Commodity recommendation method and device, computer device and storage medium

Abstract

The application relates to the technical field of data processing, and discloses a commodity recommendation method and device, computer equipment and a storage medium. The commodity recommendation method comprises the following steps: acquiring first user demand information; determining a business scenario according to the first user demand information, screening out a head node corresponding to the business scenario in a node pool; acquiring a first pointer list of the head node, screening out first pointer information matched with the first user demand information in the first pointer list; determining a sub-node corresponding to a first judgment direction according to the first pointer information; judging whether the sub-node is a leaf node; if the sub-node is a leaf node, acquiring a second pointer list of the leaf node; screening out second pointer information matched with the first user demand information in the second pointer list; and determining a target commodity according to the second pointer information. The recommendation logic of the application has strong correlation, can be iterated for different demands, does not need to be redeveloped, and resources are saved.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, specifically to a product recommendation method, apparatus, computer equipment, and storage medium. Background Technology

[0002] With the continuous development of the economy, the number of online business users is constantly increasing, and the customer groups are also becoming more diverse. In order to increase customers' enthusiasm for purchasing products, it is necessary to make customized product recommendations for different customer groups.

[0003] Currently, conventional recommendation logic is quite fragmented. Different businesses, products, or designers will create different recommendation schemes. While each recommendation scheme reflects personalized recommendations, there is also a lot of repetitive logic. Each iteration of requirements requires redesign and development. Even if some adjustments are made to the original recommendation logic, resources need to be invested in familiarizing themselves with the code and developing it, which is a waste of resources. Summary of the Invention

[0004] In view of this, the present invention provides a product recommendation method, apparatus, computer device, and storage medium to solve the problem of having to redesign for each iteration of requirements.

[0005] In a first aspect, the present invention provides a product recommendation method, comprising: obtaining first user demand information; determining a business scenario based on the first user demand information; filtering head nodes corresponding to the business scenario from a node pool, the node pool including multiple head nodes corresponding to multiple business scenarios respectively; obtaining a first pointer list of head nodes, the first pointer list being a list of multiple judgment directions corresponding to the head nodes; filtering first pointer information matching the first user demand information from the first pointer list, the first pointer information including a first judgment direction and a child node corresponding to the first judgment direction; determining the child node corresponding to the first judgment direction based on the first pointer information; determining whether the child node is a leaf node, the leaf node being the last node; if the child node is a leaf node, obtaining a second pointer list of leaf nodes; the second pointer list being a list of multiple judgment directions corresponding to the leaf nodes; filtering second pointer information matching the first user demand information from the second pointer list, the second pointer information including a second judgment direction and a target product corresponding to the second judgment direction; and determining the target product based on the second pointer information.

[0006] Beneficial Effects: This embodiment of the invention obtains first user demand information, determines a business scenario based on the first user demand information, filters the head node corresponding to the business scenario in the node pool, obtains a first pointer list of the head node, the first pointer list includes multiple pointer information, each pointer information corresponds to a different judgment direction, filters the first pointer information that matches the first user demand information from the first pointer list, the first pointer information includes a first judgment direction and the child node corresponding to the first judgment direction, and determines the child node corresponding to the first judgment direction based on the first pointer information. This embodiment of the invention determines the head node based on the first user demand information, and determines the child node, that is, the next level node of the head node, based on the first user demand and the different pointer information of the head node. Judging the child node based on the demand information makes the selection of child nodes more accurate. After determining the child node, it is determined whether the child node is a leaf node. The leaf node is the last node. If the child node is a leaf node, the next level node of the child node is not searched. The second pointer list of the leaf node is used to filter the second pointer information that matches the first user demand information, and the target product is determined based on the second pointer information. This embodiment of the invention, after determining that the child node is a leaf node, determines the target product based on the leaf node and the first user demand information, so that the target product meets the first user demand information. Compared with the redesign and development of various recommendation schemes in related technologies, the embodiments of the present invention have multiple pointer information for each node to meet different user needs. When a new user need is received, there is no need to redesign and develop a new recommendation link, so there will be no logical duplication, saving resources and improving the efficiency of product recommendation.

[0007] In one optional implementation, if the child node is not a leaf node, a third pointer list of the child node is obtained; the third pointer list is a list of multiple judgment directions corresponding to the child node; the third pointer information that matches the first user requirement information is filtered out from the third pointer list, the third pointer information includes the third judgment direction and the child node corresponding to the third judgment direction; the child node corresponding to the third judgment direction is determined according to the third pointer information, and it is determined whether the child node is a leaf node, until the child node is a leaf node.

[0008] Beneficial effects: In this embodiment of the invention, when it is determined that a child node is not a leaf node, a third pointer list corresponding to the child node is obtained. The third pointer list is filtered to select the third pointer information that matches the first user demand information. The child node corresponding to the third judgment direction is determined based on the third pointer information. It is then determined whether the child node is a leaf node, until the child node is a leaf node, which is the last node. The target product is determined based on the leaf node. This embodiment of the invention starts from the head node and matches and selects step by step according to the user demand information until the child node is a leaf node, thus obtaining the target product. The obtained target product better meets the user's needs.

