Class preference determination method and device, electronic equipment and medium

Abstract

The invention provides a category preference determination method which can be applied to the technical field of computer application, the technical field of artificial intelligence and the field of financial science and technology. The method comprises the following steps: acquiring first feature information and historical consumption information of a first target user; clustering the historical consumption information of the first target user to obtain article category information; inputting the first feature information of the first target user and the article category information into a consumption preference model, and determining first category preference information of the first target user; based on a decision tree structure, determining second category preference information of the first target user according to the first feature information of the first target user and the article category information; and determining target category preference information of the first target user according to the first category preference information and the second category preference information. The invention further provides a category preference determination device, electronic equipment and a medium.

Description

Technical Field

[0001] The present disclosure relates to the fields of computer application technology, artificial intelligence technology and financial technology, and specifically to a method, device, electronic device and medium for determining category preference. Background Art

[0002] In the related technology, electronic devices such as servers and mobile terminals can be used to process big data such as log data, transaction data, consumption scenario data, etc. in the field of big data. At present, a consumption recommendation system can be set up in electronic devices such as servers or mobile terminals, and the transaction data can be processed by the consumption recommendation system to output the user's category preference characteristics. However, due to the large amount of transaction data, when using the transaction data to predict the user's consumption category preference, it will not only lead to low execution efficiency and high resource consumption of electronic devices such as servers and mobile terminals, but also more data noise, resulting in a large difference between the predicted user consumption preference results and the actual consumption preference, and poor recommendation effect. Summary of the invention

[0003] In view of the above problems, the present disclosure provides a method, device, electronic device and medium for determining category preference.

[0004] According to one aspect of the present disclosure, a method for determining category preference is provided, including: obtaining first feature information and historical consumption information of a first target user; clustering the historical consumption information of the first target user to obtain item category information; inputting the first feature information and item category information of the first target user into a consumption preference model to determine the first category preference information of the first target user; based on a decision tree structure, determining the second category preference information of the first target user according to the first feature information and item category information of the first target user; and determining the target category preference information of the first target user according to the first category preference information and the second category preference information.

[0005] Another aspect of the present disclosure provides a device for determining category preference, including: a first acquisition module, used to acquire first feature information and historical consumption information of a first target user; a clustering module, used to cluster the historical consumption information of the first target user to obtain item category information; an input module, used to input the first feature information and item category information of the first target user into a consumption preference model to determine the first category preference information of the first target user; a first determination module, used to determine the second category preference information of the first target user based on a decision tree structure according to the first feature information and item category information of the first target user; and a second determination module, used to determine the target category preference information of the first target user according to the first category preference information and the second category preference information.

[0006] Another aspect of the present disclosure provides an electronic device, comprising: one or more processors; and a memory for storing one or more computer programs, wherein the one or more processors execute the one or more computer programs to implement the steps of the above method.

[0007] Another aspect of the present disclosure further provides a computer-readable storage medium having a computer program or instruction stored thereon, which implements the steps of the above method when the computer program or instruction is executed by a processor.

[0008] Another aspect of the present disclosure further provides a computer program product, including a computer program or instructions, which implement the steps of the above method when the computer program or instructions are executed by a processor.

[0009] According to the embodiment of the present disclosure, by clustering the historical consumption information of the first target user, the item category information is obtained, and based on the consumption preference model and the decision tree structure, the first category preference information and the second category preference information of the first target user are obtained according to the first feature information and the item category information of the first target user, and the target category preference information of the first target user is obtained according to the first category preference information and the second category preference information. By obtaining the first feature information and historical consumption information of the user and clustering the historical consumption information of the user, it is possible to realize the automation of electronic equipment to obtain the required data from a large amount of data to identify the item category information, make full use of the computing power of the electronic equipment, improve the execution efficiency of the electronic equipment, reduce resource consumption, and solve the technical problem of low execution efficiency and high resource consumption of the electronic equipment caused by the identification of the item category information of each item according to the identification code in the existing; at the same time, based on the combination of the consumption preference model and the decision tree structure, the prediction result of the user's consumption category preference can be improved, so that the electronic equipment can improve the processing accuracy of the data under the condition of limited computing resources, thereby increasing the consistency between the predicted user consumption preference result and the actual consumption preference, and improving the recommendation effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The above contents and other purposes, features and advantages of the present disclosure will become more apparent through the following description of the embodiments of the present disclosure with reference to the accompanying drawings, in which:

[0011] Figure 1 A diagram schematically shows an application scenario of a method and device for determining category preference according to an embodiment of the present disclosure;

[0012] Figure 2 A flowchart schematically shows a method for determining category preference according to an embodiment of the present disclosure;

[0013] Figure 3A flowchart of a method for determining first category preference information of a first target user according to an embodiment of the present disclosure is schematically shown;

[0014] Figure 4 A schematic diagram schematically illustrates a method for determining category preference according to an embodiment of the present disclosure;

[0015] Figure 5 A structural block diagram schematically shows a device for determining category preference according to an embodiment of the present disclosure; and

[0016] Figure 6 A block diagram of an electronic device suitable for implementing a method for determining category preference according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0017] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present disclosure. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present disclosure.

[0018] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. The terms "comprise", "include", etc. used herein indicate the existence of features, steps, operations and / or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.

[0019] All terms (including technical and scientific terms) used herein have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification, and should not be interpreted in an idealized or overly rigid manner.

[0020] When using expressions such as "at least one of A, B, and C, etc.", they should generally be interpreted according to the meaning of the expression commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.).

[0021] It should be noted that the method and device for determining category preference disclosed in the present invention can be used in the financial field, and can also be used in any field other than the financial field, and the application field of the method and device for determining category preference disclosed in the present invention is not limited.

