Marketing gift purchasing management method, device and system

Abstract

The invention relates to the field of computers, in particular to a marketing gift purchasing management method, device and system.The method can estimate attention changes of a user according to electronic questionnaire filling operation characteristics of the user in the electronic questionnaire survey of the user, and after the attention of the user is reduced to a certain limit value, the user can purchase a marketing gift according to the attention changes. According to the method, the inquiry mode of the questions to be answered by the user can be adjusted, the answers of the user are compared with the answers of the similar questions previously, whether the decline of attention has a large influence on the judgment of the user can be determined, if the influence is small, the answers are adopted, otherwise, the answers are not adopted, and then all questionnaires are integrated into a plurality of target questionnaires; therefore, invalid answers made when the attention of the user is low are eliminated, each answer in the target questionnaire has reference, and the preference of each user product type can be accurately determined according to the target questionnaire, so that a worker is guided to accurately purchase a marketing gift, and the marketing effect is achieved.

Description

Technical Field

[0001] This invention relates to the field of computers, and in particular to a method, apparatus and system for managing the procurement of marketing gifts. Background Technology

[0002] Marketing gifts are gifts given by companies to their target audience in order to achieve marketing goals, such as promoting products, building brand image, and enhancing customer loyalty.

[0003] To improve marketing effectiveness, businesses need to tailor their marketing gifts to user preferences. To determine user preferences, businesses often conduct surveys beforehand. Current technology directly analyzes the returned questionnaires to determine user preferences, without considering the fluctuations in user focus during questionnaire completion, which can lead to unreliable answers. This results in biased user preferences and untargeted marketing gifts. Summary of the Invention

[0004] Therefore, it is necessary to provide a marketing gift procurement management method, device, and system to address the above-mentioned problems.

[0005] This invention is implemented as follows: a marketing gift procurement management method is provided, the method comprising:

[0006] S1: Obtain a pre-set electronic questionnaire about gift preference types;

[0007] S2: Identify each question in the electronic questionnaire and generate several question formats based on each question;

[0008] S3: Distribute electronic questionnaires to all users;

[0009] S4: When any user answers a question, before displaying the next question, predict the user's attention value when the user answers the next question based on the user's operational characteristics of the questions already answered;

[0010] S5: Adjust the questioning method for the next question based on the attention score;

[0011] S6: Analyze the logical discrepancies between the user's answer to the adjusted question and the answers to previously answered questions;

[0012] S7: Determine whether to adopt the user's answer to the question being adjusted based on logical deviation;

[0013] S8: After collecting all electronic questionnaires, identify the question number distribution of the adopted answers in each questionnaire, and select electronic questionnaires for integration based on the question number distribution to obtain several target questionnaires. Among them, the proportion of the number of question numbers corresponding to the adopted answers in the target questionnaires to the total number of question numbers exceeds the preset proportion.

[0014] S9: Analyze the answers to each target questionnaire to determine the ranking of gift preferences, and generate a gift purchasing guide based on the ranking of gift preferences to guide staff in purchasing marketing gifts.

[0015] In one embodiment, the present invention provides a marketing gift procurement management device, the device comprising:

[0016] The acquisition module is used to acquire a pre-set electronic questionnaire about gift preference types;

[0017] The first processing module is used to identify each question in the electronic questionnaire and generate several question types based on each question;

[0018] The second processing module is used to distribute electronic questionnaires to each user.

[0019] The third processing module is used to predict the user's attention value when answering the next question, based on the user's operational characteristics of the already answered questions, before displaying the next question.

[0020] The fourth processing module is used to adjust the questioning method for the next question based on the attention value;

[0021] The fifth processing module is used to analyze the logical discrepancies between the user's answer to the adjusted question and the answers to previously answered questions;

[0022] The sixth processing module is used to determine whether to adopt the user's answer to the question being adjusted based on logical deviations.

[0023] The retrieval module is used to retrieve all electronic questionnaires, identify the distribution of question numbers of the adopted answers in each questionnaire, select electronic questionnaires for integration based on the question number distribution, and thus obtain several target questionnaires. The proportion of the number of question numbers corresponding to the adopted answers in the target questionnaires to the total number of question numbers exceeds a preset proportion.

[0024] The analysis module is used to analyze the answers to each target questionnaire to determine the ranking of gift preferences. Based on this ranking, a gift purchasing guide is generated to guide staff in purchasing marketing gifts.

[0025] In one embodiment, the present invention provides a marketing gift procurement management system, the system comprising:

[0026] Each user's client is used for users to answer electronic questionnaires;

[0027] Computer equipment, communicating with each user terminal, is used to execute the aforementioned marketing gift procurement management method.

