. User feedback is used as input to adjust and optimize the recommendation algorithm. For example, if a package receives a large amount of negative feedback, the recommendation system will reduce the recommendation weight of the package. When updating the strategy for updating the first recommendation probability based on the recommendation selection results, the feedback accuracy can be determined according to the recommendation selection results, and the strategy for updating the first recommendation probability can be updated based on the feedback accuracy.

[0123] Figure 4 Schematic diagram of a swim lane diagram of a business recommendation method provided in an embodiment of this specification, such as Figure 4 As shown, the schematic diagram includes: Step 4.1: The target user sends the business usage data to the blockchain.

[0124] Step 4.2: The target user sends access permission information to the blockchain.

[0125] Step 4.3: The business recommendation system obtains the first address information, and generates a first acquisition request based on the first address information.

[0126] Step 4.4: The business recommendation system sends a first acquisition request to the blockchain.

[0127] Step 4.5: The blockchain determines whether the business recommendation system has the authority to obtain the business usage data based on the first address information and access permission information in the first acquisition request.

[0128] Step 4.6: When the business recommendation system has access rights, the blockchain sends the business usage data to the business recommendation system.

[0129] Step 4.7: The business recommendation system compares the business usage data with the preset type classification table to determine the user type of the target user.

[0130] Step 4.8: The service recommendation system recommends services to the target user based on the user type and the preset service recommendation table.

[0131] The service recommendation table includes a plurality of services to be recommended corresponding to the user type and a first recommendation probability corresponding to each service to be recommended.

[0132] Step 4.9: The target user sends the recommendation selection results to the business recommendation system.

[0133] Step 4.10: The service recommendation system updates the first recommendation probability corresponding to each service to be recommended based on the recommendation selection result to obtain a second recommendation probability.

[0134] Step 4.11: The service recommendation system recommends services to the target user based on the second recommendation probability.

[0135] Step 4.12: The target user sends the evaluation result of the recommended service to the blockchain.

[0136] Step 4.13: The blockchain sends the evaluation results to the business recommendation system.

[0137] Step 4.14: The service recommendation system updates the strategy for updating the first recommendation probability according to the service evaluation result and / or the recommendation selection result.

[0138] In the embodiments of the specification, by storing the target user's business usage data and the evaluation results of the recommended business in the blockchain, and sending the business usage data and the evaluation results to the business recommendation system after the business recommendation system has access authority, not only can the accuracy of business recommendations for the target user be improved, but also the privacy and security of the target user's business usage data can be guaranteed.

[0139] It should be noted that the execution subject of the service recommendation method provided in the embodiment of the present application may be a service recommendation device, or a control module in the service recommendation device for executing the service recommendation method. In the embodiment of the present application, the service recommendation device provided in the embodiment of the present application is described by taking the service recommendation method executed by the service recommendation device as an example.

[0140] Figure 5 is a schematic diagram of the structure of a service recommendation device according to an embodiment of the present invention. Figure 5 As shown, the service recommendation device includes: a first recommendation module 502 , a first update module 504 , and a second recommendation module 506 .

[0141] The first recommendation module 502 is used to obtain the user type of the target user, and recommend services to the target user based on the user type of the target user and a preset service recommendation table, wherein the service recommendation table includes multiple services to be recommended corresponding to the user type and a first recommendation probability corresponding to each of the services to be recommended.

[0142] The first updating module 504 is configured to update the first recommendation probability of each of the services to be recommended based on the recommendation selection result after receiving the recommendation selection result of the target user, so as to obtain a second recommendation probability.

[0143] The second recommendation module 506 is configured to make a service recommendation to the target user based on the second recommendation probability.

[0144] The service recommendation device in the embodiment of the present application can be a device, or a component, integrated circuit, or chip in a terminal. The device can be a mobile electronic device or a non-mobile electronic device. Exemplarily, the mobile electronic device can be a mobile phone, a tablet computer, a laptop computer, a PDA, an in-vehicle electronic device, a wearable device, an ultra-mobile personal computer (UMPC), a netbook, or a personal digital assistant (PDA), etc. The non-mobile electronic device can be a server, a network attached storage (NAS), a personal computer (PC), a television (TV), a teller machine or a self-service machine, etc., which is not specifically limited in the embodiment of the present application.

[0145] The service recommendation device in the embodiment of the present application may be a device having an operating system. The operating system may be an Android operating system, an iOS operating system, or other possible operating systems, which are not specifically limited in the embodiment of the present application.

