Method and device for product evaluation and storage medium

Abstract

The invention relates to the technical field of data analysis, in particular to a method for product evaluation, and the method comprises the steps: determining a target user, and obtaining the reference facial micro-expression data of the target user; obtaining user facial micro-expression data of the target user in a product test time period; according to the reference facial micro-expression data and the user facial micro-expression data, determining respective data values of two elements of a two-dimensional analysis model for product evaluation; the evaluation result of the product is analyzed according to the data value; wherein the respective data types of the reference facial micro-expression data and the user facial micro-expression data at least comprise a first type of data representing negative and a second type of data representing pleasure. According to the method, multi-aspect objective feelings of the user on the product can be accurately analyzed, and a more accurate direction is provided for product optimization of merchants.

Description

Technical Field

[0001] The present invention relates to the field of data analysis technology, and in particular to a method, device and storage medium for product evaluation. Background Art

[0002] Nowadays, facing the fiercely competitive business environment, research work before new products are put into production is very necessary, and conducting product sensory testing is currently a more effective research method to understand user preferences for products.

[0003] There is an existing product testing method that obtains the facial video of the evaluator during the product testing process, identifies and encodes the microscopic movements of the evaluator's face based on the facial action coding system, obtains a set of data values ​​of the evaluator arranged in chronological order, and then performs simple operations such as averaging on the data values ​​to obtain the evaluator's objective preferences for the product. However, the type of data obtained by the algorithm for analysis is relatively simple, and the data analysis process is relatively rough, so that the evaluation results cannot truly reflect the user's objective preferences and cannot help merchants clarify the specific optimization direction of the product. Summary of the invention

[0004] The technical problem to be solved by the present invention is to provide a method, device and storage medium for product evaluation, which can accurately analyze the user's multi-faceted objective feelings about the product and provide a more accurate direction for merchants to optimize their products.

[0005] In order to solve the above technical problems, the first aspect of the present invention discloses a method for product evaluation, the method comprising:

[0006] Determine a target user, and obtain baseline facial micro-expression data of the target user;

[0007] Acquire user facial micro-expression data during the time period when the target user tests the product;

[0008] Determining data values ​​of two elements of a two-dimensional analysis model for product evaluation according to the reference facial micro-expression data and the user facial micro-expression data;

[0009] Analyze the evaluation results of the product according to the data value;

[0010] The data information types of the reference facial micro-expression data and the user facial micro-expression data respectively include at least first-type data indicating negativity and second-type data indicating pleasure.

[0011] Optionally, obtaining the benchmark facial micro-expression data of the target user includes:

[0012] Acquire pre-stored reference facial micro-expression data associated with the target user as the reference facial micro-expression data of the target user;

[0013] and / or,

[0014] The facial micro-expression data of the target user during the process of testing the anchor is obtained as the baseline facial micro-expression data of the target user; the test environment in which the target user tests the product is the same as the test environment in which the target user tests the anchor; the anchor is determined according to the category and evaluation category of the product.

[0015] Optionally, the evaluation category of the product evaluation is smell,

[0016] The step of obtaining the facial micro-expression data of the target user during the process of testing the anchor object comprises: obtaining the facial micro-expression data of the target user during the process of testing the odor of the anchor object using the sense of smell;

[0017] The obtaining of the user's facial micro-expression data during the time period when the target user tests the product comprises: obtaining the user's facial micro-expression data during the time period when the target user uses his sense of smell to test the smell of the product;

[0018] and / or,

[0019] The evaluation category of the product evaluation is visual.

[0020] The step of obtaining the facial micro-expression data of the target user during the process of testing the anchor object comprises: obtaining the facial micro-expression data of the target user during the process of visually testing the appearance of the anchor object;

[0021] The obtaining of the user's facial micro-expression data during the time period when the target user tests the product comprises: obtaining the user's facial micro-expression data during the time period when the target user visually tests the appearance of the product;

[0022] and / or,

[0023] The evaluation category of the product evaluation is taste.

[0024] The step of obtaining the facial micro-expression data of the target user during the process of testing the anchor includes: obtaining the facial micro-expression data of the target user during the process of testing the taste of the anchor using the sense of taste;

[0025] The obtaining of the user's facial micro-expression data during the time period when the target user tests the product comprises: obtaining the user's facial micro-expression data during the time period when the target user uses taste to test the taste of the product;

[0026] and / or,

[0027] The evaluation category of the product evaluation is hearing.

[0028] The step of obtaining the facial micro-expression data of the target user during the process of testing the anchor includes: obtaining the facial micro-expression data of the target user during the process of testing the sound of the anchor using hearing;

[0029] The step of obtaining the user's facial micro-expression data during the time period when the target user tests the product includes: obtaining the user's facial micro-expression data during the time period when the target user uses hearing to test the sound of the product;

[0030] and / or,

[0031] The evaluation category of the product evaluation is touch.

