Activity level quality evaluation method and device, computer equipment and storage medium

Abstract

The invention belongs to the field of artificial intelligence and big data, and relates to an activity level quality evaluation method, which comprises the following steps: acquiring activity level data, and extracting data element information from the activity level data; inputting the data element information into a pre-trained activity quantity quality evaluation model to generate a target activity prediction score; comparing the target activity prediction score with a standard score; and based on a comparison result, generating a prediction judgment result of whether the target activity is successful or not. The invention further provides an activity level quality evaluation device, computer equipment and a storage medium. In addition, the invention also relates to a block chain technology, and a factor index list and / or a pre-trained activity level quality evaluation model and the like can be stored in a block chain. According to the method, the activity quality can be effectively evaluated.

Description

Technical Field

[0001] The present application relates to the fields of artificial intelligence and big data technology, and in particular to activity quality assessment methods, devices, computer equipment and storage media. Background Art

[0002] At present, the effectiveness of face-to-face interviews and other businesses related to finance (i.e., activity quantity and quality evaluation) cannot be known. Taking insurance business as an example, the conversion efficiency of face-to-face interviews by specialists is relatively low at present, and there are many reasons for the problems: 1. Whether the online connection is sufficient and whether the basic information of the customer is mastered; 2. Whether the rights and interests are clearly informed, whether the customer rights and interests notice has been read before the interview; 3. Policy service, whether the customer preservation service is completed in time, whether the customer receives the free insurance, and whether the customer entrusts the policy; 4. Feedback from the interview, whether the interview is expressed appropriately, whether there are obstacles in the communication process, whether the customer's attitude is indifferent and uncooperative, and whether the product introduction is sufficient. The above problems cannot be known for the quality and effectiveness of the specialist interviews, and at the same time, many unnecessary interviews are generated, resulting in unnecessary waste. Summary of the invention

[0003] The purpose of the embodiments of the present application is to propose an activity quantity quality assessment method, device, computer equipment and storage medium, the main purpose of which is to effectively evaluate the quality of the activity.

[0004] In order to solve the above technical problems, the present application embodiment provides an activity quantity quality assessment method, which adopts the following technical solution:

[0005] An activity quantity quality assessment method comprises the following steps:

[0006] Acquiring activity data, and extracting data metadata from the activity data;

[0007] Inputting the data metadata into a pre-trained activity quantity quality assessment model to generate a target activity prediction score;

[0008] comparing the target activity prediction score with a standard score;

[0009] Based on the comparison result, a prediction result of whether the target activity is successful is generated.

[0010] Furthermore, before inputting the activity data into the pre-trained activity quality assessment module to generate the target activity prediction score, the following steps are also included:

[0011] Obtaining a first data element sample;

[0012] Obtaining a preset factor index list; the factor index list includes: data element factors and corresponding factor indexes;

[0013] Matching the first data element sample with the data element factor in the factor indicator list, obtaining the factor indicator corresponding to the matched data element factor, and calculating a first label score corresponding to the first data element sample according to the factor indicator;

[0014] Based on the first data element sample and the corresponding first label score, the activity quality assessment model is iteratively trained to obtain the pre-trained activity quality assessment model.

[0015] Furthermore, the method further comprises the following steps:

[0016] Obtaining a second data element sample;

[0017] Inputting the second data element sample into the pre-trained activity quantity quality assessment model to generate a sample activity prediction score;

[0018] Comparing the sample activity prediction score with the standard score to generate a sample prediction result of whether the sample activity is effective;

[0019] The sample prediction result is compared with the actual result, and a judgment result of whether the sample prediction result is valid is generated based on the comparison result.

[0020] If the judgment result is invalid, the factor index corresponding to the standard score is updated, and the pre-trained activity quality assessment model is iteratively trained based on the updated factor index to obtain an updated pre-trained activity quality assessment model.