[0146] The service recommendation device provided in the embodiment of the present application can achieve Figures 1 to 4 To avoid repetition, the various processes implemented in the method embodiment are not described here.

[0147] Based on the same technical concept, an embodiment of the present application further provides an electronic device, which is used to execute the above-mentioned service recommendation method. Figure 6 A schematic diagram of the structure of an electronic device for implementing various embodiments of the present application. The electronic device may have relatively large differences due to different configurations or performances, and may include a processor (processor) 602, a communication interface (Communications Interface) 604, a memory (memory) 606 and a communication bus 608, wherein the processor 602, the communication interface 604, and the memory 606 communicate with each other through the communication bus 608. The processor 602 may call a computer program stored in the memory 606 and executable on the processor 602 to perform the following steps: Acquire a user type of a target user, and recommend services to the target user based on the user type of the target user and a preset service recommendation table, wherein the service recommendation table includes a plurality of services to be recommended corresponding to the user type and a first recommendation probability corresponding to each of the services to be recommended; After receiving the recommendation selection result of the target user, updating the first recommendation probability of each of the services to be recommended based on the recommendation selection result to obtain a second recommendation probability; A service is recommended to the target user based on the second recommendation probability.

[0148] In one implementation, before obtaining the user type of the target user, the method further includes: Acquire service usage data of the target user, wherein the service usage data includes user identity module SIM card usage data; The user type of the target user is determined based on comparing the service usage data with a preset type classification table.

[0149] In one implementation, the acquiring of the service usage data of the target user includes: Sending a first acquisition request to the blockchain, wherein the first acquisition request is used to request the blockchain to send the service usage data of the target user to the service recommendation system. The first acquisition request is used to request the blockchain to send the service usage data of the target user to the service recommendation system; Receive the business usage data of the target user sent by the blockchain.

[0150] In one implementation, sending a first acquisition request to the blockchain includes: Acquire first address information, where the first address information is address information of a business recommendation system; A first acquisition request is generated based on the first address information, and the first acquisition request is sent to the blockchain, so that the blockchain determines whether the business recommendation system has the authority to obtain the business usage data based on the first address information and the access permission information pre-set by the target user.

[0151] In one implementation, before comparing the service usage data with a preset type classification table to determine the user type of the target user, the method further includes: Obtaining business usage data of multiple sample users; Performing cluster analysis on the plurality of sample users based on the service usage data of the plurality of sample users to obtain a first number of classifications of the plurality of sample users and a classification to which each of the sample users belongs; Determining the user type of each of the sample users based on the category to which each of the sample users belongs; The service recommendation table is set according to the user type of each of the sample users.

[0152] In one implementation, the cluster analysis is performed on the service usage data of the plurality of sample users to obtain a first number of classifications of the plurality of sample users and a classification to which each of the sample users belongs, including: Obtaining a preset number of clusters, where the number of clusters is the number of categories that the sample users can be divided into when performing cluster analysis; The first number for classifying the plurality of sample users and the category to which each of the sample users belongs are determined from the plurality of cluster numbers based on the elbow rule.

[0153] In one implementation, after determining the number of categories for classifying the plurality of sample users and the category to which each of the sample users belongs from the plurality of cluster numbers based on the elbow rule, the method further includes: Based on a preset silhouette coefficient function, determining a silhouette coefficient value when the number of categories for classifying the sample user is the first number; When it is determined that the silhouette coefficient value is greater than a preset threshold, the first number is determined as the number of categories for classifying the sample users.

[0154] In one implementation, the updating of the first recommendation probability of each of the services to be recommended based on the recommendation selection result to obtain a second recommendation probability includes: Determining a first influencing factor when updating the first recommendation probability based on the recommendation selection result; The second recommendation probability is determined based on the first recommendation probability, the first influencing factor, and a preset second influencing factor, where the second influencing factor is used to characterize a retention degree of the preset first recommendation probability.

[0155] In one implementation, determining the second recommendation probability based on the first recommendation probability, the first influencing factor, and a preset second influencing factor includes: Determine a third impact factor based on the service usage data of the target user and a preset time variation function, wherein the third impact factor is used to characterize the change of the service usage data of the target user over time; The second recommendation probability is determined based on the first recommendation probability, the first influencing factor, the second influencing factor, and the third influencing factor.

