Information processing method and device, electronic equipment and storage medium
Through the analysis of the sales and historical interactive data of the sales of goods in the field of e -commerce, it is determined that the target ethnic group with a good sales momentum in the future, solve the problem that it is difficult for merchants to accurately predict the sales of the product, and improve the effect of the operating strategy.
Patent Information
- Application Number
- CN202310934440.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-07-27
- Publication Date
- 2025-01-28
AI Technical Summary
In the e-commerce field, it is difficult for merchants to accurately predict the sales of various products in the future, resulting in poor results in operational strategy formulation and risk avoidance strategies.
By obtaining the reference object, determine the multiple target objects associated with it, the clustering class is obtained to obtain the object group, and the historical interaction data of the target ethnic group is determined, and the target object group is determined in the object group based on these data. The amount of interaction meets the preset conditions.
In the case of not knowing some of the objects, start with the reference objects for in -depth excavation, determine multiple object groups, and predict the target group with better development momentum, which improves the accuracy of sales forecasts.
Smart Images
Figure CN119379339A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the field of data processing technology, and in particular to an information processing method, device, electronic device and storage medium. Background Art
[0002] With the continuous development of Internet technology, users use applications to obtain information. Application operators decide future operation strategies based on the users' use of applications. In this case, accurate prediction of the future is particularly important.
[0003] For example, in the field of e-commerce, in order to ensure the continued healthy development of stores or platforms, merchants or platforms need to predict the sales of various commodities in the future period in advance, and formulate commodity operation strategies or risk avoidance strategies based on the prediction results. Therefore, how to accurately predict the sales of various commodities in the future period is an urgent problem to be solved. Summary of the invention
[0004] In order to solve the above technical problems or at least partially solve the above technical problems, the present disclosure provides an information processing method, device, electronic device and storage medium.
[0005] In a first aspect, the present disclosure provides an information processing method, comprising:
[0006] Get the reference object;
[0007] Determine a plurality of target objects associated with the reference object; the type of the target objects is a first type;
[0008] Clustering the multiple target objects to obtain multiple object groups;
[0009] Determining historical interaction data for each of the object groups;
[0010] Based on the historical interaction data of each of the object groups, a target object group is determined from the multiple object groups, and the total interaction volume of the target object group in a target time period meets a preset condition; the target time period is after the time when the information processing method is executed this time.
[0011] In a second aspect, the present disclosure further provides an information processing device, including:
[0012] A reference object acquisition module, used for acquiring a reference object;
[0013] A target object determination module, used to determine a plurality of target objects associated with the reference object; the type of the target objects is a first type;
[0014] A clustering module, used for clustering the multiple target objects to obtain multiple object groups;
[0015] A historical interaction data determination module, used to respectively determine the historical interaction data of each of the object groups;
[0016] The target object group determination module is used to determine a target object group from the multiple object groups based on the historical interaction data of each of the object groups, wherein the total interaction volume of the target object group in a target time period meets a preset condition; the target time period is after the moment of executing the information processing method this time.
[0017] In a third aspect, the present disclosure further provides an electronic device, the electronic device comprising:
[0018] one or more processors;
[0019] A storage device for storing one or more programs;
[0020] When the one or more programs are executed by the one or more processors, the one or more processors implement the information processing method as described above.
[0021] In a fourth aspect, the present disclosure further provides a computer-readable storage medium having a computer program stored thereon, which implements the information processing method as described above when the program is executed by a processor.
[0022] Compared with the prior art, the technical solution provided by the embodiments of the present disclosure has the following advantages:
[0023] The technical solution provided by the embodiment of the present disclosure obtains a reference object by setting; determines multiple target objects associated with the reference object; the type of the target object is the first type; clusters the multiple target objects to obtain multiple object groups; respectively determines the historical interaction data of each of the object groups; based on the historical interaction data of each of the object groups, determines a target object group among the multiple object groups, the total interaction volume of the target object group within a target time period meets a preset condition; the target time period is after the moment of executing the information processing method this time. Under the premise that it is not clear which object groups there are, the technical solution provided by the embodiment of the present disclosure can be used to start with the reference object, conduct in-depth mining, and then determine multiple object groups, and predict object groups with better development momentum. BRIEF DESCRIPTION OF THE DRAWINGS
[0024] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.
