A label data recommendation method, device, equipment and storage medium

Abstract

The application discloses a label data recommendation method and device, equipment and a storage medium. The application considers the application of the label, the quality data of the label and the similarity between the label and the query keyword comprehensively, accurately calculates the various factors by using the adaptive weighting method in the comprehensive consideration, thereby solving the problem of poor accuracy of the recommended label in the prior art, and improving the availability of the label recommendation by performing descending order sorting on the recommendation M, and recommending the optimization result obtained by descending order sorting, thereby improving the availability of the label recommendation. Since the method is based on the continuous calculation of the new data generated by the business development, business meaning and label application business scene in the computer, the problem of the update of the prior art is solved.

Description

Technical Field

[0001] This application relates to the field of financial technology, and in particular to a method, apparatus, device and storage medium for recommending tagged data. Background Technology

[0002] Tags are a data format used to describe the characteristics of business entities. Tags effectively expand the analytical perspective of business entities, and data filtering and analysis can be performed through simple operations on different tags. In the wave of enterprise digital transformation, more and more companies are establishing data platforms, and various business lines or divisions are processing more and more tags according to their own business needs. With the increase in the number of tags, how business departments determine whether there are suitable tags when launching new businesses becomes a problem that needs to be solved. To solve this problem, existing conventional processing methods include, but are not limited to, the following:

[0003] 1. Recommend tags created under the same business line or business unit based on the user's affiliation;

[0004] 2. Based on the keywords entered by users, recommend tags by matching basic tag attribute fields such as tag name, business meaning, and business scenario;

[0005] 3. Combining the two methods described above, a comprehensive matching process is used to recommend tags.

[0006] The technical issue stemming from changes in the meaning of tags and applicable business scenarios as business develops has led to a failure to update the data tags in the recommendation directory in a timely manner, significantly impacting the accuracy and usability of the recommended tags. Summary of the Invention

[0007] This application provides a tag data recommendation method, apparatus, device, and storage medium, which solves the technical problem that the data tags in the recommendation directory cannot be updated in a timely manner due to changes in information such as the business meaning of tags and the applicable business scenarios of tags as business develops, which has a significant impact on the accuracy and usability of the recommended tags.

[0008] In view of the above, the first aspect of this application provides a tag data recommendation method, the method comprising:

[0009] Step 1: Calculate the tag application score M1 based on the existing tag call data of the tag system;

[0010] Step 2: Calculate the label quality score M2 based on the existing label quality data of the label system;

[0011] Step 3: Calculate the similarity M3 between the obtained keywords and the existing tags in the tag system;

[0012] Step 4: The tag recommendation score M is obtained by weighting the tag application score M1, the tag quality score M2, and the similarity score M3 between the keyword and the existing tag;

[0013] Step 5: Sort the recommended tag score M in descending order, and use the optimization results to recommend existing tags.

[0014] Optionally, step one specifically includes:

[0015] The existing tag call data of the tag system can be obtained by adding tracking points and interface logs to the tag system.

[0016] The tag application score M1 is calculated by using a weighted score calculation formula on the existing tag call data.

[0017] Optionally, step two specifically includes:

[0018] By building a label quality monitoring service in the label system, the existing label quality data of the label system can be obtained;

[0019] The label quality score M2 is calculated using the weighted score calculation formula on the existing label quality data.

[0020] Optionally, step three specifically includes:

[0021] The tagging system obtains keywords uploaded by users.

[0022] The similarity M3 between the keyword and the existing tags in the tagging system is calculated using a similarity algorithm.

[0023] Optionally, the existing tag retrieval data includes:

[0024] The calling channel, calling department, calling system, calling business scenario, number of times used, and usage popularity.

[0025] Optionally, the existing label quality data includes: customer range, saturation, maximum value, minimum value, average value, standard deviation, median, and coefficient of variation.

[0026] Optionally, the label quality score is divided into identification-type label quality score and numerical label quality score according to the label type.

