Method, device and equipment for updating association based on user behavior track information and medium
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- HANGZHOU PINPIANYI NETWORK TECH CO LTD
- Filing Date
- 2023-06-30
- Publication Date
- 2026-06-26
AI Technical Summary
In existing technologies, when searching for item information, the results displayed based on search keywords are limited, and fuzzy searches lead to excessive resource consumption and long search times.
By acquiring user behavior trajectory data, analyzing and processing it, an initial search keyword corpus is generated to expand the corpus. Then, by using item information sets for elimination processing, a target search keyword corpus is generated to expand the corpus.
It provides rich and accurate search results for item information, meeting page display requirements while reducing resource consumption and search time.
Smart Images
Figure CN116821160B_ABST
Abstract
Description
Technical Field
[0001] The embodiments of this disclosure relate to the field of computer technology, and more specifically to a method, apparatus, device, and medium for updating associations based on user behavior trajectory information. Background Technology
[0002] Search keywords are the keywords used when performing a search. Currently, when using search keywords to search for item information, the common methods are: displaying item information whose titles include the search keywords as search results, or using fuzzy search based on the search keywords to search for item information.
[0003] However, when operating on log files in the above manner, the following technical problems often arise:
[0004] First, when displaying item information whose titles include search keywords as search results, there are relatively few item titles that fully contain the search keywords, resulting in fewer item information searched based on the search keywords, which is insufficient to meet the page display requirements.
[0005] Second, when using fuzzy search based on search keywords to search for item information, it results in a large number of search results, excessive resource consumption during the search process, and a long search time. Summary of the Invention
[0006] The summary portion of this disclosure is intended to provide a brief overview of the concepts, which will be described in detail in the detailed description portion. This summary portion is not intended to identify key or essential features of the claimed technical solutions, nor is it intended to limit the scope of the claimed technical solutions.
[0007] Some embodiments of this disclosure propose methods, apparatuses, devices, and media for association updates based on user behavior trajectory information to solve one or more of the technical problems mentioned in the background section above.
[0008] In a first aspect, some embodiments of this disclosure provide a method for association and update based on user behavior trajectory information. The method includes: acquiring behavior trajectory data of each target user in a target user group within a preset time period to obtain a user behavior trajectory dataset, wherein each user behavior trajectory data in the user behavior trajectory dataset includes a search log group, and the search logs in the search log group of the user behavior trajectory dataset include: search keywords, the number of search clicked item information, the number of search result items, and the number of search followed items; analyzing and processing the user behavior trajectory dataset to obtain a user behavior trajectory analysis dataset; generating a target item information set based on the item information set, wherein each item information in the item information set is item information used to display to users on the target platform; generating an initial search keyword expanded corpus based on the target item information set and the user behavior trajectory analysis dataset; and using the target item information set to perform a removal process on the initial search keyword expanded corpus to obtain a target search keyword expanded corpus.
[0009] Secondly, some embodiments of this disclosure provide an association update device based on user behavior trajectory information. The device includes: an acquisition unit configured to acquire behavior trajectory data of each target user in a target user group within a preset time period to obtain a user behavior trajectory dataset, wherein each user behavior trajectory data in the user behavior trajectory dataset includes a search log group, and the search logs in the search log group of the user behavior trajectory dataset include: search keywords, the number of search clicked item information, the number of search result items, and the number of search followed items; an analysis and processing unit configured to analyze and process the user behavior trajectory dataset to obtain a user behavior trajectory analysis dataset; a first generation unit configured to generate a target item information set based on the item information set, wherein each item information in the item information set is item information used to display to users on the target platform; a second generation unit configured to generate an initial search keyword expanded corpus based on the target item information set and the user behavior trajectory analysis dataset; and a removal unit configured to remove items from the initial search keyword expanded corpus using the target item information set to obtain a target search keyword expanded corpus.