[0025] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.
[0026] Figure 1 A flowchart of an information processing method provided by an embodiment of the present disclosure;
[0027] Figure 2 A method for implementing the present disclosure is provided in an embodiment Figure 1 Flow chart of the method of S120;
[0028] Figure 3 is a schematic diagram of the structure of an information processing device in an embodiment of the present disclosure;
[0029] Figure 4 It is a structural schematic diagram of an electronic device in an embodiment of the present disclosure. DETAILED DESCRIPTION
[0030] In order to more clearly understand the above-mentioned objectives, features and advantages of the present disclosure, the scheme of the present disclosure will be further described below. It should be noted that the embodiments of the present disclosure and the features in the embodiments can be combined with each other without conflict.
[0031] In the following description, many specific details are set forth to facilitate a full understanding of the present disclosure, but the present disclosure may also be implemented in other ways different from those described herein; it is obvious that the embodiments in the specification are only part of the embodiments of the present disclosure, rather than all of the embodiments.
[0032] Figure 1 This is a flowchart of an information processing method provided in an embodiment of the present disclosure. The method can be executed by an information processing device, which can be implemented in software and / or hardware, and can be configured in an electronic device, such as a terminal or a server. The terminal specifically includes but is not limited to a smart phone, a PDA, a tablet computer, a wearable device with a display screen, a desktop computer, a laptop computer, an all-in-one machine, a smart home device, etc.
[0033] like Figure 1 As shown, the method may specifically include:
[0034] S110: Acquire a reference object.
[0035] The object may be, for example, a real thing, a service, or a virtual object. The reference object is a pre-given object. The present application does not limit the specific content of the reference object. In practice, the reference object may be determined based on the content to be predicted. The reference object is the entry point for prediction.
[0036] For example, in an e-commerce scenario, suppose you want to predict what type of goods will become hot-selling goods in a certain period of time in the future. The reference object may include at least one of the following: user, merchant, brand, store, and product. In an actual scenario, the reference object may be specified by the subject (such as a merchant or e-commerce platform) who wants to know what type of goods will become hot-selling goods.
[0037] S120: Determine a plurality of target objects associated with the reference object; the type of the target objects is a first type.
[0038] The target object is an object that has an association relationship with the reference object. The specific relationship between the target object and the reference object is not limited in this application.
[0039] The first type is pre-specified. In practice, it can be determined according to the content that needs to be predicted. For example, suppose you want to predict what type of goods will become hot-selling goods in a certain period of time in the future. The first type is goods.
[0040] The type of the target object may be the same as or different from the type of the reference object. For example, suppose you want to use influencers as a starting point to predict what type of goods will become hot-selling goods in a certain period of time in the future. The type of the reference object is the user, and the type of the target object is the product.
[0041] In practice, the association relationship between the target object and the reference object can be a direct association relationship or an indirect association relationship.
[0042] Taking the e-commerce scenario as an example, if the association relationship between the target object and the reference object is a direct association relationship, the direct association relationship can be similarity, exposure, sale, like, favorite, forward, operation, agent, visit duration, repeated visit, transaction, click, add to cart, favorite, order, return or repurchase, etc. For example, if the reference object is user a and the target object is product 1, the direct association relationship between the target object and the reference object is that user a has purchased product 1. For another example, if the reference object is merchant c and the target object is product 2, the direct association relationship between the target object and the reference object is that merchant c sells product 2.
[0043] The association relationship between the target object and the reference object is an indirect association relationship, which means that there is at least one intermediate object between the target object and the reference object. The association relationship link between the target object and the reference object can be formed through the direct association relationship between the target object and the intermediate object, the direct association relationship between the intermediate objects and the intermediate objects, and the direct association relationship between the intermediate objects and the reference object.
[0044] Exemplarily, if there is only one intermediate object, the indirect association relationship between the target object and the reference object means that there is a direct association relationship between the target object and the intermediate object, and there is a direct association relationship between the intermediate object and the reference object.
[0045] In the e-commerce scenario, the intermediate object may include at least one of the following: user, merchant, brand, store, and commodity. The direct association relationship between the target object and the intermediate object, the direct association relationship between the intermediate objects, and the direct association relationship between the intermediate objects and the reference object may be similarity, exposure, sale, like, collection, forwarding, operation, agency, visit duration, repeated visit, transaction, click, add to cart, collection, order, return, or repurchase, etc.