[0156] In one implementation, recommending a service to the target user based on the second recommendation probability includes: Based on the second recommendation probability, determining a first preset number of the services to be recommended from the plurality of services to be recommended to make service recommendations to the target user; Based on a preset random recommendation probability, a second preset number of the services to be recommended is determined from the plurality of services to be recommended, and service recommendations are made to the target user.

[0157] In one implementation, after recommending a service to the target user based on the second recommendation probability, the method further includes: Obtaining the target user's evaluation result on the service to be recommended; A strategy for updating the first recommendation probability is updated based on the evaluation result and / or the recommendation selection result.

[0158] The specific execution steps can refer to the various steps of the above-mentioned business recommendation method embodiment, and can achieve the same technical effect. To avoid repetition, they will not be described here.

[0159] It should be noted that the electronic devices in the embodiments of the present application include: servers, terminals, or other devices except terminals.

[0160] The above electronic device structure does not constitute a limitation on the electronic device. The electronic device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently. For example, the input unit may include a graphics processing unit (GPU) and a microphone, and the display unit may be configured with a display panel in the form of a liquid crystal display, an organic light-emitting diode, etc. The user input unit includes a touch panel and at least one of other input devices. The touch panel is also called a touch screen. Other input devices may include, but are not limited to, a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, and a joystick, which will not be repeated here.

[0161] The memory can be used to store software programs and various data. The memory may mainly include a first storage area for storing programs or instructions and a second storage area for storing data, wherein the first storage area may store an operating system, an application program or instructions required for at least one function (such as a sound playback function, an image playback function, etc.), etc. In addition, the memory may include a volatile memory or a non-volatile memory, or the memory may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. Volatile memory can be random access memory (RAM), static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM) and direct memory bus random access memory (DRRAM).

[0162] The processor may include one or more processing units; optionally, the processor integrates an application processor and a modem processor, wherein the application processor mainly processes operations related to the operating system, user interface, and application programs, and the modem processor mainly processes wireless communication signals, such as a baseband processor. It is understandable that the modem processor may not be integrated into the processor.

[0163] An embodiment of the present application also provides a service recommendation method, which is applied to a terminal device, and includes: receiving multiple services to be recommended recommended by a service recommendation system, and generating a recommendation selection result based on the multiple services to be recommended recommended by the service recommendation system, wherein the multiple services to be recommended are determined by the service recommendation system based on the acquired user type of the target user and a preset service recommendation table, and service recommendations are made to the target user, wherein the service recommendation table includes multiple services to be recommended corresponding to the user type and a first recommendation probability corresponding to each service to be recommended; sending the recommendation selection result to the service recommendation system, so that the service recommendation system updates the first recommendation probability of each service to be recommended based on the recommendation selection result to obtain a second recommendation probability, and recommends services to the target user based on the second recommendation probability.

[0164] That is to say, the service recommendation system obtains the user type of the target user, and then recommends services to the target user based on the user type and a preset service recommendation table, wherein the service recommendation table includes multiple services to be recommended corresponding to the user type and a first recommendation probability corresponding to each service to be recommended. The terminal device receives multiple services to be recommended recommended by the service recommendation system and displays them to the target user, then receives and generates a recommendation selection result based on the target user's selection operation for the service to be recommended, and then sends the recommendation selection result to the service recommendation system. The service recommendation system updates the first recommendation probability corresponding to each service to be recommended based on the recommendation selection result, obtains a second recommendation probability, and updates the service recommendation system based on the updated second recommendation probability corresponding to each service to be recommended.

[0165] In one implementation, the method further includes: sending the target user's business usage data to the blockchain for storage; sending access permission information to the blockchain so that when the blockchain determines that the business recommendation system has access permission based on the access permission information, the business usage data of the target user is sent to the business recommendation system, and the business recommendation system determines the user type of the target user based on the obtained business usage data of the target user and comparing it with a preset type classification table.

[0166] That is to say, the terminal device can send the target user's business usage data to the blockchain, and send access permission information to the blockchain, so that the blockchain can determine which access source can obtain the business usage data based on the access permission information. When the business recommendation system obtains the target user's business usage data through the blockchain, it can generate an acquisition request based on the address information of the business recommendation system, and send the acquisition request to the blockchain, so that the blockchain determines whether the business recommendation system has the authority to obtain the business usage data based on the address information and access permission information in the acquisition request. After the blockchain determines that the business recommendation system has the authority to obtain the business usage, the blockchain sends the business usage data to the business recommendation system. After the business recommendation system receives the target user's business usage data, it can compare the business usage data with the pre-set type classification table to determine the user type of the target user.