[0021] Furthermore, before comparing the target activity prediction score with the standard score, the following steps are also included:

[0022] Obtaining a preset factor index list; the factor index list includes: data element factors and corresponding factor indexes;

[0023] Extracting the factor indicator corresponding to each of the data element factors based on the factor indicator list;

[0024] The standard score is obtained by combining the factor indicators corresponding to all the data element factors in the factor indicator list based on the weighted average method.

[0025] Furthermore, before obtaining the preset factor index list, the following steps are also included:

[0026] Setting the first data element factor and the corresponding first factor index before the activity;

[0027] Setting the second data element factor and the corresponding second factor indicator in the activity;

[0028] Setting the third data element factor after the activity and the corresponding third factor index;

[0029] The first data element factor and the corresponding first factor indicator, the second data element factor and the corresponding second factor indicator, and the third data element factor and the corresponding third factor indicator are combined to generate the factor indicator list.

[0030] Furthermore, after generating a prediction result of whether the target activity is successful based on the comparison result, the following steps are also included:

[0031] Record activity information during the activity;

[0032] The data meta-factors and the corresponding factor indicators in the factor indicator list are updated based on the activity information.

[0033] In order to solve the above technical problems, the present application provides an activity quality assessment device, which adopts the following technical solution:

[0034] An activity quantity quality assessment device, comprising:

[0035] A data acquisition module, used to acquire activity data and extract data metadata from the activity data;

[0036] A score prediction module, used to input the data metadata into a pre-trained activity quantity quality assessment model to generate a target activity prediction score;

[0037] A score comparison module, used to compare the target activity prediction score with a standard score;

[0038] The result judgment module is used to generate a prediction result of whether the target activity is successful based on the result of the comparison.

[0039] Furthermore, it also includes:

[0040] A first acquisition module, used to acquire a first data element sample;

[0041] A list acquisition module is used to acquire a preset factor index list; the factor index list includes: data element factors and corresponding factor indexes;

[0042] A tag extraction module, configured to extract a first tag score corresponding to the first data element sample based on the factor indicator list;

[0043] A model training module is used to iteratively train an activity quality assessment model based on the first data element sample and the corresponding first label score to obtain the pre-trained activity quality assessment model.

[0044] A computer device comprises a memory and a processor, wherein the memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, the steps of the activity quality assessment method as described in any one of the above items are implemented.

[0045] In order to solve the above technical problems, the embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solution:

[0046] A computer-readable storage medium having computer-readable instructions stored thereon, wherein the computer-readable instructions, when executed by a processor, implement the steps of the activity quality assessment method as described in any one of the above items.

[0047] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0048] The embodiment of the present application generates a target activity prediction score by inputting activity volume data related to customer activities into a pre-trained activity volume quality assessment model, compares the target activity prediction score with the standard score, and generates a prediction result of whether the target activity is successful based on the comparison result. That is, the activity volume data related to the activity can be effectively qualitatively evaluated for the activity quality, and targeted improvements can be made for activities such as invalid face-to-face interviews to improve the quality of subsequent activities. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0050] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0051] Figure 2 is a flow chart of an embodiment of the activity quantity quality assessment method of the present application;

[0052] Figure 3 It is a flowchart of a specific implementation method of updating a pre-trained activity quality assessment model in the activity quality assessment method of the present application;

[0053] Figure 4 is a structural schematic diagram of an embodiment of an activity quantity quality assessment device according to the present application;

[0054] Figure 5 It is a structural diagram of an embodiment of a computer device according to the present application. DETAILED DESCRIPTION

[0055] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0056] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0057] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0058] like Figure 1 As shown, the system architecture 100 may include a terminal device 101, a network 102 and a server 103. The terminal device 101 may be a laptop 1011, a tablet computer 1012 or a mobile phone 1013. The network 102 is used to provide a medium for a communication link between the terminal device 101 and the server 103. The network 102 may include various connection types, such as wired, wireless communication links or optical fiber cables.

[0059] The user can use the terminal device 101 to interact with the server 103 through the network 102 to receive or send messages, etc. Various communication client applications can be installed on the terminal device 101, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0060] The terminal device 101 can be any electronic device with a display screen and supporting web browsing. In addition to a laptop computer 1011, a tablet computer 1012 or a mobile phone 1013, the terminal device 101 can also be an e-book reader, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 (Moving Picture Experts Group Audio Layer IV), a laptop computer, a desktop computer, etc.

