Information recommendation method and device, electronic device and medium

Abstract

The present disclosure provides an information recommendation method, device, electronic device, computer-readable storage medium and computer program product, which relate to the computer field, and in particular to the intelligent recommendation and natural language processing technology fields. The implementation scheme is: determining one or more first text contents of the user to be recommended and their corresponding first feature words; obtaining multiple reference text contents, which are associated with corresponding recommendation information, and determining the second feature words corresponding to the multiple reference text contents; according to the first feature words and the second feature words, determining the binarization vectors of the first text content and the reference text content based on the text semantic hash algorithm, so as to determine the second text content similar to the first text content from the multiple reference text contents based on the binarization vector for each first text content; and counting the recommended information associated with all the second text contents, so as to adopt a voting mechanism to recommend information to the user.

Description

Technical Field

[0001] The present disclosure relates to the field of computers, and in particular to the fields of intelligent recommendation and natural language processing technology, and specifically to an information recommendation method, device, electronic device, computer-readable storage medium, and computer program product. Background Art

[0002] Artificial intelligence is a discipline that studies how to use computers to simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, planning, etc.). It includes both hardware-level and software-level technologies. Artificial intelligence hardware technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, and big data processing. Artificial intelligence software technologies mainly include computer vision technology, speech recognition technology, natural language processing technology, as well as machine learning / deep learning, big data processing technology, knowledge graph technology, and other major directions.

[0003] With the development of the Internet and artificial intelligence, the amount of various network information and products has increased exponentially. Some network users recommend relevant network information or products by creating text content. Therefore, how to choose the right network information or product to mount becomes the key. Summary of the invention

[0004] The present disclosure provides an information recommendation method, device, electronic device, computer-readable storage medium, and computer program product.

[0005] According to one aspect of the present disclosure, a computer-implemented information recommendation method is provided, comprising: determining first feature words corresponding to one or more first text contents of a user; acquiring multiple reference text contents, and determining second feature words corresponding to the multiple reference text contents; based on the corresponding first feature words and second feature words, using a hash algorithm to obtain binary text feature vectors corresponding to the one or more first text contents and the multiple reference text contents; for each of the one or more first text contents, determining, from the multiple reference text contents, based on the binary text feature vector, second text content whose similarity with the first text content meets a first threshold; and recommending information to the user based on the recommended information associated with all the second text contents.

[0006] According to another aspect of the present disclosure, there is provided an information recommendation device, comprising: a first determination unit, configured to determine first feature words respectively corresponding to one or more first text contents of a user; a second determination unit, configured to obtain multiple reference text contents, and determine second feature words respectively corresponding to the multiple reference text contents; an acquisition unit, configured to obtain binary text feature vectors respectively corresponding to the one or more first text contents and the multiple reference text contents using a hash algorithm based on the corresponding first feature words and second feature words; a third determination unit, configured to determine, for each of the one or more first text contents, from the multiple reference text contents, second text contents whose similarity with the first text content meets a first threshold based on the binary text feature vector; and a recommendation unit, configured to recommend information to the user based on the recommended information associated with all the second text contents.

[0007] According to another aspect of the present disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method described in the present disclosure.

[0008] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided. The computer instructions are used to cause a computer to execute the method described in the present disclosure.

[0009] According to another aspect of the present disclosure, a computer program product is provided, including a computer program, which implements the method described in the present disclosure when executed by a processor.

[0010] According to one or more embodiments of the present disclosure, user characteristics can be characterized based on the user's text content, the similarity between text contents, and high-quality text content similar to the user's posting, so as to recommend information associated with the high-quality text content to the user; and, by converting high-dimensional vectors into binary vectors through a hash algorithm, the amount of calculation can be greatly reduced when the amount of data is large, thereby improving both the accuracy of information recommendation and the efficiency of data processing.

[0011] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The accompanying drawings exemplarily illustrate the embodiments and constitute a part of the specification, and together with the text description of the specification, are used to explain the exemplary implementation of the embodiments. The embodiments shown are for illustrative purposes only and do not limit the scope of the claims. In all drawings, the same reference numerals refer to similar but not necessarily identical elements.