[0046] Exemplarily, if the reference object is user a and the target object is product 1, the association relationship between user a and product 1 is an indirect association relationship. The indirect association relationship can be that user b, who is similar to user a, has purchased product 1, wherein user b is an intermediate object. For another example, if the reference object is merchant c and the target object is product 2, the association relationship between merchant c and product 2 is an indirect association relationship. The indirect association relationship can be that user d, who has purchased product 5 sold by merchant c, has also purchased product 2, wherein product 5 and user d are both intermediate objects. Alternatively, the indirect association relationship can be that product 6 sold by merchant c is a similar model to product 2, wherein product 6 is an intermediate object.
[0047] The essence of this step is to take the reference object as the starting point and mine the target object that has an association relationship with the reference object.
[0048] There are many ways to implement this step, and this application does not limit this. For example, see Figure 2 , the implementation method of this step includes:
[0049] S121. Obtain the target knowledge graph.
[0050] The target knowledge graph is a pre-built database for querying target objects corresponding to reference objects. Triples are the basic units of the target knowledge graph. A triple consists of two objects and the relationship between the two objects. That is, a triple can be expressed as "object 1-relationship-object 2".
[0051] This application does not limit the things that the two objects in the triplet refer to respectively. The two objects in the triplet can be objects of the same type or objects of different types. In the e-commerce scenario, the type of the object can be a user, a merchant, a brand, a store or a product, etc. The association between two objects includes exposure, likes, collections, visit duration, repeat visits, transactions, clicks, add-on purchases, collections, orders, returns or repeat purchases, etc. Exemplarily, the triplet can be expressed as "user-click-product", "user-collection-product", "user-order-product", "user-return-product", "user-collection-store", "user-repeat visit-store", etc.
[0052] S122. Using the reference object as a query condition, query is performed in the target knowledge graph to obtain multiple target objects associated with the reference object.
[0053] There are many methods for implementing this step, and this application does not limit this. Exemplarily, the target knowledge graph includes multiple triples and scores of each triple, and the triple includes two objects and the association relationship between the two objects; the type of one of the objects in at least some of the triples is the first type; the implementation method of this step includes: using the reference object as the query condition, querying in the target knowledge graph, obtaining multiple candidate objects and a query path from the reference object to each candidate object; based on the scores of the triples included in the query path, determining the relevance value of each candidate object with the reference object, and taking the candidate object whose relevance value is greater than the set threshold as the target object.
[0054] In practice, the association relationship between two objects in a triple is diverse; different association relationships determine different degrees of closeness between two objects. The score of a triple is used to reflect the closeness between the two objects it includes. Optionally, the score of a triple is determined according to the association relationship between the two objects. Exemplarily, assume that there are the following triples: "user-collection-product", "user-order-product" and "user-return-product". The score of "user-collection-product" is higher than the score of "user-return-product", and the score of "user-order-product" is higher than the score of "user-collection-product".
[0055] The candidate object is an object that has an association relationship with the reference object obtained by querying the target knowledge graph. The type of the candidate object is the same as the type of the target object, which is the first type.
[0056] In practice, due to different association relationships, the closeness between the reference object and the candidate object is different. The candidate object includes an object with a high degree of closeness to the reference object and an object with a low degree of closeness to the reference object. The target object is a candidate object with a high degree of closeness to the reference object.
[0057] In practice, when querying a reference object as a query condition, a query in the target knowledge graph may use only one triple to obtain a candidate object, or two or more triples may be used to obtain a candidate object. The query path from a reference object to a candidate object refers to a multi-hop reasoning path formed by all the triples that need to be used, with the reference object as the reasoning starting point and the candidate object as the reasoning end point.
[0058] There are many specific implementation methods for “determining the relevance value of each candidate object with the reference object based on the score of the triples included in the query path”, and this application does not limit this. Exemplarily, “determining the relevance value of each candidate object with the reference object based on the score of the triples included in the query path” includes determining the sum of the scores of each triple in each query path as the relevance value of the candidate object with the reference object obtained by the query path.
