A menu data acquisition method and apparatus

Abstract

The application provides a menu data acquisition method and device, relates to the technical field of data processing, and can be applied to the financial field or other technical fields.The method comprises the following steps: in response to an execution action of a target menu sequence searched by a user through a menu keyword, obtaining a candidate menu list corresponding to the menu keyword; calculating the similarity between each character data in the candidate menu list and the menu keyword to obtain a first menu sequence similar in semantics to the menu keyword; and generating the target menu sequence according to a second menu sequence containing historical click rate data corresponding to the user and the first menu sequence obtained in advance.The device executes the above method.The menu data acquisition method and device provided in the embodiment of the application can quickly and accurately find the menu data required by the user.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and specifically to a method and apparatus for acquiring menu data. Background Technology

[0002] Frontline tellers typically operate within the credit investment management system using menus to complete various transactions. Traditional menu search functions in the banking industry are relatively simple: users input keywords, and the system directly searches for and displays menu names containing those keywords. However, with the expansion of banking business and the need for more refined operations, the number of menus that frontline tellers interact with on the credit investment management system has surged, and existing menu search functions can no longer meet the demands for accurate, fast, and personalized searches.

[0003] The existing menu search logic outputs too many candidate menus for users to choose from when there are a large number of menus and the menu names are highly similar. Users need to spend more time selecting the menu data they need, resulting in low work efficiency. Summary of the Invention

[0004] To address the problems in the prior art, embodiments of the present invention provide a menu data acquisition method and apparatus, which can at least partially solve the problems existing in the prior art.

[0005] On one hand, the present invention proposes a method for obtaining menu data, including:

[0006] In response to a user's action of searching for a target menu sequence using menu keywords, obtain a list of candidate menus corresponding to the menu keywords;

[0007] Calculate the similarity between each data item in the candidate menu list and the menu keyword to obtain a first menu sequence that is semantically similar to the menu keyword;

[0008] The target menu sequence is generated based on a pre-obtained second menu sequence containing historical click-through rate data corresponding to the user and the first menu sequence;

[0009] The historical click-through rate data is the ratio of the number of clicks corresponding to each data item in the user's historical operation menu list to the total number of clicks corresponding to each data item in the user's historical operation menu list.

[0010] The step of generating the target menu sequence based on a pre-obtained second menu sequence containing historical click-through rate data corresponding to the user and the first menu sequence includes:

[0011] The target menu sequence is generated based on the second menu sequence, the first menu sequence, and their respective corresponding menu sequence weights.

[0012] The step of generating the target menu sequence based on the second menu sequence, the first menu sequence, and their respective corresponding menu sequence weights includes:

[0013] Traverse each data item in the menu sequence, and obtain the menu sequence data value corresponding to each data item based on the similarity data of each data item in the first menu sequence, the historical click rate data in the second menu sequence, and the menu sequence weight; the menu sequence includes the first menu sequence and the second menu sequence.

[0014] Select a preset number of menu items in descending order of the menu sequence data values, and combine the preset number of menu items to form the target menu sequence.

[0015] The first menu sequence is arranged in descending order of similarity data from high to low, and the second menu sequence is arranged in descending order of historical click-through rate data from high to low; correspondingly, the traversal of each data item in the menu sequence includes:

[0016] The data items in the menu sequence are traversed sequentially according to the descending order of the first menu sequence or the descending order of the second menu sequence.

[0017] The acquisition of the historical click-through rate data includes:

[0018] The system responds to the historical click-through rate data selected by the user based on a preset data statistics dimension; wherein, the preset data statistics dimension includes the full historical click-through rate data and the recent historical click-through rate data from a preset number of days ago.

[0019] The acquisition of the historical click-through rate data also includes:

[0020] The historical click-through rate data is calculated based on the statistical dimension data values ​​of each dimension data in the preset data statistical dimensions and the statistical dimension data weights corresponding to each dimension data.

[0021] The acquisition of the historical click-through rate data includes:

[0022] The historical click-through rate data is obtained through a front-end tracking component.

[0023] On one hand, the present invention proposes a menu data acquisition device, comprising:

[0024] The acquisition unit is used to respond to the user's action of searching for a target menu sequence by menu keywords and to acquire a list of candidate menus corresponding to the menu keywords;

[0025] A calculation unit is used to calculate the similarity between each data item in the candidate menu list and the menu keyword, and to obtain a first menu sequence that is semantically similar to the menu keyword;

[0026] A generation unit is configured to generate the target menu sequence based on a pre-obtained second menu sequence containing historical click-through rate data corresponding to the user and a first menu sequence;

[0027] The historical click-through rate data is the ratio of the number of clicks corresponding to each data item in the user's historical operation menu list to the total number of clicks corresponding to each data item in the user's historical operation menu list.