[0027] A second aspect of this application provides a tag data recommendation device, the device comprising:

[0028] The first calculation unit is used to calculate the tag application score M1 based on the existing tag call data of the tag system.

[0029] The second calculation unit is used to calculate the label quality score M2 based on the existing label quality data of the label system.

[0030] The third calculation unit is used to calculate the similarity M3 between the keywords and the existing tags in the acquired keyword and tag system.

[0031] The fourth calculation unit is used to calculate the tag recommendation score M by weighting the tag application score M1, the tag quality score M2, and the similarity score M3 between the keyword and the existing tag.

[0032] The recommendation unit is used to sort the tag recommendation scores M in descending order, obtain the optimization results, and recommend existing tags according to the optimization results.

[0033] A third aspect of this application provides a tag data recommendation device, the device comprising a processor and a memory:

[0034] The memory is used to store program code and transmit the program code to the processor;

[0035] The processor is configured to execute the steps of the tag data recommendation method as described in the first aspect above, according to the instructions in the program code.

[0036] A fourth aspect of this application provides a computer-readable storage medium for storing program code for executing the tag data recommendation method described in the first aspect above.

[0037] As can be seen from the above technical solutions, the embodiments of this application have the following advantages:

[0038] This application provides a tag data recommendation method. By comprehensively considering the application status of tags, the quality of tag data, and the similarity between tags and query keywords, a weighted method is selected to accurately calculate various factors, thereby solving the problem of poor tag recommendation accuracy in existing technologies. By sorting the recommended data (M) in descending order and recommending based on the optimized results obtained from this descending order, the usability of tag recommendations is improved. Because this method relies on the computer continuously calculating based on new data generated by business development, business meaning, and the applicable business scenarios of tags, it solves the problem of untimely updates in existing technologies. Attached Figure Description

[0039] Figure 1 This is a flowchart of a tag data recommendation method according to an embodiment of this application;

[0040] Figure 2This is a schematic diagram of the structure of a tag data recommendation device according to an embodiment of this application;

[0041] Figure 3 This is a schematic diagram of the structure of a tag data recommendation device according to an embodiment of this application. Detailed Implementation

[0042] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present application.

[0043] This application designs a tag data recommendation method, apparatus, device, and storage medium, which solves the technical problem that the data tags in the recommendation directory cannot be updated in a timely manner due to changes in information such as the business meaning of tags and the applicable business scenarios of tags as business develops, which has a significant impact on the accuracy and usability of the recommended tags.

[0044] For easier understanding, please refer to Figure 1 , Figure 1 This is a flowchart of a tag data recommendation method according to an embodiment of this application, such as... Figure 1 As shown, specifically:

[0045] S1. Calculate the tag application score M1 based on the existing tag call data of the tag system;

[0046] Specifically, it includes:

[0047] By adding event tracking points and API logs to the tag system, we can obtain existing tag call data from the tag system.

[0048] The label application score M1 is calculated by using the weighted score calculation formula on the existing label call data.

[0049] It should be noted that, for the existing tags included in the tag system, the tag application score M1 of each existing tag can be calculated based on the data retrieved from the existing tags.

[0050] Obtaining existing tag call data can be achieved by adding tracking points to the tag system or by parsing interface logs. Existing tag call data includes, but is not limited to, call channel, call department, call system, call business scenario, usage frequency, and usage popularity. In essence, all data generated from calls to existing tags can be used as existing tag call data.

[0051] Secondly, the existing tag application score M1 is obtained by calculating the weighted score based on the existing tag application data using a weighted scoring formula. Considering the system's ability to statistically analyze existing tag application data, which may contain multiple metrics (e.g., application channel and application portion are two different metrics), the following methods can be used to calculate the weights of each metric in the existing tag application data:

[0052] 1. Utilizing expert scoring methods, this solution provides a weighting service that allows for the addition, deletion, and modification of application scoring data, as well as flexible setting of the weight of each parameter. Understandably, this approach is highly subjective, requiring manual adjustment of the weighting of each parameter, and is significantly limited by the expertise, authority, and experience of the specialists.