[0009] In one optional implementation, the nodes in the node pool include multiple head nodes and multiple child nodes. Each node includes a node name, the corresponding function, the node's level, whether it is a head node, and pointer information.

[0010] Beneficial effects: The node name in the node is the node identifier, and different nodes have different node names to identify different nodes; the function corresponding to the node is used to match and select according to user requirements; the node hierarchy is used to enable parallel asynchronous processing of nodes at the same level.

[0011] In one optional implementation, determining whether a child node is a leaf node includes: determining whether a preset field in the child node is a first preset character; if the preset field of the child node is the first preset character, then the child node is a leaf node; if the preset field of the child node is a second preset character, then the child node is not a leaf node.

[0012] In an alternative implementation, before obtaining the first user requirement information, the method further includes: when creating a node, configuring the relationship between the node and its parent and child nodes, whether the node is a head node, and whether the node is a leaf node.

[0013] Beneficial effects: When creating nodes, maintaining the relationship between upper-level and lower-level nodes and configuring each node to be a head node or leaf node on different links ensures that nodes are linked together in a chain, which can meet the needs of different users. When a new user request is received, the target product that meets the user's needs can be directly selected from the nodes in the node pool without redesigning or developing a new recommendation link, thus avoiding logical duplication, saving resources, and improving the efficiency of product recommendation. When it is necessary to add, delete, or adjust nodes, only the configuration needs to be modified, without redeveloping new code, saving R&D resources.

[0014] In one optional implementation, if multiple child nodes corresponding to multiple judgment directions in the first pointer list are the same child node, then the child node is renamed.

[0015] Beneficial effect: If multiple child nodes corresponding to multiple judgment directions in the first pointer list are the same child node, even though they point to the same node, that is, when the same child node appears repeatedly, the target products recommended by the corresponding leaf nodes are different. Therefore, the child node is renamed to distinguish them.

[0016] In one optional implementation, multiple second user demand information are obtained; application configuration information is obtained, and product recommendation is enabled based on the application configuration information; a recommendation tree is queried based on multiple business scenarios in the multiple second user demand information, the recommendation tree including multiple nodes corresponding to multiple business scenarios; multiple head nodes are determined based on the recommendation tree, and the multiple head nodes are processed in parallel; multiple child nodes corresponding to the multiple head nodes are determined based on the multiple head nodes; it is determined whether the hierarchy of the multiple child nodes has changed, if not, the execution results of the multiple child nodes are obtained; the lower-level nodes of the multiple child nodes are obtained based on the execution results; it is determined whether the lower-level nodes of the multiple child nodes are leaf nodes; if the lower-level nodes of the multiple child nodes are leaf nodes, the product corresponding to the leaf node is determined to be the target product.

[0017] Beneficial Effects: In this embodiment of the invention, multiple second user demand information and application configuration information are obtained. Product recommendation is initiated based on the application configuration information. A recommendation tree is queried based on multiple business scenarios within the multiple second user demand information. Multiple head nodes are determined based on the recommendation tree, and these head nodes are processed in parallel. This embodiment of the invention achieves batch asynchronous processing of nodes at the same level, improving the efficiency of product recommendation and saving time. Multiple child nodes corresponding to the multiple head nodes are determined based on the multiple head nodes. It is determined whether the level of the multiple child nodes has changed. If not, the execution results of the multiple child nodes are obtained. This embodiment of the invention also processes child nodes at the same level in batches asynchronously. The lower-level nodes of the multiple child nodes are obtained based on the execution results. It is determined whether the lower-level nodes of the multiple child nodes are leaf nodes. If the lower-level nodes of the multiple child nodes are leaf nodes, the product corresponding to the leaf node is determined to be the target product. Compared with the redesigned recommendation schemes in related technologies, this embodiment of the invention sets multiple pointer information for each node to meet different user needs. When a new user demand is received, there is no need to redesign or develop a new recommendation chain, thus avoiding logical duplication, saving resources, and improving the efficiency of product recommendation.

[0018] In one optional implementation, determining whether the hierarchy of multiple child nodes has changed further includes: if there has been a change, determining whether the multiple head nodes corresponding to the multiple child nodes have finished executing; if they have finished executing, processing the multiple child nodes in parallel; if they have not finished executing, waiting for the multiple head nodes to finish executing, and then processing the multiple child nodes in parallel.

[0019] Beneficial effects: If the hierarchy changes, it checks whether the multiple head nodes corresponding to the multiple child nodes have finished executing. If they have finished executing, the multiple child nodes are processed in parallel. If they have not finished executing, it waits for the multiple head nodes to finish executing and processes the multiple child nodes in parallel. Parallel processing saves time and improves the efficiency of product recommendation.