[0028] This invention provides a marketing gift procurement management method, comprising: acquiring a pre-set electronic questionnaire about gift preference types; identifying each question in the electronic questionnaire and generating several question formats based on each question; distributing the electronic questionnaire to users; when any user answers a question, before displaying the next question, predicting the user's attention value when answering the next question based on the user's operational characteristics of the already answered questions; adjusting the question format of the next question based on the attention value; analyzing the logical deviation between the user's answer to the adjusted question and the answers to the already answered questions; determining whether to adopt the user's answer to the adjusted question based on the logical deviation; after collecting all electronic questionnaires, identifying the question number distribution of the adopted answers in each questionnaire, and selecting and integrating electronic questionnaires based on the question number distribution to obtain several target questionnaires; analyzing the answers of each target questionnaire to determine the ranking of gift preference types, and generating a gift preference type ranking based on the ranking of gift preference types. This gift procurement guide aims to instruct staff on how to purchase marketing gifts. In this application, during electronic questionnaire surveys, the system can predict changes in user attention based on the user's operational characteristics when completing the questionnaire. When user attention drops to a certain limit, the questioning method can be adjusted, and the user's answer to that question can be compared with previous answers to similar questions. This determines whether the decline in attention significantly impacts the user's judgment. If the impact is minor, the answer is adopted; otherwise, it is not. Subsequently, based on the distribution of adopted answers in each questionnaire, the questionnaires are integrated into several target questionnaires. This eliminates invalid answers given when user attention is low, ensuring that all answers in the target questionnaires are meaningful. Based on these target questionnaires, the product type preferences of each user can be accurately determined, guiding staff to accurately purchase marketing gifts to achieve marketing results. Attached Figure Description

[0029] Figure 1 A flowchart of a marketing gift procurement management method provided in one embodiment;

[0030] Figure 2 This is a diagram illustrating the application environment of a marketing gift procurement management method provided in one embodiment.

[0031] Figure 3 This is a schematic diagram illustrating the questionnaire integration of a marketing gift procurement management method provided in one embodiment;

[0032] Figure 4 A flowchart of a marketing gift procurement management device provided in one embodiment;

[0033] Figure 5 This is a block diagram of the internal structure of a computer device in one embodiment. Detailed Implementation

[0034] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0035] It is understood that the terms "first," "second," etc., used in this invention may be used to describe various elements herein, but unless specifically stated otherwise, these elements are not limited by these terms. These terms are used only to distinguish one element from another. For example, without departing from the scope of this invention, a first script may be referred to as a second script, and similarly, a second script may be referred to as a first script.

[0036] like Figure 1 As shown, in one embodiment, a marketing gift procurement management method is proposed, the method comprising:

[0037] S1: Obtain a pre-set electronic questionnaire about gift preference types;

[0038] S2: Identify each question in the electronic questionnaire and generate several question formats based on each question;

[0039] S3: Distribute electronic questionnaires to all users;

[0040] S4: When any user answers a question, before displaying the next question, predict the user's attention value when the user answers the next question based on the user's operational characteristics of the questions already answered;

[0041] S5: Adjust the questioning method for the next question based on the attention score;

[0042] S6: Analyze the logical discrepancies between the user's answer to the adjusted question and the answers to previously answered questions;

[0043] S7: Determine whether to adopt the user's answer to the question being adjusted based on logical deviation;

[0044] S8: After collecting all electronic questionnaires, identify the question number distribution of the adopted answers in each questionnaire, and select electronic questionnaires for integration based on the question number distribution to obtain several target questionnaires. Among them, the proportion of the number of question numbers corresponding to the adopted answers in the target questionnaires to the total number of question numbers exceeds the preset proportion.

[0045] S9: Analyze the answers to each target questionnaire to determine the ranking of gift preferences, and generate a gift purchasing guide based on the ranking of gift preferences to guide staff in purchasing marketing gifts.

[0046] In this embodiment, as Figure 2As shown, this method is executed in a computer device, which can be an independent physical server or terminal, or a server cluster consisting of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud servers, cloud databases, cloud storage and CDN; the computer device can communicate with the user's client to send / return electronic questionnaires to the user's client; the user's client can be a mobile phone, tablet computer, laptop computer, etc.

[0047] In this embodiment, the computer device sends an authorization letter to the user while sending the electronic questionnaire to the user terminal. The authorization letter includes the execution steps of this method and the user data (such as operation feature data) that needs to be collected during the execution process. The computer device can only execute this method after the user confirms the authorization.

[0048] In this embodiment, the questions in the electronic questionnaire are pre-set by the staff, such as questions about the degree of preference for different types of products (e.g., fruits, rice, flour, oil, snacks, smart bracelets, books, etc.).

