Financial product recommendation method, device and computer equipment based on data analysis

Abstract

The present invention discloses a financial product recommendation method, device and computer equipment based on data analysis, which relates to the field of big data. The method comprises: obtaining webpage texts browsed by a target user within a predetermined time period; determining a user tag vector of the target user based on the webpage texts; obtaining a description text describing the financial product for each financial product; determining a product tag vector of each financial product based on the description text; and pushing financial products to the target user based on the matching result of the user tag vector and the product tag vector. The method improves the accuracy of pushing financial products to the target user.

Description

Background Art

[0002] With the rapid development of Internet technology, many businesses in many fields will use Internet technology to process and analyze information. In insurance sales, the existing technology uses the method of labeling the target user, labeling the product, and finally matching the labels of the two to determine the product to be sold to the user. This matching method stops at the "label" level, and the matching results are relatively rough, and it is impossible to further process and analyze them more accurately, resulting in a large amount of waste of detailed information in the entire processing process. Summary of the invention

[0003] Based on this, in order to solve the technical problem faced in the related technology of how to push financial products to target users more accurately from a technical level, the present invention provides a financial product recommendation method and device based on data analysis.

[0004] In a first aspect, a financial product recommendation method based on data analysis is provided, comprising:

[0005] Obtain the webpage texts browsed by the target user within a predetermined time period;

[0006] Determining a user tag vector of the target user based on the webpage text;

[0007] For each financial product, obtain a description text describing the financial product;

[0008] Based on the description text, determining a product label vector for each financial product;

[0009] Based on the matching result between the user label vector and the product label vector, the financial product is pushed to the target user.

[0010] In an exemplary embodiment of the present disclosure, determining the user tag vector of the target user based on the webpage text includes:

[0011] Performing word segmentation on the webpage text;

[0012] For each separated word, input it into the CBOW model to obtain the word vector of each separated word;

[0013] Using the words separated from the webpage text that are identical to the concept words in the preset concept word library as user concept words for the target user;

[0014] Using the words other than the user concept words among the words separated from the webpage text as the behavior text words for the target user;

[0015] Based on the matching result of the word vector of the user concept word and the word vector of the behavior text word, a user label vector of the target user is determined.

[0016] In an exemplary embodiment of the present disclosure, determining the user label vector of the target user based on the matching result of the word vector of the user concept word and the word vector of the behavior text word includes:

[0017] For each of the user concept words, determining an average value of the cosine distances between the word vectors of all the behavior text words and the word vector of the user concept word;

[0018] According to the pre-ordering of the user concept words, for each of the user concept words, the corresponding cosine distance average values ​​are sequentially arranged as vector elements, and the arranged vector elements are packaged as the user label vector of the target user.

[0019] In an exemplary embodiment of the present disclosure, determining a product label vector of each financial product based on the description text includes:

[0020] Segmenting the description text;

[0021] For each separated word, input it into the CBOW model to obtain the word vector of each separated word;

[0022] Using the same word as the user concept word as the product concept word for the financial product;

[0023] Using the words separated from the description text, except for the product concept words, as description text words for the financial product;

[0024] Based on the matching result of the word vector of the product concept word and the word vector of the description text word, a product label vector of the financial product is determined.

[0025] In an exemplary embodiment of the present disclosure, determining the product label vector of the financial product based on the matching result of the word vector of the product concept word and the word vector of the description text word includes:

[0026] For each of the product concept words, determining an average value of the cosine distances between the word vectors of all the description text words and the word vector of the product concept word;

[0027] According to the pre-ordering of the product concept words, for each of the product concept words, the corresponding cosine distance average values ​​are arranged in turn as a vector element, and the arranged vector elements are encapsulated as the product label vector of the financial product.

[0028] In an exemplary embodiment of the present disclosure, based on the matching result between the user label vector and the product label vector, pushing a financial product to the target user includes:

[0029] For each of the financial products, determining a cosine distance value between a product label vector corresponding to the financial product and a user label vector corresponding to the target user;

[0030] The cosine distance values ​​are sorted from large to small, and the financial product corresponding to the largest cosine distance value is pushed to the target user.