[0061] The server 103 may be a server that provides various services, such as a background server that provides support for a web page displayed on the terminal device 101 .

[0062] It should be noted that the activity quality assessment method provided in the embodiment of the present application is generally executed by a server / terminal device, and accordingly, the activity quality assessment device is generally arranged in the server / terminal device.

[0063] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0064] Continue to refer Figure 2 , shows a flow chart of an embodiment of an activity quality assessment method according to the present application. The activity quality assessment method comprises the following steps:

[0065] Step S201, acquiring activity data, and extracting data metadata from the activity data.

[0066] In this embodiment, the electronic device (eg Figure 1 shown server / Terminal equipment ) can obtain customer activity related information data (i.e., activity volume data) through wired connection or wireless connection based on various means such as information technology, and divide the customer activity related information data into multiple data element information. It should be noted that the above wireless connection method may include but is not limited to 3G / 4G / 5G connection, WiFi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultra wideband) connection, and other wireless connection methods currently known or to be developed in the future.

[0067] For example, taking financial insurance business as an example, we can use information technology to obtain basic customer information, telephone / corporate WeChat interaction information, online contact information, face-to-face visit duration, customer satisfaction evaluation and other data metadata related to face-to-face customer insurance policy business activities.

[0068] Step S202: input the data metadata into a pre-trained activity quantity quality assessment model to generate a target activity prediction score.

[0069] The embodiment of the present application inputs the above-obtained data metadata related to the customer's insurance business activities into a pre-trained activity quantity quality assessment model to generate a target activity prediction score.

[0070] Specifically, the above-mentioned activity quality assessment model can adopt various pre-trained neural network models that exist now or will be developed in the future. As long as it can generate the corresponding target activity prediction score based on the input activity data, it falls within the scope of protection of this application.

[0071] Step S203, comparing the target activity prediction score with the standard score.

[0072] In the embodiment of the present application, the above standard score can be obtained by weighted average calculation based on the scores and weights of various factors related to the standard activity. For the standard score, please refer to the relevant description of the following embodiment.

[0073] Step S204: Based on the comparison result, a prediction result of whether the target activity is successful is generated.

[0074] For example, if the result of the comparison is that the predicted score of the target activity is greater than or equal to the standard score, the activity (for example, the salesperson's face-to-face visit to the customer) can be considered effective; if the result of the comparison is that the predicted score of the target activity is less than the standard score, the activity (for example, the salesperson's face-to-face visit to the customer) can be considered invalid. Improvements can be made to ineffective face-to-face visits and other activities. After the improvements, the frequency of face-to-face visits can be effectively controlled through the amount of activities, unnecessary or ineffective face-to-face visits can be reduced, and face-to-face visits can be made more efficient, thereby increasing communication and trust between customers and companies, allowing customers to better understand products and rights, better accept services, and better understand customer needs, thereby providing personalized solutions. In addition, effective face-to-face visits can also improve customer conversion rates, thereby increasing business, and are also an important way to improve customer satisfaction and establish a good reputation for the company.

[0075] The embodiment of the present application generates a target activity prediction score by inputting activity volume data related to customer activities into a pre-trained activity volume quality assessment model, compares the target activity prediction score with the standard score, and generates a prediction result of whether the target activity is successful based on the comparison result. That is, the activity volume data related to the activity can be effectively qualitatively evaluated for the activity quality, and targeted improvements can be made for activities such as invalid face-to-face interviews to improve the quality of subsequent activities.

[0076] In an optional embodiment of the present application, before step S202 inputs the activity data into the pre-trained activity quality assessment model to generate the target activity prediction score, the following method steps may also be included:

[0077] A first data element sample is obtained.

