A user experience comprehensive evaluation system and method based on big data

Abstract

The present invention relates to the field of big data processing, and discloses a user experience comprehensive evaluation system and method based on big data, wherein the comprehensive evaluation system comprises: a project information module, a personnel information module, an experience information module and an analysis module; the basic project information comprises positioning information of a survey product and basic project information; the positioning information and basic project information of each survey product are input through a product positioning module; the basic information of experience personnel is collected through a personnel information module; the basic information of the experience personnel and the positioning information and time information of each survey product are analyzed through an analysis module, and the survey product is sent to the experience personnel according to the analysis result; the experience information of using the same survey product is then analyzed to obtain a comprehensive evaluation result of the survey product; thereby, the survey product and the experience personnel are highly matched, and the accuracy of the comprehensive evaluation result of the survey product is improved.

Description

Technical Field

[0001] The present invention relates to the field of big data processing, and in particular to a user experience comprehensive evaluation system and method based on big data. Background Art

[0002] User experience evaluation is to evaluate products or services through user feedback on their experience using the product or their attitude towards the service, so as to optimize the product or service, improve user satisfaction, and thus enhance user loyalty.

[0003] Market research is the main way to obtain user feedback. Traditional market research is conducted by staff outdoors to survey consumers one by one, which takes a lot of time to find users who have used the corresponding products. With the development of network technology, users can send application information to the market research platform through the Internet. The market research staff receives the application information and randomly sends products to the applying users; after using the product, the user sends the corresponding experience, and then a comprehensive evaluation of the user experience of the product is conducted based on all the user experiences received.

[0004] However, since the market fishing platform involves many products and each product has a different positioning and different consumer groups, if the experiencer is different from the consumer of the product positioning, the feedback information will be inaccurate, making the final comprehensive evaluation result of the user experience inaccurate. Summary of the invention

[0005] The purpose of the present invention is to provide a user experience comprehensive evaluation system and method based on big data to solve the following technical problems:

[0006] How to improve the accuracy of comprehensive evaluation of user experience.

[0007] The purpose of the present invention can be achieved through the following technical solutions:

[0008] A user experience comprehensive evaluation system based on big data, the comprehensive evaluation system comprising:

[0009] The project information module is used to establish projects and input basic project information of each project; the basic project information includes positioning information of the researched product and basic project information;

[0010] Personnel information module, used to collect basic information of experience personnel;

[0011] Experience information module, used to collect experience information of experiencers;

[0012] The analysis module is used to analyze the basic information of the experiencer and the location information and time information of each research product, and send the research product to the experiencer based on the analysis results; then analyze the experience information of using the same research product to obtain the comprehensive evaluation results of the research product.

[0013] As a further solution of the present invention: the positioning information includes product type and product customer portrait; the basic project information includes the number of people required for experience and the survey deadline.

[0014] As a further solution of the present invention: the analysis process of the analysis module is:

[0015] S10: obtaining the desired product type of the experiencer through the personnel information module;

[0016] S20; retrieve the product types of the research products in each project through the project information module; and select multiple research products that match the desired product types;

[0017] S30: Analyze the product customer portraits of multiple survey products that match the desired product types, basic information of experiencers, the number of people required for experience, and the survey deadline according to preset rules, and send the survey products to the experiencers based on the analysis results;

[0018] S40: After receiving the research product, the experiencer sends the experience information to the experience information module;

[0019] S50: Obtain experience information of using the same research product through the experience information module for analysis to obtain a comprehensive evaluation result of the research product.

[0020] As a further solution of the present invention: the product customer portrait includes N first features; each of the first features includes a feature name, multiple feature ranges and multiple preset matching coefficients; the feature ranges correspond one-to-one to the preset matching coefficients; the basic information of the experiencer includes N second features; the second feature includes a feature name and a feature value corresponding to the second feature name; the first feature and the second feature correspond one-to-one, and the feature name of the second feature is the same as that of the corresponding first feature; the feature value of the second feature belongs to one of the feature ranges corresponding to the first feature.

[0021] As a further solution of the present invention: in step S30, the preset rules include:

[0022] S100: Mark the survey products that match the intended product type, respectively, with a mark k (k ≥ 1);

[0023] S200: Analyze the N first features of the product customer portrait of the research product marked as k and the N second features of the basic information of the experiencer; obtain a comprehensive matching coefficient between the experiencer and the research product marked as k;

[0024] S300: Send the research product with the highest comprehensive matching coefficient among all research products to the experience personnel for experience.