[0031] According to a second aspect of the present disclosure, there is provided a financial product recommendation device based on data analysis, comprising:

[0032] The first acquisition module is used to acquire the webpage text browsed by the target user;

[0033] A first determination module, configured to determine a user tag vector of the target user based on the webpage text;

[0034] A second acquisition module is used to acquire, for each financial product, a description text describing the financial product;

[0035] A second determination module, configured to determine a product label vector of each financial product based on the description text;

[0036] A matching module is used to push financial products to the target user based on the matching result between the user label vector and the product label vector.

[0037] According to a third aspect of the present disclosure, there is provided an electronic device for recommending financial products based on data analysis, comprising:

[0038] A memory configured to store executable instructions.

[0039] The processor is configured to execute the executable instructions stored in the memory to perform the above method.

[0040] According to a fourth aspect of the present disclosure, a computer-readable program medium is provided, which stores computer program instructions. When the computer instructions are executed by a computer, the computer executes the method described above.

[0041] Compared with the traditional technology in which financial products are pushed to target users directly based on the matching of the labels of the financial products with the labels of the target users, the embodiments of the present disclosure improve the accuracy of pushing financial products to target users by first mathematically measuring the labels of the financial products and the labels of the target users, expressing them as vectors respectively, and then matching them by the cosine distance between the vectors.

[0042] Other features and advantages of the present disclosure will become apparent from the following detailed description, or may be learned in part by the practice of the present disclosure.

[0043] It is to be understood that the foregoing general description and the following detailed description are exemplary only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 A flowchart of financial product recommendation based on data analysis according to an example implementation of the present disclosure is shown.

[0045] Figure 2 A block diagram of a financial product recommendation device based on data analysis according to an example embodiment of the present disclosure is shown.

[0046] Figure 3 A detailed flowchart of determining a user tag vector of the target user based on the webpage text according to an example implementation of the present disclosure is shown.

[0047] Figure 4 A detailed flowchart of determining the user label vector of the target user based on the matching results of the word vector of the user concept word and the word vector of the behavior text word according to an example implementation of the present disclosure is shown.

[0048] Figure 5 A detailed flowchart of determining a product label vector for each financial product based on the description text according to an exemplary embodiment of the present disclosure is shown.

[0049] Figure 6 A detailed flowchart of determining a product label vector for the financial product based on the matching results of the word vectors of the product concept words and the word vectors of the description text words according to an example implementation of the present disclosure is shown.

[0050] Figure 7 A detailed flowchart of pushing a financial product to the target user based on a matching result between the user label vector and the product label vector according to an example implementation of the present disclosure is shown.

[0051] Figure 8 A system architecture diagram of financial product recommendation based on data analysis according to an example implementation of the present disclosure is shown.

[0052] Fig. 9 A diagram of an electronic device showing financial product recommendation based on data analysis according to an example embodiment of the present disclosure.

[0053] Fig.10 A diagram of a computer-readable storage medium showing financial product recommendation based on data analysis according to an example embodiment of the present disclosure. DETAILED DESCRIPTION

[0054] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as being limited to the examples set forth herein; on the contrary, these embodiments are provided so that the present disclosure will be more comprehensive and complete, and the concepts of the example embodiments are fully conveyed to those skilled in the art. The described features, structures, or characteristics may be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced while omitting one or more of the specific details, or other methods, components, devices, steps, etc. may be adopted. In other cases, known technical solutions are not shown or described in detail to avoid obscuring various aspects of the present disclosure.

[0055] In addition, the accompanying drawings are only schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor devices and / or microcontroller devices.

[0056] The purpose of the present disclosure is to improve the accuracy of pushing financial products to target users from a technical aspect. According to an embodiment of the present disclosure, a financial product recommendation method based on data analysis includes: obtaining web page texts that the target user has browsed within a predetermined time period; determining the user tag vector of the target user based on the web page text; obtaining, for each financial product, a description text describing the financial product; determining the product tag vector of each financial product based on the description text; and pushing the financial product to the target user based on the matching result of the user tag vector and the product tag vector. Compared with the traditional technology in which financial products are pushed to target users directly based on the matching of the labels of the financial products with the labels of the target users, the embodiment of the present disclosure improves the accuracy of pushing financial products to target users by first mathematically measuring the labels of the financial products and the labels of the target users, respectively expressing them as vectors, and then matching them by the cosine distance between the vectors.