[0010] Thirdly, some embodiments of this disclosure provide an electronic device, including: one or more processors; and a storage device having one or more programs stored thereon, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation of the first aspect above.
[0011] Fourthly, some embodiments of this disclosure provide a computer-readable medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the method described in any of the implementations of the first aspect above.
[0012] The above embodiments of this disclosure have the following beneficial effects: The association update method based on user behavior trajectory information in some embodiments of this disclosure can provide rich search results for item information based on search keywords, meeting page display requirements. First, the behavior trajectory data of each target user in the target user group within a preset time period is obtained to obtain a user behavior trajectory dataset. Each user behavior trajectory data in the above user behavior trajectory dataset includes a search log group. The search logs in the search log group of the above user behavior trajectory dataset include: search keywords, number of search clicked item information, number of search result items, and number of search followed items. Then, the above user behavior trajectory dataset is analyzed and processed to obtain a user behavior trajectory analysis dataset. Next, a target item information set is generated based on the item information set. Each item information in the above item information set is the item information used to display to users on the target platform. Then, based on the above target item information set and the above user behavior trajectory analysis dataset, an initial search keyword expansion corpus is generated. Thus, the keyword corpus can be further enriched based on the user behavior trajectory analysis dataset and the target item information set. Finally, the initial search keyword-expanded corpus is processed using the aforementioned target item information set to obtain the target search keyword-expanded corpus. This allows for the provision of richer search results based on the search keywords, meeting the page display requirements. Attached Figure Description
[0013] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and elements are not necessarily drawn to scale.
[0014] Figure 1 These are flowcharts of some embodiments of the association update method based on user behavior trajectory information according to this disclosure;
[0015] Figure 2 This is a schematic diagram of the structure of some embodiments of the association update device based on user behavior trajectory information disclosed herein;
[0016] Figure 3 This is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure. Detailed Implementation
[0017] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.
[0018] It should also be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings. Unless otherwise specified, the embodiments and features described in this disclosure can be combined with each other.
[0019] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.
[0020] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".
[0021] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.
[0022] The collection, storage, and use of user information (such as user behavior trajectory data) involved in this disclosure shall be carried out in accordance with relevant laws and regulations, provided that the relevant organizations or individuals have fulfilled their obligations, including conducting personal information security impact assessments, informing personal information subjects, obtaining prior authorization and consent from personal information subjects, and other obligations before performing the corresponding operations.
[0023] This disclosure will now be described in detail with reference to the accompanying drawings and embodiments.
[0024] refer to Figure 1 The diagram illustrates a flow 100 of some embodiments of the association update method based on user behavior trajectory information according to this disclosure. This association update method based on user behavior trajectory information includes the following steps:
[0025] Step 101: Obtain the behavioral trajectory data of each target user in the target user group within a preset time period to obtain the user behavioral trajectory dataset.
[0026] In some embodiments, the entity executing the association update method based on user behavior trajectory information can obtain the behavior trajectory data of each target user in the target user group within a preset time period through a wired or wireless connection, thereby obtaining a user behavior trajectory dataset.
[0027] Each user behavior trajectory data point in the aforementioned user behavior trajectory dataset may include a search log group. The search logs in the search log group of the aforementioned user behavior trajectory dataset may include: search keywords, the number of clicked item information, the number of search result items, and the number of search-followed items. Search keywords can be the search terms entered when searching for item information on the item information search page. The number of search result items can be the total number of item information displayed and pending display on the search page after performing a search operation for the search keywords. The number of clicked item information can be the total number of item information clicked after completing the search operation. The number of search-followed items can be the number of item information saved or of interest after completing the search operation.
[0028] In some optional implementations of certain embodiments, before obtaining the behavior trajectory data of each target user in the target user group within a preset time period and obtaining the user behavior trajectory dataset, the aforementioned executing entity may also perform the following steps:
[0029] The first step is to obtain the user information table. The user information in this table may include: user ID, registration time, and item transfer volume. The item transfer volume in the user information table can be the total amount of items transferred from the item transfer location represented by the user ID within the aforementioned preset time period.