[0025] As a further solution of the present invention: in step S200, the process of obtaining the comprehensive matching coefficient is:

[0026] S1000: find out the second features corresponding to N first features respectively; record the nth first feature as P1 n ; The second feature corresponding to the nth first feature is recorded as P2 n ;

[0027] S2000: In the marked P2 n The eigenvalue of the second feature is marked as P1 n The characteristic range of the first characteristic is compared; the characteristic range corresponding to the characteristic value is obtained; and the characteristic range is recorded as P3 n ; and obtain the preset matching coefficient corresponding to the feature range, which is recorded as δ n ;

[0028] S3000: Calculate the comprehensive matching coefficient using a preset formula.

[0029] As a further solution of the present invention: the preset formula is:

[0030]

[0031] Wherein, f(X) is the first judgment function, when X>0, f(X)=X; when X≤0, f(X)=0; is the second judgment function, when hour, when hour, Z k is the comprehensive matching coefficient between the experiencer and the research product marked as k, 0 <Z k ≤1;D k is the number of days remaining from the current time to the deadline of the project where the research product marked as k is located; D0 is the preset number of days; R k R is the number of people who have participated in the experience of the research product marked as k; ak h is the number of people required to experience the project of the research product marked as k; i is the preset ratio; C is the preset constant; ε is the adjustment coefficient.

[0032] As a further solution of the present invention: the preset ratio h i for:

[0033] Will Compare with the preset threshold [R1, R2]; [R1, R2]∈(0,1);

[0034] when When i =h1;

[0035] when When i =h2;

[0036] when When i =h3;

[0037] Among them, h1 is the first-level preset ratio; h2 is the second-level preset ratio; h3 is the third-level preset ratio; and h1 <h2<h3。

[0038] A comprehensive evaluation method for user experience based on big data, the evaluation method comprising the following steps:

[0039] S1: Obtain the basic information of the experiencer through the personnel information module;

[0040] S2: Analyze the basic information of the experiencer, the positioning information of the research product and the basic information of the project through the analysis module, and send the research product to the experiencer based on the analysis results;

[0041] S3: After receiving the research product, the experiencer sends the experience information to the experience information module;

[0042] S4: The experience information module is used to obtain experience information of the same research product for analysis to obtain a comprehensive evaluation result of the research product.

[0043] Beneficial effects of the present invention:

[0044] (1) The present invention inputs the positioning information and basic project information of each research product through the product positioning module; collects the basic information of the experiencer through the personnel information module; analyzes the basic information of the experiencer and the positioning information and time information of each research product through the analysis module, and sends the research product to the experiencer according to the analysis result; then analyzes the experience information of using the same research product to obtain the comprehensive evaluation result of the research product; thereby, the matching degree between the research product and the experiencer is higher, and the accuracy of the comprehensive evaluation result of the research product is improved;

[0045] (2) The present invention is the ratio of the difference between the preset number of days and the remaining days from the current time to the deadline of the project where the research product marked as k is located to the preset number of days; when The larger the value, the closer to the deadline. Compare with the preset threshold [R1, R2]; the closer to the cut-off period, h in i The system also changes accordingly, so as to increase the number of experiencers as soon as possible before the deadline, increase the sample size and improve the matching between the survey product and the experiencers. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The present invention will be further described below in conjunction with the accompanying drawings.

[0047] Figure 1 A system module framework diagram of an embodiment of the present invention;

[0048] Figure 2 The present invention is a method flow chart of an embodiment of the present invention. DETAILED DESCRIPTION

[0049] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0050] See also Figure 1 As shown, in one embodiment, a user experience comprehensive evaluation system based on big data is provided, including:

[0051] The project information module is used to establish projects and input basic project information of each project; the basic project information includes positioning information of the researched product and basic project information;

[0052] Personnel information module, used to collect basic information of experience personnel;

[0053] Experience information module, used to collect experience information of experiencers;

[0054] The analysis module is used to analyze the basic information of the experiencer and the location information and time information of each research product, and send the research product to the experiencer based on the analysis results; and then analyze the experience information of using the same research product to obtain the comprehensive evaluation results of the research product;

[0055] Through the above technical solution, this embodiment inputs the positioning information and basic project information of each research product through the product positioning module; collects the basic information of the experiencer through the personnel information module; analyzes the basic information of the experiencer and the positioning information and time information of each research product through the analysis module, and sends the research product to the experiencer according to the analysis result; then analyzes the experience information of using the same research product to obtain the comprehensive evaluation result of the research product; thereby making the matching degree between the research product and the experiencer higher and improving the accuracy of the comprehensive evaluation result of the research product;

[0056] It should be noted that obtaining a comprehensive evaluation result of a research product based on experience information of the same research product is a prior art and will not be described in detail here.