[0028] In another aspect, embodiments of the present invention provide an electronic device, including: a processor, a memory, and a bus, wherein,

[0029] The processor and the memory communicate with each other via the bus;

[0030] The memory stores program instructions that can be executed by the processor, and the processor can execute the following methods by calling the program instructions:

[0031] In response to a user's action of searching for a target menu sequence using menu keywords, obtain a list of candidate menus corresponding to the menu keywords;

[0032] Calculate the similarity between each data item in the candidate menu list and the menu keyword to obtain a first menu sequence that is semantically similar to the menu keyword;

[0033] The target menu sequence is generated based on a pre-obtained second menu sequence containing historical click-through rate data corresponding to the user and the first menu sequence;

[0034] The historical click-through rate data is the ratio of the number of clicks corresponding to each data item in the user's historical operation menu list to the total number of clicks corresponding to each data item in the user's historical operation menu list.

[0035] This invention provides a non-transitory computer-readable storage medium, comprising:

[0036] The non-transitory computer-readable storage medium stores computer instructions that cause the computer to perform the following methods:

[0037] In response to a user's action of searching for a target menu sequence using menu keywords, obtain a list of candidate menus corresponding to the menu keywords;

[0038] Calculate the similarity between each data item in the candidate menu list and the menu keyword to obtain a first menu sequence that is semantically similar to the menu keyword;

[0039] The target menu sequence is generated based on a pre-obtained second menu sequence containing historical click-through rate data corresponding to the user and the first menu sequence;

[0040] The historical click-through rate data is the ratio of the number of clicks corresponding to each data item in the user's historical operation menu list to the total number of clicks corresponding to each data item in the user's historical operation menu list.

[0041] The menu data acquisition method and apparatus provided in this invention respond to a user's action of searching for a target menu sequence through menu keywords, and acquire a list of candidate menus corresponding to the menu keywords; calculate the similarity between each character data in the candidate menu list and the menu keywords to obtain a first menu sequence semantically similar to the menu keywords; generate the target menu sequence based on a pre-obtained second menu sequence containing historical click-through rate data corresponding to the user and the first menu sequence; wherein, the historical click-through rate data is the ratio of the click volume corresponding to each character data in the user's historical operation menu list to the total click volume corresponding to each character data in the user's historical operation menu list, which can quickly and accurately find the menu data needed by the user. Attached Figure Description

[0042] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. In the drawings:

[0043] Figure 1 This is a flowchart illustrating a menu data acquisition method provided in an embodiment of the present invention.

[0044] Figure 2 This is a schematic diagram illustrating the componentization of the menu data acquisition method provided in the embodiments of the present invention.

[0045] Figure 3 This is a schematic diagram of the structure of a menu data acquisition device provided in an embodiment of the present invention.

[0046] Figure 4 This is a schematic diagram of the physical structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0047] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings. Here, the illustrative embodiments and descriptions of the present invention are used to explain the present invention, but are not intended to limit the present invention. It should be noted that, unless otherwise specified, the embodiments and features in the embodiments of this application can be arbitrarily combined with each other.

[0048] Figure 1 This is a flowchart illustrating a menu data acquisition method according to an embodiment of the present invention, as shown below. Figure 1 As shown, the menu data acquisition method provided in this embodiment of the invention includes:

[0049] Step S1: Respond to the user's action of searching for a target menu sequence by menu keywords, and obtain a list of candidate menus corresponding to the menu keywords.

[0050] Step S2: Calculate the similarity between each data item in the candidate menu list and the menu keyword to obtain a first menu sequence that is semantically similar to the menu keyword.

[0051] Step S3: Generate the target menu sequence based on the second menu sequence containing historical click-through rate data corresponding to the user and the first menu sequence obtained in advance;

[0052] The historical click-through rate data is the ratio of the number of clicks corresponding to each data item in the user's historical operation menu list to the total number of clicks corresponding to each data item in the user's historical operation menu list.