[0057] Figure 1 A flowchart of financial product recommendation based on data analysis according to an example implementation of the present disclosure is shown below:

[0058] Step S100: obtaining the webpage texts browsed by the target user within a predetermined time period;

[0059] Step S110: determining a user tag vector of the target user based on the webpage text;

[0060] Step S120: for each financial product, obtaining a description text describing the financial product;

[0061] Step S130: determining a product label vector of each financial product based on the description text;

[0062] Step S140: Pushing financial products to the target user based on the matching result between the user label vector and the product label vector.

[0063] Below, each step of the above-mentioned financial product recommendation method based on data analysis in this example implementation will be explained and illustrated in detail with reference to the accompanying drawings.

[0064] In step S100, the webpage texts browsed by the target user within a predetermined time period are obtained.

[0065] Target users refer to users to whom you want to push financial products.

[0066] By acquiring the webpage texts browsed by the target user within a predetermined time period, the server can judge the preferences and behavioral tendencies of the target user based on the webpage texts.

[0067] In one embodiment, if a user shows a willingness to purchase a financial product, such as browsing an introduction page of a financial product, the user is determined as a target user to whom the financial product is recommended. From the log of the target user's client behavior recorded by the server, all web pages browsed by the target user within a predetermined time period, such as within 12 hours before the current time point, are determined, and the text content of the web pages is crawled to obtain the text of the web pages browsed by the target user within the predetermined time period.

[0068] In step S110, a user tag vector of the target user is determined based on the webpage text.

[0069] In one embodiment, if Figure 3 As shown, step S110 includes:

[0070] Step S1101: segmenting the webpage text;

[0071] Step S1102: input each separated word into the CBOW model to obtain a word vector for each separated word;

[0072] Step S1103: using the words separated from the webpage text that are identical to the concept words in the preset concept word library as user concept words for the target user;

[0073] Step S1104: using the words separated from the webpage text except the user concept words as the behavior text words for the target user;

[0074] Step S1105: Determine a user label vector of the target user based on the matching between the user concept word and the behavior text word.

[0075] The user label vector refers to a vector composed of a group of numbers in sequence after each user concept word of the target user is digitally measured according to a predetermined rule.

[0076] Through this method, digital measurement of user concept words of target users is achieved.

[0077] In one embodiment, after the web page text is segmented, each word is obtained. For each unique word, it is represented as a discrete word vector of [0, 0, ..., 1, 0, ..., 0]. The dimension of each word vector is equal to the number of unique words in the separated words. The discrete word vector assignment is direct and simple, but it cannot reflect the relationship between words. For the input discrete word vector, the CBOW model will output the probability of the current input word appearing according to the known context. Among the outputs of the model, there is a byproduct parameter, which is the distributed word vector of the current input word, such as [0.8, ..., -1.3, 0.5, ..., 1.4]. In this way, the similarity between words can be measured by the cosine distance between vectors. Therefore, for each separated word, it is first assigned a discrete word vector, and then it is input into the CBOW model to obtain a distributed word vector.

[0078] In one embodiment, after the webpage text is segmented, the words obtained are "running", "swimming", "diet", "sports", "steak", and "moon cake". The preset concept word library includes the words "sports", "diet", and "shopping", so the user concept words of the target user are "sports" and "diet", and the behavior text words are "running", "swimming", "steak", and "moon cake".

[0079] In one embodiment, if Figure 4 As shown, step S1105 includes:

[0080] Step S11051: for each of the user concept words, determine the average value of the cosine distance between the word vectors of all the behavior text words and the word vector of the user concept word;

[0081] Step S11052: according to the pre-ordering of the user concept words, for each of the user concept words, the corresponding cosine distance average values ​​are arranged in turn as a vector element, and the arranged vector elements are encapsulated as a user label vector of the target user.

[0082] In one embodiment, distributed word vectors are obtained for all separated words, and the user concept words are sorted in the order of pinyin letters, that is, the order of user concept words is: "diet", "exercise". For the user concept word "diet", the average cosine distance between the word vectors of all behavior text words and the word vector of "diet" is determined, and the obtained cosine distance average is 0.2. For the user concept word "exercise", the average cosine distance between the word vectors of all behavior text words and the word vector of "exercise" is determined, and the obtained cosine distance average is 0.6. According to the pre-arranged order of the user concept words, the obtained cosine distance averages are arranged as vector elements, and then encapsulated as the user label vector of the target user: [0.2, 0.6].