[0032] The step of obtaining the facial micro-expression data of the target user during the process of testing the anchor object comprises: obtaining the facial micro-expression data of the target user during the process of testing the tactile sensation of the anchor object using the sense of touch;

[0033] The obtaining of the user's facial micro-expression data during the time period when the target user tests the product includes: obtaining the user's facial micro-expression data during the time period when the target user tests the tactile sense of the product using tactile sense.

[0034] Optionally, the reference facial micro-expression data and the user facial micro-expression data are respectively sorted into time series results in chronological order, the time series results corresponding to the user facial micro-expression data are first time series results, and the time series results corresponding to the reference facial micro-expression data are second time series results; the two elements of the two-dimensional analysis model are product impact and user pleasure; the data values ​​of the two elements of the two-dimensional analysis model are calculated based on the reference facial micro-expression data and the user facial micro-expression data, including:

[0035] Calculate product impact force

[0036] Where t is the total number of data values ​​in the first time series result, x i is the i-th data value in the first time series result, is the data average value of the second time series results;

[0037] The negative intensity index corresponding to the first type of data and the pleasure intensity index corresponding to the second type of data are calculated, and the user pleasure is calculated based on the negative intensity index and the pleasure intensity index.

[0038] Optionally, the calculating the negative intensity index corresponding to the first type of data and the pleasure intensity index corresponding to the second type of data, and calculating the user pleasure according to the negative intensity index and the pleasure intensity index, includes:

[0039] Arrange the first time series results into a negative first sub-time series and a pleasant first sub-time series according to data type, and arrange the second time series results into a negative second sub-time series and a pleasant second sub-time series according to data type;

[0040] Calculating Negative Strength Index

[0041] Where e is the total number of data values ​​in the negative first sub-time series results, α i is the i-th data value in the negative first sub-time series result, is the data average of the negative second sub-time series results;

[0042] Calculating the Pleasure Intensity Index

[0043] Where r is the total number of data values ​​in the first sub-time series of pleasure, β i is the i-th data value in the first sub-time series result of the pleasure, is the data average of the results of the second sub-time series of pleasure;

[0044] According to a preset conversion rule, the negative intensity index Q is converted into a percentage system Q*, and the pleasure intensity index P is converted into a percentage system P*;

[0045] The user pleasure is calculated, where the user pleasure is a weighted sum of the negative intensity index Q* and the pleasure intensity index P*.

[0046] Optionally, analyzing the evaluation result of the product according to the data value includes:

[0047] According to the conversion rule, the product impact force D is converted into a percentage system D*;

[0048] When the product impact force D* is greater than or equal to the first threshold and the user pleasure W is greater than or equal to the first threshold, displaying the coordinate points corresponding to the two elements of the two-dimensional analysis model in the area representing "very attractive" in the two-dimensional analysis model;

[0049] When the product impact force D* is greater than or equal to the second threshold and less than the first threshold, and the user pleasure W is greater than or equal to the first threshold, the coordinate points corresponding to the two elements of the two-dimensional analysis model are displayed in the area representing "liking the product" in the two-dimensional analysis model;

[0050] When the product impact force D* is greater than or equal to the first threshold and the user pleasure W is greater than or equal to the second threshold and less than the first threshold, the coordinate points corresponding to the two elements of the two-dimensional analysis model are displayed in the area representing "interest in the product" in the two-dimensional analysis model;

[0051] When the product impact force D* is greater than or equal to the second threshold and less than the first threshold, and the user pleasure W is greater than or equal to the second threshold and less than the first threshold, the coordinate points corresponding to the two elements of the two-dimensional analysis model are displayed in the area of ​​the two-dimensional analysis model indicating "the product feels ordinary";

[0052] When the product impact force D* is less than the second threshold value and the user pleasure W is greater than or equal to the first threshold value, the coordinate points corresponding to the two elements of the two-dimensional analysis model are displayed in the area of ​​the two-dimensional analysis model indicating "familiarity and satisfaction with the product";

[0053] When the product impact force D* is less than the second threshold value and the user pleasure W is greater than or equal to the second threshold value and less than the first threshold value, the coordinate points corresponding to the two elements of the two-dimensional analysis model are displayed in the area representing "familiarity with the product" in the two-dimensional analysis model;

[0054] When the product impact force D* is less than the second threshold value and the user pleasure W is less than the second threshold value, the coordinate points corresponding to the two elements of the two-dimensional analysis model are displayed in the area of ​​the two-dimensional analysis model indicating "no feeling towards the product";

[0055] When the product impact force D* is greater than or equal to the second threshold and less than the first threshold, and the user pleasure W is less than the second threshold, the coordinate points corresponding to the two elements of the two-dimensional analysis model are displayed in the area representing "dislike for product" in the two-dimensional analysis model;

[0056] When the product impact force D* is greater than or equal to the first threshold and the user pleasure W is less than the second threshold, the coordinate points corresponding to the two elements of the two-dimensional analysis model are displayed in the area representing "strong product stimulation" in the two-dimensional analysis model;

[0057] The first threshold is greater than the second threshold.