[0020] Secondly, the present invention provides a product recommendation device, comprising: a head node determination module, configured to acquire first user demand information; determine a business scenario based on the first user demand information, and filter out head nodes corresponding to the business scenario from a node pool, the node pool including multiple head nodes corresponding to multiple business scenarios respectively; a first pointer list acquisition module, configured to acquire a first pointer list of head nodes, the first pointer list being a list of multiple judgment directions corresponding to the head node; a first pointer information matching module, configured to filter out first pointer information matching the first user demand information from the first pointer list, the first pointer information including a first judgment direction and a child node corresponding to the first judgment direction; a child node confirmation module, configured to determine the child node corresponding to the first judgment direction based on the first pointer information; a leaf node judgment module, configured to determine whether a child node is a leaf node, the leaf node being the last node; a second pointer list acquisition module, configured to acquire a second pointer list of leaf nodes based on the child node being a leaf node, the second pointer list being a list of multiple judgment directions corresponding to the leaf node; a second pointer information matching module, configured to filter out second pointer information matching the first user demand information from the second pointer list, the second pointer information including a second judgment direction and a target product corresponding to the second judgment direction; and a target product determination module, configured to determine the target product based on the second pointer information.

[0021] Thirdly, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the computer instructions to perform the product recommendation method of the first aspect or any corresponding embodiment thereof.

[0022] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to perform the product recommendation method of the first aspect or any corresponding embodiment thereof. Attached Figure Description

[0023] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0024] Figure 1 This is a flowchart illustrating a product recommendation method according to an embodiment of the present invention;

[0025] Figure 2 This is a flowchart illustrating another product recommendation method according to an embodiment of the present invention;

[0026] Figure 3 This is a schematic diagram of the overall product recommendation process according to an embodiment of the present invention;

[0027] Figure 4 This is a flowchart illustrating another product recommendation method according to an embodiment of the present invention;

[0028] Figure 5 This is a schematic diagram of the recommendation tree structure according to an embodiment of the present invention;

[0029] Figure 6 This is a schematic diagram of the target product recommendation logic flow according to an embodiment of the present invention;

[0030] Figure 7 This is a structural block diagram of a product recommendation device according to an embodiment of the present invention;

[0031] Figure 8 This is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. Detailed Implementation

[0032] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0033] This invention provides a product recommendation method that confirms the pointer information between head nodes and child nodes. The head node corresponds to the business scenario of user needs, and each node has a pointer list. Different pointer information in the pointer list represents different judgment directions. Therefore, by combining the relationship between the head node and child nodes and the judgment direction with user needs, the effect of product recommendation can be achieved.

[0034] According to an embodiment of the present invention, a product recommendation method embodiment is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0035] This embodiment provides a product recommendation method, which can be used for the product recommendation described above. Figure 1 This is a flowchart of a product recommendation method according to an embodiment of the present invention, such as... Figure 1 As shown, the process includes the following steps:

[0036] Step S101: Obtain first user demand information; determine business scenarios based on first user demand information; filter out head nodes corresponding to business scenarios from the node pool; the node pool includes multiple head nodes corresponding to multiple business scenarios.

[0037] Among them, the first user need is the user's overall need for product recommendations. The first user need contains several key points. For example, if the first user need is a new customer moving, the rented house has a bathroom, and they have participated in promotional activities, then the business scenario corresponding to this first user need is moving, and the key points are new customer, bathroom, and participation in promotional activities.

[0038] In some optional implementations, the nodes in the node pool include multiple head nodes and multiple child nodes. Each node includes a node name, the corresponding function, the node's level, whether it is a head node, and pointer information.

[0039] In this embodiment of the invention, the node pool includes all head nodes and all child nodes. Each node includes a node name (node), a corresponding function (cmd), the node's level (lever), whether it is a head node (headNode), and pointer information. The node name serves as the node's identifier; different nodes have different names to distinguish them. The corresponding function is used for matching and selecting based on user requirements. The node's level allows nodes at the same level to process asynchronously in parallel. Whether a node is a head node determines whether it is the head node in a recommendation chain. The node's pointer information includes the direction of judgment (point) and the corresponding child node (next), and also whether it is a leaf node (leaf).

[0040] Step S102: Obtain the first pointer list of the head node. The first pointer list is a list of multiple judgment directions corresponding to the head node.

[0041] In this embodiment of the invention, the first pointer list of the head node is a list composed of different judgment directions of the head node. For example, the head node is "Moving". For the head node "Moving", the judgment logic is to determine whether the customer is a new customer. There are two judgment directions: one is that the customer is a new customer, and the other is that the customer is not a new customer. Therefore, the first pointer list of the head node is: the customer is a new customer, and the customer is not a new customer.

[0042] Step S103: Filter out the first pointer information that matches the first user requirement information from the first pointer list. The first pointer information includes the first judgment direction and the child node corresponding to the first judgment direction.