[0083] In step S120, for each financial product, a description text describing the financial product is obtained.

[0084] Explanatory text refers to the text that explains and describes the financial product in detail.

[0085] By acquiring the description text describing the financial product, the server can determine the applicable user group of the financial product based on the description text.

[0086] In step S130 , a product label vector of each financial product is determined based on the description text.

[0087] In one embodiment, if Figure 5 As shown, step S130 includes:

[0088] Step S1301: segmenting the description text;

[0089] Step S1302: input each separated word into the CBOW model to obtain a word vector for each separated word;

[0090] Step S1303: using the word identical to the user concept word as a product concept word for the financial product;

[0091] Step S1304: using the words separated from the description text, except for the product concept words, as description text words for the financial product;

[0092] Step S1305: Determine a product label vector of the financial product based on the matching between the product concept words and the description text words.

[0093] The product label vector refers to a vector composed of a group of numbers in sequence after each product concept word of a financial product is digitally measured according to predetermined rules.

[0094] Through this method, digital measurement of product concept words of financial products is achieved.

[0095] In one embodiment, after the description text is segmented, each segmented word is first assigned a discrete word vector, and then input into the CBOW model to obtain a distributed word vector.

[0096] In one embodiment, after the description text is segmented, the words obtained include "income", "running", "exercise", "diet", "fitness", and "meal". Since the user concept words of the target user are "exercise" and "diet", and the product concept words of the financial product are also "exercise" and "diet", the description text words of the financial product are "income", "running", "fitness", and "meal".

[0097] In one embodiment, if Figure 6 As shown, step S1305 includes:

[0098] Step S13051: for each of the product concept words, determine the average value of the cosine distance between the word vectors of all the description text words and the word vector of the product concept word;

[0099] Step S13052: according to the pre-ordering of the product concept words, for each of the product concept words, the corresponding cosine distance average values ​​are arranged in turn as a vector element, and the arranged vector elements are packaged as the product label vector of the financial product.

[0100] In one embodiment, distributed word vectors are obtained for all separated words, and the product concept words are sorted in the order of pinyin letters, that is, the order of the product concept words is: "diet", "exercise". For the product concept word "diet", the average cosine distance between the word vectors of all descriptive text words and the word vector of "diet" is determined, and the obtained cosine distance average is -0.3. For the product concept word "exercise", the average cosine distance between the word vectors of all descriptive text words and the word vector of "exercise" is determined, and the obtained cosine distance average is 0.5. According to the pre-arranged order of the product concept words, the obtained cosine distance averages are arranged as vector elements, and then packaged into the user label vector of the target user: [-0.3, 0.5].

[0101] In step S140, based on the matching result between the user label vector and the product label vector, the financial product is pushed to the target user.

[0102] In one embodiment, if Figure 7 As shown, step S140 includes:

[0103] Step S1401: for each of the financial products, determining a cosine distance value between a product label vector corresponding to the financial product and a user label vector corresponding to the target user;

[0104] Step S1402: sort the cosine distance values ​​from large to small, and push the financial product corresponding to the largest cosine distance value to the target user.

[0105] In one embodiment, the user label vector corresponding to the target user is [0.2, 0.6], the product label vector corresponding to financial product A is [0.3, 0.5], the product label vector corresponding to financial product B is [-0.3, 0.2], and the product label vector corresponding to financial product C is [0.1, 0.7]. The cosine distances between the product label vectors corresponding to financial products A, B, and C and the user label vector corresponding to the target user are calculated to be 0.976, 0.263, and 0.983, respectively. The cosine distance between the product label vector corresponding to financial product C and the user label vector corresponding to the target user is the largest, and financial product C is pushed to the target user.

[0106] In one embodiment, if Figure 2 As shown, a financial product recommendation device based on data analysis is provided, which specifically includes:

[0107] The first acquisition module 210 is used to acquire the text of the webpage browsed by the target user;

[0108] A first determination module 220, configured to determine a user tag vector of the target user based on the webpage text;

[0109] The second acquisition module 230 is used to acquire, for each financial product, a description text describing the financial product;

[0110] A second determination module 240, configured to determine a product label vector for each financial product based on the description text;

[0111] The matching module 250 is used to push financial products to the target user based on the matching result between the user label vector and the product label vector.