[0078] Specifically, a data element sample is obtained from a sample set including multiple first data element samples. For example, multiple data element information related to each known customer interview or other activity can be used as a first data element sample, and the score calculated based on the factor index of the interview activity is used as the label score corresponding to each first data element sample.

[0079] Get the preset factor index list; the factor index list includes: data element factors and corresponding factor indexes.

[0080] For example, the list can be found in Table 1 below:

[0081]

[0082]

[0083] Table 1

[0084] In the embodiment of the present application, the above factor indicators may include: factor score Xi and weight Wi.

[0085] The first data element sample is matched with the data element factor in the factor indicator list, and the factor indicator corresponding to the matched data element factor is obtained, and the first label score corresponding to the first data element sample is calculated according to the factor indicator.

[0086] Specifically, each data element factor information comparison table 1 under each customer can be matched with the corresponding data element factor, and the corresponding factor score and weight can be extracted according to the matched data element factor, and the score and weight of each factor can be multiplied to obtain the score of each factor, and then the weighted average can be performed to obtain the label score corresponding to the first data element sample.

[0087] Based on the first data element sample and the corresponding first label score, the activity quality assessment model is iteratively trained to obtain a pre-trained activity quality assessment model.

[0088] In an embodiment of the present application, the activity quality assessment model can be iteratively trained based on the first data element sample and the corresponding first label score through a supervised learning method until a preset termination condition is met (for example: if the interpolation of the model input score and the label score is less than a preset threshold, the training is terminated), thereby obtaining the above-mentioned pre-trained activity quality assessment model.

[0089] The embodiment of the present application calculates the first label score of the first data element sample based on the preset factor index and trains the activity quantity quality assessment model based on the supervised learning method. The model can be trained based on simple quantitative information, and the model training process is simpler and the training efficiency is higher.

[0090] like Figure 3 As shown, Figure 3 It is a flowchart of a specific implementation method of updating a pre-trained activity quality assessment model in the activity quality assessment method of the present application.

[0091] In an optional embodiment of the present application, after step S202 inputs the activity data into the pre-trained activity quality assessment model to generate the target activity prediction score, the following method steps may also be included:

[0092] Step S205, obtaining a second data element sample.

[0093] Specifically, a second data element sample is obtained from a sample set including multiple data element samples. For example, multiple data element information related to each known customer interview activity can be used as a second data element sample, and the actual result of the interview activity is used as the second tag corresponding to each second data element sample.

[0094] Step S206: input the second data element sample into the pre-trained activity quantity quality assessment model to generate a sample activity prediction score.

[0095] Step S207, comparing the sample activity prediction score with the standard score to generate a sample prediction result of whether the sample activity is effective.

[0096] Step S208, comparing the sample prediction result with the actual result, and generating a judgment result of whether the sample prediction result is valid based on the comparison result.

[0097] Exemplarily, based on a preset number of second data element sample sets or a certain period of time, a judgment result can be generated as to whether the sample prediction result corresponding to each second data element sample is valid, and a judgment result as to whether more than a preset proportion of sample prediction results are invalid can be generated. For example, if more than 20 of 100 sample prediction results are invalid sample prediction results, a judgment result as to whether the sample prediction results are invalid can be generated.

[0098] Step S209, if the judgment result is invalid, update the factor index corresponding to the standard score, and iteratively train the pre-trained activity quality assessment model based on the updated factor index to obtain an updated pre-trained activity quality assessment model.

[0099] In the embodiment of the present application, if a judgment result that the sample prediction result is invalid is generated, it is necessary to update the various factor indicators corresponding to the standard score based on certain rules or neural networks, and then retrain the model based on the updated factor indicators to obtain an updated pre-trained control model. The training method of the control model can be referred to the description of the above embodiment, which will not be repeated here.

[0100] In the embodiment of the present application, if the judgment result is valid, there is no need to update the factor index, and the activity result can be predicted based on the original pre-trained model.