[0043] For example, if the first user demand information is: a new customer is moving and the rented house has a bathroom; and the first pointer list is: the customer is a new customer and the customer is not a new customer; then the first pointer information that matches the first user demand information is filtered out from the first pointer list, that is, the first judgment direction in the filtered first pointer information is that the customer is a new customer, and the child node corresponding to the first judgment direction is node 7.

[0044] Step S104: Determine the child node corresponding to the first judgment direction based on the first pointer information.

[0045] For example, based on the first judgment direction in the first pointer information, the customer is a new customer, and the child node corresponding to the first judgment direction is node 7, the child node is determined to be node 7.

[0046] Step S105: Determine whether the child node is a leaf node. A leaf node is the last node.

[0047] In some optional implementations, determining whether a child node is a leaf node includes: determining whether a preset field in the child node is a first preset character; if the preset field of the child node is the first preset character, then the child node is a leaf node; if the preset field of the child node is a second preset character, then the child node is not a leaf node.

[0048] The preset field can be a leaf field, with the first preset character being 'y' and the second preset character being 'n'. If the preset character of the leaf field is 'y', then the child node is a leaf node; if the preset character of the leaf field is 'n', then the child node is not a leaf node.

[0049] Step S106: If the child node is a leaf node, obtain the second pointer list of the leaf node; the second pointer list is a list of multiple judgment directions corresponding to the leaf node.

[0050] Step S107: Filter out the second pointer information that matches the first user's demand information from the second pointer list. The second pointer information includes the second judgment direction and the target product corresponding to the second judgment direction.

[0051] In this embodiment of the invention, for each leaf node, there is a corresponding judgment logic. The second pointer list includes different judgment directions, and different judgment directions correspond to different recommended products. For example, if the judgment logic of the leaf node is to determine whether it has participated in a promotional activity, then participating in a promotional activity corresponds to the first product, and not participating in a promotional activity corresponds to the second product. If the first user demand information includes participating in a promotional activity, then the second pointer information indicates that the user has participated in a promotional activity, and the corresponding target product is the first product.

[0052] Step S108: Determine the target product based on the second pointer information.

[0053] The product recommendation method provided in this embodiment obtains first user demand information, determines a business scenario based on the first user demand information, filters the head node corresponding to the business scenario from the node pool, obtains a first pointer list of the head node, the first pointer list includes multiple pointer information, each pointer information corresponds to a different judgment direction, filters the first pointer information that matches the first user demand information from the first pointer list, the first pointer information includes a first judgment direction and the child node corresponding to the first judgment direction, and determines the child node corresponding to the first judgment direction based on the first pointer information. This embodiment of the invention determines the head node based on the first user demand information, and determines the child node, that is, the next-level node of the head node, based on the first user demand and the different pointer information of the head node. Judging the child node based on the demand information makes the selection of child nodes more accurate. After determining the child node, it is determined whether the child node is a leaf node. A leaf node is the last node. If the child node is a leaf node, the next-level node of the child node is not searched. The second pointer list of the leaf node is used to filter the second pointer information that matches the first user demand information, and the target product is determined based on the second pointer information. This embodiment of the invention, after determining that the child node is a leaf node, determines the target product based on the leaf node and the first user demand information, so that the target product meets the first user demand information. Compared with the redesign and development of various recommendation schemes in related technologies, the embodiments of the present invention have multiple pointer information for each node to meet different user needs. When a new user need is received, there is no need to redesign and develop a new recommendation link, so there will be no logical duplication, saving resources and improving the efficiency of product recommendation.

[0054] This embodiment provides a product recommendation method, which can be used for the product recommendation described above. Figure 2 This is a flowchart of another product recommendation method according to an embodiment of the present invention, such as... Figure 2 As shown, the process includes the following steps:

[0055] Step S201: Obtain the first user requirement information; determine the business scenario based on the first user requirement information, and filter out the head node corresponding to the business scenario from the node pool. The node pool includes multiple head nodes corresponding to multiple business scenarios. For details, please refer to [link to details]. Figure 1 Step S101 of the illustrated embodiment will not be described again here.

[0056] In some optional embodiments, before obtaining the first user requirement information, the method further includes: when creating a node, configuring the relationship between the node and its parent and child nodes, whether the node is a head node, and whether the node is a leaf node.

[0057] In this embodiment of the invention, when creating nodes, the relationship between upper-level nodes and lower-level nodes is maintained, and each node is configured to be a head node or a leaf node on different links, so that the nodes are linked together in a chain, which can meet the needs of different users. When a new user request is received, the target product that meets the user's request is directly selected according to the nodes in the node pool, without the need to redesign and develop a new recommendation link, thus avoiding logical duplication, saving resources, and improving the efficiency of product recommendation. When it is necessary to add, delete, or adjust nodes, only the configuration needs to be modified, without redeveloping new code, saving R&D resources.