[0030] In practice, the duration and end time of the above preset time period can be set according to the actual application needs; no restrictions are imposed here.
[0031] As an example, the preset time period mentioned above could be 18 months.
[0032] The second step is to select user information that meets the first filtering condition from the aforementioned user information table as the first user information set. The first filtering condition can be that the amount of items transferred in the user information is greater than a preset amount of items transferred.
[0033] In practice, the preset item transfer amount can be set according to the actual application needs; no limit is set here.
[0034] The third step is to select user information that meets the second filtering condition from the aforementioned user information table as target user information, thereby obtaining the target user information set. The second filtering condition can be that the registration time of the first user information is later than a preset registration time.
[0035] In practice, the above-mentioned preset registration time can be set according to the actual application needs; no limitation is made here.
[0036] Step 102: Analyze and process the user behavior trajectory dataset to obtain the user behavior trajectory analysis dataset.
[0037] In some embodiments, the search logs in the search log group of the aforementioned user behavior trajectory dataset further include a sequence of clicked item information. The clicked item information in the sequence of clicked item information in the aforementioned user behavior trajectory dataset includes the item identifier and the click time.
[0038] The aforementioned executing entity can analyze and process the aforementioned user behavior trajectory dataset to obtain a user behavior trajectory analysis dataset, which may include the following steps:
[0039] The first step is to perform the following analysis and processing steps for each user behavior trajectory data in the above user behavior trajectory dataset:
[0040] The first analysis and processing step is to determine the search result click-through rate as the ratio of the number of searched and clicked items to the number of search result items in the aforementioned user behavior trajectory data.
[0041] The second analysis and processing step is to determine the search result attention rate as the ratio of the number of items searched and followed to the number of items in the search results from the aforementioned user behavior trajectory data.
[0042] The third analysis and processing step involves combining the search keywords and clicked item information sequences from the aforementioned user behavior trajectory data, along with the search result click-through rate and search result attention rate, to obtain user behavior trajectory analysis data.
[0043] Step 103: Generate the target item information set based on the item information set.
[0044] In some embodiments, the item information in the above-mentioned item information set is item information used to display to users on the target platform.
[0045] The aforementioned executing entity generates a target item information set based on the item information set, which may include the following steps:
[0046] The first step is to determine whether the number of items in the aforementioned item information set exceeds a preset quantity. In practice, the preset quantity can be set according to actual application needs; no specific limit is imposed here.
[0047] As an example, the value of the preset quantity mentioned above can be 1000.
[0048] The second step is to determine that the number of item information in the above item information set is less than or equal to the above preset number, and then determine each item information in the above item information set as the target item information to obtain the target item information set.
[0049] Third, in response to the determination that the number of item information in the above item information set is greater than the preset number, the item information in the above item information set is sorted according to the item transfer volume in the item information to obtain an item information sequence. The item information in the above item information sequence can be sorted in descending order of item transfer volume.
[0050] The fourth step is to identify the item information that is ranked before the preset quantity in the above item information sequence as the target item information, thus obtaining the target item information set.
[0051] Step 104: Based on the target item information set and the user behavior trajectory analysis dataset, generate an initial search keyword expansion corpus.
[0052] In some embodiments, the search logs in the search log group of the aforementioned user behavior trajectory dataset further include a sequence of clicked item information. The clicked item information in the sequence of clicked item information in the aforementioned user behavior trajectory dataset includes the item identifier and the click time.
[0053] Based on the aforementioned target item information set and the aforementioned user behavior trajectory analysis dataset, the aforementioned executing entity generates an initial search keyword expanded corpus, which may include the following steps:
[0054] The first step is to identify user behavior trajectory analysis data in the above user behavior trajectory analysis dataset whose search result click-through rate is less than the preset click-through rate and whose search result attention rate is less than the preset attention rate as user behavior trajectory analysis data to be removed.