[0022] In the technical solution of the present disclosure, the user information (including but not limited to user personal information, user image information, user device information, such as location information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved are all information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data comply with relevant laws, regulations and standards, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0023] An embodiment of the present disclosure provides a method for determining category preference, the method comprising: obtaining first feature information and historical consumption information of a first target user; clustering the historical consumption information of the first target user to obtain item category information; inputting the first feature information and item category information of the first target user into a consumption preference model to determine the first category preference information of the first target user; based on a decision tree structure, determining the second category preference information of the first target user according to the first feature information and item category information of the first target user; and determining the target category preference information of the first target user according to the first category preference information and the second category preference information.

[0024] Figure 1 The application scenario diagram of the method and device for determining category preference according to an embodiment of the present disclosure is schematically shown.

[0025] like Figure 1 As shown, the application scenario 100 according to this embodiment may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for a communication link between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0026] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only examples).

[0027] The terminal devices 101 , 102 , and 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, and desktop computers.

[0028] The server 105 may be a server that provides various services, such as a background management server (only an example) that provides support for websites browsed by users using the terminal devices 101, 102, and 103. The background management server may analyze and process the received data such as user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal device.

[0029] It should be noted that the method for determining the category preference provided in the embodiment of the present disclosure can generally be executed by the server 105. Accordingly, the device for determining the category preference provided in the embodiment of the present disclosure can generally be set in the server 105. The method for determining the category preference provided in the embodiment of the present disclosure can also be executed by a server or a server cluster that is different from the server 105 and can communicate with the terminal devices 101, 102, 103 and / or the server 105. Accordingly, the device for determining the category preference provided in the embodiment of the present disclosure can also be set in a server or a server cluster that is different from the server 105 and can communicate with the terminal devices 101, 102, 103 and / or the server 105.

[0030] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0031] The following will be based on Figure 1 The scene described by Figure 2 to Figure 6 The ... method of the disclosed embodiment is described in detail.

[0032] Figure 2 The flowchart of the method for determining category preference according to an embodiment of the present disclosure is schematically shown.

[0033] like Figure 2 As shown, the method 200 may include operations S210 to S250.

[0034] In operation S210, first feature information and historical consumption information of a first target user are acquired.

[0035] In operation S220, clustering is performed on the historical consumption information of the first target user to obtain item category information.

[0036] In operation S230, the first characteristic information and item category information of the first target user are input into a consumption preference model to determine the first category preference information of the first target user.

[0037] In operation S240, based on the decision tree structure, second category preference information of the first target user is determined according to the first feature information and item category information of the first target user.

[0038] In operation S250, target category preference information of the first target user is determined according to the first category preference information and the second category preference information.

[0039] According to an embodiment of the present disclosure, before obtaining the first characteristic information and historical consumption information of the first target user, authorization of the first characteristic information and historical consumption information of the first target user is obtained; after obtaining the authorization of the first target user, the first characteristic information and historical consumption information of the first target user are obtained.

[0040] According to an embodiment of the present disclosure, for example, before executing operation S210, a request for obtaining the first characteristic information and historical consumption information of the first target user may be issued to the first target user. If the first target user agrees or authorizes that the first characteristic information and historical consumption information of the first target user may be obtained, operation S210 is executed.

[0041] According to an embodiment of the present disclosure, the first target user may be a user corresponding to each customer group after the users are divided into customer groups.

[0042] According to an embodiment of the present disclosure, users may be divided into customer groups by calculating the RFM score of each customer based on the most recent transaction time, transaction frequency, and transaction amount.

[0043] According to an embodiment of the present disclosure, for example, the R (Recency) score of the user can be determined by the time difference between the last transaction time and the current time; the F (Frequency) score of the user can be determined by the number of transactions of the user in the past period of time; the M (Monetary) score of the user can be determined by the transaction amount of the user in the past period of time; and the level of the customer is determined based on the average of the R, F, and M scores; and users who meet a preset threshold are determined to be in the same customer group.

[0044] According to the embodiments of the present disclosure, the past period of time may be the past month, quarter, half a year, etc., without specific limitation.

[0045] According to the embodiments of the present disclosure, it should be noted that the method for determining the category preference is to determine the category preference for the first target user in each customer group.

[0046] According to an embodiment of the present disclosure, the first characteristic information of the first target user may include information such as gender, age, occupation, etc.; the historical consumption information of the first target user may include information such as transaction items, transaction amount, transaction time, transaction method, etc.

[0047] According to the embodiments of the present disclosure, the clustering process may be a density-based clustering algorithm to determine whether any two data points in the historical consumption information are density-reachable. If they are density-reachable, the two data points may be considered to be in the same cluster. The corresponding cluster is thereby determined. The specific implementation of the density-based clustering algorithm adopts the same principle as the prior art, randomly selecting a core point from the historical consumption information as a "seed", and determining the corresponding cluster based on the seed. When all core points are traversed, the algorithm ends. In the embodiments of the present disclosure, no further details are given.

[0048] According to the embodiments of the present disclosure, the user's historical consumption information is clustered through clustering processing, which overcomes the technical problem in the prior art that the category of each item needs to be identified according to the item category identification code, resulting in low execution efficiency of the electronic device and high resource consumption, further improves the execution efficiency of the electronic device and reduces resource consumption.

[0049] According to an embodiment of the present disclosure, after clustering the historical consumption information of the first target user, the item information in each cluster can be determined, and the item category information corresponding to the cluster can be determined based on the item information in the cluster.

[0050] According to an embodiment of the present disclosure, for example, the item information included in the cluster is men's wallets, suitcases, women's backpacks, shoulder bags, etc., and the item category information corresponding to the cluster may be clothing, shoes and bags; the item information included in the cluster is car washing, auto repair, auto accessories, etc., and the item category information corresponding to the cluster may be car owners.

[0051] According to an embodiment of the present disclosure, the consumption preference model may be a model for predicting the category preference of the user. The first feature information and the item category information of the first target user may be used to recommend the corresponding item category to the first target user.

[0052] According to an embodiment of the present disclosure, for example, corresponding appropriate item categories may be recommended to the user based on the feature information of the first target user.