[0053] In step S1 above, the device responds to the user's action of searching for a target menu sequence using menu keywords, and obtains a list of candidate menus corresponding to the menu keywords. The device can be a computer device executing this method, such as a server. It should be noted that the acquisition and analysis of data involved in this embodiment of the invention are authorized by the user. The user can input menu keywords and click the search button to perform the action of searching for a target menu sequence using menu keywords.

[0054] The initial menu list can be preliminarily filtered to obtain a list of candidate menus corresponding to the menu keywords. The above preliminary filtering rules can be defined by the user, such as obtaining related words to the menu keywords and determining the initial menu list containing the related words as the list of candidate menus.

[0055] In step S2 above, the device calculates the similarity between each data item in the candidate menu list and the menu keyword to obtain a first menu sequence that is semantically similar to the menu keyword. The semantic similarity between the menu keyword and each data item can be calculated separately; the algorithm for calculating the semantic similarity can be a conventional algorithm, such as editingdistance.

[0056] Each data item whose semantic similarity is greater than the preset semantic similarity threshold is identified as a target data item; the preset semantic similarity threshold can be set independently according to the actual situation.

[0057] The data in the candidate menu list containing each target data item is determined as the first menu sequence. An example is given below:

[0058] The similarity data of the menu keywords in the first menu sequence are 0.95, 0.93 and 0.92 respectively, which are denoted as B, C and D respectively (A is assumed to be a user clicked, but not semantically similar to the current menu keyword).

[0059] In step S3 above, the device generates the target menu sequence based on a second menu sequence containing historical click-through rate data corresponding to the user and the first menu sequence obtained in advance;

[0060] The historical click-through rate (CTR) data is the ratio of the number of clicks corresponding to each data item in the user's historical operation menu list to the total number of clicks corresponding to each data item in the user's historical operation menu list. An example of historical CTR data is given below:

[0061] A user has clicked on three data items, denoted as A, B, and C. The number of clicks for A is CA, the number of clicks for B is CB, and the number of clicks for C is CC. Then, the historical click rate data AZZ for A is CA / (CA+CB+CC).

[0062] Historical click-through rate data for B: BZZ = CB / (CA + CB + CC).

[0063] C's historical click-through rate data: CZZ = CC / (CA + CB + CC).

[0064] The step of generating the target menu sequence based on a pre-obtained second menu sequence containing historical click-through rate data corresponding to the user and the first menu sequence includes:

[0065] The target menu sequence is generated based on the second menu sequence, the first menu sequence, and their respective corresponding menu sequence weights. The menu sequence weight corresponding to the first menu sequence can be denoted as X1, and the menu sequence weight corresponding to the second menu sequence can be denoted as X2. The specific values ​​of X1 and X2 can be set independently according to the actual situation, and X1 + X2 = 1.

[0066] The step of generating the target menu sequence based on the second menu sequence, the first menu sequence, and their respective corresponding menu sequence weights includes:

[0067] The process iterates through each data item in the menu sequence, and based on the similarity data of each data item in the first menu sequence, the historical click-through rate data in the second menu sequence, and the menu sequence weight, obtains the menu sequence data value corresponding to each data item; the menu sequence includes the first menu sequence and the second menu sequence; an example is given below:

[0068] You can iterate through the data items in the first menu sequence first, and then iterate through the data items in the second menu sequence, or vice versa; there's no specific restriction. Let's take iterating through the data items in the first menu sequence first, and then iterating through the data items in the second menu sequence, as an example.

[0069] For B: the similarity data is 0.95, and the historical click-through rate data BZZ is CB / (CA+CB+CC);

[0070] For C: the similarity data is 0.93, and the historical click-through rate data CZZ is CC / (CA+CB+CC);

[0071] Corresponding to D: The similarity data is 0.92, and the historical click-through rate data is zero (the user has no historical operation records);

[0072] For A: the similarity data is 0.4, and the historical click-through rate data is CA / (CA+CB+CC).

[0073] For B: The menu sequence data value of B = 0.95 × X1 + CB × X2 / (CA + CB + CC);

[0074] The corresponding menu sequence data value for C:C = 0.93×X1+CC×X2 / (CA+CB+CC);

[0075] The corresponding menu sequence data value for D:D = 0.92 × X1 + CD × 0;

[0076] For A: The menu sequence data value of A = 0.4 × X1 + CA × X2 / (CA + CB + CC).