[0101] The embodiment of the present application inputs a data element sample into a pre-trained activity quantity quality assessment model to generate a sample activity prediction score, compares the sample prediction score with the standard score, generates a prediction result of whether the sample activity is valid, and then compares the sample activity quality judgment result with the actual result, and generates a judgment result of whether the sample prediction result is valid based on the comparison result. If invalid, the factor index corresponding to the standard score is updated, and the pre-trained activity quantity quality assessment model is iteratively trained based on the updated factor index to obtain an updated pre-trained activity quantity quality assessment model. In this way, by regularly verifying the pre-trained activity quantity quality assessment model, it is possible to continuously verify whether the pre-trained activity quantity quality assessment model is accurate in prediction based on new sample data. If the prediction is inaccurate, the factor index can be updated in time, thereby ensuring the effectiveness of the quality assessment, which is conducive to timely improvement of activity quality.

[0102] In an optional embodiment of the present application, before step S203 compares the target activity prediction score with the standard score, the following method steps may also be included:

[0103] Get the preset factor index list; the factor index list includes: data element factors and corresponding factor indexes.

[0104] Specifically, the list of relevant factor indicators can refer to Table 1 described in the above embodiment.

[0105] Extract the factor indicators (such as scores and weights) corresponding to each data element factor based on the factor indicator list.

[0106] Combine the factor indicators (such as scores and weights) corresponding to all data element factors under the factor indicator list, and calculate the standard score based on the weighted average method.

[0107] That is, solve ∑(Wi*Xi) / ∑Wi.

[0108] The embodiment of the present application combines the factor scores and weights corresponding to all factors in the list, and calculates the standard score based on the weighted average method. The standard score combines the scores of multiple factors and the corresponding weight information. Therefore, the quality of subsequent activities is judged based on the standard score, and its final judgment result is more meaningful for reference and closer to the actual result.

[0109] In an optional embodiment of the present application, before the above step of "obtaining a preset factor index list", the following method steps may also be included:

[0110] Setting the first data element factor and the corresponding first factor index before the activity;

[0111] Setting the second data element factor and the corresponding second factor indicator in the activity;

[0112] Setting the third data element factor after the activity and the corresponding third factor index;

[0113] The first data element factor and the corresponding first factor index, the second data element factor and the corresponding second factor index, and the third data element factor and the corresponding third factor index are combined to generate a factor index list.

[0114] The embodiment of the present application calculates the marking score and / or standard score by combining relevant factor indicators before, during and after the activity, fully considering the impact of various information before, during and after the activity on the overall final activity effect. Therefore, the marking score and / or standard score obtained based on this is more meaningful for reference, and the final activity evaluation result is also more meaningful.

[0115] In an optional embodiment of the present application, after step 204 generates a prediction result of whether the target activity is successful based on the comparison result, the embodiment of the present application may further include the following method steps:

[0116] Record activity information during the activity;

[0117] The data meta-factors and corresponding factor indicators in the factor indicator list are updated based on the activity information.

[0118] The embodiment of the present application continuously analyzes the historical records generated by subsequent activities, adds new factor items to the list, or deletes or modifies useless factor items in the list, so that each factor in the list is more in line with the actual activity situation, so that the marking score and / or standard score obtained therefrom is more meaningful for reference, and thus the final activity evaluation result is more meaningful.

[0119] It should be emphasized that in order to further ensure the privacy and security of the above-mentioned preset data meta-factors and corresponding factor indicator lists and / or pre-trained activity quality assessment models, the above-mentioned preset data meta-factors and corresponding factor indicator lists and / or pre-trained activity quality assessment models can also be stored in a blockchain node.

[0120] The blockchain referred to in this application is a new application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, encryption algorithm, etc. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, platform product service layer, and application service layer.

[0121] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0122] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0123] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through computer-readable instructions, and the computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0124] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0125] Further references Figure 4 , as a response to the above Figure 2 The present application provides an embodiment of a picture generation device, and the embodiment of the device is similar to Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0126] like Figure 4 As shown, the activity quantity quality assessment device 400 described in this embodiment includes: a data acquisition module 401, a score prediction module 402, a score comparison module 403 and a result judgment module 404. Among them:

[0127] The data acquisition module 401 is used to acquire activity data and extract data metadata from the activity data;

[0128] The score prediction module 402 is used to input the data metadata into the pre-trained activity quantity quality assessment model to generate a target activity prediction score;

[0129] A score comparison module 403, for comparing the target activity prediction score with the standard score;

[0130] The result judgment module 404 is used to generate a prediction result of whether the target activity is successful based on the comparison result.