[0013] Figure 1 A schematic diagram showing an exemplary system in which the various methods described herein may be implemented according to an embodiment of the present disclosure;

[0014] Figure 2 A flowchart of an information recommendation method according to an embodiment of the present disclosure is shown;

[0015] Figure 3 A flowchart of obtaining multiple reference text contents according to an embodiment of the present disclosure is shown;

[0016] Figure 4 A schematic diagram showing a method of learning hash codes from text feature vectors of m documents by combining multiple Bayesian clustering according to an embodiment of the present disclosure;

[0017] Figure 5 A schematic diagram showing a method of recommending products to a user according to an embodiment of the present disclosure is shown;

[0018] Figure 6 A flowchart of an information recommendation method according to an exemplary embodiment of the present disclosure is shown;

[0019] Figure 7 A structural block diagram of an information recommendation device according to an embodiment of the present disclosure is shown; and

[0020] Figure 8 A structural block diagram of an exemplary electronic device that can be used to implement the embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0021] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope of the present disclosure. Similarly, for the sake of clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0022] In the present disclosure, unless otherwise specified, the use of the terms "first", "second", etc. to describe various elements is not intended to limit the positional relationship, timing relationship, or importance relationship of these elements, and such terms are only used to distinguish one element from another element. In some examples, the first element and the second element may refer to the same instance of the element, and in some cases, based on the description of the context, they may also refer to different instances.

[0023] The terms used in the description of various examples in this disclosure are only for the purpose of describing specific examples and are not intended to be limiting. Unless the context clearly indicates otherwise, if the number of elements is not specifically limited, the element can be one or more. In addition, the term "and / or" used in this disclosure covers any one of the listed items and all possible combinations.

[0024] The embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

[0025] Figure 1 FIG. 1 is a schematic diagram of an exemplary system 100 in which various methods and apparatuses described herein may be implemented according to an embodiment of the present disclosure. Figure 1 , the system 100 includes one or more client devices 101, 102, 103, 104, 105, and 106, a server 120, and one or more communication networks 110 coupling the one or more client devices to the server 120. The client devices 101, 102, 103, 104, 105, and 106 may be configured to execute one or more applications.

[0026] In an embodiment of the present disclosure, the server 120 may run one or more services or software applications that enable the information recommendation method to be performed.

[0027] In some embodiments, server 120 may also provide other services or software applications that may include non-virtualized environments and virtualized environments. In some embodiments, these services may be provided as web-based services or cloud services, such as provided to users of client devices 101, 102, 103, 104, 105, and / or 106 under a software as a service (SaaS) model.

[0028] exist Figure 1In the configuration shown, the server 120 may include one or more components that implement the functions performed by the server 120. These components may include software components, hardware components, or a combination thereof that can be executed by one or more processors. Users operating client devices 101, 102, 103, 104, 105, and / or 106 may in turn utilize one or more client applications to interact with the server 120 to utilize the services provided by these components. It should be understood that a variety of different system configurations are possible, which may differ from the system 100. Therefore, Figure 1 is one example of a system for implementing the various methods described herein and is not intended to be limiting.

[0029] The user may use client devices 101, 102, 103, 104, 105 and / or 106 to upload authored articles, select recommended information, etc. The client device may provide an interface that enables the user of the client device to interact with the client device. The client device may also output information to the user via the interface. Figure 1 Only six client devices are depicted, but one skilled in the art will appreciate that the present disclosure may support any number of client devices.

[0030] Client devices 101, 102, 103, 104, 105 and / or 106 may include various types of computer devices, such as portable handheld devices, general-purpose computers (such as personal computers and laptop computers), workstation computers, wearable devices, smart screen devices, self-service terminal devices, service robots, game systems, thin clients, various messaging devices, sensors or other sensing devices, etc. These computer devices may run various types and versions of software applications and operating systems, such as MICROSOFT Windows, APPLE iOS, UNIX-like operating systems, Linux or Linux-like operating systems (such as GOOGLE Chrome OS); or include various mobile operating systems, such as MICROSOFT Windows Mobile OS, iOS, Windows Phone, Android. Portable handheld devices may include cellular phones, smart phones, tablet computers, personal digital assistants (PDAs), etc. Wearable devices may include head-mounted displays (such as smart glasses) and other devices. Game systems may include various handheld game devices, Internet-enabled game devices, etc. Client devices are capable of executing various different applications, such as various Internet-related applications, communication applications (such as email applications), short message service (SMS) applications, and may use various communication protocols.