[0053] According to an embodiment of the present disclosure, the first characteristic information of the first target user can be input into the decision tree structure through a decision tree structure, and combined with the item category information, the category preference information corresponding to the first characteristic information can be determined.

[0054] According to an embodiment of the present disclosure, the first category preference information and the second category preference information can be matched based on the first category preference information determined by the consumption preference model and the second category preference information determined by the decision tree structure, and it can be determined that the two have the same category preference information, and it can be used as the target category preference information of the first target user.

[0055] According to the embodiment of the present disclosure, by clustering the historical consumption information of the first target user, the item category information is obtained, and based on the consumption preference model and the decision tree structure, the first category preference information and the second category preference information of the first target user are obtained according to the first feature information and the item category information of the first target user, and the target category preference information of the first target user is obtained according to the first category preference information and the second category preference information. By obtaining the first feature information and historical consumption information of the user and clustering the historical consumption information of the user, it is possible to realize the automation of electronic equipment to obtain the required data from a large amount of data to identify the item category information, make full use of the computing power of the electronic equipment, improve the execution efficiency of the electronic equipment, reduce resource consumption, and solve the technical problem of low execution efficiency and high resource consumption of the electronic equipment caused by the identification of the item category information of each item according to the identification code in the existing; at the same time, based on the combination of the consumption preference model and the decision tree structure, the prediction result of the user's consumption category preference can be improved, so that the electronic equipment can improve the processing accuracy of the data under the condition of limited computing resources, thereby increasing the consistency between the predicted user consumption preference result and the actual consumption preference, and improving the recommendation effect.

[0056] According to an embodiment of the present disclosure, the historical consumption record information of the first target user includes text information of the transaction item.

[0057] According to an embodiment of the present disclosure, historical consumption information of the first target user is clustered to obtain item category information, including: performing word segmentation on transaction item text information to determine weight information of each word in the transaction item text information; determining target keyword information based on the weight information of each word, wherein the target keyword information represents item information traded by the first target user; and clustering the target keyword information to obtain multiple clusters, wherein each cluster represents a different type of item category information.

[0058] According to an embodiment of the present disclosure, the transaction item text information may include the transaction item information when the first target user generates a transaction.

[0059] According to an embodiment of the present disclosure, data cleaning may be performed on the historical consumption information of the first target user to remove empty data or abnormal data in the historical consumption information.

[0060] According to an embodiment of the present disclosure, a word segmenter may be used to perform word segmentation processing on the transaction item text information in the historical consumption information, and a stop word library may be used to remove irrelevant words in the transaction item text information.

[0061] According to an embodiment of the present disclosure, after the transaction item text information is segmented, the weight information of each word can be determined. The weight information can represent the importance of each word in the transaction item text information.

[0062] According to the embodiments of the present disclosure, the words with larger weights in the weight information of each word can be determined, and the segmented words can be determined as the target keywords that can characterize the item information of the first target user's transaction. For example, the transaction item text information is "bought a backpack", and the text information is segmented into "bought", "one", "backpack", and the weights corresponding to each segmented word are calculated to be 0.1, 0.3, and 0.6, which means that the target keyword in the text information is "backpack".

[0063] According to the embodiment of the present disclosure, clustering is performed on the obtained target keywords to obtain multiple clusters, each of which can guarantee different types of item category information.

[0064] According to an embodiment of the present disclosure, the target keyword information is clustered to obtain multiple clusters, including: performing K-means clustering on the target keyword information to determine K cluster centers, where K is a positive integer greater than or equal to 1; calculating the distance between the target keyword information and each cluster center to obtain the minimum distance between the target keyword information and each cluster center; dividing the target keyword information corresponding to the minimum distance into the cluster corresponding to the minimum distance to obtain multiple clusters.

[0065] According to an embodiment of the present disclosure, K-means clustering may be performed on the target keyword information to determine an optimal clustering number K value, that is, K cluster centers.

[0066] According to the embodiments of the present disclosure, for each target keyword information, the distance between the target keyword information and each of the K cluster centers is calculated respectively, and the minimum distance value among the distances between each cluster center can be determined. The target keyword information corresponding to the minimum distance value can be divided into the corresponding cluster, and multiple clusters can be obtained by this calculation.

[0067] In an embodiment of the present disclosure, for example, there are W target keyword information. For the w-th target keyword information, the distance between the w-th target keyword information and K cluster centers is calculated, and K distance values ​​can be obtained, and the minimum distance value among the K distance values ​​is determined. Based on the minimum distance value, it can be determined that the corresponding cluster center is the k-th, and the w-th target keyword information is divided into the k-th cluster. The other target keyword information is calculated in this way, and finally a plurality of cluster clusters are obtained. Wherein, W is a positive integer greater than or equal to 1, 1≤w≤W; K is a positive integer greater than or equal to 1, 1≤k≤K.

[0068] According to an embodiment of the present disclosure, each cluster contains a plurality of item information, and the corresponding item category information can be determined according to the item information with a relatively high appearance frequency in the cluster.

[0069] Figure 3 The flowchart of the method for determining the first category preference information of the first target user according to an embodiment of the present disclosure is schematically shown.

[0070] like Figure 3 As shown, the method 300 may include operations S310 to S350.

[0071] In operation S310, J second feature information is determined from the first feature information of the first target user, wherein each second feature information has different features, each second feature information corresponds to at least one second target user, and J is a positive integer greater than or equal to 1.

[0072] According to an embodiment of the present disclosure, the second feature information may be extracted from the first feature information. Each second feature information has different features, and each second feature information corresponds to at least one second target user.

[0073] According to the embodiments of the present disclosure, for example, the first characteristic information may include gender, age, occupation, etc., and J second characteristic information with a certain characteristic range may be extracted from the first characteristic information. For example, the J second characteristic information may be men aged within a certain area, women aged within a certain area, men with a certain occupation, women with a certain occupation, etc. It should be noted that the limitation on the second characteristic information is not limited to the above-mentioned examples.