[0059] In one embodiment, the types of objects include a first type, a second type, and a third type; in the target knowledge graph, for any triple, the type of one object is the second type, and the type of the other object is the first type or the third type; the type of the reference object is the first type, the second type, or the third type; taking the reference object as the query condition, querying in the target knowledge graph to obtain multiple candidate objects and a query path from the reference object to each candidate object, including: taking the reference object as the query condition, performing a first query in the target knowledge graph to obtain multiple objects of the second type; taking each of the multiple objects of the second type as the query condition, performing a secondary query in the target knowledge graph to obtain multiple candidate objects of the first type and a query path from the reference object to each candidate object.
[0060] Take the example of predicting what style of dress will become a hot-selling product in a certain period of time in the future in an e-commerce scenario. The first type is the product type, the second type is the user type, and the third type is other types except the product type and the user type. Specifically, the third type includes merchants, brands, and stores. Assuming that the reference object is 200 stores selling fashionable dresses, each of the 200 stores is used as a query condition, and the first query is performed in the target knowledge graph to obtain users who recognize these stores ("recognition" can be expressed as users who have purchased goods sold by the store or have collected the store, etc.). Then, each of these users is used as a query condition, and a second query is performed in the target knowledge graph to obtain the dresses purchased by these users. Since experts can see through fashion trends earlier, this setting is to use the reference object to first find experts who can see through fashion trends, and then obtain dresses that can be included in the consideration range. The purpose of consideration is to determine whether it will become a hot-selling product in a certain period of time in the future.
[0061] By setting the reference object as the query condition, the first query is performed in the target knowledge graph to obtain multiple objects of the second type; each of the multiple objects of the second type is used as the query condition, and a second query is performed in the target knowledge graph to obtain multiple candidate objects of the first type and the query path from the reference object to each candidate object. In essence, when querying, no matter what type the reference object is, the second type of object associated with the reference object is obtained first, and then the second type of object is used as the condition for the second query. In this way, the number of triples included in the query path from the reference object to the candidate object can be fully reduced, and the query efficiency can be improved.
[0062] It should be noted that if the reference object is a user, the process of performing the first query in the target knowledge graph with the reference object as the query condition is to find other users who are similar to the user referred to by the reference object (such as users who have purchased the same product together, and users who have collected the same store together).
[0063] S130 , clustering multiple target objects to obtain multiple object groups.
[0064] Usually, a target object often has multiple features. The purpose of this step is to cluster target objects with the same feature into one category as an object group.
[0065] It should be noted that, in practice, a target object may belong to only one object group or may belong to multiple object groups. For example, a dress includes both ruffles and lace decorations. It belongs to both the ruffle dress group and the lace dress group.
[0066] The essence of this step is to analyze the characteristics of each target object, determine which object group or groups each target object belongs to, and then summarize the object groups corresponding to each target object to obtain multiple non-repeating object groups. Non-repeating object groups refer to target objects in two object groups that are not completely the same or completely different.
[0067] S140 , respectively determining historical interaction data of each object group.
[0068] The historical interaction data of the object group refers to the interaction data formed by the user interacting with a target object in the object group before the information processing method is executed this time. In the e-commerce scenario, the historical interaction data may include historical order data, historical likes data, historical collection data, etc.
[0069] Still taking the e-commerce scenario as an example, the e-commerce platform sells multiple products, and the target objects are only a few of the products sold by the e-commerce platform. When any product sold by the e-commerce platform is sold, order data will be generated. The historical interaction data of the object group is the order data of the target object in the sales object group selected from the numerous order data.
[0070] Exemplarily, object group Y only includes target object 1, target object 2, and target object 3. In the historical interaction data, there are historical orders m, historical orders n, historical orders p, and historical orders q, where historical order m reflects the user's purchase of target object 1, historical order n reflects the user's purchase of target object 2, historical order p reflects the user's purchase of target object 3, and historical order q reflects the user's purchase of target object 4. Historical orders m, historical orders n, and historical orders p are historical interaction data of object group Y, and historical order q is not historical interaction data of object group Y.
[0071] In some embodiments, the historical interaction data of the object group mentioned in this step is interaction data formed during an observation period corresponding to the current moment.
[0072] Among them, the observation period corresponding to the current moment may be a preset time period before the current moment. The current moment refers to the moment when the information processing method is executed this time. Exemplarily, if the current moment is 13:00 on January 23, 2023, the observation period corresponding to the current moment is within 1 month before the current moment, that is, the time period from 13:00 on December 23, 2022 to 13:00 on January 23, 2023.