[0049] In this embodiment, other questioning methods generated include reverse logic questioning, such as forward: Do you like this product? Reverse: Do you dislike this product? Proposition transformation questioning, such as original question: Do you read books every day? Adjusted question: Do you not read books for a day? Result inversion method, such as original question: If you gain weight, would you choose to run? Inverted question: Do you choose to run because you gain weight? Other questioning methods (including corresponding options) for each question can be generated after the staff designs the electronic questionnaire and stored in the computer device, and can be directly called when needed, without the need for repeated generation;

[0050] In this embodiment, if it is necessary to adjust the question format of the next question, the question format of the next question that has been answered previously and has the same question object as the previous question (e.g., both asking about the degree of preference for fruit) is first identified. Then, the question format of the next question is adjusted to be different from the previous question format (if there are multiple, the closest one is selected). Because when attention is low, people's thinking is more likely to rely on inertia. When seeing similar questions, they are prone to preconceived notions, leading them to not read the question carefully and directly answer according to the previous answer format. Since the question's question logic has changed, it will lead to a large logical deviation between the answer and the previous answer. Therefore, logical deviation can be used as a quantitative indicator of whether the answer is serious. If the logical deviation is too large, it indicates that the user's seriousness is insufficient, and the answer cannot be adopted. If the logical deviation is not large, it means that the user can overcome the impact of decreased attention, and the answer can still be adopted.

[0051] In this embodiment, the preset ratio can be 80%, meaning that 80% of the answers to a questionnaire are used as a reference for data analysis. After determining each target questionnaire, data analysis can be performed on each target questionnaire to determine the corresponding user's favorite product type (for example, if a target questionnaire consists of two questionnaires, it can be considered that the users corresponding to both questionnaires like the product type). Then, the number of people who like each product type is counted, and each product type is sorted according to the number of people, which yields the gift preference type ranking. A purchasing guide including the gift preference ranking is generated, and staff can determine which types of products to prioritize purchasing as marketing gifts based on the gift preference ranking.

[0052] In this application, the electronic questionnaire is displayed on multiple pages, with only one question per page. Users cannot see the next question until they answer it, allowing for adjustments to the questions before they can see the next one. During the electronic questionnaire survey, the user's attention span can be predicted based on their questionnaire-filling behavior. When a user's attention drops to a certain threshold, the questioning style can be adjusted, and the user's answer to that question can be compared to their previous answers to similar questions. This determines whether the decline in attention significantly impacts the user's judgment (the greater the logical deviation, the greater the impact). If the impact is minor, the answer is adopted; otherwise, it is not. Subsequently, based on the question number distribution of adopted answers in each questionnaire, the questionnaires are integrated into several target questionnaires. This eliminates invalid answers given when attention is low, ensuring that all answers in the target questionnaires are meaningful. Based on these target questionnaires, the product type preferences of each user can be accurately determined, guiding staff to accurately purchase marketing gifts to achieve marketing effectiveness.

[0053] As a preferred embodiment, predicting the user's attention change trend based on the user's operational characteristics includes:

[0054] Obtain the user's operational characteristics for the t questions that have been answered;

[0055] The attention prediction model is invoked, and the acquired operational features are input into the attention prediction model to predict the user's attention value when answering the (t+1)th question.

[0056] The attention prediction model is:

[0057]

[0058] Where A(t+1) is the user's attention value when answering the (t+1)th question, A(t) is the user's attention value when answering the tth question, and α is the attention reduction coefficient. ρ is the feature vector for weighted operations, and ρ is the feature weight vector.

[0059] The weighted operation feature vector is:

[0060]

[0061] Among them, X i Let X be the operational feature vector corresponding to the operational features of the first i problems; ω(i) is the operational feature vector of X. i Weighting function:

[0062] ω(i)=e -(t-i)

[0063] X i Represented as:

[0064]

[0065] in, The average time taken for the first i questions, This represents the average number of pauses for the first i questions. This represents the average number of revisions for the first i questions.

[0066] The feature weight vector is represented as:

[0067] ρ=[ρ t ,ρ s ,ρ m ]

[0068] Where, ρ t ρ represents the weight of the time-consuming feature. s ρ is the feature weight for the number of pauses. m To modify the feature weights for the number of times.

[0069] In this embodiment, step S4 is executed after the Kth question in the electronic questionnaire, i.e., t is greater than K. Since the user's attention level is high when answering the questionnaire at the beginning, the answers to the first questions (i.e., the first K questions) can be directly adopted, and the corresponding attention value can be regarded as a preset fixed value, such as 1000. The value of K can be consistent with the number of all product types to be investigated (for example, 3 or 5). When setting the questions, the staff can set each of the first K questions to be a question for a product type, so that the first K questions cover all product types, thus establishing a preliminary basis for the comparison of the subsequent questions.