[0053] 2. Factor analysis, utilizing the principle of information rotation and condensation in data, calculates the weights of each existing labeled data point using the variance explained ratio. Understandably, compared to expert rating methods, factor analysis can provide a more objective analysis, identify representative factors from multiple existing labeled data points, group variables with similar characteristics into a single factor, introduce the number of variables, and test hypotheses about the relationships between variables.

[0054] 3. Using the Analytic Hierarchy Process (APH), the relative magnitude of numbers is used to calculate the weights of the existing labeled data. It's understandable that the AHP is well-suited for target systems with hierarchical and interleaved evaluation indicators, and for decision-making problems where the target values ​​are difficult to quantify. In this solution, the calling department, calling channel, calling system, and calling business scenario can all be constructed with a hierarchical and interleaved architecture, thus allowing the application of the AHP to calculate the weights of the existing labeled data.

[0055] S2. Calculate the label quality score M2 based on the existing label quality data of the label system;

[0056] Specifically, it includes:

[0057] By building a label quality monitoring service in the label system, the existing label quality data of the label system can be obtained;

[0058] The label quality score M2 is calculated using a weighted scoring formula based on the existing label quality data.

[0059] It should be noted that the quality of each existing label in the labeling system is not uniform, and it is necessary to further calculate the label quality score M2 of each existing label based on the existing label quality data.

[0060] The existing label quality data is primarily obtained by building a label quality monitoring service within the label system, thereby acquiring the quality data for each existing label in the system. This existing label quality data includes: customer range, saturation, maximum value, minimum value, average value, standard deviation, median, and coefficient of variation.

[0061] Understandably, due to differences in tag types, the quality data of existing tags that can be obtained will also vary. Tag types can be divided into label types and numerical tags. Label types refer to tags that describe yes or no, while numerical tags are tags with specific numerical values.

[0062] The existing label quality data for identifiable labels cannot obtain the indicator data that can only be obtained for numerical labels such as maximum value, minimum value, average value, standard deviation, and median. It can only obtain the yes or no label.

[0063] Therefore, the label quality score M2 is calculated using a weighted scoring formula on existing label quality data according to different label types.

[0064] Furthermore, for identifier-type tags, the following methods can be used to calculate the weights of each indicator in the existing tag-based data:

[0065] 1. Utilizing expert scoring methods, this solution provides a weighting service that allows for the addition, deletion, and modification of application scoring data, as well as flexible setting of the weight of each parameter. Understandably, this approach is highly subjective, requiring manual adjustment of the weighting of each parameter, and is significantly limited by the expertise, authority, and experience of the specialists.

[0066] 2. Using the APH (Analytic Hierarchy Process), the relative magnitude of numbers is used to calculate the weights of the existing label-based data. It's understandable that the analytic hierarchy process is well-suited for target systems with hierarchical and interleaved evaluation indicators, and for decision-making problems where the target values ​​are difficult to quantify. In this solution, the application of yes / no labels in various scenarios can construct a hierarchical and interleaved architecture, thus enabling the application of the APH to calculate the weights of the existing label-based data.

[0067] For numerical labels, the following methods can be used to calculate the weights of each indicator in the existing label data:

[0068] 1. Using the Analytic Hierarchy Process (APH), the relative magnitude of numbers is used to calculate the weights of data retrieved from existing labels. It's understandable that the AHP is well-suited for target systems with hierarchical and interleaved evaluation indicators, and for decision-making problems where the target values ​​are difficult to quantify. In this solution, numerical labels such as customer range, saturation, maximum value, minimum value, average value, standard deviation, median, and coefficient of variation can be used in various scenarios to construct a hierarchical and interleaved architecture, thereby enabling the application of the AHP to calculate the weights of data retrieved from existing labels.