[0077] A preset number of menu items are selected according to the menu sequence data values ​​in descending order, and these preset number of menu items are combined to form the target menu sequence. The preset number can be set according to actual conditions and can be selected as 2. If the menu sequence data value of C > the menu sequence data value of B > the menu sequence data value of A > the menu sequence data value of D, then the target menu sequence is the menu sequence data values ​​of C and B. Furthermore, the menu items of C can be arranged before the menu items of B.

[0078] The first menu sequence is arranged in descending order of similarity data from high to low, and the second menu sequence is arranged in descending order of historical click-through rate data from high to low; correspondingly, traversing each data item in the menu sequence includes:

[0079] The menu items are traversed sequentially according to either the descending order of the first menu sequence or the descending order of the second menu sequence. If the menu items are traversed sequentially according to the descending order of the first menu sequence, then the menu items are traversed according to the BCDA order.

[0080] If CC / (CA+CB+CC)>CB / (CA+CB+CC)>CA / (CA+CB+CC), then traverse the data items in the menu sequence in the order of CBAD. Following an ordered traversal order can further improve data processing efficiency. For example, if the similarity data encountered is less than the first threshold, then discard the subsequent data; if the historical click-through rate data encountered is less than the second threshold, then discard the subsequent data, thus avoiding excessive invalid data from participating in the calculation.

[0081] Obtaining the historical click-through rate data includes:

[0082] The system responds to the user's selection of historical click-through rate (CTR) data based on preset data statistical dimensions. These preset data statistical dimensions include full historical CTR data and recent historical CTR data from a preset number of days prior to the current day. The preset data statistical dimensions can be set independently according to actual circumstances; for example, full historical CTR data can be understood as all historical CTR data with available records.

[0083] The recent historical click-through rate data from the current day can include historical click-through rate data from the last 15 days, the last 7 days, and the last 3 days.

[0084] If the user selects historical click-through rate data from the past 15 days, the above historical click-through rate data is calculated based on historical data from the past 15 days.

[0085] Obtaining the historical click-through rate data also includes:

[0086] The historical click-through rate data is calculated based on the statistical dimension data values ​​and corresponding weights of each dimension in the preset statistical dimensions. The statistical dimension data weights can be set independently according to actual needs. Taking data item B as an example, the following is an illustration:

[0087] The total historical click-through rate data for B is denoted as BZZ1, and the historical click-through rate data for B over the past 15 days is denoted as...

[0088] The historical click-through rate (CTR) data of B for the past 7 days is denoted as BZZ3, and the historical CTR data of B for the past 3 days is denoted as BZZ4. The corresponding statistical dimension data weights are denoted as Y1 to Y4. Therefore, the historical CTR data of B is BZZ = BZZ1 × Y1 + BZZ2 × Y2 + BZZ3 × Y3 + BZZ4 × Y4. The specific values ​​of Y1 to Y4 can be set according to the actual situation, and Y1 + Y2 + Y3 + Y4 = 1.

[0089] Obtaining the historical click-through rate data includes:

[0090] The historical click-through rate data is obtained through a front-end event tracking component. For example... Figure 2 As shown, the method of this embodiment of the invention can be implemented through componentization. The front-end tracking component can be deployed in advance on the front end. Data tracking is an important way of data collection, mainly used to record and collect the operation behavior of end users. Its basic principle is to deploy the collection SDK code on terminals such as App / H5 / PC. When the user's behavior meets certain conditions, such as entering a page or clicking a button, the recording and storage will be automatically triggered. Then, these data will be collected and transmitted to the terminal provider, or the request data of the user during the service process can be collected through the back end.

[0091] Combination Figure 2 The components of this embodiment of the invention are described below:

[0092] 1) Front-end interactive components. Supports user input of menu keywords.

[0093] 2) Front-end tracking component. Supports sending user behavior data when entering menus through various entry points on the system front end, including: menu name, menu ID, click time, user, organization number, etc., to the back-end database for storage.

[0094] 3) Backend data frequency batch processing component. It pulls data collected by the frontend tracking component, groups and summarizes it by institution and teller to form a second menu sequence sorted by click rate; at the same time, it processes the menu click volume of the most recent 15 days, 7 days and 3 days separately, and summarizes it into a recent high click rate menu sequence. Finally, it outputs the weighted data of the four groups.

[0095] 4) Background string similarity matching component. Receives user input, calculates the edit distance between the user input and information such as the user's menu name or menu ID using a similarity matching algorithm, and then calculates the similarity, generating a first menu sequence ordered in descending order of similarity.

