Psychological state assessment method and device based on consumption data, equipment and medium

Abstract

The embodiment of the invention provides a psychological state assessment method and device based on consumption data, equipment and a medium, and belongs to the technical field of data processing. The method comprises the following steps: dividing consumer commodities into a plurality of consumer commodity subclasses according to purposes; performing clustering according to the acquired consumption data and each consumption commodity subclass to obtain a target clustering result; determining the consumption structure of the target object as a target consumption level according to the target clustering result; performing relevance inspection on the target consumption level and the psychological dimension feature data, and obtaining relevance strength results of the target consumption level and the psychological dimension feature data; determining the psychological dimension feature data with the highest association strength in each association strength result as target psychological dimension feature data; and determining a psychological state corresponding to the target psychological dimension feature data as a target psychological state. Through the provided scheme, the accurate assessment of the psychological state of the target object is realized through the analysis of the consumption data.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method, device, equipment and medium for evaluating a psychological state based on consumption data. Background Art

[0002] The daily life behaviors of the target objects include some consumption behaviors, including the purchase of daily necessities, food, etc. These consumption behaviors will generate a large amount of data. At present, the evaluation of psychological characteristics mainly relies on psychological methods such as psychological scales and projective tests. However, these methods have certain limitations, such as the possibility of abuse or misinterpretation, and it is impossible to further analyze the psychological characteristics of target objects with different consumption habits through consumption data. Summary of the invention

[0003] In order to solve the above technical problems, the embodiments of the present application provide a method, device, electronic device and medium for evaluating a psychological state based on consumption data.

[0004] In a first aspect, an embodiment of the present application provides a method for evaluating a psychological state based on consumption data, the method comprising: acquiring consumption data of a target object from a cash register device; Divide consumer goods into multiple consumer goods subcategories according to their uses; Clustering is performed according to the consumption data and each of the consumer commodity subcategories to obtain a target clustering result; Determining the consumption structure of the target object as a target consumption level according to the target clustering result; Performing correlation tests on the target consumption level and a plurality of psychological dimension feature data respectively, and obtaining correlation strength results between the target consumption level and each of the psychological dimension feature data respectively; Determine the psychological dimension feature data with the highest correlation strength among the correlation strength results as the target psychological dimension feature data; The psychological state corresponding to the target psychological dimension feature data is determined as the target psychological state of the target object.

[0005] In one embodiment, the consumption proportion data of the target object in each of the consumer commodity subcategories is calculated based on the consumption data; Clustering the consumption proportion data to obtain multiple initial clustering results; A clustering result with the largest silhouette coefficient is determined among the initial clustering results, and the clustering result with the largest silhouette coefficient is used as the target clustering result.

[0006] In one embodiment, the consumption amount of the target object in each of the consumer commodity subcategories and the total consumption amount of the consumer commodity are respectively obtained; The consumption proportion data of the target object in each of the consumer commodity subcategories are obtained respectively according to the total consumption amount and each of the consumption amounts.

[0007] In one implementation, the number of clusters corresponding to the clustering result with the largest silhouette coefficient is determined in each of the initial clustering results; The average consumption proportion of each cluster in each of the consumer commodity subcategories is obtained respectively, and the average consumption proportion of each cluster is used as the target clustering result.

[0008] In one embodiment, variance homogeneity tests are performed on the first preset test group, the second preset test group, and the third preset test group, respectively, and variance test results are obtained, wherein the first preset test group is the average of the consumption proportions of multiple target objects in different target areas on the same consumer commodity subcategory, the second preset test group is the average of the consumption proportions of multiple target objects with different consumption structures in the same target area on the same consumer commodity subcategory, and the third preset test group is the average of the consumption proportions of multiple target objects with the same consumption structure in different target areas on the same consumer commodity subcategory; Performing normal distribution tests on the first preset test group, the second preset test group, and the third preset test group respectively, and obtaining normal distribution test results; Determine whether the variance test result and the normal distribution test result meet the preset parameter test conditions; If the preset parameter inspection condition is met, performing parameter inspection on the first preset inspection group, the second preset inspection group and the third preset inspection group respectively; If the preset parameter test condition is not met, non-parametric tests are performed on the first preset test group, the second preset test group and the third preset test group respectively.

[0009] In one embodiment, if the variance test results are all variance equality results, and the normal distribution test results are all normal distribution results, it is determined that the preset parameter test condition is met; If the variance test result shows that the variances are unequal, or the normal distribution test result shows that the normal distribution does not conform to the normal distribution, it is determined that the preset parameter test condition is not met.