[0055] The second step is to remove each user behavior trajectory analysis data to be removed from the above user behavior trajectory analysis dataset to obtain the target user behavior trajectory analysis dataset.
[0056] The third step is to generate an initial search keyword expansion corpus based on the aforementioned target item information set and the aforementioned target user behavior trajectory analysis dataset.
[0057] Fourth, for each target user behavior trajectory analysis data point in the above target user behavior trajectory analysis dataset, perform the following corpus augmentation steps:
[0058] The first corpus expansion step involves selecting target item information whose item identifier is the same as the item identifier in any clicked item information sequence of the target user behavior trajectory analysis data from the above target item information set as corpus expansion item information, thus obtaining the corpus expansion item information set.
[0059] The second corpus expansion step involves retrieving the corresponding item title from the item information storage table based on the item identifiers in each item information in the aforementioned corpus expansion item information set, thus obtaining an item title set. The item information in the aforementioned item information storage table includes item identifiers and item titles.
[0060] The third corpus expansion step involves using a semantic segmentation model to segment each item title set in the aforementioned item title set, obtaining a sequence of title keywords. The semantic segmentation model may include, but is not limited to, at least one of the following: FCN (Fully Convolutional Networks) model, U-Net model, and SegNet model.
[0061] The fifth step is to add the above title keyword sequence to the initial search keyword expansion corpus as the initial search keyword expansion corpus.
[0062] The step of generating an initial search keyword-expanded corpus based on the aforementioned target item information set and user behavior trajectory analysis dataset is an inventive point of this disclosure, solving the second technical problem mentioned in the background art: "When searching for item information using fuzzy search based on search keywords, it results in a large number of search results, excessive resource consumption during the search process, and a long search time." The factors leading to the above technical problem are often as follows: when searching for item information using fuzzy search based on search keywords, the search results are numerous and inaccurate. Solving these factors can achieve the effect of efficiently providing rich and accurate item information search results. To achieve this effect, this disclosure first identifies user behavior trajectory analysis data in the aforementioned user behavior trajectory analysis dataset whose search result click-through rate is less than a preset click-through rate and whose search result attention rate is less than a preset attention rate as user behavior trajectory analysis data to be removed. Thus, invalid user behavior trajectory analysis data is filtered out using the preset click-through rate and preset attention rate. Then, each user behavior trajectory analysis data to be removed is removed from the aforementioned user behavior trajectory analysis dataset to obtain the target user behavior trajectory analysis dataset. Thus, a valid target user behavior trajectory analysis dataset is obtained. Next, based on the aforementioned target item information set and the aforementioned target user behavior trajectory analysis dataset, an initial search keyword expansion corpus is generated. Then, for each target user behavior trajectory analysis data point in the aforementioned target user behavior trajectory analysis dataset, the following corpus expansion steps are performed: First, in the target item information set, target item information whose item identifier matches the item identifier in any clicked item information sequence of the aforementioned target user behavior trajectory analysis data is selected as the corpus expansion item information, resulting in a corpus expansion item information set. Second, in the corpus expansion step, based on the item identifiers in each corpus expansion item information point in the aforementioned corpus expansion item information set, the corresponding item title is retrieved from the item information storage table, resulting in an item title set. The item information in the aforementioned item information storage table includes item identifiers and item titles. Third, in the corpus expansion step, a semantic segmentation model is used to segment each item title set in the aforementioned item title set, resulting in a title keyword sequence. The aforementioned semantic segmentation model may include, but is not limited to, at least one of the following: FCN (Fully Convolutional Networks) model, U-Net model, and SegNet model. This allows for the generation of a preliminary search keyword expansion corpus, providing a basis for providing richer and more accurate search results in the future.
[0063] Step 105: Use the target item information set to remove keywords from the initial search keyword expansion corpus to obtain the target search keyword expansion corpus.