[0058] Optionally, the number of preset target users is a first set number; after determining the data values ​​of two elements of the two-dimensional analysis model for product evaluation according to the reference facial micro-expression data and the user facial micro-expression data, and before analyzing the evaluation result of the product according to the data values, the method further includes:

[0059] The target users are re-determined, and the method according to claim 1 is repeated to determine the data value corresponding to each target user until the number of target users reaches the first set number.

[0060] Optionally, the preset number of products is a second set number; after determining the data values ​​of two elements of the two-dimensional analysis model for product evaluation according to the reference facial micro-expression data and the user facial micro-expression data, and before analyzing the evaluation result of the product according to the data values, the method further includes:

[0061] Re-determine the product, and repeat the method as claimed in claim 1 to determine the data value corresponding to each product until the number of products reaches the second set number.

[0062] A second aspect of the present invention discloses a device for product evaluation, the device comprising:

[0063] A memory storing executable program code;

[0064] a processor coupled to the memory;

[0065] The processor calls the executable program code stored in the memory to execute the method for product evaluation disclosed in the first aspect of the present invention.

[0066] A third aspect of the present invention discloses a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and when the computer instructions are called, they are used to execute the method for product evaluation disclosed in the first aspect of the present invention.

[0067] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0068] In the embodiment of the present invention, by determining the target user, the target user's baseline facial micro-expression data is obtained; the user's facial micro-expression data during the time period when the target user tests the product is obtained; based on the baseline facial micro-expression data and the user's facial micro-expression data, the data values ​​of the two elements of the two-dimensional analysis model used for product evaluation are determined, and then the product evaluation results are analyzed based on the data values. It can be seen that the implementation of the present invention can accurately analyze the user's objective feelings about the product in many aspects, and provide a more accurate direction for merchants to optimize their products. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0070] Figure 1 It is a flowchart of a method for product evaluation disclosed in an embodiment of the present invention;

[0071] Figure 2 It is a schematic diagram of a process of acquiring facial video during a test process disclosed in an embodiment of the present invention;

[0072] Figure 3 is a schematic diagram of a two-dimensional analysis model for product evaluation disclosed in an embodiment of the present invention;

[0073] Figure 4 It is a structural schematic diagram of a device for product evaluation disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0074] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings 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.

[0075] The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, device, product or end including a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units inherent to these processes, methods, products or ends.

[0076] 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 invention. The appearance of the phrase in various places 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.

[0077] Embodiment 1

[0078] See also Figure 1 , Figure 1 FIG. 1 is a flow chart of a method for product evaluation disclosed in an embodiment of the present invention. Figure 1 As shown, the method may include:

[0079] Step 101: determine a target user and obtain baseline facial micro-expression data of the target user.

[0080] Optionally, a user recognized by a camera on a mobile device is determined as a target user.

[0081] Optionally, obtaining the target user's baseline facial micro-expression data includes: obtaining pre-stored baseline facial micro-expression data associated with the target user as the target user's baseline facial micro-expression data. In this way, when faced with a project test requirement that requires testing multiple products, the pre-stored information can be directly retrieved to avoid wasting resources and reducing efficiency caused by repeatedly obtaining the target user's baseline facial micro-expression data.

[0082] Optionally, obtaining the target user's baseline facial micro-expression data includes: obtaining the target user's facial micro-expression data during the anchor testing process as the target user's baseline facial micro-expression data; the test environment in which the target user tests the product is the same as the test environment in which the target user tests the anchor; the anchor is determined based on the product category and the evaluation category.

[0083] Here, in actual operation, technical personnel need to select corresponding basic products without additional design as anchors according to product categories and test categories. For example, the fragrance test of daily chemical products uses unscented paper towels as anchors, and the beverage taste test uses drinking warm water as anchors.

[0084] In this way, by obtaining the facial micro-expression data of the target user during the anchor testing process, the accuracy of subsequent analysis results can be improved.

[0085] Optionally, the specific method of obtaining the facial micro-expression data of the target user during the test anchor is: obtaining the video data of the target user testing the anchor, and identifying and processing the facial micro-expression of the video data. In this way, the implementation method of obtaining the user's facial micro-expression data is given.

[0086] Optionally, the evaluation category of the product evaluation is smell, and the facial micro-expression data of the target user during the process of testing the anchor object is obtained, including: obtaining the facial micro-expression data of the target user during the process of using the sense of smell to test the smell of the anchor object; obtaining the user's facial micro-expression data of the time period when the target user tests the product, including: obtaining the user's facial micro-expression data of the time period when the target user uses the sense of smell to test the smell of the product.

[0087] Optionally, the evaluation category of the product evaluation is vision, and the facial micro-expression data of the target user during the process of testing the anchor object is obtained, including: obtaining the facial micro-expression data of the target user during the process of visually testing the appearance of the anchor object; obtaining the user's facial micro-expression data of the time period when the target user tests the product, including: obtaining the user's facial micro-expression data of the time period when the target user uses vision to test the appearance of the product.