[0010] In one embodiment, the target consumption level includes: a first consumption level and a second consumption level; the first consumption level or the second consumption level is subjected to a chi-square test with each of the psychological dimension feature data to obtain a chi-square test result; A plurality of correlation strength results between the first consumption level or the second consumption level and each of the psychological dimension feature data are determined according to the chi-square test result.

[0011] In a second aspect, an embodiment of the present application provides a psychological state assessment device based on consumption data, the psychological state assessment device based on consumption data comprising: A first acquisition module is used to acquire consumption data of a target object from a cash register device; A classification module, used to classify consumer goods into multiple consumer goods subcategories according to their uses; A clustering module, used for clustering the consumption data and each of the consumer commodity subcategories to obtain a target clustering result; A first determination module, configured to determine the consumption structure of the target object as a target consumption level according to the target clustering result; A verification module, used to perform correlation tests on the target consumption level and a plurality of psychological dimension feature data, respectively, to obtain correlation strength results between the target consumption level and each of the psychological dimension feature data; A second acquisition module is used to determine the psychological dimension feature data with the highest association strength among the association strength results as the target psychological dimension feature data; The second determination module is used to determine the psychological state corresponding to the target psychological dimension feature data as the target psychological state of the target object.

[0012] In a third aspect, an embodiment of the present application provides an electronic device including a memory and a processor, wherein the memory is used to store a computer program, and when the computer program is run by the processor, the method for assessing a psychological state based on consumption data provided in the first aspect is executed.

[0013] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium storing a computer program, which, when running on a processor, executes the method for assessing a psychological state based on consumption data provided in the first aspect.

[0014] The above-mentioned psychological state assessment method, device, electronic device and medium based on consumption data provided by the present application obtain the consumption data of the target object from the cash register device; divide the consumer goods into multiple consumer goods subcategories according to their uses; cluster the consumption data and each of the consumer goods subcategories to obtain the target clustering results; determine the consumption structure of the target object as the target consumption level according to the target clustering results; perform correlation tests on the target consumption level with multiple psychological dimension feature data respectively, and obtain the correlation strength results between the target consumption level and each of the psychological dimension feature data respectively; determine the psychological dimension feature data with the highest correlation strength in each of the correlation strength results as the target psychological dimension feature data; determine the psychological state corresponding to the target psychological dimension feature data as the target psychological state of the target object. The present application obtains and analyzes the consumption data of the target object, obtains the consumption structure of the target object by clustering the consumption data and consumer goods, and determines the target psychological state of the target object by obtaining the correlation strength results of the consumption structure and the psychological dimension feature data, thereby improving the pertinence of the psychological interference provided to the target object and increasing the effectiveness and timeliness of the psychological state assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solution of the present application, the following is a brief introduction to the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present application and should not be regarded as limiting the scope of protection of the present application. In each of the drawings, similar components are numbered similarly.

[0016] Figure 1 A schematic diagram of a process of a method for evaluating a psychological state based on consumption data provided in an embodiment of the present application is shown; Figure 2 Another schematic diagram of the process of the psychological state assessment method based on consumption data provided in an embodiment of the present application is shown; Figure 3 A schematic diagram of a structure of a psychological state assessment device based on consumption data provided in an embodiment of the present application is shown; Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application is shown.

[0017] Icons: 300 - mental state assessment device based on consumption data, 301 - first acquisition module, 302 - division module, 303 - clustering module, 304 - first determination module, 305 - verification module, 306 - second acquisition module, 307 - second determination module, 400 - electronic device, 401 - transceiver, 402 - processor, 403 - memory. DETAILED DESCRIPTION

[0018] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments.

[0019] The components of the embodiments of the present application generally described and shown in the drawings herein may be arranged and designed in various configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0020] Hereinafter, the terms "including", "having" and their cognates, which may be used in various embodiments of the present application, are intended only to indicate specific features, numbers, steps, operations, elements, components, or combinations of the foregoing items, and should not be understood as first excluding the existence of one or more other features, numbers, steps, operations, elements, components, or combinations of the foregoing items or adding the possibility of one or more features, numbers, steps, operations, elements, components, or combinations of the foregoing items.

[0021] Furthermore, the terms “first”, “second”, “third”, etc. are merely used for distinguishing descriptions and are not to be understood as indicating or implying relative importance.