[0057] As an implementation mode of the present invention, the positioning information includes product type and product customer portrait; the basic project information includes the number of people required for experience and the survey deadline;

[0058] As an implementation manner of the present invention, the analysis process of the analysis module is:

[0059] S10: obtaining the desired product type of the experiencer through the personnel information module;

[0060] S20; retrieve the product types of the research products in each project through the project information module; and select multiple research products that match the desired product types;

[0061] S30: Analyze the product customer portraits of multiple survey products that match the desired product types, basic information of experiencers, the number of people required for experience, and the survey deadline according to preset rules, and send the survey products to the experiencers based on the analysis results;

[0062] S40: After receiving the research product, the experiencer sends the experience information to the experience information module;

[0063] S50: Obtaining experience information of using the same research product through the experience information module for analysis to obtain a comprehensive evaluation result of the research product;

[0064] Through the above technical scheme, this embodiment first obtains the desired product type of the experiencer through the personnel information module; then retrieves the product type of the survey product in each project through the project information module; screens out multiple survey products that match the desired product type; improves the experiencer's satisfaction and enthusiasm for experiencing the product; then analyzes the product customer portraits, basic information of the experiencer, the number of people required for the experience and the survey deadline of multiple survey products that match the desired product type according to preset rules, and sends the survey product to the experiencer according to the analysis results; thereby, the survey product and the experiencer have a high matching degree, thereby improving the accuracy of the comprehensive evaluation results of the survey product; then, after receiving the survey product, the experiencer sends the experience information to the experience information module; finally, the experience information using the same survey product is obtained through the experience information module for analysis to obtain the comprehensive evaluation results of the survey product; thereby, the survey product and the experiencer have a high matching degree, thereby improving the accuracy of the comprehensive evaluation results of the survey product.

[0065] As an implementation mode of the present invention, the product customer portrait includes N first features; each of the first features includes a feature name, multiple feature ranges and multiple preset matching coefficients; the feature ranges correspond one-to-one to the preset matching coefficients; the basic information of the experiencer includes N second features; the second feature includes a feature name and a feature value corresponding to the second feature name; the first feature and the second feature correspond one-to-one, and the second feature has the same feature name as the corresponding first feature; the feature value of the second feature belongs to one of the feature ranges corresponding to the first feature;

[0066] Through the above technical solution, the feature name of the first feature in this embodiment can be age, name, occupation, height, weight, etc.; the staff presets different feature ranges for different feature names, and presets different preset matching coefficients for the feature ranges;

[0067] As an implementation manner of the present invention, in step S30, the preset rule includes:

[0068] S100: Mark the survey products that match the intended product type, respectively, with a mark k (k ≥ 1);

[0069] S200: Analyze the N first features of the product customer portrait of the research product marked as k and the N second features of the basic information of the experiencer; obtain a comprehensive matching coefficient between the experiencer and the research product marked as k;

[0070] S300: The product with the highest comprehensive matching coefficient among all the survey products is sent to the experiencer for experience;

[0071] Through the above technical solution, this embodiment first marks the survey products that match the intended product type, mark k (k≥1); then analyze the N first features of the product customer portrait of the survey product marked as k and the N second features of the basic information of the experiencer; obtain the comprehensive matching coefficient between the experiencer and the survey product marked as k; finally, among all the survey products, the survey product with the highest comprehensive matching coefficient is sent to the experiencer for experience; thereby, the survey product and the experiencer are matched in multiple different features, and the survey product with a higher matching degree is sent to the experiencer, thereby improving the accuracy of the comprehensive evaluation results of the survey product.

[0072] As an implementation of the present invention, in step S200, the process of obtaining the comprehensive matching coefficient is:

[0073] S1000: find out the second features corresponding to N first features respectively; record the nth first feature as P1 n ; The second feature corresponding to the nth first feature is recorded as P2 n ;

[0074] S2000: In the marked P2 n The eigenvalue of the second feature is marked as P1 n The characteristic range of the first characteristic is compared; the characteristic range corresponding to the characteristic value is obtained; and the characteristic range is recorded as P3 n ; and obtain the preset matching coefficient corresponding to the feature range, which is recorded as δ n ;

[0075] S3000: Calculate the comprehensive matching coefficient through a preset formula;

[0076] Through the above technical solution, this embodiment sequentially finds the second features corresponding to N first features respectively; the nth first feature is recorded as P1 n ; The second feature corresponding to the nth first feature is recorded as P2 n ; In the marked P2 n The eigenvalue of the second feature is marked as P1 n The characteristic range of the first characteristic is compared; the characteristic range corresponding to the characteristic value is obtained; and the characteristic range is recorded as P3 n ; and obtain the preset matching coefficient corresponding to the feature range, which is recorded as δ n ; Calculate the comprehensive matching coefficient through the preset formula;