[0088] Optionally, the evaluation category of the product evaluation is taste, and the facial micro-expression data of the target user during the process of testing the anchor object is obtained, including: obtaining the facial micro-expression data of the target user during the process of using the taste to test the taste of the anchor object; obtaining the user's facial micro-expression data of the time period when the target user tests the product, including: obtaining the user's facial micro-expression data of the time period when the target user uses the taste to test the taste of the product.

[0089] Optionally, the evaluation category of the product evaluation is auditory, and the facial micro-expression data of the target user during the process of testing the anchor object is obtained, including: obtaining the facial micro-expression data of the target user during the process of using the auditory test to test the sound of the anchor object; obtaining the user's facial micro-expression data during the time period when the target user tests the product, including: obtaining the user's facial micro-expression data during the time period when the target user uses the auditory test to test the sound of the product.

[0090] Optionally, the evaluation category of the product evaluation is touch, and the facial micro-expression data of the target user during the process of testing the anchor object is obtained, including: obtaining the facial micro-expression data of the target user during the process of testing the tactile sensation of the anchor object by using the sense of touch; obtaining the user's facial micro-expression data of the time period when the target user tests the product, including: obtaining the user's facial micro-expression data of the time period when the target user uses the sense of touch to test the tactile sensation of the product.

[0091] In this way, any of the product's smell, appearance, taste, sound, and touch can be evaluated to obtain corresponding evaluation results.

[0092] Step 102: Obtain the user's facial micro-expression data during the time period when the target user tests the product.

[0093] Optionally, a specific method of obtaining the user's facial micro-expression data during the time period when the target user tests the product is: obtaining video data of the target user testing the product, and recognizing and processing the facial micro-expressions in the video data.

[0094] Step 103: Determine the data values ​​of two elements of the two-dimensional analysis model for product evaluation according to the reference facial micro-expression data and the user facial micro-expression data.

[0095] Optionally, the baseline facial micro-expression data and the user facial micro-expression data are sorted into time series results in chronological order, the time series results corresponding to the user facial micro-expression data are the first time series results, and the time series results corresponding to the baseline facial micro-expression data are the second time series results; the two elements of the two-dimensional analysis model are product impact and user pleasure; according to the baseline facial micro-expression data and the user facial micro-expression data, the data values ​​of the two elements of the two-dimensional analysis model are calculated, including: calculating the product impact Where t is the total number of data values ​​in the first time series result, x i is the i-th data value in the first time series result, is the data average of the second time series results; calculate the negative intensity index corresponding to the first type of data and the pleasure intensity index corresponding to the second type of data, and calculate the user pleasure based on the negative intensity index and the pleasure intensity index.

[0096] In the disclosed embodiment, the user pleasure among the elements of the two-dimensional analysis model represents the attractiveness of the product. The higher the pleasure, the higher the liking for the product and the lower the rejection. The product impact among the elements of the two-dimensional analysis model represents the influence of the product on emotions. The stronger the impact, the stronger the product's mobilization of emotions.

[0097] In this way, the use of reference facial data for processing and calculation can effectively eliminate the differences in the individual reference states of the evaluators, making the parameters of different test individuals and different test products comparable. In addition, the test environment and scene in which the evaluator tests the target anchor is the same as the test environment and scene in which the target evaluator tests the target product, which can eliminate the influence of the external environment and scene on the acquired parameters, so that when comparing and statistically analyzing different test individuals and different test products, more objective and accurate analysis results can be obtained.

[0098] Optionally, the hp filtering method is used to smooth and denoise various types of data in each video (video of anchor test and product test).

[0099] Optionally, the first or second time series results are obtained by extracting video frames from the facial video (generally no less than 15 frames per second), and using a facial feature point positioning algorithm based on the Facial Action Coding System (FACS) for the facial images in the video frames, and outputting the facial expression recognition results of each frame of the facial image through modeling analysis, and arranging the recognition results in chronological order of the video frames, which is the time series result.

[0100] Specifically, discrete time series results can be connected and displayed in the form of a curve.

[0101] Optionally, calculating the negative intensity index corresponding to the first type of data and the pleasure intensity index corresponding to the second type of data, and calculating the user pleasure according to the negative intensity index and the pleasure intensity index, including:

[0102] Arrange the first time series results into a negative first sub-time series and a pleasant first sub-time series according to the data type, and arrange the second time series results into a negative second sub-time series and a pleasant second sub-time series according to the data type;

[0103] Calculating Negative Strength Index

[0104] Where e is the total number of data values ​​in the negative first sub-time series results, α i is the i-th data value in the negative first sub-time series result, is the data average of the negative second sub-time series results;

[0105] Calculating the Pleasure Intensity Index

[0106] Among them, r is the total number of data values ​​in the first sub-time series results of pleasure, β i To obtain the i-th data value in the first sub-time series result, The data average of the results of the second sub-time series of pleasure;

[0107] According to the preset conversion rules, the negative intensity index Q is converted into the percentage system Q*, and the pleasure intensity index P is converted into the percentage system P*;

[0108] Calculate the user pleasure, which is the weighted sum of the negative intensity index Q* and the pleasure intensity index P*.