[0112] The implementation process of the functions and effects of each module in the above-mentioned device is specifically described in the implementation process of the corresponding steps in the above-mentioned financial product recommendation method based on data analysis, and will not be repeated here.

[0113] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into multiple modules or units to be embodied.

[0114] In addition, although the steps of the method in the present disclosure are described in a specific order in the drawings, this does not require or imply that the steps must be performed in this specific order, or that all the steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps, etc.

[0115] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0116] Figure 8 The system architecture diagram of financial product recommendation based on data analysis according to an exemplary embodiment of the present disclosure is shown. The system architecture includes: a target user client 310, a server 320, and a database 330.

[0117] In one embodiment, for a target user, the target user client 310 performs various requests and operations on the server 320, such as browsing a web page. The server 320 extracts the record of the user client 310 browsing a web page within a predetermined time period in the log, obtains the corresponding web page, and determines the label vector of the target user client 310 according to the web page. The server 320 extracts the description text of each financial product stored in the database 330, and determines the product vector of each financial product according to the description text. The server 320 matches the target user with the financial product according to the label vector and the product vector, thereby pushing the financial product to the target user.

[0118] Through the above description of the system architecture, it is easy for those skilled in the art to understand that the system architecture described here can achieve Figure 2 The functions of each module in the financial product recommendation device based on data analysis are shown.

[0119] In an exemplary embodiment of the present disclosure, an electronic device capable of implementing the above method is also provided.

[0120] It will be appreciated by those skilled in the art that various aspects of the present invention may be implemented as a system, method or program product. Therefore, various aspects of the present invention may be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software, which may be collectively referred to herein as a "circuit", "module" or "system".

[0121] Refer to the following Fig. 9 An electronic device 400 according to this embodiment of the present invention will be described. Fig. 9 The electronic device 400 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0122] like Fig. 9 As shown, the electronic device 400 is in the form of a general computing device. The components of the electronic device 400 may include but are not limited to: at least one processing unit 410, at least one storage unit 420, and a bus 430 connecting different system components (including the storage unit 420 and the processing unit 410).

[0123] The storage unit stores program codes, which can be executed by the processing unit 410, so that the processing unit 410 performs the steps according to various exemplary embodiments of the present invention described in the above “Exemplary Method” section of this specification. For example, the processing unit 410 can perform the following steps: Figure 1 Step S100 shown in: obtaining the web page text browsed by the target user within a predetermined time period; step S110: determining the user tag vector of the target user based on the web page text; step S120: for each financial product, obtaining the description text describing the financial product; step S130: determining the product tag vector of each financial product based on the description text; step S140: pushing the financial product to the target user based on the matching result of the user tag vector and the product tag vector.

[0124] The storage unit 420 may include a readable medium in the form of a volatile storage unit, such as a random access storage unit (RAM) 4201 and / or a cache storage unit 4202 , and may further include a read-only storage unit (ROM) 4203 .

[0125] The storage unit 420 may also include a program / utility 4204 having a set (at least one) of program modules 4205, such program modules 4205 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0126] Bus 430 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0127] The electronic device 400 may also communicate with one or more external devices 500 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 400, and / or communicate with any device that enables the electronic device 400 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 450. Furthermore, the electronic device 400 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter 460. As shown, the network adapter 460 communicates with other modules of the electronic device 400 via a bus 430. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 400, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0128] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0129] In an exemplary embodiment of the present disclosure, a computer-readable storage medium is also provided, on which a program product capable of implementing the above method of the present specification is stored. In some possible implementations, various aspects of the present invention can also be implemented in the form of a program product, which includes a program code, and when the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps according to various exemplary embodiments of the present invention described in the above "Exemplary Method" section of the present specification.

[0130] refer to Fig.10 As shown, a program product 600 for implementing the above method according to an embodiment of the present invention is described, which can adopt a portable compact disk read-only memory (CD-ROM) and include program code, and can be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto. In this document, a readable storage medium can be any tangible medium containing or storing a program, which can be used by or in combination with an instruction execution system, an apparatus or a device.