[0167] Specifically, the manner in which the terminal device interacts with the service recommendation system in this method refers to the service recommendation method applied to the service recommendation system described above, which will not be described in detail here.

[0168] Correspondingly, an embodiment of the present application also provides a business recommendation device, which includes a first generating module, used to receive multiple businesses to be recommended recommended by a business recommendation system, and generate a recommendation selection result based on the multiple businesses to be recommended recommended by the business recommendation system, wherein the multiple businesses to be recommended are determined by the business recommendation system based on the acquired user type of the target user and a preset business recommendation table, and the business recommendation table includes multiple businesses to be recommended corresponding to the user type and a first recommendation probability corresponding to each business to be recommended; a second sending module, used to send the recommendation selection result to the business recommendation system, so that the business recommendation system updates the first recommendation probability of each business to be recommended based on the recommendation selection result, obtains a second recommendation probability, and recommends a business to the target user based on the second recommendation probability.

[0169] The present application also provides a computer device, which includes: a processor; and a memory arranged to store computer executable instructions, the executable instructions are configured to be executed by the processor, the executable instructions include instructions for executing each step in the above-mentioned business recommendation method, and can achieve the same technical effect. To avoid repetition, they will not be repeated here.

[0170] An embodiment of the present application also provides a computer product, which includes a computer and a program. When the computer program is executed by a processor, each step in the above-mentioned business recommendation method is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0171] An embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, each process of the above-mentioned business recommendation method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0172] The processor is the processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0173] An embodiment of the present application further provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned business recommendation method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0174] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0175] It should be noted that, in this article, the terms "comprise", "include" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise one..." do not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0176] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0177] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

Claims

1. A business recommendation method, applied to a business recommendation system, comprising: Acquire a user type of a target user, and recommend services to the target user based on the user type of the target user and a preset service recommendation table, wherein the service recommendation table includes a plurality of services to be recommended corresponding to the user type and a first recommendation probability corresponding to each of the services to be recommended; After receiving the recommendation selection result of the target user, updating the first recommendation probability of each of the services to be recommended based on the recommendation selection result to obtain a second recommendation probability; A service is recommended to the target user based on the second recommendation probability.

2. According to the method of claim 1, before obtaining the user type of the target user, the method further comprises: Acquire service usage data of the target user, wherein the service usage data includes user identity module SIM card usage data; The user type of the target user is determined based on comparing the service usage data with a preset type classification table.

3. According to the method of claim 2, the step of obtaining the service usage data of the target user comprises: Sending a first acquisition request to the blockchain, wherein the first acquisition request is used to request the blockchain to send the service usage data of the target user to a service recommendation system; Receive the business usage data of the target user sent by the blockchain.

4. According to the method of claim 3, sending a first acquisition request to the blockchain comprises: Acquire first address information, where the first address information is address information of a business recommendation system; A first acquisition request is generated based on the first address information, and the first acquisition request is sent to the blockchain, so that the blockchain determines whether the business recommendation system has the authority to obtain the business usage data based on the first address information and the access permission information pre-set by the target user.

5. The method according to claim 2, before comparing the service usage data with a preset type classification table to determine the user type of the target user, the method further comprises: Obtaining business usage data of multiple sample users; Performing cluster analysis on the plurality of sample users based on the service usage data of the plurality of sample users to obtain a first number of classifications of the plurality of sample users and a classification to which each of the sample users belongs; Determining the user type of each of the sample users based on the category to which each of the sample users belongs; The service recommendation table is set according to the user type of each of the sample users.

6. The method according to claim 5, wherein the clustering analysis is performed on the service usage data of the plurality of sample users to obtain a first number of classifications of the plurality of sample users and the classification to which each of the sample users belongs, comprising: Obtaining a preset number of clusters, where the number of clusters is the number of categories that the sample users can be divided into when performing cluster analysis; The first number for classifying the plurality of sample users and the category to which each of the sample users belongs are determined from the plurality of cluster numbers based on the elbow rule.

7. The method according to claim 6, after determining the number of categories for classifying the plurality of sample users and the category to which each of the sample users belongs from the plurality of cluster numbers based on the elbow rule, the method further comprises: Based on a preset silhouette coefficient function, determining a silhouette coefficient value when the number of categories for classifying the sample user is the first number; When it is determined that the silhouette coefficient value is greater than a preset threshold, the first number is determined as the number of categories for classifying the sample users.