[0022] Unless otherwise defined, all terms (including technical terms and scientific terms) used herein have the same meanings as those generally understood by those skilled in the art to which the various embodiments of the present application belong. The terms (such as those defined in generally used dictionaries) will be interpreted as having the same meanings as the contextual meanings in the relevant technical field and will not be interpreted as having idealized meanings or overly formal meanings unless clearly defined in the various embodiments of the present application.

[0023] Example 1 At present, psychological methods such as psychological scales and projective tests are mainly used to obtain the psychological state of the target object, but these methods have certain limitations, such as possible abuse or misinterpretation. Although psychological scales can quantitatively evaluate the psychological state of the target object, their results are often affected by the subject's tendency to conceal, and it is difficult to fully and truly reflect their psychological state. Although projective tests can reveal the subconscious content of the subjects, their interpretation is often subjective and easily affected by the personal experience and prejudice of the assessor. Therefore, the embodiment of the present application provides a method for evaluating the psychological state based on consumption data.

[0024] See also Figure 1 , psychological state assessment methods based on consumption data include: S101, obtaining consumption data of a target object from a cash register device.

[0025] In this embodiment, the target object is a supervision object. In other embodiments, the target object may be a consumer user corresponding to different application scenarios, such as a shopping mall customer, etc. This application does not limit this.

[0026] S102, dividing the consumer goods into a plurality of consumer goods subcategories according to usage.

[0027] Collect consumption data of target objects in different target areas, and divide consumer goods into multiple subcategories according to their uses.

[0028] It should be noted that the following field data are obtained from supermarkets in different target areas: target object number, order time, single order amount and purchased commodity category, as shown in Table 1: Table 1 Target object purchase commodity information table

[0029] In this embodiment, common consumer goods are classified into nine categories according to their uses, as shown in Table 2. In other embodiments, common consumer goods may be classified according to their basic attributes or other standards, which are not limited here.

[0030] Table 2 Example of some product categories

[0031] S103: Clustering is performed according to the consumption data and each of the consumer commodity subcategories to obtain a target clustering result.

[0032] In one embodiment of the present application, Figure 2 As shown, S1031, calculate the consumption proportion data of the target object in each of the consumer commodity subcategories according to the consumption data. S1032, cluster the consumption proportion data to obtain multiple initial clustering results. S1033, determine the clustering result with the largest silhouette coefficient in each of the initial clustering results, and use the clustering result with the largest silhouette coefficient as the target clustering result.

[0033] It should be understood that after obtaining the consumption proportion data of each target object in each subcategory of consumer goods, the consumption proportion of each category is used as a feature to form a consumption proportion data set, and the consumption proportion data set is clustered to obtain multiple cluster initial clustering results, calculate the silhouette coefficient of each cluster, and select the clustering result with the largest silhouette coefficient as the target clustering result.

[0034] It is further understood that the purpose of the clustering algorithm is to divide the objects in the data set into several clusters, so that the similarity of objects in the same cluster is high, while the similarity of objects between different clusters is low. The silhouette coefficient measures the compactness within the cluster and the separation between clusters, and the value ranges from -1 to 1. A higher silhouette coefficient indicates that the points inside the cluster are closer to each other and farther away from the points in other clusters, reflecting a better clustering effect. In an embodiment of the present application, clustering is performed using a k-means algorithm (k-means clustering algorithm). In other embodiments, a clustering algorithm such as a hierarchical clustering algorithm can be used to cluster the consumption proportion data set to obtain a clustering result. The clustering algorithm is not limited here.

[0035] In another embodiment of the present application, the consumption amount of the target object in each of the consumer commodity subcategories and the total consumption amount of the consumer commodities are obtained respectively; and the consumption proportion data of the target object in each of the consumer commodity subcategories are obtained respectively based on the total consumption amount and each consumption amount.

[0036] It should be noted that the total amount of consumption of each target object on the nine categories of goods is obtained to calculate the consumption proportion of each target object on each category of goods. The consumption proportion data is obtained by dividing the consumption amount of the target object on the category of goods by the total consumption amount of the target object.

[0037] For example, the target object's total consumption on nine categories of goods is 100 yuan, and the consumption on daily necessities is 20 yuan. The consumption share data is the daily necessities consumption 20 / total consumption 100, and the target object's consumption share data on daily necessities is 0.2.

[0038] In another embodiment of the present application, the number of clusters corresponding to the clustering result with the largest silhouette coefficient is determined in each of the initial clustering results; the average consumption share of each cluster in each of the consumer commodity subcategories is obtained respectively, and the average consumption share of each cluster is used as a class portrait, and the class portrait is used as the target clustering result.