[0069] 2. The pecking order graph method calculates weights based on the relative size of numbers. This method is easier to understand than AHP. For example, by first calculating the average value, and then comparing the average values, a higher relative value is scored as 1 point, a lower relative value as 0 points, and an equal average value as 0.5 points. For numerical labels, the pecking order graph method is more convenient for calculating weights of data retrieved from existing labels.

[0070] S3. Calculate the similarity M3 between the keywords and existing tags based on the obtained keywords and existing tags in the tag system;

[0071] Specifically, it includes:

[0072] The tag system obtains keywords uploaded by users.

[0073] The similarity M3 between the keyword and the existing tags in the tag system is calculated using a similarity algorithm.

[0074] It should be noted that the keywords recommended based on user-uploaded tags are mainly calculated using a similarity algorithm to determine the similarity M3 between the keywords and existing tags in the tag system.

[0075] The similarity algorithms that can be used include, but are not limited to:

[0076] 1. Cosine similarity algorithm;

[0077] 2. Similarity algorithm based on Pearson correlation;

[0078] 3. A similarity algorithm based on Euclidean distance;

[0079] 4. Modify the cosine similarity algorithm;

[0080] 5. Similarity algorithm based on Manhattan distance.

[0081] S4. The tag recommendation score M is obtained by weighting the tag application score M1, the tag quality score M2, and the similarity between the keyword and the existing tag M3.

[0082] It should be noted that, based on the obtained tag application score M1, tag quality score M2, and keyword similarity with existing tags M3, the tag recommendation score M can be further calculated by weighting, specifically: M = M1 * m1% + M2 * m2% + M3 * m3%, where m1, m2, and m3 are the weights of M1, M2, and M3, respectively.

[0083] The following weight determination methods can also be applied to calculate the weight of this part:

[0084] 1. Utilizing expert scoring methods, a weight setting service is built to provide flexible settings for tag application scores, tag quality scores, keyword similarity to existing tags, and the weight of each parameter.

[0085] 2. Using the APH (Analytical Processing Hierarchy Process) method, the relative magnitude of numbers is used to calculate the weights of tag application score, tag quality score, and similarity between keywords and existing tags.

[0086] 3. Using the pecking order graph method, the relative size of the numbers is used to calculate the weights of tag application score, tag quality score, and similarity between keywords and existing tags.

[0087] S5. Sort the recommended tags M in descending order, and use the optimization results to recommend existing tags.

[0088] It should be noted that after calculating the tag recommendation score for each existing tag in the tag system for the keyword, the existing tags are sorted in descending order according to the tag recommendation score, and the top m (m is a configurable parameter) or the top m% (m is a configurable parameter) of existing tags are displayed and recommended.

[0089] Please see Figure 2 , Figure 2 This is a schematic diagram of the structure of a tag data recommendation device in an embodiment of this application, as shown below. Figure 2 As shown, specifically:

[0090] The first calculation unit 201 is used to calculate the tag application score M1 based on the existing tag call data of the tag system.

[0091] The second calculation unit 202 is used to calculate the label quality score M2 based on the existing label quality data of the label system.

[0092] The third calculation unit 203 is used to calculate the similarity M3 between the keywords and existing tags based on the acquired keywords and existing tags in the tag system.

[0093] The fourth calculation unit 204 is used to calculate the tag recommendation score M by weighting the tag application score M1, the tag quality score M2, and the similarity between the keyword and the existing tag M3.

[0094] Recommendation unit 205 is used to sort the tag recommendation scores M in descending order, obtain the optimization results, and recommend existing tags according to the optimization results.