[0064] In some embodiments, the execution entity uses the target item information set to remove elements from the initial search keyword expanded corpus to obtain the target search keyword expanded corpus, which may include the following steps:
[0065] The first step is to perform the following elimination process on each initial search keyword expansion corpus:
[0066] The first elimination step involves using a hash algorithm to map each title keyword in the initial search keyword expansion corpus to obtain a sequence of mapped strings. The mapped strings in this sequence are binary strings. The hash algorithm can be MD5 (Message-digest Algorithm 5).
[0067] The second elimination step involves performing the following comparison step for any two mapping strings in the above mapping string sequence:
[0068] The first comparison step involves comparing the digits at the same position in any two of the above mapping strings one by one.
[0069] The second comparison step involves determining the distance value by the number of different digits in the same position of any two mapped strings.
[0070] In the third comparison step, in response to determining that the distance value is less than a preset distance value, a random selection is made from any two mapping strings to be discarded. In practice, the preset distance value can be set according to actual needs; no limitation is made here.
[0071] As an example, the preset distance value mentioned above could be 3.
[0072] The fourth comparison step involves removing the aforementioned discarded mapping string from the aforementioned mapping string sequence.
[0073] The second step is to determine the target search keyword expansion corpus from the initial search keyword expansion corpus after the initial keyword elimination process.
[0074] The above-described step of using the target item information set to perform a filtering process on the initial search keyword expanded corpus to obtain the target search keyword expanded corpus is an inventive point of this disclosure, further solving the second technical problem mentioned in the background art: "When searching for item information using fuzzy search based on search keywords, it results in a large number of search results, excessive resource consumption during the search process, and a long search time." The factors leading to the above technical problem are often as follows: When searching for item information using fuzzy search based on search keywords, the search results are numerous and inaccurate. If these factors are resolved, the effect of efficiently providing rich and accurate item information search results can be achieved. To achieve this effect, this disclosure first performs the following filtering process on each initial search keyword expanded corpus in the above-described initial search keyword expanded corpus: The first filtering process involves using a hash function to map each title keyword in the above-described initial search keyword expanded corpus to obtain a mapped string sequence. Wherein, the mapped strings in the above-described mapped string sequence are binary strings. The second elimination process involves performing the following comparison steps for any two mapping strings in the aforementioned mapping string sequence: First, comparing the digits at the same position in each of the two mapping strings sequentially. Second, determining the distance value based on the number of different digits at the same position in the two mapping strings. Third, in response to the determination that the distance value is less than a preset distance value, randomly selecting one of the two mapping strings as the elimination mapping string. Fourth, removing the elimination mapping string from the aforementioned mapping string sequence. Thus, by comparing strings to determine their similarity, overly similar keywords are eliminated to ensure the accuracy and controllability of search results. Then, in the second step, the initial search keyword expansion corpus after elimination is determined as the target search keyword expansion corpus. Therefore, on the one hand, the generated target search keyword expansion corpus can be used to expand searches around the search keywords; on the other hand, it can provide more accurate search results for item information.
[0075] In some optional implementations of certain embodiments, the executing entity may further utilize the target search keywords to expand the corpus and perform association update processing on the search keywords of each target item in the target item information set. This association update may involve storing the target search keyword expansion corpus and the corresponding search keywords in the target item information set in pairs.
[0076] The above embodiments of this disclosure have the following beneficial effects: The association update method based on user behavior trajectory information in some embodiments of this disclosure can provide rich search results for item information based on search keywords, meeting page display requirements. First, the behavior trajectory data of each target user in the target user group within a preset time period is obtained to obtain a user behavior trajectory dataset. Each user behavior trajectory data in the above user behavior trajectory dataset includes a search log group. The search logs in the search log group of the above user behavior trajectory dataset include: search keywords, number of search clicked item information, number of search result items, and number of search followed items. Then, the above user behavior trajectory dataset is analyzed and processed to obtain a user behavior trajectory analysis dataset. Next, a target item information set is generated based on the item information set. Each item information in the above item information set is the item information used to display to users on the target platform. Then, based on the above target item information set and the above user behavior trajectory analysis dataset, an initial search keyword expansion corpus is generated. Thus, the keyword corpus can be further enriched based on the user behavior trajectory analysis dataset and the target item information set. Finally, the initial search keyword-expanded corpus is processed using the aforementioned target item information set to obtain the target search keyword-expanded corpus. This allows for the provision of richer search results based on the search keywords, meeting the page display requirements.