[0039] It should be noted that the number of clusters corresponding to the clustering result with the largest silhouette coefficient is determined, and then the mean consumption share corresponding to the corresponding number of clusters is calculated, where the mean consumption share is obtained by dividing the sum of the consumption shares of all target objects in each cluster on various commodities by the total number of target objects in the cluster.

[0040] For example, there are 10 target subjects in the first cluster, and the total share of daily necessities consumption of these 10 target subjects is 0.5. Divide 0.5 by 10, and the average share of daily necessities consumption in the first cluster is 0.05.

[0041] The above method uses the average consumption share of each cluster in each subcategory of consumer goods as a class portrait, thereby generalizing the unique consumption share of each target object to the consumption share of the cluster, simplifying complex data, facilitating the analysis of consumption data, and obtaining the consumption preferences of each target object, thus making preparations for preliminary data processing for the subsequent division of consumption structure.

[0042] S104: Determine the consumption structure of the target object as a target consumption level according to the target clustering result.

[0043] It should be noted that by calculating the mean consumption proportion of each consumer commodity subcategory and analyzing it, the consumption structure of the target object is classified according to the mean consumption proportion of each consumer commodity subcategory according to the clustering result. For example, the consumption structure of the target object is roughly divided into basic demand type (daily necessities, clothing and bedding account for a high proportion, and convenience foods, beverages, condiments, and cigarettes account for a low proportion) and desire satisfaction type (convenience foods, beverages, and condiments account for a high proportion, and daily necessities account for a low proportion). As shown in Tables 3 and 4, the total mean consumption proportion of each consumer commodity subcategory under each consumption structure is 1, and the selected target clustering result is determined by the obtained silhouette coefficient.

[0044] Table 3 Clustering results analysis 1

[0045] Table 4 Clustering results analysis 2

[0046] In one embodiment, a variance homogeneity test is performed on the first preset test group, the second preset test group and the third preset test group respectively, and a variance test result is obtained, wherein the first preset test group is the mean consumption proportion of multiple target objects in different target areas on the same consumer commodity subcategory, the second preset test group is the mean consumption proportion of multiple target objects with different consumption structures in the same target area on the same consumer commodity subcategory, and the third preset test group is the mean consumption proportion of multiple target objects with the same consumption structure in different target areas on the same consumer commodity subcategory; a normal distribution test is performed on the first preset test group, the second preset test group and the third preset test group respectively, and a normal distribution test result is obtained; it is determined whether the variance test result and the normal distribution test result meet the preset parameter test condition; if the preset parameter test condition is met, a parameter test is performed on the first preset test group, the second preset test group and the third preset test group respectively; if the preset parameter test condition is not met, a non-parametric test is performed on the first preset test group, the second preset test group and the third preset test group respectively.

[0047] In an embodiment of the present application, for example: if the first preset inspection group is the average consumption ratio of daily necessities of 5 target objects in target area A and 5 target objects in target area B; the second preset inspection group is the average consumption ratio of daily necessities of 5 desire-satisfied target objects in target area A and 5 basic-needs target objects in target area A; the third preset inspection group is the average consumption ratio of daily necessities of 5 desire-satisfied target objects in target area A and 5 basic-needs target objects in target area B.

[0048] A variance homogeneity test is performed on the first preset test group, the second preset test group, and the third preset test group, respectively, to obtain a variance test result; a normal distribution test is performed on the first preset test group, the second preset test group, and the third preset test group, respectively, to obtain a normal distribution test result. It should be understood that the process order of the variance homogeneity test and the normal distribution test can be permuted, and the specific order is not limited here.

[0049] It should be noted that by testing the first preset test group and the third preset test group, a foundation is laid for subsequent research on differences between different units. By testing the second preset test group, it is determined whether there are statistically significant differences in the classification results obtained by the test clustering, and then whether the classification is reasonable.

[0050] In one embodiment, if the variance test results are all equal variance results, and the normal distribution test results are all results that conform to the normal distribution, it is determined that the preset parameter test condition is met; if the variance test results have unequal variance results, or the normal distribution test results have results that do not conform to the normal distribution, it is determined that the preset parameter test condition is not met.

[0051] It should be noted that if the variance test results of the first preset test group, the second preset test group, and the third preset test group are all equal variance results, and the normal distribution test results of the first preset test group, the second preset test group, and the third preset test group are all in accordance with the normal distribution, it is determined that the preset parameter test conditions are met and the parameter test is used; If any variance test result of the first preset test group, the second preset test group and the third preset test group has an unequal variance result, or any normal distribution test result of the first preset test group, the second preset test group and the third preset test group does not conform to the normal distribution result, a non-parametric test is used.