[0058] Step S202: Obtain the first pointer list of the head node. The first pointer list is a list of multiple judgment directions corresponding to the head node. For details, please refer to [link to relevant documentation]. Figure 1 Step S102 of the illustrated embodiment will not be described again here.

[0059] In some optional embodiments, if multiple child nodes corresponding to multiple determination directions in the first pointer list are the same child node, then the child node is renamed.

[0060] In this embodiment of the invention, if multiple child nodes corresponding to multiple judgment directions in the first pointer list are the same child node, although the nodes they point to are the same, that is, when the same child node appears repeatedly, the target products recommended by the corresponding leaf nodes are different. Therefore, the child node is renamed to distinguish them.

[0061] Step S203: Filter the first pointer list to find the first pointer information that matches the first user requirement information. The first pointer information includes the first judgment direction and the child nodes corresponding to the first judgment direction. See details below. Figure 1 Step S103 of the illustrated embodiment will not be described again here.

[0062] Step S204: Determine the child node corresponding to the first judgment direction based on the first pointer information. For details, please refer to [link to relevant documentation]. Figure 1 Step S104 of the illustrated embodiment will not be described again here.

[0063] Step S205: Determine if the child node is a leaf node. A leaf node is the last node. For details, please refer to [link to relevant documentation]. Figure 1 Step S105 of the illustrated embodiment will not be described again here.

[0064] Step S206: If the child node is a leaf node, obtain the second pointer list of the leaf node; the second pointer list is a list of multiple judgment directions corresponding to the leaf node. For details, please refer to... Figure 1 Step S106 of the illustrated embodiment will not be described again here.

[0065] Step S207: Filter the second pointer list to find second pointer information that matches the first user's needs information. The second pointer information includes a second judgment direction and the target product corresponding to that second judgment direction. See details below. Figure 1 Step S107 of the illustrated embodiment will not be described again here.

[0066] Step S208: Determine the target product based on the second pointer information. For details, please refer to [link / reference]. Figure 1 Step S108 of the illustrated embodiment will not be described again here.

[0067] Step S209: If the child node is not a leaf node, obtain the third pointer list of the child node. The third pointer list is a list of multiple judgment directions corresponding to the child node.

[0068] Step S2010: Filter out the third pointer information that matches the first user requirement information from the third pointer list. The third pointer information includes the third judgment direction and the child node corresponding to the third judgment direction.

[0069] Step S2011: Determine the child node corresponding to the third judgment direction based on the third pointer information, and determine whether the child node is a leaf node until the child node is a leaf node.

[0070] like Figure 3 The diagram shows the overall process of product recommendation. First, recommendation rules are generated based on the product prototype diagram, which is to say, a recommendation tree is generated. The recommendation prototype diagram is abstracted into JSON data format to obtain the recommendation rules. The head node is found in the node pool according to the recommendation rules. The node pool stores n nodes, namely the first node, the second node, the third node, and so on up to the nth node. The pointer list of the head node is obtained. The next-level node is located according to the pointer list. It is determined whether the next-level node is a leaf node. If it is a leaf node, the target product is determined based on the leaf node. If it is not a leaf node, the next-level node is filtered in the node pool until a leaf node is found, forming a complete recommendation chain.

[0071] In this embodiment of the invention, when it is determined that a child node is not a leaf node, a third pointer list corresponding to the child node is obtained. The third pointer list is filtered to select the third pointer information that matches the first user demand information. The child node corresponding to the third judgment direction is determined according to the third pointer information. It is then determined whether the child node is a leaf node, until the child node is a leaf node, which is the last node. The target product is determined according to the leaf node. This embodiment of the invention starts from the head node and matches and selects according to the user demand information level by level until the child node is a leaf node, thus obtaining the target product. The obtained target product better meets the user demand.

[0072] This embodiment provides a product recommendation method, which can be used for the product recommendation described above. Figure 4This is a flowchart of another product recommendation method according to an embodiment of the present invention, such as... Figure 4 As shown, the process includes the following steps:

[0073] Step S401: Obtain multiple second user requirement information.

[0074] This involves simultaneously acquiring multiple sets of secondary user demand information, matching and processing these multiple sets of secondary user demand information, thereby improving the efficiency of product recommendation.

[0075] Step S402: Obtain the application's configuration information and enable product recommendation based on the application's configuration information.

[0076] The application's configuration information includes processing card balance, enabling product recommendations, and processing available plans, all of which are handled in parallel.

[0077] Step S403: Query the recommendation tree based on multiple business scenarios in multiple second user demand information. The recommendation tree includes multiple nodes corresponding to multiple business scenarios.