[0109] Preferably, the weight corresponding to the negative intensity index is 0.75, and the weight corresponding to the pleasure intensity index is 0.25.

[0110] Optionally, the weight corresponding to the negative intensity index is 0.5, and the weight corresponding to the pleasant intensity index is 0.5.

[0111] Optionally, the weight corresponding to the negative intensity index is 0.25, and the weight corresponding to the pleasant intensity index is 0.75.

[0112] The preferred and optional weight distribution methods provided by the present invention are only examples. The weight values ​​of the negative intensity index and the pleasure intensity index can be selected according to the actual needs of the tested product, and the present invention does not make specific limitations here.

[0113] Optionally, the preset conversion rule can be:

[0114] If P is less than or equal to 0.05, P* is 0 points;

[0115] If P is greater than 0.05 and less than or equal to 0.5, P* is converted between 0 and 70 points;

[0116] If P is greater than 0.5 and less than or equal to 2, P* is converted between 70-99 points;

[0117] If P is greater than 2, then P* is 100 points;

[0118] If Q is less than or equal to 0.4, P* is 100 points;

[0119] If P is greater than 0.4 and less than or equal to 1, P* is converted between 100-60 points;

[0120] If P is greater than 1 and less than or equal to 2.5, P* is converted between 60 and 0 points;

[0121] If P is greater than 2.5, P* is 0 points.

[0122] In this way, the negative intensity index and pleasure intensity index converted into percentages are obtained, and then the user pleasure is calculated, which is convenient for subsequent analysis in the model.

[0123] Step 104: Analyze the evaluation results of the product according to the data values.

[0124] Here, the data types of the reference facial micro-expression data and the user facial micro-expression data include at least a first type of data indicating negativity and a second type of data indicating pleasure. When performing facial micro-expression analysis on a facial video, at least data corresponding to negative and pleasant emotion types can be identified in each video frame. For example, in the test of olfactory products, the user emotion type can be divided into pleasant emotion and negative emotion, and the specific emotion type can be determined according to the category of the product to be tested and the facial micro-expression recognition result.

[0125] Optionally, analyze the product evaluation results based on the data values, including:

[0126] According to the preset conversion rules, the product impact force D is converted into percentage D*;

[0127] When the product impact D* is greater than or equal to the first threshold and the user pleasure W is greater than or equal to the first threshold, the coordinate points corresponding to the two elements of the two-dimensional analysis model are displayed in the area representing "very attractive" in the two-dimensional analysis model;

[0128] When the product impact D* is greater than or equal to the second threshold and less than the first threshold, and the user pleasure W is greater than or equal to the first threshold, the coordinate points corresponding to the two elements of the two-dimensional analysis model are displayed in the area representing "liking the product" in the two-dimensional analysis model;

[0129] When the product impact D* is greater than or equal to the first threshold and the user pleasure W is greater than or equal to the second threshold and less than the first threshold, the coordinate points corresponding to the two elements of the two-dimensional analysis model are displayed in the area representing "interest in the product" in the two-dimensional analysis model;

[0130] When the product impact force D* is greater than or equal to the second threshold and less than the first threshold, and the user pleasure W is greater than or equal to the second threshold and less than the first threshold, the coordinate points corresponding to the two elements of the two-dimensional analysis model are displayed in the area representing "feeling the product ordinary" in the two-dimensional analysis model;

[0131] When the product impact D* is less than the second threshold and the user pleasure W is greater than or equal to the first threshold, the coordinate points corresponding to the two elements of the two-dimensional analysis model are displayed in the area representing "familiarity and satisfaction with the product" in the two-dimensional analysis model;

[0132] When the product impact D* is less than the second threshold value and the user pleasure W is greater than or equal to the second threshold value and less than the first threshold value, the coordinate points corresponding to the two elements of the two-dimensional analysis model are displayed in the area representing "familiarity with the product" in the two-dimensional analysis model;

[0133] When the product impact D* is less than the second threshold value and the user pleasure W is less than the second threshold value, the coordinate points corresponding to the two elements of the two-dimensional analysis model are displayed in the area representing "no feeling towards the product" in the two-dimensional analysis model;

[0134] When the product impact D* is greater than or equal to the second threshold and less than the first threshold, and the user pleasure W is less than the second threshold, the coordinate points corresponding to the two elements of the two-dimensional analysis model are displayed in the area representing "dislike of the product" in the two-dimensional analysis model;

[0135] When the product impact force D* is greater than or equal to the first threshold and the user pleasure W is less than the second threshold, the coordinate points corresponding to the two elements of the two-dimensional analysis model are displayed in the area representing "strong product stimulation" in the two-dimensional analysis model;

[0136] Here, the first threshold is greater than the second threshold.