[0052] In this embodiment, the Levene's variance homogeneity test method is used for variance test, the Shapiro-Wilk test method is used for normal distribution test, the t-test method is used for parameter test, and the Mann-Whitney U test method and the Wilcoxon signed-rank test method are used for non-parametric test. In other embodiments, other test methods can be used for corresponding tests, which are not limited to this.

[0053] S105, performing correlation tests on the target consumption level and a plurality of psychological dimension feature data respectively, and obtaining correlation strength results between the target consumption level and each of the psychological dimension feature data respectively.

[0054] In one embodiment, the target consumption level includes: a first consumption level and a second consumption level; performing a chi-square test on the first consumption level or the second consumption level and each of the psychological dimension feature data to obtain a chi-square test result; and determining a plurality of correlation strength results between the first consumption level or the second consumption level and each of the psychological dimension feature data based on the chi-square test result.

[0055] In this embodiment, the first consumption level is basic demand-based consumption, and the second consumption level is desire-satisfaction-based consumption. In other embodiments, the consumption structure of the target object may be classified according to the consumption type, and this application does not make any limitation here.

[0056] It should be understood that after performing variance test and normal distribution test on the preset test group, the test result data is obtained. If there is a significant difference in the test result data after parameter test or non-parametric test, the target test result is determined to be a test failure result, and the collected consumption data needs to be re-clustered and analyzed to obtain a new mean consumption share and then re-tested.

[0057] If there is no significant difference in the test result data, the target test result is determined to be a passed test result, and a chi-square test is performed on the basic need consumption or desire satisfaction consumption and the characteristic data of each psychological dimension.

[0058] S106, determining the psychological dimension feature data with the highest association strength among the association strength results as the target psychological dimension feature data.

[0059] It should be noted that the chi-square test is used to statistically calculate the degree of deviation between basic need consumption or desire satisfaction consumption and the characteristic data of each psychological dimension. The degree of deviation determines the size of the chi-square value. If the chi-square value is larger, the deviation between the two is greater; conversely, the deviation between the two is smaller; if the two values ​​are completely equal, the chi-square value is 0, indicating that basic need consumption or desire satisfaction consumption is completely consistent with the characteristic data of each psychological dimension, that is, the smaller the chi-square value, the lower the correlation between the consumption structure type and the characteristic data of the psychological dimension.

[0060] In this embodiment, firstly, two types of consumption, basic need type and desire satisfaction type, are obtained through clustering results, and then they are divided according to the corresponding thresholds of the scale scores of the target objects to determine the psychological dimensions of the target objects (1 for yes and 0 for no), as shown in Table 5.

[0061] Table 5 Clustering threshold division table

[0062] It is further noted that the numbers in Table 5 are example numbers used for explanation. This application conducts a chi-square test by using consumption type and psychological characteristics (such as borderline personality disorder). If the chi-square value is large, it means that the gap between the observed value and the theoretical expected value is large, and the correlation between the consumption type and the psychological characteristics is strong. If the chi-square value is small, it means that the difference between the observed value and the expected value is small, and the correlation between the consumption type and the psychological characteristics is weak.

[0063] This application can more accurately assess the psychological state of the target object by analyzing its consumption behavior in the target area. Compared with traditional methods, this data-driven method may be more objective and reduce the influence of human factors. In addition, this application monitors the changes in the psychological state of the target object in real time by regularly collecting consumption data, which increases the possibility of timely discovering and dealing with potential psychological problems.

[0064] S107, determining the psychological state corresponding to the target psychological dimension feature data as the target psychological state of the target object.

[0065] It should be understood that multiple chi-square values ​​between basic demand consumption and desire satisfaction consumption and each psychological dimension feature data are obtained respectively, and the minimum chi-square value is determined among each chi-square value, that is, the psychological dimension feature data with the highest correlation is determined. And the corresponding psychological state is determined according to the psychological dimension feature data.

[0066] It should be noted that after obtaining the psychological state of the target object, the psychological state of the target object can be tracked and evaluated based on the target object's consumption data. More targeted psychological intervention and transformation plans can be provided for different types of target objects, thereby improving the correction effect.

[0067] In one embodiment, the consumption structures of basic needs and desire satisfaction can be further clustered, and the optimal clustering result can be obtained according to the maximum silhouette coefficient. The basic needs can be further divided into three subclasses, and the desire satisfaction can be further divided into two subclasses.

