Human-computer interaction method and device, equipment, system and storage medium

Abstract

The invention provides a man-machine interaction method and device, equipment, a system and a storage medium, and belongs to the technical field of man-machine interaction, and the method comprises the steps: determining the preference degree of a target user for different target commodities based on the residence time and historical purchase records of the target user, the target commodity is the commodity sold by the vending machine, and the staying time is the staying time of the sight of the target user in different target commodity display areas; updating the preference degrees based on the inventory states of the different target commodities to obtain recommendation priorities of the different target commodities; and sorting and displaying the target commodities based on the recommendation priorities or the historical purchase frequencies of the target commodities. According to the man-machine interaction method, device, equipment and system and the storage medium provided by the invention, the shopping experience of the user can be improved.

Description

Technical Field

[0001] The present disclosure belongs to the technical field of human - machine interaction, and more specifically, relates to a human - machine interaction method, device, equipment, system, and storage medium. Background Art

[0002] In the current application scenario of vending machines, with the development of technology and the improvement of user requirements, it is expected that vending machines can provide a more intelligent and convenient interaction experience. Traditional human - machine interaction methods have deficiencies.

[0003] The product recommendation of traditional vending machines lacks pertinence and cannot effectively meet the personalized needs of users. When users select products, they often need to browse a large number of products by themselves, consuming time and energy, affecting the user's willingness to purchase, and resulting in a poor shopping experience for users. Summary of the Invention

[0004] The purpose of the present disclosure is to provide a human - machine interaction method, device, equipment, system, and storage medium to improve the user's shopping experience.

[0005] In the first aspect of the embodiments of the present disclosure, a human - machine interaction method for a vending machine is provided, including: Based on the residence time of the target user and the historical purchase record, determine the preference degrees of the target user for different target products, where the target user is the user interacting with the vending machine, the target products are the products sold by the vending machine, and the residence time is the residence time of the target user's line of sight in different target product display areas; Update the preference degrees based on the inventory status of different target products to obtain the recommended priorities of different target products; Sort and display the target products based on the recommended priorities.

[0006] In the second aspect of the embodiments of the present disclosure, a human - machine interaction device for a vending machine is provided, including: A preference degree calculation module for determining the preference degrees of the target user for different target products based on the residence time of the target user and the historical purchase record, where the target user is the user interacting with the vending machine, the target products are the products sold by the vending machine, and the residence time is the residence time of the target user's line of sight in different target product display areas; A priority calculation module for updating the preference degrees based on the inventory status of different target products to obtain the recommended priorities of different target products; A product display module for sorting and displaying the target products based on the recommended priorities.

[0007] In a third aspect of the embodiments of the present disclosure, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of the above-mentioned human-computer interaction method are implemented.

[0008] In a fourth aspect of the embodiments of the present disclosure, an electronic device is provided, including: a display unit, an image acquisition unit, and an electronic device; The display unit is used to display the target commodity; The image acquisition unit is used to acquire the behavior data and portrait data of the target user; The electronic device includes a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of the above-mentioned human-computer interaction method are implemented.

[0009] In a fifth aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned human-computer interaction method are implemented.

[0010] The beneficial effects of a human-computer interaction method, device, equipment, system, and storage medium provided by the embodiments of the present disclosure are as follows: By analyzing the residence time of the target user and historical purchase records, the embodiments of the present disclosure accurately grasp the user preferences and provide personalized commodity recommendations. The preference degree is updated in combination with the commodity inventory status to determine the recommendation priority, effectively avoiding recommending out-of-stock commodities and ensuring the smoothness of the shopping process. The commodities are sorted and displayed according to the recommendation priority or historical purchase frequency. If the commodities are sorted and displayed based on the recommendation priority, the commodities that match the current user interests can be highlighted; if the commodities are sorted and displayed according to the historical purchase frequency, the popular choices of the public can be shown. Overall, the human-computer interaction process of the vending machine is optimized, the user satisfaction is enhanced, and the operation efficiency is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the following drawings are only some embodiments of the present disclosure. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0012] Figure 1 It is a flowchart of a human-computer interaction method provided by an embodiment of the present disclosure; Figure 2 It is a structural block diagram of a human-computer interaction device provided by an embodiment of the present disclosure; Figure 3 It is a structural block diagram of a human-computer interaction system provided by an embodiment of the present disclosure; Figure 4 Schematic block diagram of an electronic device provided by an embodiment of the present disclosure. Detailed implementation manners

[0013] In the following description, specific details such as specific system architectures and technologies are presented for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present disclosure. However, those skilled in the art should clearly understand that the present disclosure can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present disclosure.