[0131] The embodiment of the present application generates a target activity prediction score by inputting activity volume data related to customer activities into a pre-trained activity volume quality assessment model, compares the target activity prediction score with the standard score, and generates a prediction result of whether the target activity is successful based on the comparison result. That is, the activity volume data related to the activity can be effectively qualitatively evaluated for the activity quality, and targeted improvements can be made for activities such as invalid face-to-face interviews to improve the quality of subsequent activities.

[0132] Some optional implementations of the present application also include:

[0133] A first acquisition module, used to acquire a first data element sample;

[0134] The list acquisition module is used to obtain a preset factor index list; the factor index list includes: data element factors and corresponding factor indexes;

[0135] A tag extraction module, used to match the first data element sample with the data element factor in the factor indicator list, obtain the factor indicator corresponding to the matched data element factor, and calculate the first tag score corresponding to the first data element sample according to the factor indicator;

[0136] The model training module is used to iteratively train the activity quality assessment model based on the first data element sample and the corresponding first label score to obtain a pre-trained activity quality assessment model.

[0137] The embodiment of the present application calculates the first label score of the first data element sample based on the preset factor index and trains the activity quantity quality assessment model based on the supervised learning method. The model can be trained based on simple quantitative information, and the model training process is simpler and the training efficiency is higher.

[0138] Some optional implementations of the present application also include:

[0139] A second acquisition module, used to acquire a second data element sample;

[0140] A prediction generation module, used to input the second data element sample into the pre-trained activity quantity quality assessment model to generate a sample activity prediction score;

[0141] A first comparison module, used to compare the sample activity prediction score with the standard score to generate a sample prediction result of whether the sample activity is effective;

[0142] The second comparison module is used to compare the sample prediction result with the actual result, and generate a judgment result on whether the sample prediction result is valid based on the comparison result.

[0143] The factor updating module is used to update the factor index corresponding to the standard score if the judgment result is invalid, and iteratively train the pre-trained activity quality assessment model based on the updated factor index to obtain an updated pre-trained activity quality assessment model.

[0144] The embodiment of the present application inputs a data element sample into a pre-trained activity quantity quality assessment model to generate a sample activity prediction score, compares the sample prediction score with the standard score, generates a prediction result of whether the sample activity is valid, and then compares the sample activity quality judgment result with the actual result, and generates a judgment result of whether the sample prediction result is valid based on the comparison result. If invalid, the factor index corresponding to the standard score is updated, and the pre-trained activity quantity quality assessment model is iteratively trained based on the updated factor index to obtain an updated pre-trained activity quantity quality assessment model. In this way, by regularly verifying the pre-trained activity quantity quality assessment model, it is possible to continuously verify whether the pre-trained activity quantity quality assessment model is accurate in prediction based on new sample data. If the prediction is inaccurate, the factor index can be updated in time, thereby ensuring the effectiveness of the quality assessment, which is conducive to timely improvement of activity quality.

[0145] Some optional implementations of the present application also include:

[0146] The list acquisition module is used to obtain a preset factor index list; the factor index list includes: data element factors and corresponding factor indexes;

[0147] An indicator extraction module is used to extract the factor indicator corresponding to each data element factor based on the factor indicator list;

[0148] The standard obtaining module is used to combine the factor indicators corresponding to all data element factors under the factor indicator list and obtain the standard score based on the weighted average method.

[0149] The embodiment of the present application combines the factor scores and weights corresponding to all factors in the list, and calculates the standard score based on the weighted average method. The standard score combines the scores of multiple factors and the corresponding weight information. Therefore, the quality of subsequent activities is judged based on the standard score, and its final judgment result is more meaningful for reference and closer to the actual result.