[0068] The three sub-types of basic needs include: the type with a high proportion of daily necessities consumption, the type with a high proportion of clothing and bedding consumption, and the type with a high proportion of food consumption; the two sub-types of desire satisfaction include: the type with a high proportion of tobacco consumption, and the type with a high proportion of food consumption. The specific data are shown in Table 6: Table 6: Clustering results analysis 3

[0069] The differences in psychological dimensions between the basic needs subtype and the desire satisfaction subtype were tested again. The only psychological dimension in which the two desire satisfaction subtypes had significant differences at the 99% confidence interval was somatic symptoms (p=0.0054), and the desire satisfaction subtype was less likely to have somatic symptoms. The basic needs subtypes had significant differences in psychological characteristics at the 99% confidence interval.

[0070] The details are shown in Table 7: Table 7: Psychological state analysis table

[0071] The present embodiment provides a method for evaluating a psychological state based on consumption data. The present application obtains and analyzes the consumption data of a target object, clusters the consumption data and consumer goods to obtain the consumption structure of the target object, and determines the target psychological state of the target object by obtaining the correlation strength result between the consumption structure and the psychological dimension feature data, thereby improving the targeted nature of the psychological interference provided to the target object and increasing the effectiveness and timeliness of the psychological state evaluation.

[0072] Example 2 In addition, an embodiment of the present application provides a psychological state assessment device based on consumption data.

[0073] like Figure 3 As shown, the mental state assessment device 300 based on consumption data includes: The first acquisition module 301 is used to acquire the consumption data of the target object from the cash register device; A classification module 302 is used to classify consumer goods into multiple consumer goods subcategories according to usage; A clustering module 303 is used to perform clustering according to the consumption data and each of the consumer commodity subcategories to obtain a target clustering result; A first determination module 304, configured to determine the consumption structure of the target object as a target consumption level according to the target clustering result; A verification module 305 is used to perform correlation tests on the target consumption level and a plurality of psychological dimension feature data, respectively, to obtain correlation strength results between the target consumption level and each of the psychological dimension feature data; A second acquisition module 306 is used to determine the psychological dimension feature data with the highest association strength among the association strength results as the target psychological dimension feature data; The second determination module 307 is used to determine the psychological state corresponding to the target psychological dimension feature data as the target psychological state of the target object.

[0074] The mental state assessment device 300 based on consumption data provided in this embodiment can implement the mental state assessment method based on consumption data provided in Embodiment 1, and will not be described again here to avoid repetition.

[0075] The present embodiment provides a psychological state assessment device based on consumption data. The present application obtains and analyzes the consumption data of the target object, obtains the consumption structure of the target object by clustering the consumption data and consumer goods, and determines the target psychological state of the target object by obtaining the correlation strength result between the consumption structure and the psychological dimension feature data, thereby improving the targeted nature of the psychological interference provided to the target object and increasing the effectiveness and timeliness of the psychological state assessment.

[0076] Example 3 In addition, an embodiment of the present application provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and when the computer program runs on the processor, the method for evaluating a psychological state based on consumption data provided in Example 1 is executed.

[0077] For details, see Figure 4 The electronic device 400 includes: a transceiver 401, a bus interface and a processor 402, wherein the processor 402 is used to: obtain consumption data of a target object from a cash register; divide consumer goods into multiple consumer goods subcategories according to their uses; cluster the consumption data and each of the consumer goods subcategories to obtain a target clustering result; determine the consumption structure of the target object as a target consumption level according to the target clustering result; perform a correlation test on the target consumption level and multiple psychological dimension feature data respectively, and obtain the correlation strength results between the target consumption level and each of the psychological dimension feature data respectively; determine the psychological dimension feature data with the highest correlation strength in each of the correlation strength results as the target psychological dimension feature data; determine the psychological state corresponding to the target psychological dimension feature data as the target psychological state of the target object.

[0078] In one embodiment, the processor 402 is also used to: calculate the consumption proportion data of the target object in each of the consumer commodity subcategories based on the consumption data; cluster each of the consumption proportion data to obtain multiple initial clustering results; determine the clustering result with the largest silhouette coefficient in each of the initial clustering results, and use the clustering result with the largest silhouette coefficient as the target clustering result.

[0079] In one embodiment, the processor 402 is further used to: respectively obtain the consumption amount of the target object in each of the consumer commodity subcategories and the total consumption of the consumer commodities; and respectively obtain the consumption proportion data of the target object in each of the consumer commodity subcategories based on the total consumption and each consumption amount.