[0096] 5) Unified output component for background menu integration. By integrating the output of the background data word frequency batch processing component and the background string similarity matching component, the system can return the top 20 menu items for the user to select from, ordered by the menu sequence data values ​​from highest to lowest.

[0097] Combination Figure 2 The method and process are explained as follows:

[0098] ①

Front-end tracking component 2

[0099] ②

Backend Data Frequency Batch Processing Component 3

Frontend Tracking Component 2

[0100] ③ After weighting and processing the output data from step ②, integrate and output the high-frequency menu sequence of each teller under each institution, and save it to the database or Redis.

[0101] ④ Users can search for target menus by entering menu keywords through the

Front-end Interaction Component 1

[0102] ⑤

Backend String Similarity Matching Component 4

Frontend Interaction Component 1

[0103] ⑥ The [Backend Menu Fusion and Unified Output Component 5] receives the high-similarity menu sequence returned by the [Backend String Similarity Matching Component 4] and pulls the current user's high-click-rate menu sequence generated by the [Backend Data Frequency Batch Processing Component 3]. It generates a menu sequence containing 20 menus arranged according to the menu sequence data values ​​through weighting, merging searches, and other methods.

[0104] ⑦

Front-end Interaction Component 1

Back-end Menu Integration and Unified Output Component 5

[0105] The menu data acquisition method provided in this invention addresses the problem that users cannot quickly and accurately search for target menus in credit systems due to the large number of menus and the high similarity of menu names. This invention improves the accuracy of menu search matching by combining string similarity matching algorithm and word frequency statistics algorithm with user input, effectively reduces the user's memory cost of menu names, and optimizes the user experience of credit systems.

[0106] The menu data acquisition method provided in this embodiment of the invention has the following beneficial technical effects:

[0107] This invention uses string similarity matching algorithm and word frequency statistics algorithm to perform dynamic statistical analysis on menu usage data accumulated in the credit system. It combines user input to match a user target menu list determined by multiple dimensions such as similarity and frequency, and sorts it according to probability to achieve a personalized, dynamically updated menu matching mechanism that conforms to user habits.

[0108] This invention addresses the problem that, due to the expansion of banking business and the need for more refined operations, the number of menus available to frontline tellers has surged, making it difficult for traditional menu search functions to quickly locate target menus. Users often need to input precise keywords to find the desired menu. This invention optimizes the user experience of the credit system by recommending menus based on user input, which is crucial for reducing the burden on frontline staff and improving efficiency.

[0109] The menu data acquisition method provided in this invention responds to a user's action of searching for a target menu sequence using menu keywords, obtains a list of candidate menus corresponding to the menu keywords; calculates the similarity between each data item in the candidate menu list and the menu keywords to obtain a first menu sequence semantically similar to the menu keywords; and generates the target menu sequence based on a pre-obtained second menu sequence containing historical click-through rate data corresponding to the user and the first menu sequence. The historical click-through rate data is the ratio of the click count corresponding to each data item in the user's historical operation menu list to the total click count corresponding to each data item in the user's historical operation menu list, enabling quick and accurate retrieval of the menu data needed by the user.

[0110] Further, generating the target menu sequence based on a pre-obtained second menu sequence containing historical click-through rate data corresponding to the user and the first menu sequence includes:

[0111] The target menu sequence is generated based on the second menu sequence, the first menu sequence, and their respective corresponding menu sequence weights. This can be referred to the above embodiments for further explanation, and will not be repeated here.

[0112] The menu data acquisition method provided in this embodiment of the invention can autonomously and flexibly control the generation of target menu sequences.

[0113] Further, generating the target menu sequence based on the second menu sequence, the first menu sequence, and their respective corresponding menu sequence weights includes:

[0114] Traverse each data item in the menu sequence, and obtain the menu sequence data value corresponding to each data item based on the similarity data of each data item in the first menu sequence, the historical click rate data in the second menu sequence, and the menu sequence weight; the menu sequence includes the first menu sequence and the second menu sequence; refer to the above embodiment for explanation, and will not be repeated here.

[0115] A preset number of menu items are selected according to the menu sequence data values ​​in descending order, and these preset number of menu items are combined to form the target menu sequence. This can be referred to the above embodiment for explanation, and will not be repeated here.

[0116] The menu data acquisition method provided in this embodiment of the invention can further autonomously and flexibly control the generation of target menu sequences.