[0074] According to an embodiment of the present disclosure, for example, the J second feature information may be ladies aged 18 to 25; ladies aged 26 to 35;…; men aged 18 to 25; ladies aged 26 to 35;…; men who are teachers; ladies who are teachers; men who are athletes;…; ladies who are athletes, etc.

[0075] In operation S320, for the i-th item category information, the proportion of the group information of the second target users who consume the i-th item category information in the j-th second feature information to the total information of the second target user group in the j-th second feature information is determined to obtain first ratio information.

[0076] According to an embodiment of the present disclosure, the operation S320 may determine the first ratio information in the following manner. Specifically, determine the group information of the second target user who consumes the i-th item category information in the j-th second feature information; determine the total group information of the second target user in the j-th second feature information; determine the first ratio information based on the group information and the total group information of the second target user who consumes, 1≤i≤M, 1≤j≤J.

[0077] According to an embodiment of the present disclosure, for the i-th item category information, the number of second target users corresponding to the j-th second feature information among the J second feature information who consume the i-th item category information can be determined. The total number of second target users corresponding to the j-th feature information can be determined.

[0078] According to an embodiment of the present disclosure, first ratio information may be obtained according to the ratio of the number of second target users corresponding to the jth second characteristic information who consume the i-th item category information to the total number of second target users corresponding to the jth characteristic information.

[0079] According to an embodiment of the present disclosure, the j-th second characteristic information is 100 ladies aged between 18 and 25, and the i-th item category information is clothing and luggage as an example. The number of people who consume clothing and luggage is determined to be 60, and the total number of second target users corresponding to the j-th characteristic information is determined to be 100. Then the first ratio information can be 60:100=0.6.

[0080] In operation S330, the ratio of the group information of the first target users who consume the i-th item category information in the first feature information to the total group information of the first target users in the first feature information is determined to obtain second ratio information.

[0081] According to an embodiment of the present disclosure, the operation S330 may determine the second ratio information in the following manner: Specifically, determine the group information of the first target user who consumes the i-th item category information in the first feature information; determine the total group information of the first target user in the first feature information; and determine the second ratio information based on the group information and the total group information of the first target user who consumes.

[0082] According to an embodiment of the present disclosure, the number of first target users corresponding to the first characteristic information who consume the i-th item category information can be determined, and the total number of first target users corresponding to the first characteristic information can be determined.

[0083] According to an embodiment of the present disclosure, second ratio information may be obtained according to a ratio of information on the number of first target users who consume information on the i-th item category to information on the total number of first target users corresponding to the first feature information.

[0084] According to the embodiments of the present disclosure, the number of first target users corresponding to the first characteristic information who consume the i-th item category information can be obtained by summing the number of all second target users corresponding to the J second characteristic information who consume the i-th item category information. For example, the sum of the number of all second target users who consume the i-th item category information, including women aged 18 to 25, women aged 26 to 35, ..., men aged 18 to 25, women aged 26 to 35, ..., men who are teachers, women who are teachers, men who are athletes, ..., women who are athletes, etc.

[0085] According to an embodiment of the present disclosure, for example, the number of first target users consuming the i-th item category information of clothing and luggage corresponding to the first characteristic information is 300, and the total number of first target users corresponding to the first characteristic information is 900, then the second ratio information can be 300:900=0.3.

[0086] In operation S340, the category preference information of the second target user of the i-th item category information in the j-th second feature information is determined according to the first ratio information and the second ratio information, and the category preference information of the second target user in the J-th second feature information is obtained.

[0087] According to an embodiment of the present disclosure, the second ratio information can be weighted based on weight addition, and the category preference information of the second target user of the i-th item category information in the j-th second feature information can be determined by comparing the first ratio information and the second ratio information.

[0088] According to an embodiment of the present disclosure, for example, based on the above-mentioned embodiment, the first ratio information is 0.6, the second ratio information is 0.3, and the second ratio information is constrained by a weight h, where h can be 0.5, for example. Then, the category preference information of the second target user of the i-th item category information in the j-th second feature information can be determined to be 0.6 / (0.5*0.3)*100=400, and based on the category preference information, the preference degree of the second target user in the j-th second feature information for the i-th item category information can be determined.

[0089] According to an embodiment of the present disclosure, the category preference information of the second target user of the i-th item category information in the j-th second feature information may also be directly determined through the percentage information of the first ratio information and the second ratio information.

[0090] According to an embodiment of the present disclosure, for example, based on the above-mentioned embodiment, the first ratio information is 0.6 and the second ratio information is 0.3, then it can be determined that the category preference information of the second target user of the i-th item category information in the j-th second feature information is 0.6 / 0.3*100=200, and based on the category preference information, the preference degree of the second target user in the j-th second feature information for the i-th item category information is determined.

[0091] According to an embodiment of the present disclosure, the implementation method of determining the category preference information of the second target user of the i-th item category information in the j-th second feature information based on the first ratio information and the second ratio information is not specifically limited and can be specifically set according to actual conditions.

[0092] According to the embodiments of the present disclosure, the obtained category preference information can be compared with the set category preference threshold. If it is greater than the category preference threshold, it means that the second target user in the jth second feature information has a clear preference for the ith item category information; if it is less than or equal to the category preference threshold, it means that the second target user in the jth second feature information has no clear preference for the ith item category information. The category preference threshold can be set to 100.

[0093] According to an embodiment of the present disclosure, based on the above method, the category preference information of the second target user for the i-th item category information in the J second feature information can be determined, and the category preference information of the second target user for the M item category information in the J second feature information can be further determined.

[0094] In operation S350, first category preference information of the first target user is determined according to the category preference information of the second target user in the J second feature information.

[0095] According to an embodiment of the present disclosure, the first category preference information of the first target user may be reflected based on the category preference information of the second target user in the J second feature information.