[0031] The network 110 may be any type of network known to those skilled in the art that may support data communications using any of a variety of available protocols, including but not limited to TCP / IP, SNA, IPX, etc. By way of example only, the one or more networks 110 may be a local area network (LAN), an Ethernet-based network, a token ring, a wide area network (WAN), the Internet, a virtual network, a virtual private network (VPN), an intranet, an extranet, a public switched telephone network (PSTN), an infrared network, a wireless network (e.g., Bluetooth, WIFI), and / or any combination of these and / or other networks.

[0032] Server 120 may include one or more general purpose computers, dedicated server computers (e.g., PC (personal computer) servers, UNIX servers, mid-range servers), blade servers, mainframe computers, server clusters, or any other suitable arrangement and / or combination. Server 120 may include one or more virtual machines running virtual operating systems, or other computing architectures involving virtualization (e.g., one or more flexible pools of logical storage devices that may be virtualized to maintain a server's virtual storage device). In various embodiments, server 120 may run one or more services or software applications that provide the functionality described below.

[0033] The computing units in the server 120 may run one or more operating systems including any of the above operating systems and any commercially available server operating systems. The server 120 may also run any of a variety of additional server applications and / or middle-tier applications, including HTTP servers, FTP servers, CGI servers, JAVA servers, database servers, etc.

[0034] In some implementations, server 120 may include one or more applications to analyze and consolidate data feeds and / or event updates received from users of client devices 101, 102, 103, 104, 105, and 106. Server 120 may also include one or more applications to display data feeds and / or real-time events via one or more display devices of client devices 101, 102, 103, 104, 105, and 106.

[0035] In some embodiments, the server 120 may be a server of a distributed system, or a server combined with a blockchain. The server 120 may also be a cloud server, or an intelligent cloud computing server or intelligent cloud host with artificial intelligence technology. A cloud server is a host product in a cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and virtual private servers (VPS) services.

[0036] The system 100 may also include one or more databases 130. In some embodiments, these databases may be used to store data and other information. For example, one or more of the databases 130 may be used to store information such as audio files and video files. The databases 130 may reside in various locations. For example, the database used by the server 120 may be local to the server 120, or may be remote from the server 120 and may communicate with the server 120 via a network-based or dedicated connection. The databases 130 may be of different types. In some embodiments, the databases used by the server 120 may be, for example, relational databases. One or more of these databases may store, update, and retrieve data to and from the databases in response to commands.

[0037] In some embodiments, one or more of the databases 130 may also be used by applications to store application data. The databases used by the applications may be different types of databases, such as a key-value store, an object store, or a conventional store backed by a file system.

[0038] Figure 1 The system 100 may be configured and operated in various ways to enable the application of various methods and apparatuses described in the present disclosure.

[0039] With the abundance of online information today, many online authors have emerged to recommend relevant information, including product recommendations. Specifically, product recommendations (content-driven sales) refer to authors attaching related products while creating content to promote user purchases. In the feed multi-monetization scenario, there are some novice authors with the potential to drive sales, but these authors do not know how to choose the right products to drive sales.

[0040] Usually, the features of multiple products to be recommended (such as popularity, sales volume, commission, etc.) can be obtained, and recommendations can be made to users after sorting based on the features. However, the method of recommending based on product features is difficult to ensure the relevance between the product and the author due to the lack of characterization of the author's behavior, and personalized recommendations cannot be made. Alternatively, it is also possible to find products similar to the author's posting content based on the author's historical posts and recommend them to the author. However, the recommendation method based on the similarity between article content and products only considers the similarity between article content and product content, and fails to make full use of the mounting behavior of existing authors with goods, making it difficult to solve the following problems: A home author who often publishes articles on interior decoration may not be able to match green plants in terms of text, making it difficult to recommend green plant products. However, historical data shows that the conversion rate of home authors mounting green plant-related products to promote user purchases is very high.

[0041] Therefore, according to an embodiment of the present disclosure, a computer-implemented information recommendation method is provided. Figure 2 As shown, the information recommendation method 200 includes: determining first feature words corresponding to one or more first text contents of the user (step 210); obtaining multiple reference text contents, and determining second feature words corresponding to the multiple reference text contents (step 220); based on the corresponding first feature words and second feature words, using a hash algorithm to obtain binary text feature vectors corresponding to one or more first text contents and multiple reference text contents (step 230); for each of the one or more first text contents, determining second text contents whose similarity with the first text content meets a first threshold from multiple reference text contents based on the binary text feature vector (step 240); and recommending information to the user based on the recommended information associated with all second text contents (step 250).