[0095] This application also provides another tag data recommendation device, such as... Figure 3 As shown, for ease of explanation, only the parts related to the embodiments of this application are shown. For specific technical details not disclosed, please refer to the method section of the embodiments of this application. The terminal can be any terminal device including mobile phones, tablets, personal digital assistants (PDAs), point-of-sales terminals (POS), in-vehicle computers, etc. Taking a mobile phone as an example:

[0096] Figure 3 This is a block diagram illustrating a portion of the structure of a mobile phone related to the terminal provided in the embodiments of this application. (Reference) Figure 3 The mobile phone includes: a radio frequency (RF) circuit 1010, a memory 1020, an input unit 1030, a display unit 1040, a sensor 1050, an audio circuit 1060, a wireless fidelity (WiFi) module 1070, a processor 1080, and a power supply 1090, etc. Those skilled in the art will understand that... Figure 3 The mobile phone structure shown does not constitute a limitation on the mobile phone and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0097] The following is combined with Figure 3 A detailed introduction to each component of a mobile phone:

[0098] The RF circuit 1010 can be used for receiving and transmitting signals during information transmission or calls. Specifically, it receives downlink information from the base station and processes it with the processor 1080; additionally, it transmits uplink data to the base station. Typically, the RF circuit 1010 includes, but is not limited to, an antenna, at least one amplifier, a transceiver, a coupler, a low-noise amplifier (LNA), a duplexer, etc. Furthermore, the RF circuit 1010 can also communicate wirelessly with networks and other devices. The aforementioned wireless communications may use any communication standard or protocol, including but not limited to Global System for Mobile Communications (GSM), General Packet Radio Service (GPRS), Code Division Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), Long Term Evolution (LTE), email, and Short Messaging Service (SMS).

[0099] The memory 1020 can be used to store software programs and modules. The processor 1080 executes various mobile phone functions and data processing by running the software programs and modules stored in the memory 1020. The memory 1020 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, applications required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the mobile phone (such as audio data, phonebook, etc.). In addition, the memory 1020 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0100] The input unit 1030 can be used to receive input numerical or character information, and to generate key signal inputs related to user settings and function control of the mobile phone. Specifically, the input unit 1030 may include a touch panel 1031 and other input devices 1032. The touch panel 1031, also known as a touch screen, can collect touch operations performed by the user on or near it (such as operations performed by the user using a finger, stylus, or any suitable object or accessory on or near the touch panel 1031), and drive the corresponding connection devices according to a pre-set program. Optionally, the touch panel 1031 may include two parts: a touch detection device and a touch controller. The touch detection device detects the user's touch position and the signal generated by the touch operation, and transmits the signal to the touch controller; the touch controller receives touch information from the touch detection device, converts it into touch point coordinates, and sends it to the processor 1080, and can also receive and execute commands sent by the processor 1080. In addition, the touch panel 1031 can be implemented using various types such as resistive, capacitive, infrared, and surface acoustic wave. In addition to the touch panel 1031, the input unit 1030 may also include other input devices 1032. Specifically, other input devices 1032 may include, but are not limited to, one or more of the following: physical keyboard, function keys (such as volume control buttons, power buttons, etc.), trackball, mouse, joystick, etc.

[0101] The display unit 1040 can be used to display information input by the user or information provided to the user, as well as various menus of the mobile phone. The display unit 1040 may include a display panel 1041, which may optionally be configured as a Liquid Crystal Display (LCD), Organic Light-Emitting Diode (OLED), or similar display panel 1041. Further, a touch panel 1031 may cover the display panel 1041. When the touch panel 1031 detects a touch operation on or near it, it transmits the information to the processor 1080 to determine the type of touch event. Subsequently, the processor 1080 provides corresponding visual output on the display panel 1041 according to the type of touch event. Although in Figure 3 In this embodiment, the touch panel 1031 and the display panel 1041 are two separate components to realize the input and output functions of the mobile phone. However, in some embodiments, the touch panel 1031 and the display panel 1041 can be integrated to realize the input and output functions of the mobile phone.