[0070] In this embodiment, α can be 0.98; the operation features include the time spent answering questions, the number of pauses, and the number of modifications; for each question, the time spent is the duration taken to complete the question; any interval between two operations exceeding a set duration is considered a pause, thus allowing for the counting of pauses; changing an answer after filling it in is considered a modification, thus allowing for the counting of modifications; the operation features can be monitored by the user terminal and sent to the computer device; the weighted operation feature vector is the operation feature vector X corresponding to various values ​​of i. i The weighted average value, which takes into account the changes in attention at different stages, has a higher accuracy in representing the user's current attention status. The weight function increases with the increase of i, making X... i The weight of ρ increases with the increase of i, even though the most recent operation feature vector can have a greater representational weight, which is consistent with the objective reality that the most recent operation features are more meaningful; in addition, ρ t ρ s ρ m The weights can be 0.3, 0.4, 0.3, or other combinations, which are not limited here.

[0071] As a preferred embodiment, adjusting the questioning method for the next question based on the attention value includes:

[0072] Determine if the attention value is lower than the first preset value; if not, do not adjust the questioning method for the next question.

[0073] If so, determine the cognitive load index for each way of asking the next question;

[0074] Divide the attention value by each cognitive load index and compare the resulting quotients with the set quotients.

[0075] The question format corresponding to the quotient closest to the set quotient is determined as the target question format;

[0076] Adjust the question format for the next question to the target question format.

[0077] In this embodiment, the first preset value can be set to 800; the cognitive load index of each question for each inquiry method can be evaluated after the inquiry method is generated (it can be evaluated manually by staff or by computer equipment) and stored in the computer equipment for later retrieval.

[0078] The cognitive load index can be assessed using the following formula:

[0079]

[0080] Where C is the cognitive load index, Ds Given the sentence complexity of the problem (e.g., 2 for a single sentence, 4 for a single sentence plus one clause, and 6 for a single sentence plus two clauses), D r E represents the number of logical transformation adverbs (such as because, therefore, although, but, and, or, not) in the problem. i The number of keywords in the question; D s Weighting coefficients; D r Weighting coefficients; For E i Weighting coefficients; as well as The values ​​can be 0.5, 0.3, and 0.2 respectively, or other combinations, which are not limited here.

[0081] In this embodiment, the quotient can be set to 100. For example, if the attention value is 720, the cognitive load index of inquiry method 1 is 8, and the cognitive load index of inquiry method 2 is 9, then the quotient corresponding to inquiry method 1 is 720 / 8 = 90 (closer to 100), and the quotient corresponding to inquiry method 2 is 720 / 9 = 80. In this way, inquiry method 1 is selected as the target inquiry method. In this way, the next question can be adjusted to an inquiry method that matches the user's attention value (i.e., if the attention is high, the inquiry method with a high cognitive load index is selected, and vice versa).

[0082] As a preferred embodiment, analyzing the logical discrepancy between the user's answer to the adjusted question and the answers to previously answered questions includes:

[0083] Obtain the question subjects for all questions in the electronic questionnaire, and retrieve the numerical values ​​of all answers for each question. The numerical values ​​of the answers range from 0 to 1, representing the user's degree of preference for the corresponding question subject. The question subject is the product type targeted by the question.

[0084] Identify the problem object of the next question as the target object;

[0085] Filter out the questions whose corresponding question objects match the target object from the already answered questions;

[0086] From the screened questions, those with attention values ​​greater than the first preset value are identified as reference questions;

[0087] Identify the numerical value of the user's answer to each reference question and calculate the average value;

[0088] Identify the numerical value of the answer to the adjusted question and calculate the logical bias using the following formula:

[0089]

[0090] Among them, B L For logical deviation, n a The numerical value of the answer to the question being adjusted. This is the average value;

[0091] Determining whether to adopt a user's answer to the question being adjusted based on logical deviations includes:

[0092] Determine if the logical deviation is lower than the preset deviation. If so, use the corresponding answer; otherwise, do not use the corresponding answer.

[0093] In this embodiment, each question in the electronic questionnaire targets the degree of preference for a product type, which is the object of the question. Each question has several answers (i.e., several options), and each answer has a preset numerical value representing the degree of preference (the higher the value, the more liking). For example, for the question 'Do you like fruit?', answer A is 'Not at all' (value is 0), answer B is 'Dislike' (value is 0.25), answer C is 'Indifferent' (value is 0.5), answer D is 'Like' (value is 0.75), and answer E is 'Like very much' (value is 1).

[0094] In this embodiment, the preset deviation can be 0.3 or other values; the calculated average value can characterize the user's overall preference for the corresponding product. If the calculated logical deviation is too large, it indicates that the answer is likely to be incorrect and the answer cannot be adopted.