[0042] According to the embodiments of the present disclosure, user characteristics can be characterized based on the user's text content, the similarity between text contents, and high-quality text content similar to the user's posting, so as to recommend information associated with the high-quality text content to the user; and, by converting high-dimensional vectors into binary vectors through a hash algorithm, the amount of calculation can be greatly reduced when the amount of data is large, thereby improving the accuracy of information recommendation and improving data processing efficiency.

[0043] In step 210, first feature words corresponding to one or more first text contents of the user are determined.

[0044] In some embodiments, the information includes the goods to be mounted. One or more first text contents of the user are obtained, and the user may be a novice author with potential for bringing goods. Therefore, the one or more first text contents may be the captured historical postings of the novice author.

[0045] In some embodiments, articles (i.e., first text content) within a predetermined time period (e.g., within the past month) can be captured on the platform. First, data preprocessing can be performed on the captured articles. For example, some invalid data resources can be deleted, including but not limited to articles that have not been reviewed, articles without titles, etc. Additionally or alternatively, articles by authors whose publication volume is less than a predetermined number (e.g., 5 articles) can also be deleted, because authors with too few publications may not be suitable for recommending information such as goods.

[0046] In some examples, the content of authors whose posts have more than a predetermined number of category labels (e.g., 3 categories) can also be deleted, because authors who post too many categories of posts may not be suitable for building a recommendation system for fine-grained information such as goods. The category label of an article can be automatically identified by the platform according to the content of the article, or it can be automatically selected by the author when uploading the article, and there is no limitation here.

[0047] After obtaining the first text content (ie, article), the corresponding first characteristic words can be obtained based on the text content. It should be noted that the first characteristic words here include one or more characteristic words, that is, a first text content can include one or more first characteristic words.

[0048] In some embodiments, the predetermined content of the acquired first text content may be segmented to obtain the first characteristic word. For example, the title of the first text content may be segmented to obtain the first characteristic word. The segmentation may be performed based on any suitable algorithm or method based on natural language processing (NLP), which is not limited here.

[0049] In step 220, a plurality of reference text contents are obtained, and second characteristic words respectively corresponding to the plurality of reference text contents are determined.

[0050] In some embodiments, a plurality of reference text contents are obtained. For example, the reference text contents may be posts or articles by authors with relatively high quality on the platform.

[0051] In some embodiments, high-quality articles (i.e., reference text content) within a predetermined time period (e.g., within the past three months) can be captured on the platform. First, data preprocessing can also be performed on the captured articles. For example, some invalid data resources can be deleted, including but not limited to articles that have not been reviewed, articles without titles, etc. Additionally or alternatively, articles by authors whose publication volume is less than a predetermined number (e.g., 5 articles) can also be deleted; content by authors whose publication classification labels are greater than a predetermined category (e.g., 3 categories) can also be deleted, and so on.

[0052] In some embodiments, Figure 3 As shown, when the information to be recommended includes commodities, obtaining multiple reference text contents may include: obtaining a first number of reference text contents within a first predetermined time period (step 310); sorting the first number of reference text contents based on commodity conversion rates and / or gross merchandise volume (GMV) of the recommended information associated with each of the first number of reference text contents (step 320); and obtaining multiple reference text contents based on the sorting results (step 330).

[0053] The product conversion rate and the total amount of product transactions can be data used to evaluate the user's ability to bring goods. For example, the product conversion rate, GMV (total amount of goods transactions) and other data of the articles bringing goods (i.e., the reference text content) can be considered and sorted comprehensively (for example, sorted after weighted summation), and the tail resources can be removed, so as to remove the non-high-quality articles bringing goods and obtain multiple high-quality articles bringing goods as reference text content.

[0054] After obtaining the reference text content, the corresponding second characteristic words can be obtained based on the reference text content. It should also be noted that the second characteristic words here include one or more characteristic words, that is, a reference text content can include one or more second characteristic words.

[0055] In some embodiments, the predetermined content of the obtained reference text content may be segmented to obtain the second characteristic word. For example, the title of the reference text content may be segmented to obtain the second characteristic word. The segmentation may be based on any suitable algorithm or method based on natural language processing (NLP), which is not limited here.

[0056] In some embodiments, the first feature word and the second feature word may further include classification labels of the first text content and the reference text content, respectively, which is not limited here.