[0073] The essence of this step is to filter out the historical interaction data corresponding to each object group from all the historical interaction data according to the target objects included in each object group.
[0074] S150, determining a target object group from multiple object groups based on historical interaction data of each object group, wherein the total interaction volume of the target object group in a target period meets a preset condition; the target period is after the time of executing the information processing method this time.
[0075] The target period is a pre-specified period, and this application does not limit which period it specifically refers to. Exemplarily, the target period is the third month after the current moment. The current moment is the moment when the information processing method is executed this time. Exemplarily, if the current moment is 13:00 on January 23, 2023, the target period is 13:00 on April 23, 2023-13:00 on May 23, 2023.
[0076] The target object group is the prediction result. For example, if it is desired to predict what type of goods will become hot-selling goods in a certain period of time in the future, the target object group is a set of goods that may become hot-selling goods.
[0077] The preset conditions are used to measure whether an object group can be used as a judgment condition for prediction results. This application does not limit the specific content of the preset conditions. Exemplarily, the goods whose orders will surge during the target period are defined as hot-selling goods. Suppose you want to predict what type of goods will become hot-selling goods in a certain period in the future. Based on this goal, setting the preset conditions includes: Condition 1, specifying the volume of commodity orders for the object group within a historical observation period (such as the observation period when the order for the goods in the object group first appears) is X, and the estimated volume of commodity orders for the object group in the target period is more than twice that of X. Condition 2, the estimated volume of commodity orders for the object group in the target period is greater than or equal to 1000. Condition 3, the estimated growth rate of the commodity orders for the object group in the target period is greater than 0.
[0078] There are many implementation methods for this step, which are not limited by the subject of this application. Exemplarily, the specific implementation method of this step includes: based on the historical interaction data of each object group, respectively determining the historical interaction feature data corresponding to each object group; based on the historical interaction feature data corresponding to each object group, determining the target object group from multiple object groups.
[0079] The historical interaction feature data is the result of feature extraction and digitization of the historical interaction data of the object group. The specific content of the historical interaction feature data of the object of this application is not limited. Exemplarily, the historical interaction feature data includes first feature data and / or second feature data; the first feature data is used to describe the number of target objects included in the object group during the target observation period; the second feature data is the growth of the historical interaction data of the object group during the target observation period; the target observation period is earlier than the time when the information processing method is executed this time.
[0080] Among them, the target observation period can be a pre-specified period. Exemplarily, the target observation period is the observation period corresponding to the current moment, specifically the preset time period before the current moment. The current moment refers to the moment when the information processing method is executed this time. Exemplarily, if the current moment is 13:00 on January 23, 2023, the target observation period is within 1 month before the current moment, that is, the time period from 13:00 on December 23, 2022 to 13:00 on January 23, 2023.
[0081] Furthermore, it is defined that the number of target objects included in an object group during the observation period corresponding to the current moment is a first value. The number of objects involved in all historical transaction data during the observation period corresponding to the current moment is a second value. The first characteristic data is the ratio of the first value to the second value; the second characteristic data is the growth rate of the historical interaction data of the object group during the target observation period. The growth rate can be a year-on-year growth rate or a month-on-month growth rate.
[0082] For example, during the observation period corresponding to the current moment, 50,000 orders are formed, of which 500 orders correspond to the object group N. Since in practice there are situations where multiple people purchase the same item, and the same person purchases the same item multiple times, the 50,000 orders involve a total of 44,000 items, and the 500 orders corresponding to the object group N involve a total of 60 items. The first characteristic data is 60 / 44,000. The second indicator is the growth rate of the order volume of the target object included in the object group.
[0083] In one embodiment, optionally, based on the historical interaction feature data corresponding to each object group, a target object group is determined among multiple object groups, including: based on the historical interaction feature data corresponding to each object group, determining the prediction parameters corresponding to each object group; and taking the object group whose prediction parameters are greater than or equal to a set threshold as the target object group.
[0084] The prediction parameter is a parameter used to characterize the total interaction volume of the object group within the target period. The present application does not limit the specific implementation method of determining the prediction parameter corresponding to each object group based on the historical interaction feature data corresponding to each object group. For example,
[0085] Optionally, the prediction parameters are calculated as follows:
[0086] M=k 1 *A+k 2 *B+k 3 *C.