[0014] To make the objectives, technical solutions, and advantages of the present disclosure clearer, the following will be described through specific embodiments in conjunction with the accompanying drawings.

[0015] Please refer to Figure 1 , Figure 1 Flow schematic diagram of a human-computer interaction method provided by an embodiment of the present disclosure. This method is used for a vending machine and includes: S101: Based on the stay time of the target user and the historical purchase records, determine the preference degrees of the target user for different target commodities. The target user is the user who interacts with the vending machine, the target commodities are the commodities sold by the vending machine, and the stay time is the stay time of the target user's line of sight in different target commodity display areas.

[0016] In this embodiment, the longer the stay time of the target user's line of sight in a certain target commodity display area, the higher the attention of the user to this commodity, and the stronger the potential purchase intention. For example, if the user stays in the beverage display area for a long time, it means that he is more interested in beverage commodities.

[0017] The historical purchase records can directly reflect the user's past consumption choices and preferences. If the user has often purchased a certain commodity in the past, it can be inferred that he has a high preference for this commodity. For example, if the user has purchased a certain kind of chocolate many times, it means that he likes this kind of chocolate.

[0018] Comprehensively determine the preference degree: In this embodiment, the stay time and the historical purchase records can be combined by weighted summation to comprehensively evaluate the preference degrees of the target user for different target commodities. The stay time and the historical purchase records are converted into numerical values to represent the preference degree, and the weights can be adjusted according to the actual situation to reflect the relative importance of the two in judging the user's preferences.

[0019] Exemplarily, an infrared sensor can be installed inside the vending machine. When a customer approaches the vending machine, the camera is activated to track the direction of the customer's line of sight. Through image recognition technology, determine the stay time of the customer's line of sight in different commodity display areas (i=1, 2,…, n, n is the total number of target product display areas).

[0020] The payment system and backend database of the vending machine can be used to record the historical purchase records of each customer. The information of each purchased product is stored in the form of a unique product code in the historical purchase record list H = {h1, h2, ..., h m}, m is the number of purchases.

[0021] S102: updating the preference degree based on the inventory status of different target commodities to obtain the recommendation priority of different target commodities.

[0022] In this embodiment, the vending machine needs to know the inventory status of the target product in real time, which is divided into two situations: in stock and out of stock. The inventory status is an important factor affecting product recommendations. Even if a product has a high user preference, if it is out of stock, recommending the product will not only fail to meet user needs, but also reduce user experience.

[0023] The determined preference is adjusted based on inventory status.

[0024] In this embodiment, an inventory-preference dynamic adjustment model can be constructed based on inventory quantity, replenishment cycle, product attributes, season and time period, and the preference can be updated based on the inventory-preference dynamic adjustment model to obtain a more accurate recommendation priority.

[0025] The inventory quantity coefficient can be determined based on the proportion of the inventory quantity to the total inventory under full stock conditions. For example, suppose the full stock is , the current inventory is Q, then .

[0026] Set the replenishment cycle coefficient r. The shorter the replenishment cycle T, the higher r. Suppose the longest replenishment cycle is , the current replenishment cycle is T, then .

[0027] The product attribute coefficient p can be set based on the popularity and profit margin of the product. For example, p=1.2 for popular and high-profit products, p=1 for ordinary products, and p=0.8 for unpopular products.

[0028] To set the season and time period coefficient s, you can analyze the demand changes of various commodities in different seasons and time periods based on historical sales data. For example, in summer, the demand for beverages is large during the day, so the s value of beverages can be set to 1.5; in winter, the demand for hot drinks is large in the morning and evening, so the s value of hot drinks in the morning and evening can be set to 1.3.

[0029] The preference update formula is:

[0030] Among them, is the recommended priority of the target commodity, is the original preference degree.

[0031] S103: Sort and display the target commodities based on the recommended priority or historical purchase frequency of the target commodities.