[0096] According to an embodiment of the present disclosure, the first characteristic information and item category information of the first target user are input into a consumption preference model to determine the first category preference information of the first target user, and also includes: based on preset rules of category correlation, performing consumption analysis and prediction on the category preference information of the second target user in J second characteristic information to obtain the target category preference information of the second target user in the J second characteristic information; and determining the first category preference information of the first target user based on the target category preference information of the second target user in the J second characteristic information.

[0097] According to an embodiment of the present disclosure, the category correlation preset rules may include a category association principle and a category mutual exclusion principle.

[0098] According to an embodiment of the present disclosure, the category preference information predicted for the second target user corresponding to the jth second feature information can be adjusted based on the category preference information predicted for the second target user corresponding to the jth second feature information by utilizing the category association principle or the category mutual exclusion principle.

[0099] According to an embodiment of the present disclosure, for example, if the category preference information predicted for the second target user corresponding to the j-th second feature information includes furniture category information, the furniture category information can be recommended to the second target user corresponding to the j-th second feature information based on the category association principle.

[0100] According to an embodiment of the present disclosure, for example, the category preference information predicted for the second target user corresponding to the jth second feature information includes electronic product category information and clothing, shoes and bags category information. According to the principle of category mutual exclusion, the category information of electronic products or clothing, shoes and bags can be deleted.

[0101] According to an embodiment of the present disclosure, the above-mentioned category correlation preset rules can be utilized to adjust the category preference information predicted for the second target user corresponding to J second feature information, so as to obtain the target category preference information of the second target user in the J second feature information, and then based on the target category preference information of the second target user in the J second feature information, the first category preference information of the first target user can be obtained.

[0102] According to an embodiment of the present disclosure, the category association principle can be implemented by using principal component analysis to reduce the dimension of category samples to generate associated category combinations, and the above-mentioned category preference information can be adjusted based on the associated category combinations.

[0103] According to the embodiments of the present disclosure, the category mutual exclusion principle can divide customer samples into different clusters through clustering. By observing the clustering results, the category preference of each customer group and the mutual exclusion relationship between categories can be obtained. Based on the category mutual exclusion relationship, the above-mentioned category preference information can be adjusted.

[0104] According to an embodiment of the present disclosure, a decision tree structure can be constructed by the following method: determining the first feature information of the first target user and the item category information as a target feature set, the target feature set including N target feature information, N being a positive integer greater than or equal to 1; for the nth target feature information, determining the information entropy of the nth target feature information based on the nth target feature information, 1≤n≤N; determining the information gain of the nth target feature information based on the information entropy of the nth target feature information, and obtaining the information gain of the N target feature information; constructing a decision tree structure based on the information gain of the N target feature information.

[0105] According to an embodiment of the present disclosure, the target feature set may be data required for building a decision tree. Each target feature information in the target feature set may be taken as a category. For example, the target feature set includes gender, age, occupation, etc.; then gender, age, and occupation may be taken as a category respectively.

[0106] According to an embodiment of the present disclosure, the information entropy of each feature information represents the degree of disorder of the data of the target feature set. The larger the information entropy, the higher the degree of disorder of the data, that is, the lower the data purity.

[0107] According to an embodiment of the present disclosure, for the nth target feature information, multiple specific categories corresponding to the nth target feature information can be determined according to the nth target feature information. The information entropy of the nth target feature information can be determined according to the quantity ratio of each category in the nth target feature information.

[0108] According to an embodiment of the present disclosure, information gain may represent the change in data complexity of the root node and the data complexity of the split node before and after the split.

[0109] According to an embodiment of the present disclosure, the information entropy of N target feature information can be used as a node and split according to the nth target feature information among the N target feature information, that is, split according to target feature 1 among the N target feature information to generate two corresponding child nodes; split according to target feature 2 among the N target feature information to generate two corresponding child nodes;…; split according to target feature n among the N target feature information to generate two corresponding child nodes;…; split according to target feature N among the N target feature information to generate two corresponding child nodes.

[0110] According to the embodiments of the present disclosure, the information gain after splitting according to target feature 1, the information gain after splitting according to target feature 2, ..., the information gain after splitting according to target feature n, ..., the information gain after splitting according to target feature N can be calculated respectively; the target feature with the largest information gain value among the N information gains can be used as the root node of the decision tree structure. The above method can be used to sequentially generate other nodes of the decision tree structure to construct a decision tree structure.

[0111] According to an embodiment of the present disclosure, target category preference information of the first target user is determined based on the first category preference information and the second category preference information, including: coupling the first category preference information and the second category preference information to obtain the target category preference information of the first target user.

[0112] According to an embodiment of the present disclosure, the first category preference information and the second category preference information may be coupled and processed to extract the same category preference information between the first category preference information and the second category preference information, and determine the same category preference information as the target category preference information of the first target user.

[0113] Figure 4 A schematic diagram schematically shows a method for determining category preference according to an embodiment of the present disclosure.

[0114] like Figure 4 As shown, in the schematic diagram 400, the first characteristic information 401 and the historical consumption information 402 of the first target user are obtained, and the historical consumption information 402 is clustered to obtain the item category information 403. J second characteristic information 404 are determined from the first characteristic information 401 of the first target user, and for the i-th item category information in the item category information 403, the group information 405 of the second target user who consumes the i-th item category information in the j-th second characteristic information is determined, and the total group information 406 of the second target user in the j-th second characteristic information is determined. According to the group information 405 of the second target user who consumes the j-th second characteristic information and the total group information 406 of the second target user, the first ratio information 407 is determined. The group information 408 of the first target user who consumes the i-th item category information in the first characteristic information is determined, and the total group information 409 of the first target user in the first characteristic information is determined. According to the group information 408 of the first target user who consumes the i-th item category information in the first characteristic information and the total group information 409 of the first target user, the second ratio information 410 is determined. According to the first ratio information 407 and the second ratio information 410, the category preference information 411 of the second target user in the J second feature information is obtained, thereby obtaining the first category preference information 412 of the first target user.