[0077] Further reference Figure 2 As an implementation of the methods shown in the above figures, this disclosure provides some embodiments of a correlation update device based on user behavior trajectory information. These device embodiments are similar to... Figure 1 Corresponding to the method embodiments shown, the device can be specifically applied to various electronic devices.
[0078] like Figure 2As shown, the association update device 200 based on user behavior trajectory information in some embodiments includes: an acquisition unit 201, an analysis and processing unit 202, a first generation unit 203, a second generation unit 204, and a removal unit 205. The acquisition unit 201 is configured to acquire the behavioral trajectory data of each target user in the target user group within a preset time period to obtain a user behavior trajectory dataset. Each user behavior trajectory data in the aforementioned user behavior trajectory dataset includes a search log group, and the search logs in the search log group of the aforementioned user behavior trajectory dataset include: search keywords, number of search clicked item information, number of search result items, and number of search followed items. The analysis and processing unit 202 is configured to analyze and process the aforementioned user behavior trajectory dataset to obtain a user behavior trajectory analysis dataset. The first generation unit 203 is configured to generate a target item information set based on the item information set, wherein each item information in the aforementioned item information set is the item information used to display to users on the target platform. The second generation unit 204 is configured to generate an initial search keyword expansion corpus based on the aforementioned target item information set and the aforementioned user behavior trajectory analysis dataset. The elimination unit 205 is configured to use the aforementioned target item information set to perform elimination processing on the aforementioned initial search keyword expansion corpus to obtain a target search keyword expansion corpus.
[0079] It is understandable that the units and references described in the association update device 200 based on user behavior trajectory information are... Figure 1 The steps in the described method correspond to each other. Therefore, the operations, features, and beneficial effects described above for the method also apply to the association update device 200 based on user behavior trajectory information and the units contained therein, and will not be repeated here.
[0080] The following is for reference. Figure 3 It shows a schematic diagram of the structure of an electronic device 300 suitable for implementing some embodiments of the present disclosure. Figure 3 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of this disclosure.
[0081] like Figure 3 As shown, the electronic device 300 may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 into a random access memory (RAM) 303. The RAM 303 also stores various programs and data required for the operation of the electronic device 300. The processing unit 301, ROM 302, and RAM 303 are interconnected via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.
[0082] Typically, the following devices can be connected to I / O interface 305: input devices 306 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 307 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; and communication devices 309. Communication device 309 allows electronic device 300 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 3 An electronic device 300 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively. Figure 3 Each box shown can represent a device or multiple devices as needed.
[0083] In particular, according to some embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, some embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication device 309, or installed from storage device 308, or installed from ROM 302. When the computer program is executed by processing device 301, it performs the functions defined in the methods of some embodiments of this disclosure.
[0084] It should be noted that, in some embodiments of this disclosure, the computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium may be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In some embodiments of this disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In some embodiments of this disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.
[0085] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.