[0117] Furthermore, the first menu sequence is arranged in descending order of similarity data from high to low, and the second menu sequence is arranged in descending order of historical click-through rate data from high to low; correspondingly, traversing each data item in the menu sequence includes:

[0118] The data items in the menu sequence are traversed sequentially according to either the descending order of the first menu sequence or the descending order of the second menu sequence. This can be referred to the above embodiment for explanation, and will not be repeated here.

[0119] The menu data acquisition method provided in this embodiment of the invention helps to further improve data processing efficiency.

[0120] Further, obtaining the historical click-through rate data includes:

[0121] The system responds to the user's selection of historical click-through rate (CTR) data based on preset data statistical dimensions. These preset CTR dimensions include full historical CTR data and recent historical CTR data from a preset number of days prior to the current day. This can be referred to the above embodiment for further explanation and will not be repeated here.

[0122] The menu data acquisition method provided in this embodiment of the invention can flexibly select historical click-through rate data.

[0123] Furthermore, obtaining the historical click-through rate data also includes:

[0124] The historical click-through rate data is calculated based on the statistical dimension data values ​​and corresponding statistical dimension data weights of each dimension data in the preset data statistical dimensions. This can be referred to the above embodiment for further explanation, and will not be repeated here.

[0125] The menu data acquisition method provided in this embodiment of the invention can more reasonably determine historical click-through rate data.

[0126] Further, obtaining the historical click-through rate data includes:

[0127] The historical click-through rate data is obtained through a front-end tracking component. This can be referred to the above embodiment for further explanation, and will not be repeated here.

[0128] The menu data acquisition method provided in this embodiment of the invention can efficiently acquire historical click-through rate data.

[0129] It should be noted that the menu data acquisition method provided in this embodiment of the invention can be used in the financial field, or in any technical field other than the financial field. This embodiment of the invention does not limit the application field of the menu data acquisition method.

[0130] Figure 3 This is a schematic diagram of the structure of a menu data acquisition device provided in an embodiment of the present invention, as shown below. Figure 3 As shown, the menu data acquisition device provided in this embodiment of the invention includes an acquisition unit 301, a calculation unit 302, and a generation unit 303, wherein:

[0131] The acquisition unit 301 is used to respond to the user's action of searching for a target menu sequence through menu keywords, and acquire a list of candidate menus corresponding to the menu keywords; the calculation unit 302 is used to calculate the similarity between each data item in the candidate menu list and the menu keywords, and obtain a first menu sequence that is semantically similar to the menu keywords; the generation unit 303 is used to generate the target menu sequence based on a pre-obtained second menu sequence containing historical click-through rate data corresponding to the user and the first menu sequence; wherein, the historical click-through rate data is the ratio of the click volume corresponding to each data item in the user's historical operation menu list to the total click volume corresponding to each data item in the user's historical operation menu list.

[0132] Specifically, the acquisition unit 301 in the device is used to respond to the user's action of searching for a target menu sequence through menu keywords, and to acquire a list of candidate menus corresponding to the menu keywords; the calculation unit 302 is used to calculate the similarity between each data item in the candidate menu list and the menu keywords, and to obtain a first menu sequence that is semantically similar to the menu keywords; the generation unit 303 is used to generate the target menu sequence based on a pre-obtained second menu sequence containing historical click-through rate data corresponding to the user and the first menu sequence; wherein, the historical click-through rate data is the ratio of the number of clicks corresponding to each data item in the user's historical operation menu list to the total number of clicks corresponding to each data item in the user's historical operation menu list.

[0133] The menu data acquisition device provided in this embodiment of the invention responds to a user's action of searching for a target menu sequence through menu keywords, acquires a list of candidate menus corresponding to the menu keywords; calculates the similarity between each character data in the candidate menu list and the menu keywords to obtain a first menu sequence semantically similar to the menu keywords; and generates the target menu sequence based on a pre-obtained second menu sequence containing historical click-through rate data corresponding to the user and the first menu sequence; wherein, the historical click-through rate data is the ratio of the click volume corresponding to each character data in the user's historical operation menu list to the total click volume corresponding to each character data in the user's historical operation menu list, which can quickly and accurately find the menu data needed by the user.

[0134] Furthermore, the generation unit 303 is specifically used for:

[0135] The target menu sequence is generated based on the second menu sequence, the first menu sequence, and their respective corresponding menu sequence weights.