[0150] Some optional implementations of the present application also include:

[0151] A first setting module, used to set the first data element factor and the corresponding first factor index before the activity;

[0152] A second setting module, used to set a second data element factor and a corresponding second factor indicator in the activity;

[0153] A third setting module, used to set the third data element factor and the corresponding third factor index after the activity;

[0154] The fourth setting module is used to combine the first data element factor and the corresponding first factor indicator, the second data element factor and the corresponding second factor indicator, and the third data element factor and the corresponding third factor indicator to generate a factor indicator list.

[0155] The embodiment of the present application calculates the marking score and / or standard score by combining relevant factor indicators before, during and after the activity, fully considering the impact of various information before, during and after the activity on the overall final activity effect. Therefore, the marking score and / or standard score obtained based on this is more meaningful for reference, and the final activity evaluation result is also more meaningful.

[0156] Some optional implementations of the present application also include:

[0157] Record activity information during the activity;

[0158] The data meta-factors and corresponding factor indicators in the factor indicator list are updated based on the activity information.

[0159] The embodiment of the present application continuously analyzes the historical records generated by subsequent activities, adds new factor items to the list, or deletes or modifies useless factor items in the list, so that each factor in the list is more in line with the actual activity situation, so that the marking score and / or standard score obtained therefrom is more meaningful for reference, and thus the final activity evaluation result is more meaningful.

[0160] To solve the above technical problems, the present application also provides a computer device. Figure 5 , Figure 5 This is a basic structural block diagram of the computer device in this embodiment.

[0161] The computer device 6 includes a memory 61, a processor 62, and a network interface 63 that are interconnected and communicated through a system bus. It should be noted that the figure only shows a computer device 6 with a memory 61, a processor 62, and a network interface 63, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.

[0162] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0163] The memory 61 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 61 can be an internal storage unit of the computer device 6, such as a hard disk or memory of the computer device 6. In other embodiments, the memory 61 can also be an external storage device of the computer device 6, such as a plug-in hard disk equipped on the computer device 6, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. Of course, the memory 61 can also include both the internal storage unit of the computer device 6 and its external storage device. In this embodiment, the memory 61 is generally used to store the operating system and various application software installed on the computer device 6, such as computer-readable instructions of the activity quantity quality assessment method, etc. In addition, the memory 61 can also be used to temporarily store various types of data that have been output or are to be output.

[0164] The processor 62 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip in some embodiments. The processor 62 is generally used to control the overall operation of the computer device 6. In this embodiment, the processor 62 is used to run computer-readable instructions or process data stored in the memory 61, such as computer-readable instructions for running the activity quality assessment method.

[0165] The network interface 63 may include a wireless network interface or a wired network interface. The network interface 63 is generally used to establish a communication connection between the computer device 6 and other electronic devices.

[0166] The embodiment of the present application generates a target activity prediction score by inputting activity volume data related to customer activities into a pre-trained activity volume quality assessment model, compares the target activity prediction score with the standard score, and generates a prediction result of whether the target activity is successful based on the comparison result. That is, the activity volume data related to the activity can be effectively qualitatively evaluated for the activity quality, and targeted improvements can be made for activities such as invalid face-to-face interviews to improve the quality of subsequent activities.

[0167] The present application also provides another embodiment, namely, providing a computer-readable storage medium, wherein the computer-readable storage medium stores computer-readable instructions, and the computer-readable instructions can be executed by at least one processor to enable the at least one processor to perform the steps of the activity quality assessment method as described above.

[0168] The embodiment of the present application generates a target activity prediction score by inputting activity volume data related to customer activities into a pre-trained activity volume quality assessment model, compares the target activity prediction score with the standard score, and generates a prediction result of whether the target activity is successful based on the comparison result. That is, the activity volume data related to the activity can be effectively qualitatively evaluated for the activity quality, and targeted improvements can be made for activities such as invalid face-to-face interviews to improve the quality of subsequent activities.

[0169] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0170] The non-Company software tools or components appearing in the embodiments of this application are merely examples and do not represent actual use.