[0078] In embodiments of the present invention, such as Figure 5 The diagram shows the structure of a recommendation tree. The recommendation tree includes multiple head nodes corresponding to multiple scenarios. The head nodes include moving, cleaning, and repair. The two pointers for moving are node 1 and node 2, with node 2 being a leaf node. The child node corresponding to node 1 is node 8, which is also a leaf node. The two pointers for cleaning are node 3 and node 4, with node 4 being a leaf node. The child node corresponding to node 3 is node 9, which is also a leaf node. The two pointers for repair are node 5 and node 6, with node 5 being a leaf node. The child node corresponding to node 6 is node 10, which is also a leaf node.

[0079] In this embodiment of the invention, multiple business scenarios are queried based on multiple second user demand information, such as... Figure 5 The recommendation tree shown.

[0080] Step S404: Determine multiple head nodes based on the recommendation tree and process multiple head nodes in parallel.

[0081] In this embodiment of the invention, since the recommendation processing logic is numerous and complex, synchronously processing each node in the recommendation chain would be time-consuming. To improve the recommendation response speed, nodes at the same level are processed asynchronously in batches. If a node does not depend on the judgment results of other nodes and can determine the desired result entirely from the front-end input parameters, then that node is a first-level node, and the head node is a first-level node. If a node depends on the judgment results of other nodes, then that node is a second-level node, and so on for subsequent levels. Since nodes at the same level are independent of each other, when batch processing nodes at a level, these nodes can be processed asynchronously, which greatly reduces the time consumption.

[0082] Step S405: Determine the multiple child nodes corresponding to the multiple head nodes based on the multiple head nodes.

[0083] In this process, multiple head nodes are used to determine different pairs of child nodes corresponding to each head node.

[0084] Step S406: Determine whether the hierarchy of multiple child nodes has changed.

[0085] Step S407: If there are no changes, obtain the execution results of multiple child nodes.

[0086] Step S408: Obtain the lower-level nodes of multiple child nodes based on the execution result.

[0087] The process involves determining whether the hierarchy of multiple child nodes has changed. If it has not changed, it means that the multiple child nodes have completed execution. The execution results of the multiple child nodes are then obtained, and the lower-level nodes of the multiple child nodes are obtained based on the execution results.

[0088] Step S409: Determine whether the lower-level nodes of multiple child nodes are leaf nodes.

[0089] Step S4010: If the lower-level nodes of multiple child nodes are leaf nodes, then determine that the product corresponding to the leaf node is the target product.

[0090] In step S4011, if there are any changes, determine whether the execution of the multiple head nodes corresponding to the multiple child nodes has ended.

[0091] Step S4012: If the execution is complete, process multiple child nodes in parallel.

[0092] In step S4013, if the process has not finished, wait for multiple head nodes to finish executing and process multiple child nodes in parallel.

[0093] The process involves determining whether the hierarchy of multiple child nodes has changed. If it has changed, it means that multiple child nodes have not finished executing. It also involves determining whether the multiple head nodes corresponding to the multiple child nodes have finished executing. If they have finished executing, the process involves processing multiple child nodes in parallel. If they have not finished executing, the process involves waiting for the multiple head nodes to finish executing and then processing the multiple child nodes in parallel.

[0094] like Figure 6 The diagram shows the target product recommendation logic flowchart. After starting, multiple user demand information is obtained. Based on this information, multiple business scenarios are determined. For example, business scenarios include cleaning, repair, housekeeping, and moving. The application's configuration information is obtained, including processing card balance, enabling product recommendations, and processing available packages. These three are processed in parallel. Product recommendations are enabled based on the application's configuration information. The recommendation tree is queried based on the multiple business scenarios from the user demand information. Multiple head nodes corresponding to the multiple business scenarios are obtained from the recommendation tree. The first-level nodes are processed in parallel. Recursion begins. The level of the current recursive node is determined. It is checked whether the levels of multiple child nodes have changed. If they have changed, it is checked whether the upper-level node has finished executing. If it has, the lower-level node is processed in parallel. If it has not finished, the lower-level node is processed in parallel after the upper-level node has finished executing. If the levels of multiple child nodes have not changed, the execution result of the current level node is obtained. The lower-level node is obtained based on the execution result. It is checked whether the lower-level node is a leaf node. If it is a leaf node, the recursion ends. If it is not a leaf node, the recursion continues to the next level until a leaf node is found.

[0095] In this embodiment of the invention, multiple second user demand information and application configuration information are obtained. Product recommendation is initiated based on the application configuration information. A recommendation tree is queried based on multiple business scenarios within the multiple second user demand information. Multiple head nodes are determined based on the recommendation tree, and these head nodes are processed in parallel. This embodiment of the invention achieves batch asynchronous processing of nodes at the same level, improving the efficiency of product recommendation and saving time. Multiple child nodes corresponding to the multiple head nodes are determined based on the multiple head nodes. It is determined whether the level of the multiple child nodes has changed. If not, the execution results of the multiple child nodes are obtained. This embodiment of the invention also processes child nodes at the same level in batches asynchronously. The lower-level nodes of the multiple child nodes are obtained based on the execution results. It is determined whether the lower-level nodes of the multiple child nodes are leaf nodes. If the lower-level nodes of the multiple child nodes are leaf nodes, the product corresponding to the leaf node is determined to be the target product. If the level has changed, it is determined whether the multiple head nodes corresponding to the multiple child nodes have finished executing. If they have finished, the multiple child nodes are processed in parallel. If they have not finished, the process waits for the multiple head nodes to finish executing, and then processes the multiple child nodes in parallel. This parallel processing saves time and improves the efficiency of product recommendation. Compared with the redesign and development of various recommendation schemes in related technologies, the embodiments of the present invention have multiple pointer information for each node to meet different user needs. When a new user need is received, there is no need to redesign and develop a new recommendation link, so there will be no logical duplication, saving resources and improving the efficiency of product recommendation.