[0057] In step 230, based on the corresponding first feature words and second feature words, a hash algorithm is used to obtain binary text feature vectors corresponding to the one or more first text contents and the multiple reference text contents. And, in step 240, for each of the one or more first text contents, a second text content whose similarity with the first text content meets a first threshold is determined from the multiple reference text contents based on the binary text feature vector.

[0058] In some embodiments, step 230 may include: determining text feature vectors corresponding to one or more first text contents and multiple reference text contents respectively based on corresponding first feature words and second feature words; and converting the text feature vectors into binary hash codes through multiple Bayesian clustering algorithms to obtain binary text feature vectors.

[0059] In the present disclosure, a text feature vector may be a digital vector or matrix used to represent the overall content of a text.

[0060] In some embodiments, the text feature vector may include a TF-IDF value. That is, the TF-IDF value corresponding to the corresponding text content may be calculated based on the acquired feature words to serve as the text feature vector of the text content. TF (Term Frequency) is the term frequency, and IDF (Inverse Document Frequency) is the inverse document frequency, which indicates the inverse ratio of the size of a word to common words.

[0061] For example, the TF-IDF value of the text content can be calculated based on the bag of words. The bag of words is a corpus, which is used to simulate the usage environment of the language. For example, the feature words of all the first text content and the reference text content can be used as the bag of words, which is not limited here. When calculating the TF-IDF value of the text content based on the bag of words, the word frequency is first calculated, that is, the word frequency (TF) = the number of times a word appears in the article / the total number of times the article appears. Then the inverse document frequency is calculated, the inverse document frequency (IDF) = log (the total number of documents in the corpus / the number of documents containing the word). Log means taking the logarithm of the obtained value. Then calculate the TF-IDF value: TF-IDF = TF*IDF. It can be seen that TF-IDF is proportional to the number of times a word appears in a document, and inversely proportional to the number of times the word appears in the entire document.

[0062] In some embodiments, respectively determining the text feature vectors corresponding to one or more first text contents and multiple reference text contents may include: determining the word vectors corresponding to the corresponding first feature words and second feature words; and respectively determining the text feature vectors corresponding to one or more first text contents and multiple reference text contents based on the word vectors.

[0063] In some embodiments, determining the text feature vectors corresponding to one or more first text contents and multiple reference text contents respectively based on word vectors includes any one of the following: adding the word vectors corresponding to one or more first text contents and multiple reference text contents respectively to obtain the text feature vectors corresponding to one or more first text contents and multiple reference text contents respectively; and weighted summing the word vectors corresponding to one or more first text contents and multiple reference text contents respectively to obtain the text feature vectors corresponding to one or more first text contents and multiple reference text contents respectively.

[0064] In some embodiments, the hash algorithm includes a text semantic hash algorithm BCTH (A Novel Text Hashing Approach via Bayesian Clustering). Semantic hashing refers to a hash algorithm that maps a high-dimensional space vector to a low-dimensional Hamming space and maintains the similarity of the original space vector, so that the Hamming distance of the new space vector reflects the similarity of the original space vector. Therefore, determining the second text content whose similarity with the first text content meets the first threshold based on the binary text feature vector may include: determining the second text content whose similarity with the first text content meets the first threshold based on the Hamming distance between the binary text feature vectors.

[0065] Semantic hashing introduces the concept of approximation, believing that in most cases, completely accurate searches are not necessary in the search of massive data, and approximate solutions are sufficient to meet the requirements of most users. Therefore, the hash algorithm can quickly locate data related to the search keyword with a certain probability in the data set, combined with the rapidity of the Hamming space similarity measurement and the easy further expansion of index results, which can greatly improve the efficiency of indexing and retrieval.

[0066] Figure 4 A schematic diagram of learning hash codes from text feature vectors of m documents by combining multiple Bayesian clustering according to an embodiment of the present disclosure is shown, wherein the size of the hash code is 4 bits. In some examples, a 32-bit hash can be used to hash embed the text feature vector, that is, the text feature vector is converted into a 32-bit hash code by 32 times of the Bayesian clustering algorithm. Then, the similarity between the corresponding hash codes is calculated based on the Hamming distance to obtain the similarity between the two pairs of text feature vectors (a pair of text feature vectors composed of a first text content and a reference text content). Through the text semantic hash algorithm, high-dimensional vectors can be converted into binary hash codes, which can greatly reduce the amount of calculation and improve data processing efficiency when the amount of data is large.