[0102] The mobile phone may also include at least one sensor 1050, such as a light sensor, a motion sensor, and other sensors. Specifically, the light sensor may include an ambient light sensor and a proximity sensor. The ambient light sensor can adjust the brightness of the display panel 1041 according to the ambient light level, and the proximity sensor can turn off the display panel 1041 and / or the backlight when the phone is moved to the ear. As a type of motion sensor, an accelerometer sensor can detect the magnitude of acceleration in various directions (generally three axes). When stationary, it can detect the magnitude and direction of gravity and can be used for applications that recognize the phone's posture (such as landscape / portrait switching, related games, magnetometer posture calibration), vibration recognition-related functions (such as pedometer, taps), etc. Other sensors that may be configured in the mobile phone, such as gyroscopes, barometers, hygrometers, thermometers, and infrared sensors, will not be described in detail here.

[0103] The audio circuit 1060, speaker 1061, and microphone 1062 provide an audio interface between the user and the mobile phone. The audio circuit 1060 converts the received audio data into electrical signals and transmits them to the speaker 1061, where the speaker 1061 converts them into sound signals for output. On the other hand, the microphone 1062 converts the collected sound signals into electrical signals, which are then received by the audio circuit 1060, converted into audio data, and then processed by the processor 1080 before being transmitted via the RF circuit 1010 to, for example, another mobile phone, or the audio data can be output to the memory 1020 for further processing.

[0104] WiFi is a short-range wireless transmission technology. Through the WiFi module 1070, mobile phones can help users send and receive emails, browse web pages, and access streaming media, providing users with wireless broadband internet access. Although Figure 3 The WiFi module 1070 is shown, but it is understood that it is not an essential component of a mobile phone and can be omitted as needed without changing the essence of the invention.

[0105] The processor 1080 is the control center of the mobile phone, connecting various parts of the phone through various interfaces and lines. It executes software programs and / or modules stored in the memory 1020 and calls data stored in the memory 1020 to perform various functions and process data, thereby providing overall monitoring of the phone. Optionally, the processor 1080 may include one or more processing units; preferably, the processor 1080 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the modem processor mainly handles wireless communication. It is understood that the modem processor may not be integrated into the processor 1080.

[0106] The mobile phone also includes a power supply 1090 (such as a battery) that supplies power to various components. Preferably, the power supply can be logically connected to the processor 1080 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system.

[0107] Although not shown, mobile phones may also include a camera, Bluetooth module, etc., which will not be described in detail here.

[0108] In this embodiment of the application, the processor 1080 included in the terminal also has the following functions:

[0109] The tag application score M1 is calculated based on the existing tag call data of the tag system.

[0110] The label quality score M2 is calculated based on the existing label quality data of the label system.

[0111] The similarity M3 between the keywords and existing tags is calculated based on the obtained keywords and existing tags in the tag system.

[0112] The tag recommendation score M is obtained by weighting the tag application score M1, the tag quality score M2, and the similarity between the keyword and existing tags M3.

[0113] The recommended tags M are sorted in descending order, and the optimized results are used to recommend existing tags.

[0114] This application also provides a computer-readable storage medium for storing program code that executes any one of the implementation methods of the tag data recommendation method described in the foregoing embodiments.

[0115] This application provides a tag data recommendation method, apparatus, device, and storage medium. By comprehensively considering the application status of tags, tag quality data, and the similarity between tags and query keywords, and by employing a weighted method appropriate to each factor for precise calculation, it solves the problem of poor tag recommendation accuracy in existing technologies. Furthermore, by sorting the recommended data (M) in descending order and then recommending based on the optimized results obtained from this descending order, the usability of tag recommendations is improved. Since this method relies on the computer continuously calculating based on new data generated by business development, business meaning, and the applicable business scenarios of the tags, it solves the problem of untimely updates in existing technologies.

[0116] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0117] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented, for example, in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0118] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0119] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection between apparatuses or units through some interfaces, and may be electrical, mechanical, or other forms.

[0120] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0121] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0122] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes: USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, optical disks, and other media capable of storing program code.