[0095] As a preferred embodiment, the distribution of question numbers of the answers used in each questionnaire is identified, and electronic questionnaires are selected and integrated based on the question number distribution to obtain several target questionnaires, including:

[0096] S81: Determine whether the proportion of the number of question numbers corresponding to the adopted answers in each of the returned electronic questionnaires exceeds the preset proportion. If yes, the electronic questionnaire is the target questionnaire; otherwise, the electronic questionnaire is the non-target questionnaire.

[0097] S82: Select one questionnaire from the unqualified questionnaires as the base questionnaire;

[0098] S83: Compare the basic questionnaire with each of the other unqualified questionnaires to determine if there is a matching questionnaire for the basic questionnaire among the other unqualified questionnaires. If so, integrate the basic questionnaire and the corresponding matching questionnaire into a target questionnaire and delete the two unqualified questionnaires. If not, the basic questionnaire cannot be integrated into the target questionnaire.

[0099] S84: Repeat steps S82-S83 until all target questionnaires are obtained.

[0100] The basic questionnaire was compared one by one with other non-compliant questionnaires to determine if there were any matching questionnaires among the other non-compliant questionnaires.

[0101] S831: Delete the question number corresponding to the unused answer in each questionnaire, and retain the question number of the used answer;

[0102] S832: Select one non-compliant questionnaire from the other non-compliant questionnaires as a comparison questionnaire;

[0103] S833: Calculate the sum of the number of question numbers in the comparison questionnaire and the basic questionnaire, subtract the number of duplicate question numbers from the sum of the sum to get the first quantity, divide the first quantity by the total number of question numbers to get the first ratio, and determine whether the first ratio is greater than the preset ratio. If not, the comparison questionnaire is not a matching questionnaire.

[0104] S834: If so, identify each group of identical question numbers in the comparison questionnaire and the basic questionnaire;

[0105] S835: For each pair of questions with the same number, calculate the numerical difference between the answers corresponding to the two question numbers;

[0106] S836: Calculate the mean of the differences between the values, and determine whether the mean is lower than the second preset value. If so, the comparison questionnaire is a matching questionnaire of the basic questionnaire. Otherwise, the comparison questionnaire is not a matching questionnaire of the basic questionnaire. Delete the comparison questionnaire, and select another unqualified questionnaire from the other unqualified questionnaires as the comparison questionnaire. Execute steps S833 to S836 until a matching questionnaire is determined or it is determined that there is no matching questionnaire of the basic questionnaire among the other unqualified questionnaires.

[0107] In this embodiment, if the number of question numbers corresponding to the adopted answers in a single questionnaire exceeds a preset ratio of the total number of question numbers, then the questionnaire can be directly identified as the target questionnaire without the need for integration.

[0108] In this embodiment, if the first ratio is greater than the preset ratio, it indicates that the number of question numbers in the questionnaire obtained after integrating the two questionnaires has reached the standard of the target questionnaire. Furthermore, in step S834, if the number of groups with the same question number identified does not reach the set number of groups (for example, if there are a total of 20 questions, the set number of groups can be set to 10 groups), then the comparison questionnaire is not a matching questionnaire. Furthermore, the smaller the mean of the numerical difference, the closer the users' preferences of the two questionnaires are. Therefore, the product pointed to by the questionnaire integrated from the two questionnaires can be regarded as the preferred product of the two questionnaires, which has better matching.

[0109] In this embodiment, after obtaining each target questionnaire, for each target questionnaire, the average value of the answer values ​​of the questions corresponding to each product type can be determined comprehensively, and the product type corresponding to the highest average value can be determined as the type most preferred by the user.

[0110] In this embodiment, as Figure 3 As shown, the basic questionnaire and the corresponding matching questionnaire are integrated into a target questionnaire, that is, the questions (corresponding to a question number) and their corresponding answers in the matching questionnaire that are not in the basic questionnaire are integrated into the basic questionnaire.

[0111] like Figure 4 As shown, in one embodiment, a marketing gift procurement management device is proposed, the device comprising:

[0112] The acquisition module is used to acquire a pre-set electronic questionnaire about gift preference types;

[0113] The first processing module is used to identify each question in the electronic questionnaire and generate several question types based on each question;

[0114] The second processing module is used to distribute electronic questionnaires to each user.

[0115] The third processing module is used to predict the user's attention value when answering the next question, based on the user's operational characteristics of the already answered questions, before displaying the next question.

[0116] The fourth processing module is used to adjust the questioning method for the next question based on the attention value;

[0117] The fifth processing module is used to analyze the logical discrepancies between the user's answer to the adjusted question and the answers to previously answered questions;

[0118] The sixth processing module is used to determine whether to adopt the user's answer to the question being adjusted based on logical deviations.