[0115] The first characteristic information 401 and the item category information 403 of the first target user are input into the decision tree structure 415 to obtain the second category preference information 413 of the first target user. According to the first category preference information 412 and the second category preference information 413, the target category preference information 414 of the first target user is determined.

[0116] Based on the above method for determining category preference, the present disclosure also provides a device for determining category preference. Figure 5 The device is described in detail.

[0117] Figure 5 The structural block diagram of the device for determining category preference according to an embodiment of the present disclosure is schematically shown.

[0118] like Figure 5As shown, the apparatus 500 may include: a first acquisition module 510 , a clustering module 520 , an input module 530 , a first determination module 540 , and a second determination module 550 .

[0119] The first acquisition module 510 is used to acquire the first characteristic information and historical consumption information of the first target user. In one embodiment, the first acquisition module 510 can be used to perform the operation S210 described above, which will not be described in detail here.

[0120] The clustering module 520 is used to perform clustering processing on the historical consumption information of the first target user to obtain item category information. In one embodiment, the clustering module 520 can be used to perform the operation S220 described above, which will not be described in detail here.

[0121] The input module 530 is used to input the first characteristic information and the item category information of the first target user into the consumption preference model to determine the first category preference information of the first target user. In one embodiment, the input module 530 can be used to perform the operation S230 described above, which will not be repeated here.

[0122] The first determination module 540 is used to determine the second category preference information of the first target user based on the decision tree structure and the first feature information and item category information of the first target user. In one embodiment, the first determination module 540 can be used to perform the operation S240 described above, which will not be described in detail here.

[0123] The second determination module 550 is used to determine the target category preference information of the first target user according to the first category preference information and the second category preference information. In one embodiment, the second determination module 550 can be used to perform the operation S250 described above, which will not be described in detail here.

[0124] According to an embodiment of the present disclosure, the historical consumption record information of the first target user includes transaction item text information, and the clustering module 520 may include: a word segmentation submodule, a first determination submodule and a clustering submodule.

[0125] The word segmentation submodule is used to perform word segmentation processing on the transaction item text information and determine the weight information of each word in the transaction item text information.

[0126] The first determination submodule is used to determine target keyword information according to the weight information of each word, wherein the target keyword information represents the item information traded by the first target user.

[0127] The clustering submodule is used to perform clustering processing on the target keyword information to obtain multiple clusters, wherein each cluster represents different types of item category information.

[0128] According to an embodiment of the present disclosure, the clustering submodule may include: a clustering unit, a computing unit, and a partitioning unit.

[0129] The clustering unit is used to perform K-means clustering on the target keyword information and determine K cluster centers, where K is a positive integer greater than or equal to 1.

[0130] The calculation unit is used to calculate the distance between the target keyword information and each cluster center, and obtain the minimum distance between the target keyword information and each cluster center.

[0131] The division unit is used to divide the target keyword information corresponding to the minimum distance into the cluster corresponding to the minimum distance to obtain multiple clusters.

[0132] According to an embodiment of the present disclosure, the item category information includes M item category information, where M is a positive integer greater than or equal to 1.

[0133] The input module 530 may include: a second determining submodule, a third determining submodule, a fourth determining submodule, an obtaining submodule, and a fifth determining submodule.

[0134] The second determination submodule is used to determine J second feature information from the first feature information of the first target user, wherein each second feature information has different features, each second feature information corresponds to at least one second target user, and J is a positive integer greater than or equal to 1.

[0135] The third determination submodule is used to determine, for the i-th item category information, the proportion of the group information of the second target user who consumes the i-th item category information in the j-th second characteristic information to the total information of the second target user group in the j-th second characteristic information, and obtain the first ratio information, 1≤i≤M, 1≤j≤J.

[0136] The fourth determination submodule is used to determine the proportion of the group information of the first target users who consume the i-th item category information in the first feature information to the total group information of the first target users in the first feature information to obtain second ratio information.

[0137] The obtaining submodule is used to determine the category preference information of the second target user of the i-th item category information in the j-th second feature information according to the first ratio information and the second ratio information, and obtain the category preference information of the second target user in the J-th second feature information.

[0138] The fifth determination submodule is used to determine the first category preference information of the first target user according to the category preference information of the second target user in the J second feature information.

[0139] According to an embodiment of the present disclosure, the third determining submodule may include: a first determining unit, a second determining unit, and a third determining unit.

[0140] The first determining unit is used to determine the group information of the second target user who consumes the i-th item category information in the j-th second feature information.

[0141] The second determining unit is used to determine the total group information of the second target user in the j-th second characteristic information.

[0142] The third determining unit is used to determine the first ratio information according to the group information and the total group information of the second target consumer.

[0143] According to an embodiment of the present disclosure, the fourth determining submodule may include: a fourth determining unit, a fifth determining unit, and a sixth determining unit.

[0144] The fourth determining unit is used to determine the group information of the first target user who consumes the i-th item category information in the first feature information.

[0145] The fifth determining unit is used to determine the total group information of the first target user in the first characteristic information.

[0146] The sixth determining unit is used to determine the second ratio information according to the group information and the total group information of the first target consumer.

[0147] According to an embodiment of the present disclosure, the input module 530 may further include: a prediction unit and a seventh determination unit.

[0148] The prediction unit is used to perform consumption analysis and prediction on the category preference information of the second target user in the J second feature information based on preset rules of category relevance, and obtain the target category preference information of the second target user in the J second feature information.

[0149] The seventh determination unit is used to determine the first category preference information of the first target user according to the target category preference information of the second target user in the J second feature information.

[0150] According to an embodiment of the present disclosure, the first determining module 540 may include: a sixth determining submodule, a seventh determining submodule, an eighth determining submodule and a constructing submodule.

[0151] The sixth determination submodule is used to determine the first feature information of the first target user and the item category information as a target feature set, where the target feature set includes N target feature information, where N is a positive integer greater than or equal to 1.