[0123] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A method for recommending tags, characterized in that, Includes the following steps: Step 1: Calculate the tag application score M1 based on the existing tag call data of the tag system; Step 2: Calculate the label quality score M2 based on the existing label quality data of the label system; Step 3: Calculate the similarity M3 between the obtained keywords and the existing tags in the tag system; Step 4: The tag recommendation score M is obtained by weighting the tag application score M1, the tag quality score M2, and the similarity score M3 between the keyword and the existing tag; Step 5: Sort the recommended tag score M in descending order to obtain the optimization result, and recommend existing tags according to the optimization result; Step one specifically includes: The existing tag call data of the tag system can be obtained by adding tracking points and interface logs to the tag system. The tag application score M1 is calculated by using a weighted score calculation formula on the existing tag call data; Among them, the existing tag application score M1 is obtained by calculating the existing tag application data through the weighted score calculation formula. The calculation methods for the weights of each indicator of the existing tag application data include: expert scoring method, factor analysis method, and APH hierarchical analysis method. Step two specifically includes: By building a label quality monitoring service in the label system, the existing label quality data of the label system can be obtained; The label quality score M2 is calculated using a weighted scoring formula on the existing label quality data. The label quality score M2 is calculated according to different label types by using the weighted scoring formula on the existing label quality data. Among them, the identification type labels are calculated by expert scoring or APH (Analytic Hierarchy Process), and the numerical type labels are calculated by APH or by the quorum method. APH uses the relative size information of numbers to calculate the weight of each existing label data, while the quorum method uses the relative size of numbers to calculate the weight.

2. The tag data recommendation method according to claim 1, characterized in that, Step three specifically includes: The tagging system acquires keywords uploaded by users; The similarity M3 between the keyword and the existing tags in the tagging system is calculated using a similarity algorithm.

3. The tag data recommendation method according to claim 1, characterized in that, The existing tag retrieval data includes: The calling channel, calling department, calling system, calling business scenario, number of times used, and usage popularity.

4. The tag data recommendation method according to claim 1, characterized in that, The existing tag quality data includes: customer range, saturation, maximum value, minimum value, average value, standard deviation, median, and coefficient of variation.

5. The tag data recommendation method according to claim 1, characterized in that, The label quality score is divided into two types based on label type: identification-type label quality score and numerical-type label quality score.

6. A tag data recommendation device, characterized in that, include: The first calculation unit is used to calculate the tag application score M1 based on the existing tag call data of the tag system. Specifically, it is used to obtain the existing tag call data of the tag system by adding tracking points and interface logs to the tag system, and to calculate the tag application score M1 using a weighted score calculation formula on the existing tag call data. The calculation methods for the weights of each indicator of the existing tag call data include: expert scoring method, factor analysis method, and APH hierarchical analysis method. The second calculation unit is used to calculate the label quality score M2 based on the existing label quality data of the label system. Specifically, it is used to build a label quality monitoring service in the label system, obtain the existing label quality data of the label system, and calculate the label quality score M2 using a weighted score calculation formula on the existing label quality data. The label quality score M2 is calculated according to different label types by using a weighted score calculation formula on the existing label quality data. Among them, identification type labels are calculated using the expert scoring method or the APH (Analytic Hierarchy Process) method, and numerical type labels are calculated using the APH method or the pecking order graph method. The APH method uses the relative size information of numbers to calculate the weight of each existing label data, and the pecking order graph method uses the relative size of numbers to calculate the weight. The third calculation unit is used to calculate the similarity M3 between the keywords and the existing tags in the acquired keyword and tag system. The fourth calculation unit is used to calculate the tag recommendation score M by weighting the tag application score M1, the tag quality score M2, and the similarity score M3 between the keyword and the existing tag. The recommendation unit is used to sort the tag recommendation scores M in descending order to obtain the optimization results and recommend existing tags according to the optimization results.

7. A tag data recommendation device, characterized in that, The device includes a processor and a memory: The memory is used to store program code and transmit the program code to the processor; The processor is configured to execute the tag data recommendation method according to any one of claims 1-5 according to the instructions in the program code.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store program code for performing the tag data recommendation method according to any one of claims 1-5.

Images