8. The method according to claim 1, wherein the updating the first recommendation probability of each of the services to be recommended based on the recommendation selection result to obtain a second recommendation probability comprises: Determining a first influencing factor when updating the first recommendation probability based on the recommendation selection result; The second recommendation probability is determined based on the first recommendation probability, the first influencing factor, and a preset second influencing factor, where the second influencing factor is used to characterize a retention degree of the preset first recommendation probability.

9. The method according to claim 8, wherein determining the second recommendation probability based on the first recommendation probability, the first influencing factor and a preset second influencing factor comprises: Determine a third impact factor based on the service usage data of the target user and a preset time variation function, wherein the third impact factor is used to characterize the change of the service usage data of the target user over time; The second recommendation probability is determined based on the first recommendation probability, the first influencing factor, the second influencing factor, and the third influencing factor.

10. The method according to claim 1, performing a service recommendation for the target user based on the second recommendation probability, comprising: Based on the second recommendation probability, determining a first preset number of the services to be recommended from the plurality of services to be recommended to make service recommendations to the target user; Based on a preset random recommendation probability, a second preset number of the services to be recommended is determined from the plurality of services to be recommended, and service recommendations are made to the target user.

11. The method according to claim 1, after performing a service recommendation to the target user based on the second recommendation probability, the method further comprises: Obtaining the target user's evaluation result on the service to be recommended; A strategy for updating the first recommendation probability is updated based on the evaluation result and / or the recommendation selection result.

12. A service recommendation method, applied to a terminal device, comprising: Receiving a plurality of to-be-recommended services recommended by a service recommendation system, and generating a recommendation selection result based on the plurality of to-be-recommended services recommended by the service recommendation system, wherein the plurality of to-be-recommended services are determined by the service recommendation system by recommending services to the target user based on the acquired user type of the target user and a preset service recommendation table, wherein the service recommendation table includes a plurality of to-be-recommended services corresponding to the user type and a first recommendation probability corresponding to each of the to-be-recommended services; The recommendation selection result is sent to the service recommendation system, so that the service recommendation system updates the first recommendation probability of each service to be recommended based on the recommendation selection result to obtain a second recommendation probability, and recommends a service to the target user based on the second recommendation probability.

13. The method according to claim 12, further comprising: Sending the target user's business usage data to the blockchain for storage; Access permission information is sent to the blockchain so that when the blockchain determines that the business recommendation system has access permission based on the access permission information, the business usage data of the target user is sent to the business recommendation system, and the business recommendation system determines the user type of the target user based on the obtained business usage data of the target user and comparing it with a preset type classification table.

14. A business recommendation device, comprising: A first recommendation module, configured to obtain a user type of a target user, and recommend services to the target user based on the user type of the target user and a preset service recommendation table, wherein the service recommendation table includes a plurality of services to be recommended corresponding to the user type and a first recommendation probability corresponding to each of the services to be recommended; A first updating module is used to update the first recommendation probability of each of the services to be recommended based on the recommendation selection result after receiving the recommendation selection result of the target user, so as to obtain a second recommendation probability; The second recommendation module is used to make a service recommendation to the target user based on the second recommendation probability.

15. A business recommendation device, comprising: A first generating module, configured to receive a plurality of to-be-recommended services recommended by a service recommendation system, and generate a recommendation selection result based on the plurality of to-be-recommended services recommended by the service recommendation system, wherein the plurality of to-be-recommended services are determined by the service recommendation system by recommending services to the target user based on the acquired user type of the target user and a preset service recommendation table, wherein the service recommendation table includes the plurality of to-be-recommended services corresponding to the user type and a first recommendation probability corresponding to each of the to-be-recommended services; The second sending module is used to send the recommendation selection result to the business recommendation system, so that the business recommendation system updates the first recommendation probability of each of the to-be-recommended businesses based on the recommendation selection result to obtain a second recommendation probability, and recommends a business to the target user based on the second recommendation probability.

16. A computer device, characterized in that: The device comprises: Processor; and A memory arranged to store computer executable instructions, wherein the executable instructions are configured to be executed by the processor, and the executable instructions include instructions for executing the steps in the business recommendation method according to any one of claims 1 to 11.

17. A storage medium, characterized in that: The storage medium is used to store computer-executable instructions, and the executable instructions enable a computer to execute the service recommendation method according to any one of claims 1 to 11.

18. A computer program product, characterized in that The invention comprises a computer program, which, when executed by a processor, implements the service recommendation method according to any one of claims 1 to 11.

Images