[0119] The retrieval module is used to retrieve all electronic questionnaires, identify the distribution of question numbers of the adopted answers in each questionnaire, select electronic questionnaires for integration based on the question number distribution, and thus obtain several target questionnaires. The proportion of the number of question numbers corresponding to the adopted answers in the target questionnaires to the total number of question numbers exceeds a preset proportion.

[0120] The analysis module is used to analyze the answers to each target questionnaire to determine the ranking of gift preferences. Based on this ranking, a gift purchasing guide is generated to guide staff in purchasing marketing gifts.

[0121] The process by which each module in the marketing gift procurement management device provided in this application implements its respective function can be found in the foregoing. Figure 1 The description of the illustrated embodiment will not be repeated here.

[0122] like Figure 2 As shown, in one embodiment, a marketing gift procurement management system is proposed, the system comprising:

[0123] Each user's client is used for users to answer electronic questionnaires;

[0124] Computer equipment, communicating with each user terminal, is used to execute the aforementioned marketing gift procurement management method.

[0125] In this embodiment, the computer equipment collaborates with each user terminal to predict changes in user attention during electronic questionnaire surveys. When user attention drops to a certain limit, the questioning method can be adjusted, and the user's answer to that question can be compared with previous answers to similar questions. This determines whether the decline in attention significantly impacts the user's judgment (the greater the logical deviation, the greater the impact). If the impact is minor, the answer is adopted; otherwise, it is not. Subsequently, based on the distribution of adopted answers in each questionnaire, the questionnaires are integrated into several target questionnaires. This eliminates invalid answers given by users when their attention is low, ensuring that all answers in the target questionnaires are relevant. Based on these target questionnaires, the product type preferences of each user can be accurately determined, guiding staff to accurately purchase marketing gifts to achieve marketing results.

[0126] Figure 5 An internal structural diagram of a computer device in one embodiment is shown. Figure 5 As shown, the computer device includes a processor, memory, network interface, input device, and display screen connected via a system bus. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and may also store a computer program. When executed by the processor, this computer program enables the processor to implement the marketing gift procurement management method provided in this embodiment of the invention. The internal memory may also store a computer program, which, when executed by the processor, enables the processor to execute the marketing gift procurement management method provided in this embodiment of the invention. The display screen of the computer device can be a liquid crystal display screen or an e-ink display screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, a trackball, or a touchpad mounted on the casing of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0127] Those skilled in the art will understand that Figure 5 The structure shown is merely a block diagram of a portion of the structure related to the present invention and does not constitute a limitation on the computer device to which the present invention is applied. A specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0128] In one embodiment, the marketing gift procurement management device provided by this invention can be implemented as a computer program, which can be implemented in various ways, such as... Figure 5 The computer device shown runs on this device. The computer device's memory can store the various program modules that make up the marketing gift procurement management device, for example, Figure 4 The diagram shows an acquisition module, a first processing module, a second processing module, a third processing module, a fourth processing module, a fifth processing module, a sixth processing module, a recycling module, and an analysis module. The computer program comprised of these modules causes the processor to execute the steps of the marketing gift procurement management method of the various embodiments of the present invention described in this specification.

[0129] For example, Figure 5 The computer device shown can be used as follows Figure 4 The marketing gift procurement management device shown executes step S1 through the acquisition module; step S2 through the computer device; step S3 through the second processing module; step S4 through the third processing module; step S5 through the fourth processing module; step S6 through the fifth processing module; step S7 through the sixth processing module; step S8 through the recycling module; and step S9 through the analysis module.

[0130] In one embodiment, a computer device is provided, the computer device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, performs the following steps:

[0131] S1: Obtain a pre-set electronic questionnaire about gift preference types;

[0132] S2: Identify each question in the electronic questionnaire and generate several question formats based on each question;

[0133] S3: Distribute electronic questionnaires to all users;

[0134] S4: When any user answers a question, before displaying the next question, predict the user's attention value when the user answers the next question based on the user's operational characteristics of the questions already answered;

[0135] S5: Adjust the questioning method for the next question based on the attention score;

[0136] S6: Analyze the logical discrepancies between the user's answer to the adjusted question and the answers to previously answered questions;

[0137] S7: Determine whether to adopt the user's answer to the question being adjusted based on logical deviation;

[0138] S8: After collecting all electronic questionnaires, identify the question number distribution of the adopted answers in each questionnaire, and select electronic questionnaires for integration based on the question number distribution to obtain several target questionnaires. Among them, the proportion of the number of question numbers corresponding to the adopted answers in the target questionnaires to the total number of question numbers exceeds the preset proportion.