[0086] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device. The aforementioned computer-readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to: acquire behavioral trajectory data of each target user in a target user group within a preset time period, obtaining a user behavior trajectory dataset, wherein each user behavior trajectory data in the aforementioned user behavior trajectory dataset includes a search log group, and the search logs in the search log group of the aforementioned user behavior trajectory dataset include: search keywords, the number of search clicked item information, the number of search result items, and the number of search-followed items; analyze and process the aforementioned user behavior trajectory dataset to obtain a user behavior trajectory analysis dataset; generate a target item information set based on the item information set, wherein each item information in the aforementioned item information set is item information used to display to users on the target platform; generate an initial search keyword expansion corpus based on the aforementioned target item information set and the aforementioned user behavior trajectory analysis dataset; and perform a removal process on the aforementioned initial search keyword expansion corpus using the aforementioned target item information set to obtain a target search keyword expansion corpus.
[0087] Computer program code for performing operations of some embodiments of this disclosure can be written in one or more programming languages or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, and C++, and conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).
[0088] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.
[0089] The units described in some embodiments of this disclosure can be implemented in software or hardware. The described units can also be housed in a processor; for example, a processor may be described as including an acquisition unit, an analysis and processing unit, a first generation unit, a second generation unit, and a rejection unit. The names of these units do not necessarily limit the specific unit; for example, the acquisition unit may also be described as "a unit that acquires behavioral trajectory data of each target user in a target user group within a preset time period."
[0090] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.
Claims
1. A method for correlation and update based on user behavior trajectory information, comprising: The behavior trajectory data of each target user in the target user group within a preset time period is obtained to obtain a user behavior trajectory dataset. Each user behavior trajectory data in the user behavior trajectory dataset includes a search log group. The search logs in the search log group of the user behavior trajectory dataset include: search keywords, number of search clicked item information, number of search result items, and number of search followed items. The user behavior trajectory dataset is analyzed and processed to obtain a user behavior trajectory analysis dataset; Based on the item information set, a target item information set is generated, wherein each item information in the item information set is the item information used to be displayed to the user on the target platform; Based on the target item information set and the user behavior trajectory analysis dataset, an initial search keyword expansion corpus is generated, including: identifying user behavior trajectory analysis data in the user behavior trajectory analysis dataset whose search result click-through rate is less than a preset click-through rate and whose search result attention rate is less than a preset attention rate as user behavior trajectory analysis data to be removed; removing each user behavior trajectory analysis data to be removed from the user behavior trajectory analysis dataset to obtain the target user behavior trajectory analysis dataset; generating an initial search keyword expansion corpus based on the target item information set and the target user behavior trajectory analysis dataset; and performing the following corpus expansion steps for each target user behavior trajectory analysis data in the target user behavior trajectory analysis dataset: From the target item information set, select target item information whose item identifier is the same as the item identifier in any clicked item information sequence of the target user behavior trajectory analysis data as corpus expansion item information, thus obtaining a corpus expansion item information set; based on the item identifier in each corpus expansion item information in the corpus expansion item information set, search for the corresponding item title from the item information storage table to obtain an item title set, wherein the item information in the item information storage table includes item identifiers and item titles; use a semantic segmentation model to segment each item title set in the item title set to obtain a title keyword sequence; add the title keyword sequence as the initial search keyword expansion corpus to the initial search keyword expansion corpus; The target item information set is used to remove items from the initial search keyword expanded corpus to obtain the target search keyword expanded corpus.
2. The method according to claim 1, wherein, The method further includes: The corpus is expanded using the target search keywords, and the search keywords for each target item in the target item information set are updated and associated.
3. The method according to claim 1, wherein, Before obtaining the behavioral trajectory data of each target user in the target user group within a preset time period to obtain the user behavioral trajectory dataset, the method further includes: Obtain a user information table, wherein the user information in the user information table includes: user ID, registration time, and item transfer volume, and the item transfer volume in the user information table is the total amount of items transferred from the item transfer location represented by the user ID within the preset time period; Select user information that meets the first filtering condition from the user information table as the first user information to obtain the first user information set, wherein the first filtering condition is that the item transfer amount in the user information is greater than the preset item transfer amount. Select user information that meets the second filtering condition from the user information table as target user information to obtain a target user information set, wherein the second filtering condition is that the registration time of the first user information is later than the preset registration time.