[0067] In step 250, information is recommended to the user based on all the recommended information associated with the second text content.

[0068] In some embodiments, recommending information to the user based on all the recommended information associated with the second text content may include: counting the number of each piece of recommended information associated with all the second text content; and recommending information to the user based on the statistical result.

[0069] In some embodiments, information can be recommended to users based on a voting mechanism. For example, recommending information to users based on a voting mechanism may include at least one of the following: determining the recommended information whose quantity is greater than a third threshold, so as to recommend information to the user; and determining the recommended information whose quantity is greater than a fourth threshold to the quantity of the one or more first text contents, so as to recommend information to the user.

[0070] For example, user A includes 3 first text contents, among which first text content 1 is similar to reference text content a, and reference text content a is associated with L types of information to be recommended; first text content 2 is similar to reference text content b, and reference text content b is associated with M types of information to be recommended; first text content 3 is similar to reference text content c, and reference text content c is associated with N types of information to be recommended. Statistics are collected on the L types of information to be recommended, the M types of information to be recommended, and the N types of information to be recommended to determine whether there is repeated information to be recommended and the number of repetitions. For example, the first information to be recommended is repeated 3 times, and the second information to be recommended is repeated 2 times... A voting mechanism is used to select several types of high-quality information (such as products) with the highest number of repetitions and recommend them to the user.

[0071] Figure 5 FIG. 2 shows a schematic diagram of recommending products to users according to an embodiment of the present disclosure. Figure 5 As shown, after finding reference articles 1-4 (i.e., the second text content) that are similar to articles 1-3 published by user 1 through similarity calculation, the commodities associated with these reference articles 1-4 are sorted through a voting mechanism and aggregated to user 1. Specifically, a voting mechanism can be used to select several commodities with the highest number of repetitions, and further determine high-quality commodities with a number of correlations with user 1 greater than a threshold (e.g., 0.3*the number of articles published by the user), so as to recommend the determined high-quality information to the user. In this way, the above-mentioned problem of being unable to recommend green plant commodities to home furnishing authors who often publish interior decoration articles can be well solved.

[0072] It should be understood that other methods for recommending the determined associated information to the user are also possible and are not limited here.

[0073] In some embodiments, the method according to the present disclosure may further include: executing the information recommendation method every third predetermined time period. By executing the information recommendation method every predetermined time period (e.g., every month), new users can be discovered regularly and information can be updated in a timely manner, thereby improving the conversion rate of recommended information.

[0074] Figure 6 FIG. 4 is a flowchart of an information recommendation method according to an exemplary embodiment of the present disclosure. Figure 6As shown, in step 610, the user's text content and multiple reference text contents are obtained, and the multiple reference contents are associated with corresponding recommended information; in step 620, the obtained text content is preprocessed to filter out some unqualified text content; in step 630, one or more feature words of each text content are obtained; in step 640, the text feature vector of each text content is determined based on the corresponding feature words; in step 650, the text feature vector is converted into a binary text feature vector through a text semantic hash algorithm; in step 660, similarity calculation is performed based on the binary text feature vector to find reference text contents similar to the user's text content from multiple reference text contents; in step 670, the recommended information associated with all similar reference text contents is determined and counted to determine whether there is repeated information to be recommended and the number of repetitions; in step 680, based on the counted recommended information, a voting mechanism is used to recommend information to the user.

[0075] According to the information recommendation method disclosed in the present invention, high-quality reference text content similar to the article posted by the user (i.e., the author of the article) is found through the similarity between text contents, and the information associated with the high-quality reference text content is summarized to the user to recommend information to the user; and through the text semantic hash algorithm, high-dimensional vectors can be converted into binary hash codes, which can greatly reduce the amount of calculation when the data volume is large and improve data processing efficiency.

[0076] According to the embodiments of the present disclosure, Figure 7 As shown, an information recommendation device 700 is also provided, including: a first determination unit 710, configured to determine the first feature words corresponding to one or more first text contents of the user; a second determination unit 720, configured to obtain multiple reference text contents and determine the second feature words corresponding to the multiple reference text contents; an acquisition unit 730, configured to use a hash algorithm to obtain binary text feature vectors corresponding to the one or more first text contents and the multiple reference text contents based on the corresponding first feature words and second feature words; a third determination unit 740, configured to determine, for each of the one or more first text contents, from the multiple reference text contents, a second text content whose similarity with the first text content meets a first threshold based on the binary text feature vector; and a recommendation unit 750, configured to recommend information to the user based on the recommended information associated with all the second text contents.