[0137] Optionally, according to a preset conversion rule, the specific method of converting the product impact force D into a percentage system D* may be:

[0138] If D is less than or equal to 0.1, D* is 0 points;

[0139] If D is greater than 0.1 and less than or equal to 0.6, D* is converted between 0-30 points;

[0140] If D is greater than 0.6 and less than or equal to 1, D* is converted between 30 and 70 points;

[0141] If D is greater than 1 and less than or equal to 2.5, D* is converted between 70-99 points;

[0142] If D is greater than 2.5, D* is 100 points.

[0143] In this way, combining the two factors of product impact and user pleasure can accurately analyze the user's multi-faceted objective feelings about the product.

[0144] Optionally, the first threshold is 67.

[0145] Optionally, the second threshold is 34.

[0146] Optionally, the number of preset target users is a first set number; after determining the data values ​​of the two elements of the two-dimensional analysis model used for product evaluation based on the baseline facial micro-expression data and the user's facial micro-expression data, and before analyzing the evaluation results of the product based on the data values, the method also includes: re-determining the target users, and repeating the method of claim 1 to determine the data values ​​corresponding to each target user until the number of target users reaches the first set number. In this way, in a product evaluation project, multiple evaluators may be included, and the number of evaluators is the first set number. The evaluation results of all evaluators on a certain product can be displayed simultaneously in the corresponding area of ​​the two-dimensional analysis model, thereby facilitating more complex and in-depth analysis to obtain more accurate analysis results.

[0147] Optionally, the number of products is preset to a second set number; after determining the data values ​​of the two elements of the two-dimensional analysis model for product evaluation based on the baseline facial micro-expression data and the user's facial micro-expression data, and before analyzing the evaluation results of the product based on the data values, the method further includes: re-determining the product, and repeating the method of claim 1 to determine the data values ​​corresponding to each product until the number of products reaches the second set number. In this way, Figure 2 As shown, in the product evaluation project, multiple products belonging to the same category to be evaluated may be included. For example, the daily chemical product smell test may include multiple daily chemical products with different fragrances to be evaluated. During the test, the evaluator performs smell tests on multiple daily chemical products with different fragrances respectively. After all the tests are completed, the test results of multiple tests are simultaneously displayed in the corresponding area of ​​the two-dimensional analysis model, so as to facilitate more complex and in-depth analysis to obtain more accurate analysis results.

[0148] In a specific embodiment, the two-dimensional analysis model for product evaluation is as follows: Figure 3 As shown, based on the analysis of the regions where product 315 , product 490 , and product 628 are located, it is found that the user is familiar with and satisfied with product 315 , likes product 490 , and is interested in product 628 .

[0149] Optionally, after analyzing the evaluation results of the product according to the data value, the method further includes: determining the endpoint values ​​of the weakening interval, the interval without significant change, and the enhancement interval pre-divided into the effect interval according to the baseline facial micro-expression data of the target user; determining the effect interval where the user's facial micro-expression data is located at each moment; calculating one or more of the emotion enhancement intensity index, emotion weakening intensity index, emotion enhancement duration, and emotion weakening duration according to the baseline facial micro-expression data, the user's facial micro-expression data, and the effect interval where the user's facial micro-expression data is located at each moment. In this way, the situation of the evaluator being stimulated by the product during the product test can be understood based on the calculated data, thereby meeting the multi-dimensional analysis needs of the product.

[0150] Optionally, based on the target user's baseline facial micro-expression data, determining the respective interval endpoint values ​​of the pre-divided weakening interval, the no-significant-change interval, and the enhancement interval, including: dividing the second time series results corresponding to the baseline facial micro-expression data into a plurality of second sub-time series results according to the data type, each second sub-time series result including a plurality of data values ​​arranged in chronological order; respectively calculating the average value of the second sub-time series results corresponding to each data type Calculate the standard deviation sd of the second sub-time series results corresponding to each data type respectively; according to the average value corresponding to each data type and standard deviation sd, determine the interval endpoint values ​​of the effect interval corresponding to each data type; among which, the interval with no significant change is: The weakening range is The enhancement interval is

[0151] Optional, emotion enhancement intensity index

[0152] Here, t2 is the total number of data values ​​in the enhanced interval of the first sub-time series result corresponding to this data type, and x 2i is the i-th data value of the first sub-time series result corresponding to this data type in the enhancement interval, The data average value of the second sub-time series results corresponding to this data type;

[0153] The calculation of the emotion reduction intensity index refers to the emotion enhancement intensity index and will not be repeated here.

[0154] Optionally, the data types of the reference facial micro-expression data and the user facial micro-expression data respectively further include a third type of data indicating immersion and a fourth type of data indicating curiosity.

[0155] The method for product evaluation provided by the embodiment of the present disclosure is adopted to obtain the target user's baseline facial micro-expression data by determining the target user; obtain the user's facial micro-expression data during the time period when the target user tests the product; determine the data values ​​of the two elements of the two-dimensional analysis model used for product evaluation based on the baseline facial micro-expression data and the user's facial micro-expression data, and then analyze the product evaluation results based on the data values. It can be seen that the implementation of the present invention can accurately analyze the user's objective feelings about the product in many aspects, and provide a more accurate direction for merchants to optimize their products.