[0077] As an implementation manner of the present invention, the preset formula is:

[0078]

[0079] Wherein, f(X) is the first judgment function, when X>0, f(X)=X; when X≤0, f(X)=0; is the second judgment function, when hour, when hour, Z k is the comprehensive matching coefficient between the experiencer and the research product marked as k, 0 <Z k ≤1;D k is the number of days remaining from the current time to the deadline of the project where the research product marked as k is located; D0 is the preset number of days; R k R is the number of people who have participated in the experience of the research product marked as k; ak h is the number of people required to experience the project of the research product marked as k; i is the preset ratio; C is the preset constant; ε is the adjustment coefficient;

[0080] Through the above technical solution, this embodiment The product of the preset matching coefficients of the feature ranges of the second features corresponding to the feature values ​​of the N first features represents the basic matching coefficients of the N first features; D0-D k is the difference between the preset number of days and the remaining number of days from the current time to the deadline of the project where the research product marked as k is located; when D0-D k When ≤0, it means that the number of days remaining from the current time to the deadline of the project where the research product marked as k belongs is greater than the preset number of days; is the ratio of the number of people who have participated in the research product marked as k to the number of people who have participated in the research product marked as k; when D0-D k When >0, it means that the number of days remaining from the current time to the deadline of the project where the research product marked as k belongs is less than the preset number of days; The ratio of the number of people who have participated in the research product marked as k to the number of people who have participated in the research product marked as k; is the difference between the preset ratio and the ratio of the number of people who have participated in the experience of the research product marked as k to the number of people who have participated in the experience of the research product marked as k; When , it means that the preset ratio is less than or equal to the ratio of the number of people who have participated in the experience of the research product marked as k to the number of people who have participated in the experience of the research product marked as k; when When , it means that the preset ratio is greater than the ratio of the number of people who have participated in the experience of the research product marked as k to the number of people who have participated in the experience of the research product marked as k; the number of people participating in the experience is small at present, when D0-D k >0 and , it means that when the deadline of the research product marked as k is approaching, the number of people who have participated in the experience of the research product marked as k is small. D0-D k The larger the value, the greater the comprehensive matching coefficient Z k The larger the R ak -R k The larger the value, the greater the comprehensive matching coefficient Z k The bigger;

[0081] It should be noted that the preset number of days D0 and the preset ratio h i , preset constant C and adjustment coefficient ε are preset values, obtained based on experience, R k The number of people who have participated in the experience of the research product marked as k is obtained through the experience information module, and the number of people required to experience the project where the research product marked as k is located is R ak It is obtained through the project information module, which is a prior art and will not be described in detail here.

[0082] As an implementation mode of the present invention, the preset ratio h i for:

[0083] Will Compare with the preset threshold [R1, R2]; [R1, R2]∈(0,1);

[0084] when When i =h1;

[0085] when When i =h2;

[0086] when When i =h3;

[0087] Among them, h1 is the first-level preset ratio; h2 is the second-level preset ratio; h3 is the third-level preset ratio; and h1 <h2<h3;

[0088] Through the above technical solution, this embodiment is the ratio of the difference between the preset number of days and the remaining days from the current time to the deadline of the project where the research product marked as k is located to the preset number of days; when The larger the value, the closer to the deadline. Compare with the preset threshold [R1, R2]; when When i =h1; when When i =h2; when When i= h3, and h1 < h2 < h3; such that the closer to the deadline, the h in i also changes accordingly, so as to increase the number of experienced persons as soon as possible before the deadline, increase the sample size, and improve the matching degree between the research product and the experienced persons;

[0089] It should be noted that the preset threshold [R1, R2], the first-level preset ratio h1, the second-level preset ratio h2, and the third-level preset ratio h3 are preset values obtained according to experience and will not be elaborated here.

[0090] A comprehensive user experience evaluation method based on big data, the evaluation method includes the following steps:

[0091] S1: Obtain the basic information of the experienced persons through the personnel information module;

[0092] S2: Analyze the basic information of the experienced persons, the positioning information of the research product, and the basic information of the project through the analysis module, and send the research product to the experienced persons according to the analysis results;

[0093] S3: After receiving the research product, the experienced persons send the experience information to the experience information module;

[0094] S4: Obtain and analyze the experience information of using the same research product through the experience information module to obtain the comprehensive evaluation result of the research product.