4. The method according to claim 3, wherein, The search logs in the search log group of the user behavior trajectory dataset also include a sequence of clicked item information, and the clicked item information in the sequence of clicked item information in the user behavior trajectory dataset includes the item identifier and the click time; as well as The process of analyzing and processing the user behavior trajectory dataset to obtain a user behavior trajectory analysis dataset includes: For each user behavior trajectory data in the user behavior trajectory dataset, perform the following analysis and processing steps: The ratio of the number of searched and clicked items in the user behavior trajectory data to the number of search results items is determined as the search result click-through rate; The ratio of the number of items searched and followed in the user behavior trajectory data to the number of items in the search results is determined as the search result attention rate; The user behavior trajectory data is obtained by combining the search keywords and clicked item information sequences in the user behavior trajectory data, as well as the search result click-through rate and search result attention rate.
5. The method according to claim 1, wherein, The step of generating a target item information set based on the item information set includes: Determine whether the number of item information in the item information set is greater than a preset number; In response to determining that the number of item information in the item information set is less than or equal to the preset number, each item information in the item information set is identified as the target item information, thus obtaining the target item information set.
6. The method according to claim 5, wherein, The step of generating the target item information set based on the item information set further includes: In response to determining that the number of item information in the item information set is greater than the preset number, the item information in the item information set is sorted according to the item transfer amount in the item information to obtain an item information sequence, wherein each item information in the item information sequence is sorted in descending order of item transfer amount; The item information that is ordered before the preset quantity in the item information sequence is identified as the target item information, thus obtaining the target item information set.
7. A correlation update device based on user behavior trajectory information, comprising: The acquisition unit is configured to acquire the behavioral trajectory data of each target user in the target user group within a preset time period to obtain a user behavior trajectory dataset. Each user behavior trajectory data in the user behavior trajectory dataset includes a search log group. The search logs in the search log group of the user behavior trajectory dataset include: search keywords, number of search clicked item information, number of search result items, and number of search followed items. The analysis and processing unit is configured to analyze and process the user behavior trajectory dataset to obtain a user behavior trajectory analysis dataset. The first generation unit is configured to generate a target item information set based on the item information set, wherein each item information in the item information set is item information used to be displayed to the user on the target platform; The second generation unit is configured to generate an initial search keyword expansion corpus based on the target item information set and the user behavior trajectory analysis dataset, including: identifying user behavior trajectory analysis data in the user behavior trajectory analysis dataset whose search result click-through rate is less than a preset click-through rate and whose search result attention rate is less than a preset attention rate as user behavior trajectory analysis data to be removed; removing each user behavior trajectory analysis data to be removed from the user behavior trajectory analysis dataset to obtain a target user behavior trajectory analysis dataset; generating an initial search keyword expansion corpus based on the target item information set and the target user behavior trajectory analysis dataset; and performing the following corpus analysis for each target user behavior trajectory analysis data in the target user behavior trajectory analysis dataset. Expansion steps: Select target item information whose item identifier matches the item identifier in any clicked item information sequence from the target user behavior trajectory analysis data, as the expanded corpus item information, to obtain the expanded corpus item information set; Based on the item identifiers in each expanded item information in the expanded corpus item information set, search for the corresponding item title in the item information storage table to obtain the item title set, wherein the item information in the item information storage table includes item identifiers and item titles; Use a semantic segmentation model to segment each item title set in the item title set to obtain a title keyword sequence; Add the title keyword sequence as the initial search keyword expanded corpus to the initial search keyword expanded corpus; The elimination unit is configured to use the target item information set to perform elimination processing on the initial search keyword expanded corpus to obtain the target search keyword expanded corpus.
8. An electronic device, comprising: One or more processors; Storage device, on which one or more programs are stored, When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1-6.
9. A computer-readable medium having a computer program stored thereon, wherein, When the program is executed by the processor, it implements the method as described in any one of claims 1-6.