[0087] Among them, M is the prediction parameter, k 1 , k 2 , and k 3 is a constant, k 1 , k 2 , and k 3 Determined according to the length of the target period and the time interval between the target period and the current moment. A is the total order volume during the target observation period (including orders involving target objects and orders involving non-target objects). B is the first feature data. C is the second feature data.
[0088] The above technical solution obtains a reference object by setting; determines multiple target objects associated with the reference object; the type of the target object is the first type; clusters the multiple target objects to obtain multiple object groups; determines the historical interaction data of each object group respectively; determines the target object group from multiple object groups based on the historical interaction data of each object group, and the total interaction volume of the target object group in the target time period meets the preset conditions; the target time period is after the moment of executing the information processing method this time. Under the premise that it is not clear what object groups there are, the above technical solution can start with the reference object and conduct in-depth mining to determine multiple object groups and predict object groups with better development momentum.
[0089] Those skilled in the art can understand that, in practice, due to the cognitive limitations of merchants or platform operators, the number of parameter objects that can be provided is relatively small. If the reference objects are not expanded, and the reference objects are directly clustered to obtain object groups, the number of commodities included in the determined object groups is extremely limited, which will result in inaccurate prediction results of the total interaction volume of each object group in the target time period. In contrast, the technical solution provided by the present application can ensure that the number of commodities included in the object group is large by mining with reference objects as the starting point, and can improve the accuracy of the prediction results of the interaction volume of each object group in the target time period, thereby ensuring that the output target object group is more accurate.
[0090] Based on the above technical solutions, optionally, obtaining the target knowledge graph may include: obtaining sample data, the sample data including historical interaction data; identifying triples from the sample data; constructing the target knowledge graph based on the identified triples; and determining the score corresponding to each triple according to the association between two objects in each triple. In the e-commerce scenario, the historical interaction data includes but is not limited to order data, collection data, and consultation data.
[0091] In practice, in order to ensure that the target knowledge graph has high timeliness, and then ensure that the prediction results of the total interaction volume of each object group in the target time period have a high accuracy, the target knowledge graph can be periodically reconstructed. The present application does not limit the interval between two adjacent constructions of the target knowledge graph. Exemplarily, the target knowledge graph is constructed before each execution of the information processing method. "Using the reference object as the query condition, querying in the target knowledge graph, and obtaining multiple target objects associated with the reference object" includes: "Using the reference object as the query condition, querying in the latest target knowledge graph, and obtaining multiple target objects associated with the reference object".
[0092] It should be noted that the acquisition, storage and application of user personal information involved in the technical solutions of the embodiments of the present disclosure are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.
[0093] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the described action sequence, because according to the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.
[0094] Figure 3 Schematic diagram of the structure of an information processing device in an embodiment of the present disclosure. The information processing device provided in the embodiment of the present disclosure can be configured in a client or in a server. Figure 3 , the information processing device specifically includes:
[0095] A reference object acquisition module 310, used to acquire a reference object;
[0096] A target object determination module 320 is used to determine a plurality of target objects associated with the reference object; the type of the target objects is a first type;
[0097] A clustering module 330 is used to cluster the multiple target objects to obtain multiple object groups;
[0098] A historical interaction data determination module 340, used to respectively determine the historical interaction data of each of the object groups;
[0099] The target object group determination module 350 is used to determine a target object group from the multiple object groups based on the historical interaction data of each of the object groups, wherein the total interaction volume of the target object group in a target period meets a preset condition; the target period is after the time when the information processing method is executed this time.
[0100] Furthermore, the target object determination module is used to:
[0101] Obtain the target knowledge graph;
[0102] Taking the reference object as a query condition, a query is performed in the target knowledge graph to obtain multiple target objects associated with the reference object.
[0103] Furthermore, the target knowledge graph includes a plurality of triples and scores of each triple, the triple includes two objects and an association relationship between the two objects; at least one of the objects in some of the triples is of the first type; the target object determination module is used to:
[0104] Taking the reference object as a query condition, querying the target knowledge graph to obtain multiple candidate objects and a query path from the reference object to each of the candidate objects;
[0105] Determining a relevance value between each of the candidate objects and the reference object based on the scores of the triples included in the query path;
[0106] The candidate object whose correlation value is greater than a set threshold is taken as the target object.