[0131] The program product may use any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The 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 (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable 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.

[0132] Computer readable signal media may include data signals propagated in baseband or as part of a carrier wave, in which readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Readable signal media may also be any readable medium other than a 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.

[0133] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.

[0134] Program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device may 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 may be connected to an external computing device (e.g., through the Internet using an Internet service provider).

[0135] In addition, the above-mentioned figures are only schematic illustrations of the processes included in the method according to an exemplary embodiment of the present invention, and are not intended to be limiting. It is easy to understand that the processes shown in the above-mentioned figures do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be performed synchronously or asynchronously, for example, in multiple modules.

[0136] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary technical means in the art that are not disclosed in the present disclosure. The specification and examples are to be considered as exemplary only, and the true scope and spirit of the present disclosure are indicated by the claims.

Claims

1. A financial product recommendation method based on data analysis, characterized in that: include: Acquire webpage texts browsed by a target user within a predetermined time period, wherein the webpage texts contain user concept words and behavior text words of the target user, wherein the user concept words refer to words in the webpage texts that are identical to concept words in a preset concept word library, and the behavior text words refer to words in the webpage texts other than the user concept words; For each of the user concept words, determine the average cosine distance between the word vectors of all the behavior text words and the word vector of the user concept word, and according to the pre-sorting of all the user concept words, sequentially arrange the average cosine distance corresponding to each of the user concept words as a vector element, and encapsulate the arranged vector elements as the user label vector of the target user; For each financial product, obtain a description text describing the financial product, wherein the description text includes a product concept word and a description text word, wherein the product concept word refers to a word in the description text that is the same as the user concept word, and the description text word refers to a word in the description text other than the product concept word; For each of the product concept words, determine the average cosine distance between the word vectors of all the description text words and the word vector of the product concept word, and according to the pre-sorting of the product concept words, for each of the product concept words, sequentially arrange the corresponding cosine distance average values ​​as a vector element, and encapsulate the arranged vector elements as the product label vector of the financial product; Based on the matching result between the user label vector and the product label vector, the financial product is pushed to the target user.

2. The method according to claim 1, characterized in that Pushing a financial product to the target user based on a matching result between the user label vector and the product label vector includes: For each of the financial products, determining a cosine distance value between a product label vector corresponding to the financial product and a user label vector corresponding to the target user; The cosine distance values ​​are sorted from large to small, and the financial product corresponding to the largest cosine distance value is pushed to the target user.

3. A financial product recommendation device based on data analysis, characterized in that: include: The first acquisition module is used to acquire webpage texts browsed by a target user within a predetermined time period, wherein the webpage texts contain user concept words and behavior text words of the target user, wherein the user concept words refer to words in the webpage text that are identical to concept words in a preset concept word library, and the behavior text words refer to words in the webpage text other than the user concept words; The first determination module is used to determine, for each user concept word, the average cosine distance between the word vectors of all the behavior text words and the word vector of the user concept word, and according to the pre-sorting of all the user concept words, sequentially arrange the average cosine distance corresponding to each user concept word as a vector element, and encapsulate the arranged vector elements as the user label vector of the target user; A second acquisition module is used to acquire, for each financial product, an explanatory text describing the financial product, wherein the explanatory text includes product concept words and description text words, wherein the product concept words refer to words in the explanatory text that are the same as the user concept words, and the description text words refer to words in the explanatory text other than the product concept words; The second determination module is used to determine, for each of the product concept words, the average cosine distance between the word vectors of all the description text words and the word vector of the product concept word, and according to the pre-sorting of the product concept words, for each of the product concept words, sequentially arrange the corresponding cosine distance average as a vector element, and encapsulate the arranged vector elements as the product label vector of the financial product; A matching module is used to push financial products to the target user based on the matching result between the user label vector and the product label vector.

4. An electronic device for recommending financial products based on data analysis, characterized in that: include: a memory configured to store executable instructions; A processor configured to execute the executable instructions stored in the memory to perform the method according to any one of claims 1-2.

5. A computer-readable program medium, characterized in that: The computer program instructions are stored therein, and when the computer program instructions are executed by a computer, the computer is caused to execute the method according to any one of claims 1-2.

Images