[0156] Embodiment 2

[0157] See also Figure 4 , Figure 4 Schematic diagram of a device for product evaluation disclosed in an embodiment of the present invention. Figure 4 As shown, the device for product evaluation may include:

[0158] A memory 201 storing executable program codes;

[0159] a processor 202 coupled to the memory 201;

[0160] The processor 202 calls the executable program code stored in the memory 201 to execute the steps in the method for product evaluation described in the above embodiment of the present invention.

[0161] Embodiment 3

[0162] An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute the steps in the method for product evaluation described in the above embodiment.

[0163] The device embodiments described above are only illustrative, wherein the modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, i.e., they may be located in one place, or they may be distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative work.

[0164] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0165] Through the specific description of the above embodiments, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the above technical solution can be essentially or partly contributed to the prior art in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, and the storage medium includes a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable rewritable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, a magnetic disk storage, a magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0166] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0167] Finally, it should be noted that the method, device and storage medium for product evaluation disclosed in the embodiments of the present invention are only preferred embodiments of the present invention, which are only used to illustrate the technical solution of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, it should be understood by those skilled in the art that the technical solutions described in the aforementioned embodiments can still be modified, or some of the technical features therein can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for product evaluation, characterized in that: The method comprises: Determine a target user, and obtain baseline facial micro-expression data of the target user; Acquire user facial micro-expression data during the time period when the target user tests the product; Determining data values ​​of two elements of a two-dimensional analysis model for product evaluation according to the reference facial micro-expression data and the user facial micro-expression data; Analyze the evaluation results of the product according to the data value; The data types of the reference facial micro-expression data and the user facial micro-expression data respectively include at least first-type data indicating negativity and second-type data indicating pleasure.

2. The method according to claim 1, characterized in that The step of obtaining the target user's baseline facial micro-expression data comprises: Acquire pre-stored reference facial micro-expression data associated with the target user as the reference facial micro-expression data of the target user; and / or, The facial micro-expression data of the target user during the process of testing the anchor is obtained as the baseline facial micro-expression data of the target user; the test environment in which the target user tests the product is the same as the test environment in which the target user tests the anchor; the anchor is determined according to the category and evaluation category of the product.

3. The method according to claim 2, characterized in that The evaluation category of the product evaluation is smell. The step of obtaining the facial micro-expression data of the target user during the process of testing the anchor object comprises: obtaining the facial micro-expression data of the target user during the process of testing the odor of the anchor object using the sense of smell; The obtaining of the user's facial micro-expression data during the time period when the target user tests the product comprises: obtaining the user's facial micro-expression data during the time period when the target user uses his sense of smell to test the smell of the product; and / or, The evaluation category of the product evaluation is visual. The step of obtaining the facial micro-expression data of the target user during the process of testing the anchor object comprises: obtaining the facial micro-expression data of the target user during the process of visually testing the appearance of the anchor object; The obtaining of the user's facial micro-expression data during the time period when the target user tests the product comprises: obtaining the user's facial micro-expression data during the time period when the target user visually tests the appearance of the product; and / or, The evaluation category of the product evaluation is taste. The step of obtaining the facial micro-expression data of the target user during the process of testing the anchor includes: obtaining the facial micro-expression data of the target user during the process of testing the taste of the anchor using the sense of taste; The obtaining of the user's facial micro-expression data during the time period when the target user tests the product comprises: obtaining the user's facial micro-expression data during the time period when the target user uses taste to test the taste of the product; and / or, The evaluation category of the product evaluation is hearing. The step of obtaining the facial micro-expression data of the target user during the process of testing the anchor includes: obtaining the facial micro-expression data of the target user during the process of testing the sound of the anchor using hearing; The step of obtaining the user's facial micro-expression data during the time period when the target user tests the product includes: obtaining the user's facial micro-expression data during the time period when the target user tests the sound of the product by hearing; and / or, The evaluation category of the product evaluation is touch. The step of obtaining the facial micro-expression data of the target user during the process of testing the anchor object comprises: obtaining the facial micro-expression data of the target user during the process of testing the tactile sensation of the anchor object using the sense of touch; The obtaining of the user's facial micro-expression data during the time period when the target user tests the product includes: obtaining the user's facial micro-expression data during the time period when the target user uses touch to test the tactile sensation of the product.

4. The method according to claim 1, characterized in that The reference facial micro-expression data and the user facial micro-expression data are respectively sorted into time series results in chronological order, the time series results corresponding to the user facial micro-expression data are the first time series results, and the time series results corresponding to the reference facial micro-expression data are the second time series results; the two elements of the two-dimensional analysis model are product impact and user pleasure; The step of calculating the data values ​​of the two elements of the two-dimensional analysis model according to the reference facial micro-expression data and the user facial micro-expression data comprises: Calculate product impact force Where t is the total number of data values ​​in the first time series result, x i is the i-th data value in the first time series result, is the data average value of the second time series results; The negative intensity index corresponding to the first type of data and the pleasure intensity index corresponding to the second type of data are calculated, and the user pleasure is calculated based on the negative intensity index and the pleasure intensity index.