[0171] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. A method for evaluating the quality of activity, characterized in that: The steps include: Acquiring activity data, and extracting data metadata from the activity data; Inputting the data metadata into a pre-trained activity quantity quality assessment model to generate a target activity prediction score; comparing the target activity prediction score with a standard score; Based on the comparison result, a prediction result of whether the target activity is successful is generated.

2. The activity quality assessment method according to claim 1, characterized in that: Before inputting the activity data into the pre-trained activity quality assessment model to generate the target activity prediction score, the following steps are also included: Obtaining a first data element sample; Get the preset factor indicator list; The factor index list includes: data element factors and corresponding factor indexes; Matching the first data element sample with the data element factor in the factor indicator list, obtaining the factor indicator corresponding to the matched data element factor, and calculating a first label score corresponding to the first data element sample according to the factor indicator; Based on the first data element sample and the corresponding first label score, the activity quality assessment model is iteratively trained to obtain the pre-trained activity quality assessment model.

3. The activity quality assessment method according to claim 1 or 2, characterized in that: After inputting the activity data into the pre-trained activity quality assessment model to generate the target activity prediction score, the following steps are also included: Obtaining a second data element sample; Inputting the second data element sample into the pre-trained activity quantity quality assessment model to generate a sample activity prediction score; Comparing the sample activity prediction score with the standard score to generate a sample prediction result of whether the sample activity is effective; Compare the sample prediction result with the actual result, and generate a judgment result of whether the sample prediction result is valid based on the comparison result; If the judgment result is invalid, the factor index corresponding to the standard score is updated, and the pre-trained activity quality assessment model is iteratively trained based on the updated factor index to obtain an updated pre-trained activity quality assessment model.

4. The activity quality assessment method according to claim 1, characterized in that: Before comparing the target activity prediction score with the standard score, the following steps are also included: Obtaining a preset factor index list; the factor index list includes: data element factors and corresponding factor indexes; Extracting the factor indicator corresponding to each of the data element factors based on the factor indicator list; The standard score is obtained by combining the factor indicators corresponding to all the data element factors in the factor indicator list based on the weighted average method.

5. The activity quantity quality assessment method according to claim 2 or 4, characterized in that: Before obtaining the preset factor index list, the following steps are also included: Setting the first data element factor and the corresponding first factor index before the activity; Setting the second data element factor and the corresponding second factor indicator in the activity; Setting the third data element factor after the activity and the corresponding third factor index; The first data element factor and the corresponding first factor indicator, the second data element factor and the corresponding second factor indicator, and the third data element factor and the corresponding third factor indicator are combined to generate the factor indicator list.

6. The activity quality assessment method according to claim 1 or 2, characterized in that: After generating a prediction result of whether the target activity is successful based on the comparison result, the following steps are also included: Record activity information during the activity; The data meta-factors and the corresponding factor indicators in the factor indicator list are updated based on the activity information.

7. An activity quantity evaluation device, characterized in that: include: A data acquisition module, used to acquire activity data and extract data metadata from the activity data; A score prediction module, used to input the data metadata into a pre-trained activity quantity quality assessment model to generate a target activity prediction score; A score comparison module, used to compare the target activity prediction score with a standard score; The result judgment module is used to generate a prediction result of whether the target activity is successful based on the result of the comparison.

8. The activity quantity evaluation device according to claim 7, characterized in that: Also includes: A first acquisition module, used to acquire a first data element sample; List acquisition module, used to obtain a preset factor indicator list; The factor index list includes: data element factors and corresponding factor indexes; A tag extraction module, configured to extract a first tag score corresponding to the first data element sample based on the factor indicator list; A model training module is used to iteratively train the activity quality assessment model based on the first data element sample and the corresponding first label score to obtain the pre-trained activity quality assessment model.

9. A computer device, characterized in that: It comprises a memory and a processor, wherein the memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, the steps of the activity quality assessment method as described in any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, implement the steps of the activity quality assessment method according to any one of claims 1 to 6.

Images