[0139] S9: Analyze the answers to each target questionnaire to determine the ranking of gift preferences, and generate a gift purchasing guide based on the ranking of gift preferences to guide staff in purchasing marketing gifts.

[0140] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a processor, causes the processor to perform the following steps:

[0141] S1: Obtain a pre-set electronic questionnaire about gift preference types;

[0142] S2: Identify each question in the electronic questionnaire and generate several question formats based on each question;

[0143] S3: Distribute electronic questionnaires to all users;

[0144] S4: When any user answers a question, before displaying the next question, predict the user's attention value when the user answers the next question based on the user's operational characteristics of the questions already answered;

[0145] S5: Adjust the questioning method for the next question based on the attention score;

[0146] S6: Analyze the logical discrepancies between the user's answer to the adjusted question and the answers to previously answered questions;

[0147] S7: Determine whether to adopt the user's answer to the question being adjusted based on logical deviation;

[0148] S8: After collecting all electronic questionnaires, identify the question number distribution of the adopted answers in each questionnaire, and select electronic questionnaires for integration based on the question number distribution to obtain several target questionnaires. Among them, the proportion of the number of question numbers corresponding to the adopted answers in the target questionnaires to the total number of question numbers exceeds the preset proportion.

[0149] S9: Analyze the answers to each target questionnaire to determine the ranking of gift preferences, and generate a gift purchasing guide based on the ranking of gift preferences to guide staff in purchasing marketing gifts.

[0150] It should be understood that although the steps in the flowcharts of the various embodiments of the present invention are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the various embodiments may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least a portion of the sub-steps or stages of other steps.

[0151] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided by this invention can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0152] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0153] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention. Therefore, the scope of protection of this patent should be determined by the appended claims.

Claims

1. A method for managing the procurement of marketing gifts, characterized in that, The method includes: S1: Obtain a pre-set electronic questionnaire about gift preference types; S2: Identify each question in the electronic questionnaire and generate several question formats based on each question; S3: Distribute electronic questionnaires to all users; S4: When any user answers a question, before displaying the next question, predict the user's attention value when the user answers the next question based on the user's operational characteristics of the already answered questions; S5: Adjust the questioning method for the next question based on the attention score; S6: Analyze the logical discrepancies between the user's answer to the adjusted question and the answers to previously answered questions; S7: Determine whether to adopt the user's answer to the question being adjusted based on logical deviation; S8: After collecting all electronic questionnaires, identify the question number distribution of the adopted answers in each questionnaire, and select electronic questionnaires for integration based on the question number distribution to obtain several target questionnaires. Among them, the proportion of the number of question numbers corresponding to the adopted answers in the target questionnaires to the total number of question numbers exceeds the preset proportion. S9: Analyze the answers to each target questionnaire to determine the ranking of gift preferences, and generate a gift purchasing guide based on the ranking of gift preferences to guide staff in purchasing marketing gifts.

2. The method according to claim 1, characterized in that, Based on the user's operational characteristics, the predicted trend of their attention changes includes: Obtain the user's operational characteristics for the t questions that have been answered; The attention prediction model is invoked, and the acquired operational features are input into the attention prediction model to predict the user's attention value when answering the (t+1)th question. The attention prediction model is: Where A(t+1) is the user's attention value when answering the (t+1)th question, A(t) is the user's attention value when answering the tth question, and α is the attention reduction coefficient. ρ is the feature vector for weighted operations, and ρ is the feature weight vector.

3. The method according to claim 2, characterized in that, The weighted operation feature vector is: Among them, X i Let ω(i) be the operation feature vector corresponding to the operation features of the first i problems; ω(i) is - i Weighting function: ω(i)=e -(t-i) X i Represented as: in, The average time taken for the first i questions, This represents the average number of pauses for the first i questions. This represents the average number of revisions for the first i questions. The feature weight vector is represented as: p=[p t ,r s ,r m ] Where, ρ t ρ represents the weight of the time-consuming feature. s ρ is the feature weight for the number of pauses. m To modify the feature weights for the number of times.

4. The method according to claim 2, characterized in that, Adjusting the way the next question is asked based on the attention score includes: Determine if the attention value is lower than the first preset value; if not, do not adjust the questioning method for the next question. If so, determine the cognitive load index for each way of asking the next question; Divide the attention value by each cognitive load index and compare the resulting quotients with the set quotients. The question format corresponding to the quotient closest to the set quotient is determined as the target question format; Adjust the question format for the next question to the target question format.