[0152] The seventh determination submodule is used to determine the information entropy of the nth target feature information according to the nth target feature information, 1≤n≤N.

[0153] The eighth determination submodule is used to determine the information gain of the nth target feature information according to the information entropy of the nth target feature information, so as to obtain the information gain of N target feature information.

[0154] The submodule is constructed to construct a decision tree structure according to the information gain of N target feature information.

[0155] According to an embodiment of the present disclosure, the second determination module 550 may include: a coupling submodule.

[0156] The coupling submodule is used to perform information coupling processing on the first category preference information and the second category preference information to obtain the target category preference information of the first target user.

[0157] According to an embodiment of the present disclosure, the device 500 may further include: an authorization module and a second acquisition module.

[0158] The authorization module is used to obtain authorization for the first characteristic information and historical consumption information of the first target user.

[0159] The second acquisition module is used to acquire the first characteristic information and historical consumption information of the first target user after obtaining the authorization of the first target user.

[0160] According to an embodiment of the present disclosure, any multiple modules among the first acquisition module 510, the clustering module 520, the input module 530, the first determination module 540 and the second determination module 550 can be combined into one module for implementation, or any one of the modules can be split into multiple modules. Alternatively, at least part of the functions of one or more of these modules can be combined with at least part of the functions of other modules and implemented in one module.

[0161] According to an embodiment of the present disclosure, at least one of the first acquisition module 510, the clustering module 520, the input module 530, the first determination module 540 and the second determination module 550 may be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application-specific integrated circuit (ASIC), or may be implemented by hardware or firmware such as any other reasonable way of integrating or packaging the circuit, or implemented in any one of the three implementation methods of software, hardware and firmware or in an appropriate combination of any of them. Or at least one of the first acquisition module 510, the clustering module 520, the input module 530, the first determination module 540 and the second determination module 550 may be at least partially implemented as a computer program module, and when the computer program module is run, the corresponding function may be executed.

[0162] Figure 6 A block diagram of an electronic device suitable for implementing a method for determining category preference according to an embodiment of the present disclosure is schematically shown.

[0163] like Figure 6 As shown, the electronic device 600 according to an embodiment of the present disclosure includes a processor 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage part 608 into a random access memory (RAM) 603. The processor 601 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or a related chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 601 may also include an onboard memory for caching purposes. The processor 601 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.

[0164] In RAM 603, various programs and data required for the operation of electronic device 600 are stored. Processor 601, ROM 602 and RAM 603 are connected to each other via bus 604. Processor 601 performs various operations of the method flow according to the embodiment of the present disclosure by executing the program in ROM 602 and / or RAM 603. It should be noted that the program can also be stored in one or more memories other than ROM 602 and RAM 603. Processor 601 can also perform various operations of the method flow according to the embodiment of the present disclosure by executing the program stored in one or more memories.

[0165] According to an embodiment of the present disclosure, the electronic device 600 may further include an input / output (I / O) interface 605, which is also connected to the bus 604. The electronic device 600 may further include one or more of the following components connected to the I / O interface 605: an input portion 606 including a keyboard, a mouse, etc.; an output portion 607 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage portion 608 including a hard disk, etc.; and a communication portion 609 including a network interface card such as a LAN card, a modem, etc. The communication portion 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the I / O interface 605 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 610 as needed, so that a computer program read therefrom is installed into the storage portion 608 as needed.

[0166] The present disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or may exist independently without being assembled into the device / apparatus / system. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the method according to the embodiment of the present disclosure is implemented.

[0167] According to an embodiment of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, for example, may include but is not limited to: 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), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, an apparatus or a device. For example, according to an embodiment of the present disclosure, a computer-readable storage medium may include the ROM 602 and / or RAM 603 described above and / or one or more memories other than ROM 602 and RAM 603.

[0168] The embodiment of the present disclosure also includes a computer program product, which includes a computer program, and the computer program contains program code for executing the method shown in the flowchart. When the computer program product is run in a computer system, the program code is used to enable the computer system to implement the method provided by the embodiment of the present disclosure.

[0169] The above functions defined in the system / device of the embodiment of the present disclosure are performed when the computer program is executed by the processor 601. According to the embodiment of the present disclosure, the system, device, module, unit, etc. described above can be implemented by a computer program module.

[0170] In one embodiment, the computer program may rely on tangible storage media such as optical storage devices, magnetic storage devices, etc. In another embodiment, the computer program may also be transmitted and distributed in the form of signals on a network medium, and downloaded and installed through the communication part 609, and / or installed from a removable medium 611. The program code contained in the computer program may be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0171] In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 609, and / or installed from the removable medium 611. When the computer program is executed by the processor 601, the above functions defined in the system of the embodiment of the present disclosure are performed. According to the embodiment of the present disclosure, the system, device, apparatus, module, unit, etc. described above can be implemented by a computer program module.

[0172] According to an embodiment of the present disclosure, the program code for executing the computer program provided by the embodiment of the present disclosure can be written in any combination of one or more programming languages. Specifically, these computing programs can be implemented using high-level process and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, Java, C++, python, "C" language or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on the remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, using an Internet service provider to connect through the Internet).

[0173] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two 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 box in the block diagram or flow chart, and the combination of the boxes in the block diagram 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.

[0174] It will be appreciated by those skilled in the art that the features described in the various embodiments and / or claims of the present disclosure may be combined and / or combined in a variety of ways, even if such combinations and / or combinations are not explicitly described in the present disclosure. In particular, the features described in the various embodiments and / or claims of the present disclosure may be combined and / or combined in a variety of ways without departing from the spirit and teachings of the present disclosure. All of these combinations and / or combinations fall within the scope of the present disclosure.