[0080] In one embodiment, the processor 402 is also used to: determine the number of clusters corresponding to the clustering result with the largest silhouette coefficient in each of the initial clustering results; obtain the average consumption share of each cluster in each of the consumer commodity subcategories, and use the average consumption share of each cluster as the target clustering result.

[0081] In one embodiment, the processor 402 is also used to: perform variance homogeneity tests on the first preset test group, the second preset test group, and the third preset test group, respectively, and obtain variance test results, wherein the first preset test group is the average consumption share of multiple target objects in different target areas on the same consumer commodity subcategory, the second preset test group is the average consumption share of multiple target objects with different consumption structures in the same target area on the same consumer commodity subcategory, and the third preset test group is the average consumption share of multiple target objects with the same consumption structure in different target areas on the same consumer commodity subcategory; perform normal distribution tests on the first preset test group, the second preset test group, and the third preset test group, respectively, and obtain normal distribution test results; determine whether the variance test results and the normal distribution test results meet the preset parameter test conditions; if the preset parameter test conditions are met, perform parameter tests on the first preset test group, the second preset test group, and the third preset test group, respectively; if the preset parameter test conditions are not met, perform non-parametric tests on the first preset test group, the second preset test group, and the third preset test group, respectively.

[0082] In one embodiment, the processor 402 is further used to: if the variance test results are all equal variance results, and the normal distribution test results are all conforming to the normal distribution results, then determine that the preset parameter test conditions are met; if the variance test results have unequal variance results, or the normal distribution test results have results that do not conform to the normal distribution, then determine that the preset parameter test conditions are not met.

[0083] In one embodiment, the processor 402 is also used for: the target consumption level includes a first consumption level and a second consumption level; performing a chi-square test on the first consumption level or the second consumption level and each of the psychological dimension feature data to obtain a chi-square test result; and determining a plurality of the association strength results between the first consumption level or the second consumption level and each of the psychological dimension feature data based on the chi-square test result.

[0084] In the embodiment of the present application, the electronic device 400 further includes a memory 403. Figure 4 In the embodiment, the bus architecture may include any number of interconnected buses and bridges, specifically connecting various circuits of one or more processors represented by processor 402 and memory represented by memory 403. The bus architecture may also connect various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. The bus interface provides an interface. The transceiver 401 may be a plurality of components, i.e., including a transmitter and a receiver, providing a unit for communicating with various other devices on a transmission medium. The processor 402 is responsible for managing the bus architecture and general processing, and the memory 403 may store data used by the processor 402 when performing operations.

[0085] The electronic device 400 provided in the embodiment of the present application can execute the steps of the psychological state assessment method based on consumption data provided in the above method embodiment 4, which will not be described again here to avoid repetition.

[0086] The electronic device provided in this embodiment obtains and analyzes the consumption data of the target object, obtains the consumption structure of the target object by clustering the consumption data and consumer goods, and determines the target psychological state of the target object by obtaining the correlation strength results between the consumption structure and the psychological dimension feature data, thereby improving the targeted nature of the psychological interference provided to the target object and increasing the effectiveness and timeliness of the psychological state assessment.

[0087] Example 4 The present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method for evaluating a psychological state based on consumption data provided in Example 1 is implemented.

[0088] In this embodiment, the computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0089] The computer-readable storage medium provided in this embodiment can implement the psychological state assessment method based on consumption data provided in Example 1, and will not be described again here to avoid repetition.

[0090] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal 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, article or terminal. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or terminal including the element.

[0091] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0092] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

Claims

1. A method for evaluating psychological state based on consumption data, characterized in that: Applied to a computer device, the method comprises: Obtain consumption data of the target object from the cash register device; Divide consumer goods into multiple consumer goods subcategories according to their uses; Clustering is performed according to the consumption data and each of the consumer commodity subcategories to obtain a target clustering result; Determining the consumption structure of the target object as a target consumption level according to the target clustering result; Performing correlation tests on the target consumption level and a plurality of psychological dimension feature data respectively, and obtaining correlation strength results between the target consumption level and each of the psychological dimension feature data respectively; Determine the psychological dimension feature data with the highest correlation strength among the correlation strength results as the target psychological dimension feature data; The psychological state corresponding to the target psychological dimension feature data is determined as the target psychological state of the target object.