[0107] Furthermore, the types of the objects include the first type, the second type and the third type; in the target knowledge graph, for any triple, the type of one object is the second type, and the type of the other object is the first type or the third type; the type of the reference object is the first type, the second type or the third type;
[0108] The target object determination module is used to:
[0109] Taking the reference object as a query condition, a first query is performed in the target knowledge graph to obtain a plurality of objects of the second type;
[0110] Taking each of the multiple second-type objects as a query condition, a secondary query is performed in the target knowledge graph to obtain multiple first-type candidate objects and a query path from the reference object to each of the candidate objects.
[0111] Furthermore, the target object determination module is used to:
[0112] Acquire sample data, where the sample data includes historical interaction data;
[0113] From the sample data, identifying triples;
[0114] Based on the identified triples, construct a target knowledge graph;
[0115] The score corresponding to each triple is determined according to the association relationship between two objects in each triple.
[0116] Furthermore, the target object group determination module is used to:
[0117] Based on the historical interaction data of each of the object groups, respectively determine the historical interaction feature data corresponding to each of the object groups;
[0118] Based on the historical interaction feature data corresponding to each of the object groups, a target object group is determined from among the plurality of object groups.
[0119] Further, the historical interaction feature data includes first feature data and / or second feature data;
[0120] The first characteristic data is used to describe the number of target objects included in the object group during the target observation period; the second characteristic data is the growth of historical interaction data of the object group during the target observation period; the target observation period is earlier than the moment when the information processing method is executed this time.
[0121] The information processing device provided in the embodiment of the present disclosure can execute the steps executed by the client or server in the information processing method provided in the embodiment of the method of the present disclosure, and has the execution steps and beneficial effects, which will not be repeated here.
[0122] Figure 4 Schematic diagram of the structure of an electronic device in the embodiment of the present disclosure. Figure 4 , which shows a schematic diagram of the structure of an electronic device 1000 suitable for implementing the embodiment of the present disclosure. The electronic device 1000 in the embodiment of the present disclosure may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle terminals (such as vehicle navigation terminals), wearable electronic devices, etc., and fixed terminals such as digital TVs, desktop computers, smart home devices, etc. Figure 4 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.
[0123] like Figure 4 As shown, the electronic device 1000 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 1001, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1008 to a random access memory (RAM) 1003 to implement the information processing method of the embodiment described in the present disclosure. In the RAM 1003, various programs and information required for the operation of the electronic device 1000 are also stored. The processing device 1001, the ROM 1002, and the RAM 1003 are connected to each other via a bus 1004. An input / output (I / O) interface 1005 is also connected to the bus 1004.
[0124] Typically, the following devices may be connected to the I / O interface 1005: an input device 1006 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 1007 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 1008 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 may allow the electronic device 1000 to communicate with other devices wirelessly or by wire to exchange information. Although Figure 4 The electronic device 1000 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.
[0125] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains a program code for executing the method shown in the flowchart, thereby implementing the information processing method as described above. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device 1009, or installed from a storage device 1008, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.
[0126] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include an information signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated information signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.
[0127] In some embodiments, the client and the server may communicate using any known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital information communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any known or future developed network.
[0128] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.
[0129] The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device:
[0130] Get the reference object;
[0131] Determine a plurality of target objects associated with the reference object; the type of the target objects is a first type;
[0132] Clustering the multiple target objects to obtain multiple object groups;
[0133] Determining historical interaction data for each of the object groups;
[0134] Based on the historical interaction data of each of the object groups, a target object group is determined from the multiple object groups, and the total interaction volume of the target object group in a target time period meets a preset condition; the target time period is after the time when the information processing method is executed this time.
[0135] Optionally, when the above one or more programs are executed by the electronic device, the electronic device may also execute other steps described in the above embodiments.
[0136] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages or a combination thereof, including, but not limited to, object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).
[0137] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.
[0138] The units involved in the embodiments described in the present disclosure may be implemented by software or hardware, wherein the name of a unit does not, in some cases, limit the unit itself.
[0139] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.
[0140] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
[0141] According to one or more embodiments of the present disclosure, the present disclosure provides an electronic device, including:
[0142] one or more processors;
[0143] A memory for storing one or more programs;
[0144] When the one or more programs are executed by the one or more processors, the one or more processors implement any information processing method provided in the present disclosure.