[0096] This embodiment also provides a product recommendation device for implementing the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0097] This embodiment provides a product recommendation device, such as... Figure 7 As shown, it includes:

[0098] The head node determination module 701 is used to obtain the first user requirement information; determine the business scenario based on the first user requirement information; and filter the head node corresponding to the business scenario from the node pool. The node pool includes multiple head nodes corresponding to multiple business scenarios.

[0099] The first pointer list acquisition module 702 is used to acquire the first pointer list of the head node. The first pointer list is a list of multiple judgment directions corresponding to the head node.

[0100] The first pointer information matching module 703 is used to filter out the first pointer information that matches the first user requirement information from the first pointer list. The first pointer information includes a first judgment direction and the child node corresponding to the first judgment direction.

[0101] The child node confirmation module 704 is used to determine the child node corresponding to the first judgment direction based on the first pointer information.

[0102] The leaf node determination module 705 is used to determine whether a child node is a leaf node. A leaf node is the last node.

[0103] The second pointer list acquisition module 706 is used to acquire the second pointer list of the leaf node based on the child node being a leaf node; the second pointer list is a list of multiple judgment directions corresponding to the leaf node.

[0104] The second pointer information matching module 707 is used to filter out the second pointer information that matches the first user demand information from the second pointer list. The second pointer information includes the second judgment direction and the target product corresponding to the second judgment direction.

[0105] The target product determination module 708 is used to determine the target product based on the second pointer information.

[0106] Specifically, the aforementioned product recommendation device also includes:

[0107] The third pointer list acquisition module is used to obtain the third pointer list of a child node if the child node is not a leaf node. The third pointer list is a list of multiple judgment directions corresponding to the child node.

[0108] The third pointer information matching module is used to filter out the third pointer information that matches the first user requirement information from the third pointer list. The third pointer information includes the third judgment direction and the child node corresponding to the third judgment direction.

[0109] The leaf node confirmation module is used to determine the child node corresponding to the third judgment direction based on the third pointer information, and to determine whether the child node is a leaf node until the child node is a leaf node.

[0110] Specifically, the leaf node determination module 705 mentioned above includes:

[0111] The field judgment unit is used to determine whether the preset field in the child node is the first preset character. If the preset field of the child node is the first preset character, then the child node is a leaf node. If the preset field of the child node is the second preset character, then the child node is not a leaf node.

[0112] Further functional descriptions of the above modules and units are the same as those in the corresponding embodiments described above, and will not be repeated here.

[0113] In this embodiment, the product recommendation device is presented in the form of a functional unit. Here, a unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0114] This invention also provides a computer device having the above-described features. Figure 7 The product recommendation device shown.

[0115] Please see Figure 8 , Figure 8 This is a schematic diagram of the structure of a computer device provided in an optional embodiment of the present invention, such as... Figure 8 As shown, the computer device includes one or more processors 810, memory 820, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The components communicate with each other via different buses and can be mounted on a common motherboard or otherwise installed as needed. The processors can process instructions executed within the computer device, including instructions stored in or on memory to display graphical information of a GUI on external input / output devices (such as display devices coupled to the interfaces). In some alternative implementations, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple computer devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). Figure 8 Take the 810 processor as an example.

[0116] The processor 810 may be a central processing unit, a network processor, or a combination thereof. The processor 810 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GPA), or any combination thereof.

[0117] The memory 820 stores instructions executable by at least one processor 810 to cause the at least one processor 810 to perform the method shown in the above embodiments.

[0118] The memory 820 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the computer device. Furthermore, the memory 820 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory 820 may optionally include memory remotely located relative to the processor 810, and these remote memories may be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0119] The memory 820 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid-state drive; the memory 820 may also include a combination of the above types of memory.

[0120] The computer device also includes a communication interface 830 for communicating with other devices or communication networks.

[0121] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code, which, when accessed and executed by the computer, processor, or hardware, implements the methods shown in the above embodiments.