[0095] The above has described an embodiment of the present invention in detail, but the described content is only a preferred embodiment of the present invention and cannot be considered as limiting the implementation scope of the present invention. All equivalent changes and improvements made according to the scope of the present invention application should still fall within the scope covered by the patent of the present invention.

Claims

1. A comprehensive user experience evaluation system based on big data, characterized in that: The comprehensive evaluation system includes: The project information module is used to establish projects and input basic project information of each project; the basic project information includes positioning information of the researched product and basic project information; Personnel information module, used to collect basic information of experience personnel; Experience information module, used to collect experience information of experiencers; The analysis module is used to analyze the basic information of the experiencer and the location information and time information of each research product, and send the research product to the experiencer based on the analysis results; and then analyze the experience information of using the same research product to obtain the comprehensive evaluation results of the research product; The analysis process of the analysis module is as follows: S10: obtaining the desired product type of the experiencer through the personnel information module; S20; retrieve the product types of the research products in each project through the project information module; and select multiple research products that match the desired product types; S30: Analyze the product customer portraits, basic information of experiencers, required number of experiencers, and survey deadline of multiple survey products that match the desired product types according to preset rules, and send the survey products to the experiencers according to the analysis results; S40: After receiving the research product, the experiencer sends the experience information to the experience information module; S50: Obtaining experience information of using the same research product through the experience information module for analysis to obtain a comprehensive evaluation result of the research product; In step S30, the preset rules include: S100: Mark the survey products that match the intended product type, respectively, with a mark k (k ≥ 1); S200: Analyze the N first features of the product customer portrait of the research product marked as k and the N second features of the basic information of the experiencer; obtain a comprehensive matching coefficient between the experiencer and the research product marked as k; S300: The product with the highest comprehensive matching coefficient among all the survey products is sent to the experiencer for experience; In step S200, the process of obtaining the comprehensive matching coefficient is as follows: S1000: find out the second features corresponding to N first features respectively; record the nth first feature as P1 n ; The second feature corresponding to the nth first feature is recorded as P2 n ; S2000: In the marked P2 n The eigenvalue of the second feature is marked as P1 n The characteristic range of the first characteristic is compared; the characteristic range corresponding to the characteristic value is obtained; and the characteristic range is recorded as P3 n ; and obtain the preset matching coefficient corresponding to the feature range, which is recorded as δ n ; S3000: Calculate the comprehensive matching coefficient through a preset formula; The preset formula is: Wherein, f(X) is the first judgment function, when X>0, f(X)=X; when X≤0, f(X)=0; is the second judgment function, when hour, when hour, Z k is the comprehensive matching coefficient between the experiencer and the research product marked as k, 0 <Z k ≤1;D k is the number of days remaining from the current time to the deadline of the project where the research product marked as k is located; D0 is the preset number of days; R k R is the number of people who have participated in the experience of the research product marked as k; ak h is the number of people required to experience the project of the research product marked as k; i is the preset ratio; C is the preset constant; ε is the adjustment coefficient.

2. According to the big data-based comprehensive user experience evaluation system of claim 1, it is characterized in that: The positioning information includes product type and product customer portrait; the basic project information includes the number of people required for the experience and the survey deadline.

3. According to the big data-based comprehensive user experience evaluation system of claim 1, it is characterized in that: The product customer portrait includes N first features; each of the first features includes a feature name, multiple feature ranges and multiple preset matching coefficients; the feature ranges correspond one-to-one to the preset matching coefficients; the basic information of the experiencer includes N second features; the second feature includes a feature name and a feature value corresponding to the second feature name; the first feature and the second feature correspond one-to-one, and the feature name of the second feature is the same as that of the corresponding first feature; the feature value of the second feature belongs to one of the feature ranges corresponding to the first feature.

4. According to the big data-based comprehensive user experience evaluation system of claim 1, it is characterized in that: The preset ratio h i for: Will Compare with the preset threshold [R1, R2]; [R1, R2]∈(0,1); when When i =h1; when When i =h2; when When i =h3; Among them, h1 is the first-level preset ratio; h2 is the second-level preset ratio; h3 is the third-level preset ratio; and h1 <h2<h3。 5. A user experience comprehensive evaluation method based on big data, applicable to a user experience comprehensive evaluation system based on big data as described in any one of claims 1 to 4, characterized in that: The evaluation method comprises the following steps: S1: Obtain the basic information of the experiencer through the personnel information module; S2: Analyze the basic information of the experiencer, the positioning information of the research product and the basic information of the project through the analysis module, and send the research product to the experiencer based on the analysis results; S3: After receiving the research product, the experiencer sends the experience information to the experience information module; S4: The experience information module is used to obtain experience information of the same research product for analysis to obtain a comprehensive evaluation result of the research product.

Images