5. The method according to claim 4, characterized in that, The analysis of logical discrepancies between the user's answers to the adjusted question and their answers to previously answered questions includes: Obtain the question subjects for all questions in the electronic questionnaire, and retrieve the numerical values ​​of all answers for each question. The numerical values ​​of the answers range from 0 to 1, representing the user's degree of preference for the corresponding question subject. The question subject is the product type targeted by the question. Identify the problem object of the next question as the target object; Filter out the questions whose corresponding question objects match the target object from the already answered questions; From the screened questions, those with attention values ​​greater than the first preset value are identified as reference questions; Identify the numerical value of the user's answer to each reference question and calculate the average value; Identify the numerical value of the answer to the adjusted question and calculate the logical bias using the following formula: Among them, B L For logical deviation, n a The numerical value of the answer to the question being adjusted. This is the average value; Determining whether to adopt a user's answer to the question being adjusted based on logical deviations includes: Determine if the logical deviation is lower than the preset deviation. If so, use the corresponding answer; otherwise, do not use the corresponding answer.

6. The method according to claim 5, characterized in that, Identify the question number distribution of the answers used in each questionnaire, and select and integrate electronic questionnaires based on the question number distribution to obtain several target questionnaires, including: S81: Determine whether the proportion of the number of question numbers corresponding to the adopted answers in each of the returned electronic questionnaires exceeds the preset proportion. If yes, the electronic questionnaire is the target questionnaire; otherwise, the electronic questionnaire is the non-target questionnaire. S82: Select one questionnaire from the unqualified questionnaires as the base questionnaire; S83: Compare the basic questionnaire with each of the other unqualified questionnaires to determine if there is a matching questionnaire for the basic questionnaire among the other unqualified questionnaires. If so, integrate the basic questionnaire and the corresponding matching questionnaire into a target questionnaire and delete the two unqualified questionnaires. If not, the basic questionnaire cannot be integrated into the target questionnaire. S84: Repeat steps S82-S83 until all target questionnaires are obtained.

7. The method according to claim 6, characterized in that, The basic questionnaire was compared one by one with other non-compliant questionnaires to determine if there were any matching questionnaires among the other non-compliant questionnaires. S831: Delete the question number corresponding to the unused answer in each questionnaire, and retain the question number of the used answer; S832: Select one non-compliant questionnaire from the other non-compliant questionnaires as a comparison questionnaire; S833: Calculate the sum of the number of question numbers in the comparison questionnaire and the basic questionnaire, subtract the number of duplicate question numbers from the sum of the sum to get the first quantity, divide the first quantity by the total number of question numbers to get the first ratio, and determine whether the first ratio is greater than the preset ratio. If not, the comparison questionnaire is not a matching questionnaire. S834: If so, identify each group of identical question numbers in the comparison questionnaire and the basic questionnaire; S835: For each pair of questions with the same number, calculate the numerical difference between the answers corresponding to the two question numbers; S836: Calculate the mean of the differences between the values, and determine whether the mean is lower than the second preset value. If so, the comparison questionnaire is a matching questionnaire of the basic questionnaire. Otherwise, the comparison questionnaire is not a matching questionnaire of the basic questionnaire. Delete the comparison questionnaire, and select another unqualified questionnaire from the other unqualified questionnaires as the comparison questionnaire. Execute steps S833 to S836 until a matching questionnaire is determined or it is determined that there is no matching questionnaire of the basic questionnaire among the other unqualified questionnaires.

8. A marketing gift procurement management device, characterized in that, The device includes: The acquisition module is used to acquire a pre-set electronic questionnaire about gift preference types; The first processing module is used to identify each question in the electronic questionnaire and generate several question types based on each question; The second processing module is used to distribute electronic questionnaires to each user. The third processing module is used to predict the user's attention value when answering the next question, based on the user's operational characteristics of the already answered questions, before displaying the next question. The fourth processing module is used to adjust the questioning method for the next question based on the attention value; The fifth processing module is used to analyze the logical discrepancies between the user's answer to the adjusted question and the answers to previously answered questions; The sixth processing module is used to determine whether to adopt the user's answer to the question being adjusted based on logical deviations. The retrieval module is used to retrieve all electronic questionnaires, identify the distribution of question numbers of the adopted answers in each questionnaire, select electronic questionnaires for integration based on the question number distribution, and thus obtain several target questionnaires. The proportion of the number of question numbers corresponding to the adopted answers in the target questionnaires to the total number of question numbers exceeds a preset proportion. The analysis module is used to analyze the answers to each target questionnaire to determine the ranking of gift preferences. Based on this ranking, a gift purchasing guide is generated to guide staff in purchasing marketing gifts.

9. A marketing gift procurement management system, characterized in that, The system includes: Each user's client is used for users to answer electronic questionnaires; A computer device that communicates with various user terminals to execute the marketing gift procurement management method as described in any one of claims 1-7.

Images