[0077] Here, the operations of the above-mentioned units 710 to 750 of the information recommendation device 700 are respectively similar to the operations of the above-described steps 210 to 250, and will not be described in detail here.

[0078] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0079] According to an embodiment of the present disclosure, an electronic device, a readable storage medium and a computer program product are also provided.

[0080] refer to Figure 8 , a block diagram of an electronic device 800 that can be used as a server or client of the present disclosure will now be described, which is an example of a hardware device that can be applied to various aspects of the present disclosure. The electronic device is intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0081] like Figure 8 As shown, the electronic device 800 includes a computing unit 801, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 802 or a computer program loaded from a storage unit 808 into a random access memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the electronic device 800 can also be stored. The computing unit 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0082] Multiple components in the electronic device 800 are connected to the I / O interface 805, including: an input unit 806, an output unit 807, a storage unit 808, and a communication unit 809. The input unit 806 can be any type of device that can input information to the electronic device 800. The input unit 806 can receive input digital or character information and generate key signal input related to user settings and / or function control of the electronic device, and can include but is not limited to a mouse, a keyboard, a touch screen, a track pad, a track ball, a joystick, a microphone, and / or a remote controller. The output unit 807 can be any type of device that can present information, and can include but is not limited to a display, a speaker, a video / audio output terminal, a vibrator, and / or a printer. The storage unit 808 can include but is not limited to a disk, an optical disk. The communication unit 809 allows the electronic device 800 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks, and can include but is not limited to a modem, a network card, an infrared communication device, a wireless communication transceiver, and / or a chipset, such as a Bluetooth™ device, an 802.11 device, a WiFi device, a WiMax device, a cellular communication device, and / or the like.

[0083] The computing unit 801 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 801 performs the various methods and processes described above, such as method 200. For example, in some embodiments, the method 200 may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 808. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 800 via the ROM 802 and / or the communication unit 809. When the computer program is loaded into the RAM 803 and executed by the computing unit 801, one or more steps of the method 200 described above may be performed. Alternatively, in other embodiments, the computing unit 801 may be configured to perform the method 200 in any other appropriate manner (e.g., by means of firmware).

[0084] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0085] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0086] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0087] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0088] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0089] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0090] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0091] Although the embodiments or examples of the present disclosure have been described with reference to the accompanying drawings, it should be understood that the above-mentioned methods, systems and devices are merely exemplary embodiments or examples, and the scope of the present invention is not limited by these embodiments or examples, but only by the claims after authorization and their equivalent scope. Various elements in the embodiments or examples can be omitted or replaced by their equivalent elements. In addition, each step can be performed in an order different from that described in the present disclosure. Further, the various elements in the embodiments or examples can be combined in various ways. It is important that with the evolution of technology, many elements described herein can be replaced by equivalent elements that appear after the present disclosure.

Claims

1. A computer-implemented information recommendation method, wherein the information includes a commodity to be mounted, the method comprising: Determining first characteristic words corresponding to one or more first text contents created by the first user; Acquire multiple reference text contents, and determine the second characteristic words respectively corresponding to the multiple reference text contents, wherein the multiple reference text contents are each associated with corresponding recommended information, wherein the multiple reference text contents are reference text contents created by one or more second users, each of the one or more second users includes a corresponding classification label, and the number of classification labels included by each second user is less than a preset number of categories, wherein the classification label is a classification label of the one or more reference text contents created by the corresponding second user, wherein acquiring the multiple reference text contents includes: Acquire a first quantity of reference text content within a first predetermined time period; sorting the first number of reference text contents based on the commodity conversion rate and / or the total commodity transaction amount of the recommended information associated with each of the first number of reference text contents; and Acquire the plurality of reference text contents based on the sorting result; Based on the corresponding first characteristic words and second characteristic words, using a hash algorithm to obtain binary text feature vectors corresponding to the one or more first text contents and the plurality of reference text contents respectively; For each of the one or more first text contents, determining, from the plurality of reference text contents, a reference text content whose similarity with the first text content meets a first threshold based on the binary text feature vector, as the second text content; Based on all the recommended information associated with the second text content, information is recommended to the first user.