[0122] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A product recommendation method, characterized in that, The method includes: Obtain first user demand information; determine business scenarios based on the first user demand information; filter out the head nodes corresponding to the business scenarios from the node pool, wherein the node pool includes multiple head nodes corresponding to multiple business scenarios respectively; Obtain the first pointer list of the head node, wherein the first pointer list is a list of multiple judgment directions corresponding to the head node; The first pointer information that matches the first user requirement information is filtered out from the first pointer list. The first pointer information includes a first judgment direction and a child node corresponding to the first judgment direction. The child node corresponding to the first judgment direction is determined based on the first pointer information; Determine whether the child node is a leaf node, where the leaf node is the last node; If the child node is a leaf node, obtain the second pointer list of the leaf node; the second pointer list is a list of multiple judgment directions corresponding to the leaf node; The second pointer list is filtered to select the second pointer information that matches the first user demand information. The second pointer information includes a second judgment direction and the target product corresponding to the second judgment direction. The target product is determined based on the second pointer information.

2. The method according to claim 1, characterized in that, The method further includes: If the child node is not a leaf node, obtain the third pointer list of the child node; the third pointer list is a list of multiple judgment directions corresponding to the child node; The third pointer information that matches the first user requirement information is filtered out from the third pointer list. The third pointer information includes a third judgment direction and the child node corresponding to the third judgment direction. Based on the third pointer information, determine the child node corresponding to the third judgment direction, and determine whether the child node is a leaf node, until the child node is a leaf node.

3. The method according to claim 1 or 2, characterized in that, The nodes in the node pool include multiple head nodes and multiple child nodes. Each node includes a node name, the corresponding function, the node's level, whether it is a head node, and pointer information.

4. The method according to claim 1 or 2, characterized in that, The step of determining whether the child node is a leaf node includes: Determine whether the preset field in the child node is the first preset character; If the preset field of the child node is the first preset character, then the child node is the leaf node; If the preset field of the child node is a second preset character, then the child node is not the leaf node.

5. The method according to claim 1 or 2, characterized in that, Before obtaining the first user demand information, the method further includes: When creating a node, configure the relationship between the node and its parent and child nodes, whether the node is a head node, and whether the node is a leaf node.

6. The method according to claim 1 or 2, characterized in that, If the multiple child nodes corresponding to the multiple judgment directions in the first pointer list are the same child node, then the child node is renamed.

7. The method according to claim 1 or 2, characterized in that, The method further includes: Obtain multiple second-user demand information; Obtain the application's configuration information and enable product recommendations based on the application's configuration information; A recommendation tree is queried based on multiple business scenarios from the multiple second user demand information, and the recommendation tree includes multiple nodes corresponding to multiple business scenarios; Multiple head nodes are determined based on the recommendation tree, and the multiple head nodes are processed in parallel. Based on the multiple head nodes, determine the multiple child nodes corresponding to the multiple head nodes; Determine whether the hierarchy of the multiple child nodes has changed; if not, obtain the execution results of the multiple child nodes. Based on the execution result, obtain the lower-level nodes of the multiple child nodes; Determine whether the lower-level node of the multiple child nodes is a leaf node; If the lower-level nodes of the multiple child nodes are leaf nodes, then the product corresponding to the leaf node is determined to be the target product.

8. The method according to claim 7, characterized in that, The determination of whether the hierarchy of the multiple child nodes has changed also includes: If there are any changes, it is determined whether the execution of the multiple head nodes corresponding to the multiple child nodes has ended. If the execution has ended, the multiple child nodes are processed in parallel. If the execution has not finished, wait for the multiple head nodes to finish executing, and then process the multiple child nodes in parallel.

9. A product recommendation device, characterized in that, The device includes: The head node determination module is used to obtain first user demand information; determine business scenarios based on the first user demand information; and filter out the head nodes corresponding to the business scenarios from the node pool, wherein the node pool includes multiple head nodes corresponding to multiple business scenarios respectively. The first pointer list acquisition module is used to acquire the first pointer list of the head node, wherein the first pointer list is a list of multiple judgment directions corresponding to the head node; The first pointer information matching module is used to filter out first pointer information that matches the first user requirement information from the first pointer list; the first pointer information includes a first judgment direction and a child node corresponding to the first judgment direction. The child node confirmation module is used to determine the child node corresponding to the first judgment direction based on the first pointer information. The leaf node determination module is used to determine whether the child node is a leaf node, where the leaf node is the last node. The second pointer list acquisition module is used to acquire a second pointer list of the leaf node based on the fact that the child node is a leaf node. The second pointer list is a list of multiple judgment directions corresponding to the leaf node. The second pointer information matching module is used to filter out the second pointer information that matches the first user demand information from the second pointer list. The second pointer information includes a second judgment direction and the target product corresponding to the second judgment direction. The target product determination module is used to determine the target product based on the second pointer information.

10. A computer device, characterized in that, include: A memory and a processor are communicatively connected, the memory storing computer instructions, and the processor executing the computer instructions to perform the product recommendation method according to any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing a computer to perform the product recommendation method according to any one of claims 1 to 8.

Images