2. The method for evaluating psychological state based on consumption data according to claim 1, characterized in that: The clustering according to the consumption data and each of the consumer commodity subcategories to obtain a target clustering result includes: Calculate the consumption proportion data of the target object in each of the consumer commodity subcategories according to the consumption data; Clustering the consumption proportion data to obtain multiple initial clustering results; A clustering result with the largest silhouette coefficient is determined among the initial clustering results, and the clustering result with the largest silhouette coefficient is used as the target clustering result.

3. The method for evaluating psychological state based on consumption data according to claim 2, characterized in that: The calculating, based on the consumption data, the consumption proportion data of the target object in each of the consumer commodity subcategories includes: Respectively obtaining the consumption amount of the target object in each of the consumer commodity subcategories and the total consumption amount of the consumer commodity; The consumption proportion data of the target object in each of the consumer commodity subcategories are obtained respectively according to the total consumption amount and each of the consumption amounts.

4. The method for evaluating psychological state based on consumption data according to claim 3, characterized in that: The step of determining a clustering result with a maximum silhouette coefficient among the initial clustering results, and taking the clustering result with the maximum silhouette coefficient as the target clustering result, comprises: Determine the number of clusters corresponding to the clustering result with the largest silhouette coefficient in each of the initial clustering results; The average consumption proportion of each cluster in each of the consumer commodity subcategories is obtained respectively, and the average consumption proportion of each cluster is used as the target clustering result.

5. The method for evaluating psychological state based on consumption data according to claim 1, characterized in that: The step of performing correlation tests on the target consumption level and a plurality of psychological dimension feature data respectively includes: Performing variance homogeneity tests on the first preset test group, the second preset test group, and the third preset test group respectively, and obtaining variance test results, wherein the first preset test group is the average of the consumption proportions of multiple target objects in different target areas on the same consumer commodity subcategory, the second preset test group is the average of the consumption proportions of multiple target objects with different consumption structures in the same target area on the same consumer commodity subcategory, and the third preset test group is the average of the consumption proportions of multiple target objects with the same consumption structure in different target areas on the same consumer commodity subcategory; Performing normal distribution tests on the first preset test group, the second preset test group, and the third preset test group respectively, and obtaining normal distribution test results; Determine whether the variance test result and the normal distribution test result meet the preset parameter test conditions; If the preset parameter inspection condition is met, performing parameter inspection on the first preset inspection group, the second preset inspection group and the third preset inspection group respectively; If the preset parameter test condition is not met, non-parametric tests are performed on the first preset test group, the second preset test group and the third preset test group respectively.

6. The method for evaluating psychological state based on consumption data according to claim 5, characterized in that: The determining whether the variance test result and the normal distribution test result meet the preset parameter test conditions includes: If the variance test results are all equal variance results, and the normal distribution test results are all normal distribution results, it is determined that the preset parameter test condition is met; If the variance test result shows that the variances are unequal, or the normal distribution test result shows that the normal distribution does not conform to the normal distribution, it is determined that the preset parameter test condition is not met.

7. The method for evaluating psychological state based on consumption data according to claim 5, characterized in that: The target consumption level includes: a first consumption level and a second consumption level; The step of respectively obtaining the correlation strength results between the target consumption level and each of the psychological dimension feature data includes: Performing a chi-square test on the first consumption level or the second consumption level and each of the psychological dimension feature data to obtain a chi-square test result; A plurality of correlation strength results between the first consumption level or the second consumption level and each of the psychological dimension feature data are determined according to the chi-square test result.

8. A psychological state assessment device based on consumption data, characterized in that: The device comprises: A first acquisition module is used to acquire consumption data of a target object from a cash register device; A classification module, used to classify consumer goods into multiple consumer goods subcategories according to their uses; A clustering module, used for clustering the consumption data and each of the consumer commodity subcategories to obtain a target clustering result; A first determination module, configured to determine the consumption structure of the target object as a target consumption level according to the target clustering result; A verification module, used to perform correlation tests on the target consumption level and a plurality of psychological dimension feature data, respectively, to obtain correlation strength results between the target consumption level and each of the psychological dimension feature data; A second acquisition module is used to determine the psychological dimension feature data with the highest association strength among the association strength results as the target psychological dimension feature data; The second determination module is used to determine the psychological state corresponding to the target psychological dimension feature data as the target psychological state of the target object.

9. An electronic device, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program, and when the computer program is run on the processor, the method for evaluating a psychological state based on consumption data according to any one of claims 1 to 7 is executed.

10. A computer-readable storage medium, characterized in that: The computer program stores a computer program, which, when running on a processor, executes the method for evaluating a psychological state based on consumption data as claimed in any one of claims 1 to 7.

Images