[0175] The embodiments of the present disclosure are described above. However, these embodiments are only for illustrative purposes and are not intended to limit the scope of the present disclosure. Although the embodiments are described above separately, this does not mean that the measures in the various embodiments cannot be used in combination to advantage. The scope of the present disclosure is defined by the attached claims and their equivalents. Without departing from the scope of the present disclosure, those skilled in the art may make a variety of substitutions and modifications, which should all fall within the scope of the present disclosure.

Claims

1. A method for determining category preference, characterized in that: The method comprises: Acquire first characteristic information and historical consumption information of a first target user; Clustering the historical consumption information of the first target user to obtain item category information; Inputting the first characteristic information of the first target user and the item category information into a consumption preference model to determine the first category preference information of the first target user; Based on a decision tree structure, determining second category preference information of the first target user according to the first feature information of the first target user and the item category information; The target category preference information of the first target user is determined according to the first category preference information and the second category preference information.

2. The method according to claim 1, characterized in that The historical consumption record information of the first target user includes text information of transaction items; The clustering process of the historical consumption information of the first target user to obtain the item category information includes: Performing word segmentation processing on the transaction item text information to determine weight information of each word in the transaction item text information; Determine target keyword information according to the weight information of each word, wherein the target keyword information represents the item information traded by the first target user; The target keyword information is clustered to obtain a plurality of clusters, wherein each cluster represents a different type of item category information.

3. The method according to claim 2, characterized in that The clustering process is performed on the target keyword information to obtain multiple clusters, including: Performing K-means clustering on the target keyword information to determine K cluster centers, where K is a positive integer greater than or equal to 1; Calculating the distance between the target keyword information and each of the cluster centers to obtain the minimum distance between the target keyword information and each of the cluster centers; The target keyword information corresponding to the minimum distance is divided into clusters corresponding to the minimum distance to obtain a plurality of clusters.

4. The method according to claim 1, characterized in that: The item category information includes M item category information, where M is a positive integer greater than or equal to 1; The step of inputting the first characteristic information of the first target user and the item category information into a consumption preference model to determine the first category preference information of the first target user includes: Determine J second feature information from the first feature information of the first target user, wherein each of the second feature information has different features, each of the second feature information corresponds to at least one second target user, and J is a positive integer greater than or equal to 1; For the i-th item category information, determine the proportion of the group information of the second target user who consumes the i-th item category information in the j-th second feature information to the total information of the second target user group in the j-th second feature information, and obtain first ratio information, 1≤i≤M, 1≤j≤J; Determine the ratio of the group information of the first target users who consume the i-th item category information in the first feature information to the total group information of the first target users in the first feature information to obtain second ratio information; Determine, according to the first ratio information and the second ratio information, the category preference information of the second target user of the i-th item category information in the j-th second feature information, and obtain the category preference information of the second target user in the J-th second feature information; The first category preference information of the first target user is determined according to the category preference information of the second target user in the J second feature information.

5. The method according to claim 4, characterized in that The determining of the proportion of the group information of the second target users who consume the i-th item category information in the j-th second feature information to the total group information of the second target users in the j-th second feature information to obtain the first ratio information includes: Determine group information of the second target user who consumes the i-th item category information in the j-th second feature information; Determine the total group information of the second target user in the j-th second characteristic information; The first ratio information is determined according to the group information of the second target user of the consumption and the total group information.

6. The method according to claim 4, characterized in that The determining the proportion of the group information of the first target users who consume the i-th item category information in the first feature information to the total group information of the first target users in the first feature information to obtain the second ratio information includes: Determining group information of the first target user who consumes the i-th item category information in the first feature information; Determine the total group information of the first target user in the first characteristic information; The second ratio information is determined according to the group information of the first target user of the consumption and the total group information.

7. The method according to claim 4, characterized in that The step of inputting the first characteristic information of the first target user and the item category information into a consumption preference model to determine the first category preference information of the first target user further includes: Based on a preset rule of category relevance, performing consumption analysis and prediction on the category preference information of the second target user in the J second feature information to obtain the target category preference information of the second target user in the J second feature information; The first category preference information of the first target user is determined according to the target category preference information of the second target user in the J second feature information.

8. The method according to claim 1, characterized in that The decision tree structure is constructed by the following method: Determine the first characteristic information of the first target user and the item category information as a target characteristic set, wherein the target characteristic set includes N target characteristic information, where N is a positive integer greater than or equal to 1; For the nth target feature information, determine the information entropy of the nth target feature information according to the nth target feature information, 1≤n≤N; Determine the information gain of the n-th target feature information according to the information entropy of the n-th target feature information, and obtain the information gain of N target feature information; The decision tree structure is constructed according to the information gain of the N target feature information.

9. The method according to claim 1, characterized in that: The determining the target category preference information of the first target user according to the first category preference information and the second category preference information includes: The first category preference information and the second category preference information are coupled to obtain the target category preference information of the first target user.

10. The method according to claim 1, characterized in that The method further comprises: Obtaining authorization for first characteristic information and historical consumption information of the first target user; After obtaining authorization from the first target user, first feature information and historical consumption information of the first target user are obtained.

11. A device for determining category preference, characterized in that: The device comprises: A first acquisition module, used to acquire first characteristic information and historical consumption information of a first target user; A clustering module, used for clustering the historical consumption information of the first target user to obtain item category information; An input module, configured to input the first characteristic information of the first target user and the item category information into a consumption preference model to determine the first category preference information of the first target user; A first determination module is used to determine the second category preference information of the first target user based on a decision tree structure and according to the first feature information of the first target user and the item category information; The second determination module is used to determine the target category preference information of the first target user according to the first category preference information and the second category preference information.

12. An electronic device comprising: one or more processors; a memory for storing one or more computer programs, The method is characterized in that the one or more processors execute the one or more computer programs to implement the steps of the method according to any one of claims 1 to 10.

13. A computer-readable storage medium having a computer program or instruction stored thereon, characterized in that: When the computer program or instruction is executed by a processor, the steps of the method according to any one of claims 1 to 10 are implemented.

Images