[0145] According to one or more embodiments of the present disclosure, the present disclosure provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any information processing method provided by the present disclosure.
[0146] The embodiments of the present disclosure further provide a computer program product, which includes a computer program or instructions. When the computer program or instructions are executed by a processor, the information processing method described above is implemented.
[0147] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one object or operation from another object or operation, and do not necessarily require or imply any such actual relationship or order between these objects or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also 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 a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.
[0148] The above description is only a specific embodiment of the present disclosure, so that those skilled in the art can understand or implement the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure will not be limited to the embodiments described herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. An information processing method, characterized in that: include: Get the reference object; determining a plurality of target objects associated with the reference object; The type of the target object is the first type; Clustering the multiple target objects to obtain multiple object groups; Determining historical interaction data for each of the object groups; Based on the historical interaction data of each of the object groups, a target object group is determined from the multiple object groups, and the total interaction volume of the target object group in a target time period meets a preset condition; the target time period is after the time when the information processing method is executed this time.
2. The method according to claim 1, characterized in that: The determining of a plurality of target objects associated with the reference object comprises: Obtain the target knowledge graph; Taking the reference object as a query condition, a query is performed in the target knowledge graph to obtain multiple target objects associated with the reference object.
3. The method according to claim 2, characterized in that The target knowledge graph includes a plurality of triples and scores of each triple, the triple includes two objects and an association relationship between the two objects; the type of one of the objects in at least some of the triples is a first type; the query is performed in the target knowledge graph using the reference object as a query condition to obtain a plurality of target objects associated with the reference object, including: Taking the reference object as a query condition, querying the target knowledge graph to obtain multiple candidate objects and a query path from the reference object to each of the candidate objects; Determining a relevance value between each of the candidate objects and the reference object based on the scores of the triples included in the query path; The candidate object whose correlation value is greater than a set threshold is taken as the target object.
4. The method according to claim 3, characterized in that The types of the objects include the first type, the second type and the third type; in the target knowledge graph, for any triple, the type of one object is the second type, and the type of the other object is the first type or the third type; the type of the reference object is the first type, the second type or the third type; The querying the target knowledge graph using the reference object as a query condition to obtain multiple candidate objects and a query path from the reference object to each candidate object includes: Taking the reference object as a query condition, a first query is performed in the target knowledge graph to obtain a plurality of objects of the second type; Taking each of the multiple second-type objects as a query condition, a secondary query is performed in the target knowledge graph to obtain multiple first-type candidate objects and a query path from the reference object to each of the candidate objects.
5. The method according to any one of claims 2 to 4, characterized in that: The obtaining of the target knowledge graph includes: Acquire sample data, where the sample data includes historical interaction data; From the sample data, identifying triples; Based on the identified triples, construct a target knowledge graph; The score corresponding to each triple is determined according to the association relationship between two objects in each triple.
6. The method according to claim 1, characterized in that The determining a target object group from the plurality of object groups based on the historical interaction data of each of the object groups further includes: Based on the historical interaction data of each of the object groups, respectively determine the historical interaction feature data corresponding to each of the object groups; Based on the historical interaction feature data corresponding to each of the object groups, a target object group is determined from among the plurality of object groups.
7. The method according to claim 6, characterized in that The historical interaction feature data includes first feature data and / or second feature data; The first characteristic data is used to describe the number of target objects included in the object group during the target observation period; the second characteristic data is the growth of historical interaction data of the object group during the target observation period; the target observation period is earlier than the moment when the information processing method is executed this time.
8. An information processing device, characterized in that: include: A reference object acquisition module, used for acquiring a reference object; A target object determination module, used to determine a plurality of target objects associated with the reference object; The type of the target object is the first type; A clustering module, used for clustering the multiple target objects to obtain multiple object groups; A historical interaction data determination module, used to respectively determine the historical interaction data of each of the object groups; The target object group determination module is used to determine a target object group from the multiple object groups based on the historical interaction data of each of the object groups, wherein the total interaction volume of the target object group in a target time period meets a preset condition; the target time period is after the moment of executing the information processing method this time.
9. An electronic device, characterized in that: The electronic device comprises: one or more processors; A storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.