5. The method according to claim 4, characterized in that The calculating the negative intensity index corresponding to the first type of data and the pleasure intensity index corresponding to the second type of data, and calculating the user pleasure according to the negative intensity index and the pleasure intensity index, includes: Arrange the first time series results into a negative first sub-time series and a pleasant first sub-time series according to data type, and arrange the second time series results into a negative second sub-time series and a pleasant second sub-time series according to data type; Calculating Negative Strength Index Where e is the total number of data values ​​in the negative first sub-time series results, α i is the i-th data value in the negative first sub-time series result, is the data average of the negative second sub-time series results; Calculating the Pleasure Intensity Index Where r is the total number of data values ​​in the first sub-time series of pleasure, β i is the i-th data value in the first sub-time series result of the pleasure, is the data average of the results of the second sub-time series of pleasure; According to a preset conversion rule, the negative intensity index Q is converted into a percentage system Q*, and the pleasure intensity index P is converted into a percentage system P*; The user pleasure is calculated, where the user pleasure is a weighted sum of the negative intensity index Q* and the pleasure intensity index P*.

6. The method according to claim 5, characterized in that Analyzing the evaluation result of the product according to the data value includes: According to the conversion rule, the product impact force D is converted into a percentage system D*; When the product impact force D* is greater than or equal to the first threshold and the user pleasure W is greater than or equal to the first threshold, the coordinate points corresponding to the two elements of the two-dimensional analysis model are displayed in the area representing "very attractive" in the two-dimensional analysis model; When the product impact force D* is greater than or equal to the second threshold and less than the first threshold, and the user pleasure W is greater than or equal to the first threshold, the coordinate points corresponding to the two elements of the two-dimensional analysis model are displayed in the area representing "liking the product" in the two-dimensional analysis model; When the product impact force D* is greater than or equal to the first threshold value and the user pleasure W is greater than or equal to the second threshold value and less than the first threshold value, the coordinate points corresponding to the two elements of the two-dimensional analysis model are displayed in the area representing "interest in the product" in the two-dimensional analysis model; When the product impact force D* is greater than or equal to the second threshold and less than the first threshold, and the user pleasure W is greater than or equal to the second threshold and less than the first threshold, the coordinate points corresponding to the two elements of the two-dimensional analysis model are displayed in the area of ​​the two-dimensional analysis model indicating "the product feels ordinary"; When the product impact force D* is less than the second threshold value and the user pleasure W is greater than or equal to the first threshold value, the coordinate points corresponding to the two elements of the two-dimensional analysis model are displayed in the area of ​​the two-dimensional analysis model indicating "familiarity and satisfaction with the product"; When the product impact force D* is less than the second threshold value and the user pleasure W is greater than or equal to the second threshold value and less than the first threshold value, the coordinate points corresponding to the two elements of the two-dimensional analysis model are displayed in the area representing "familiarity with the product" in the two-dimensional analysis model; When the product impact force D* is less than the second threshold value and the user pleasure W is less than the second threshold value, the coordinate points corresponding to the two elements of the two-dimensional analysis model are displayed in the area of ​​the two-dimensional analysis model indicating "no feeling towards the product"; When the product impact force D* is greater than or equal to the second threshold and less than the first threshold, and the user pleasure W is less than the second threshold, the coordinate points corresponding to the two elements of the two-dimensional analysis model are displayed in the area representing "dislike for product" in the two-dimensional analysis model; When the product impact force D* is greater than or equal to the first threshold value and the user pleasure W is less than the second threshold value, the coordinate points corresponding to the two elements of the two-dimensional analysis model are displayed in the area representing "strong product stimulation" in the two-dimensional analysis model; The first threshold is greater than the second threshold.

7. The method according to claim 1, characterized in that The number of target users is preset as a first set number; after determining the data values ​​of the two elements of the two-dimensional analysis model for product evaluation according to the reference facial micro-expression data and the user facial micro-expression data, and before analyzing the evaluation result of the product according to the data values, the method further includes: The target users are re-determined, and the method according to claim 1 is repeated to determine the data value corresponding to each target user until the number of target users reaches the first set number.

8. The method according to claim 1, characterized in that The number of products is preset to be a second set number; after determining the data values ​​of the two elements of the two-dimensional analysis model for product evaluation according to the reference facial micro-expression data and the user facial micro-expression data, and before analyzing the evaluation results of the product according to the data values, the method further includes: Re-determine the product, and repeat the method as claimed in claim 1 to determine the data value corresponding to each product until the number of products reaches the second set number.

9. A device for product evaluation, characterized in that: The device comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the method for product evaluation as described in any one of claims 1-8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and when the computer instructions are called, they are used to execute the method for product evaluation as described in any one of claims 1-8.

Images