[0136] The menu data acquisition device provided in this embodiment of the invention can autonomously and flexibly control the generation of target menu sequences.

[0137] Furthermore, the generation unit 303 is specifically used for:

[0138] Traverse each data item in the menu sequence, and obtain the menu sequence data value corresponding to each data item based on the similarity data of each data item in the first menu sequence, the historical click rate data in the second menu sequence, and the menu sequence weight; the menu sequence includes the first menu sequence and the second menu sequence.

[0139] Select a preset number of menu items in descending order of the menu sequence data values, and combine the preset number of menu items to form the target menu sequence.

[0140] The menu data acquisition device provided in this embodiment of the invention is further capable of autonomously and flexibly controlling the generation of target menu sequences.

[0141] Furthermore, the first menu sequence is arranged in descending order of similarity data from high to low, and the second menu sequence is arranged in descending order of historical click-through rate data from high to low; correspondingly, the generation unit 303 is also specifically used for:

[0142] The data items in the menu sequence are traversed sequentially according to the descending order of the first menu sequence or the descending order of the second menu sequence.

[0143] The menu data acquisition device provided in this embodiment of the invention helps to further improve data processing efficiency.

[0144] Furthermore, the menu data acquisition device is also used for:

[0145] The system responds to the historical click-through rate data selected by the user based on a preset data statistics dimension; wherein, the preset data statistics dimension includes the full historical click-through rate data and the recent historical click-through rate data from a preset number of days ago.

[0146] The menu data acquisition device provided in this embodiment of the invention can autonomously and flexibly select historical click rate data.

[0147] Furthermore, the menu data acquisition device is also specifically used for:

[0148] The historical click-through rate data is calculated based on the statistical dimension data values ​​of each dimension data in the preset data statistical dimensions and the statistical dimension data weights corresponding to each dimension data.

[0149] The menu data acquisition device provided in this embodiment of the invention can more reasonably determine historical click-through rate data.

[0150] Furthermore, the menu data acquisition device is also specifically used for:

[0151] The historical click-through rate data is obtained through a front-end tracking component.

[0152] The menu data acquisition device provided in this embodiment of the invention can efficiently acquire historical click-through rate data.

[0153] The embodiments of the menu data acquisition device provided in this invention can be used to execute the processing flow of the above-described method embodiments. Its functions will not be repeated here, but can be referred to the detailed description of the above-described method embodiments.

[0154] Figure 4 This is a schematic diagram of the physical structure of an electronic device provided in an embodiment of the present invention, such as... Figure 4 As shown, the electronic device includes: a processor 401, a memory 402, and a bus 403;

[0155] The processor 401 and the memory 402 communicate with each other via the bus 403.

[0156] The processor 401 is used to call program instructions in the memory 402 to execute the methods provided in the above-described method embodiments, including, for example:

[0157] In response to a user's action of searching for a target menu sequence using menu keywords, obtain a list of candidate menus corresponding to the menu keywords;

[0158] Calculate the similarity between each data item in the candidate menu list and the menu keyword to obtain a first menu sequence that is semantically similar to the menu keyword;

[0159] The target menu sequence is generated based on a pre-obtained second menu sequence containing historical click-through rate data corresponding to the user and the first menu sequence;

[0160] The historical click-through rate data is the ratio of the number of clicks corresponding to each data item in the user's historical operation menu list to the total number of clicks corresponding to each data item in the user's historical operation menu list.

[0161] This embodiment discloses a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium. The computer program includes program instructions, and when the program instructions are executed by a computer, the computer can perform the methods provided in the above-described method embodiments, such as:

[0162] In response to a user's action of searching for a target menu sequence using menu keywords, obtain a list of candidate menus corresponding to the menu keywords;

[0163] Calculate the similarity between each data item in the candidate menu list and the menu keyword to obtain a first menu sequence that is semantically similar to the menu keyword;

[0164] The target menu sequence is generated based on a pre-obtained second menu sequence containing historical click-through rate data corresponding to the user and the first menu sequence;

[0165] The historical click-through rate data is the ratio of the number of clicks corresponding to each data item in the user's historical operation menu list to the total number of clicks corresponding to each data item in the user's historical operation menu list.