2. The method of claim 1, wherein: Based on the corresponding first feature words and second feature words, using a hash algorithm to obtain binary text feature vectors corresponding to the one or more first text contents and the multiple reference text contents respectively includes: Determine text feature vectors corresponding to the one or more first text contents and the plurality of reference text contents based on the corresponding first feature words and second feature words; and The text feature vector is converted into a binary hash code through multiple Bayesian clustering algorithms to obtain the binary text feature vector.

3. The method of claim 1, wherein: Determining, based on the binary text feature vector, second text content whose similarity to the first text content satisfies a first threshold includes: Based on the Hamming distance between the binary text feature vectors, second text content whose similarity with the first text content meets a first threshold is determined.

4. The method of claim 1, wherein: Recommending information to the user based on all the recommended information associated with the second text content includes: Counting the number of each recommended information associated with all the second text contents; and Recommend information to the user based on the statistical results.

5. The method of claim 4, wherein: Recommending information to the user based on the statistical results includes at least one of the following: Determining the recommended information whose quantity is greater than a third threshold, so as to recommend information to the user; as well as Determine the recommended information whose quantity ratio to the quantity of the one or more first text contents is greater than a fourth threshold, so as to recommend the information to the user.

6. The method of claim 2, wherein: The text feature vector includes a TF-IDF value.

7. The method of claim 2, wherein: Respectively determining the text feature vectors corresponding to the one or more first text contents and the plurality of reference text contents comprises: Determine the word vectors corresponding to the first feature word and the second feature word respectively; and Based on the word vectors, text feature vectors corresponding to the one or more first text contents and the multiple reference text contents are respectively determined.

8. The method of claim 7, wherein: Determining the text feature vectors corresponding to the one or more first text contents and the multiple reference text contents based on the word vectors includes any one of the following: Adding word vectors corresponding to the one or more first text contents and the multiple reference text contents to obtain text feature vectors corresponding to the one or more first text contents and the multiple reference text contents; as well as The word vectors corresponding to the one or more first text contents and the multiple reference text contents are weightedly summed to obtain text feature vectors corresponding to the one or more first text contents and the multiple reference text contents.

9. The method of claim 1, wherein: Determining the first characteristic words corresponding to the one or more first text contents of the user includes: Performing word segmentation operations on the one or more first text contents respectively to obtain corresponding first feature words; and Determining the second characteristic words corresponding to the plurality of reference text contents respectively includes: The word segmentation operation is performed on the multiple reference text contents respectively to obtain second feature words corresponding to the multiple reference text contents respectively.

10. The method according to claim 1 or 9, wherein: The first feature word and the second feature word include classification labels of the first text content and the reference text content, respectively.

11. The method of claim 1 , further comprising: The information recommendation method is performed every third predetermined time period.

12. An information recommendation device, wherein the information includes a commodity to be mounted, the device comprising: A first determining unit is configured to determine first characteristic words corresponding to one or more first text contents created by a first user; The second determination unit is configured to obtain a plurality of reference text contents and determine second characteristic words respectively corresponding to the plurality of reference text contents, wherein the plurality of reference text contents are each associated with corresponding recommended information, wherein the plurality of reference text contents are reference text contents created by one or more second users, each of the one or more second users each includes a corresponding classification label, and the number of classification labels included by each second user is less than a preset number of categories, wherein the classification label is a classification label of the one or more reference text contents created by the corresponding second user, wherein obtaining the plurality of reference text contents includes: Acquire a first quantity of reference text content within a first predetermined time period; sorting the first number of reference text contents based on the commodity conversion rate and / or the total commodity transaction amount of the recommended information associated with each of the first number of reference text contents; and Acquire the plurality of reference text contents based on the sorting result; An acquisition unit is configured to obtain binary text feature vectors corresponding to the one or more first text contents and the plurality of reference text contents respectively by using a hash algorithm based on the corresponding first feature words and second feature words; A third determining unit is configured to determine, for each of the one or more first text contents, from the plurality of reference text contents, based on the binary text feature vector, a reference text content whose similarity with the first text content satisfies a first threshold, as the second text content; and The recommendation unit is configured to recommend information to the first user based on all the recommended information associated with the second text content.

13. An electronic device, comprising: at least one processor; as well as a memory communicatively coupled to the at least one processor; in The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 11.

14. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-11.

15. A computer program product comprising a computer program, wherein: When the computer program is executed by a processor, the method according to any one of claims 1 to 11 is implemented.

Images