[0166] This embodiment provides a computer-readable storage medium storing a computer program that causes the computer to execute the methods provided in the above-described method embodiments, including, for example:

[0167] In response to a user's action of searching for a target menu sequence using menu keywords, obtain a list of candidate menus corresponding to the menu keywords;

[0168] Calculate the similarity between each data item in the candidate menu list and the menu keyword to obtain a first menu sequence that is semantically similar to the menu keyword;

[0169] The target menu sequence is generated based on a pre-obtained second menu sequence containing historical click-through rate data corresponding to the user and the first menu sequence;

[0170] The historical click-through rate data is the ratio of the number of clicks corresponding to each data item in the user's historical operation menu list to the total number of clicks corresponding to each data item in the user's historical operation menu list.

[0171] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0172] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0173] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0174] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0175] In the description of this specification, the references to terms such as "an embodiment," "a specific embodiment," "some embodiments," "for example," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0176] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for acquiring menu data, characterized in that, include: In response to a user's action of searching for a target menu sequence using menu keywords, obtain a list of candidate menus corresponding to the menu keywords; Calculate the similarity between each data item in the candidate menu list and the menu keyword to obtain a first menu sequence that is semantically similar to the menu keyword; The target menu sequence is generated based on a pre-obtained second menu sequence containing historical click-through rate data corresponding to the user and the first menu sequence; The historical click-through rate data is the ratio of the number of clicks corresponding to each data item in the user's historical operation menu list to the total number of clicks corresponding to each data item in the user's historical operation menu list. The step of generating the target menu sequence based on a pre-obtained second menu sequence containing historical click-through rate data corresponding to the user and the first menu sequence includes: The target menu sequence is generated based on the second menu sequence, the first menu sequence, and their respective corresponding menu sequence weights; The step of generating the target menu sequence based on the second menu sequence, the first menu sequence, and their respective corresponding menu sequence weights includes: Traverse each data item in the menu sequence, and obtain the menu sequence data value corresponding to each data item based on the similarity data of each data item in the first menu sequence, the historical click rate data in the second menu sequence, and the menu sequence weight; the menu sequence includes the first menu sequence and the second menu sequence. Select a preset number of menu items in descending order of the menu sequence data values, and combine the preset number of menu items to form the target menu sequence.

2. The menu data acquisition method according to claim 1, characterized in that, The first menu sequence is arranged in descending order of similarity data from high to low, and the second menu sequence is arranged in descending order of historical click-through rate data from high to low; correspondingly, traversing each data item in the menu sequence includes: The data items in the menu sequence are traversed sequentially according to the descending order of the first menu sequence or the descending order of the second menu sequence.

3. The menu data acquisition method according to any one of claims 1 to 2, characterized in that, Obtaining the historical click-through rate data includes: The system responds to the historical click-through rate data selected by the user based on a preset data statistics dimension; wherein, the preset data statistics dimension includes the full historical click-through rate data and the recent historical click-through rate data from a preset number of days ago.

4. The menu data acquisition method according to claim 3, characterized in that, Obtaining the historical click-through rate data also includes: The historical click-through rate data is calculated based on the statistical dimension data values ​​of each dimension data in the preset data statistical dimensions and the statistical dimension data weights corresponding to each dimension data.

5. The menu data acquisition method according to claim 3, characterized in that, Obtaining the historical click-through rate data includes: The historical click-through rate data is obtained through a front-end tracking component.

6. A menu data acquisition device, characterized in that, include: The acquisition unit is used to respond to the user's action of searching for a target menu sequence by menu keywords and to acquire a list of candidate menus corresponding to the menu keywords; A calculation unit is used to calculate the similarity between each data item in the candidate menu list and the menu keyword, and to obtain a first menu sequence that is semantically similar to the menu keyword; A generation unit is configured to generate the target menu sequence based on a pre-obtained second menu sequence containing historical click-through rate data corresponding to the user and a first menu sequence; The historical click-through rate data is the ratio of the number of clicks corresponding to each data item in the user's historical operation menu list to the total number of clicks corresponding to each data item in the user's historical operation menu list. Specifically, the generation unit is used for: The target menu sequence is generated based on the second menu sequence, the first menu sequence, and their respective corresponding menu sequence weights; The generating unit is further specifically used for: Traverse each data item in the menu sequence, and obtain the menu sequence data value corresponding to each data item based on the similarity data of each data item in the first menu sequence, the historical click rate data in the second menu sequence, and the menu sequence weight; the menu sequence includes the first menu sequence and the second menu sequence. Select a preset number of menu items in descending order of the menu sequence data values, and combine the preset number of menu items to form the target menu sequence.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 5.

Images