[0032] In this embodiment, when sorting the target commodities, there are two sorting bases to choose from, namely the recommended priority of the commodities and the historical purchase frequency. Which basis to choose specifically can be set according to the actual situation. It is possible to sort and display the target commodities based on the recommended priority or historical purchase frequency of the target commodities according to the pedestrian flow in the area near the vending machine. For example, when the pedestrian flow is small, the recommended priority can be preferentially used for sorting; when the pedestrian flow is large, sorting can be carried out according to the historical purchase frequency.

[0033] If the recommended priority is used for sorting, the commodities with a higher recommended priority will be ranked in the front; if the historical purchase frequency is used for sorting, the commodities with a higher historical purchase frequency will be ranked in the front. After sorting, the vending machine will display the sorted commodity information on the display screen to facilitate the user to quickly browse and select commodities.

[0034] It can be concluded from the above that in this embodiment, by analyzing the residence time and historical purchase records of the target user, the user preferences are accurately grasped, and personalized commodity recommendations are provided for the user. The preference degree is updated in combination with the commodity inventory status to determine the recommended priority, effectively avoiding recommending out-of-stock commodities and ensuring the smoothness of the shopping process. The commodities are sorted and displayed using the recommended priority or historical purchase frequency. If the commodities are sorted and displayed based on the recommended priority, the commodities that match the current user interests can be highlighted; if the commodities are sorted and displayed according to the historical purchase frequency, the popular choices of the public can be shown. Overall, the human-computer interaction process of the vending machine is optimized, the user satisfaction is enhanced, and the operation efficiency is improved.

[0035] In an embodiment of the present disclosure, sorting and displaying the target commodities based on the recommended priority or historical purchase frequency of the target commodities includes: In response to the passenger flow being greater than the passenger flow threshold, sorting and displaying the target commodities based on the target commodities corresponding to the historical purchase frequency being greater than the purchase frequency threshold: In response to the passenger flow being less than or equal to the passenger flow threshold, sorting and displaying the target commodities based on the recommended priority.

[0036] In this embodiment, a passenger flow statistical sensor can be installed at a suitable position around the vending machine, and the passenger flow is statistically counted at fixed time intervals (for example, 15 minutes) , j represents different time intervals. Connect with the system clock to obtain the current time T to determine which time period of the day is currently.

[0037] In this embodiment, two thresholds can be pre-set, namely, a passenger flow threshold and a purchase frequency threshold. The passenger flow threshold is a standard for distinguishing high and low passenger flow. The passenger flow threshold can be set based on the historical passenger flow data of the location of the vending machine and the operating experience. For example, for a vending machine in a subway station with a large passenger flow, 100 people passing through per hour can be set as the passenger flow threshold. The purchase frequency threshold is used to define the popularity of the product. It can be determined based on comprehensive factors such as the historical sales data, click volume, and search popularity of the product. For example, the sales volume of a certain product in the past week exceeding 50 pieces is set as the purchase frequency threshold.

[0038] When it is detected that the passenger flow around the vending machine is greater than the pre-set passenger flow threshold, it indicates that it is in the peak passenger flow period. At this time, in order to improve the customer's shopping efficiency and reduce the time for customers to choose from a large number of products, the vending machine chooses to only display the target products whose historical purchase frequency is greater than the purchase frequency threshold. Popular products are of general interest to most customers. By displaying them first, the needs of most customers can be quickly met, avoiding the display of too many products, which causes customers to spend too much time choosing during peak hours and cause congestion.

[0039] When the customer flow is less than or equal to the customer flow threshold: When the customer flow is less than or equal to the customer flow threshold, it indicates that the customer flow is low. Customers have relatively ample time to select goods. The vending machine sorts and displays the target goods based on the recommendation priority determined by the user's stay time, historical purchase records, and inventory status. This can give full play to the advantages of personalized recommendations, meet the personalized needs of different customers, provide customers with product recommendations that are more in line with their personal preferences, and enhance customers' shopping experience.

[0040] It can be concluded from the above that the present embodiment can flexibly adjust the product display strategy according to the customer flow. During peak hours, when the customer flow is large, displaying popular products can quickly meet the needs of most people, improve shopping efficiency, and avoid congestion; during low hours, displaying products based on recommendation priority can meet the personalized needs of customers, make full use of low hours to improve services, and comprehensively optimize the human-computer interaction experience of the vending machine.

[0041] In one embodiment of the present disclosure, based on the target user's stay time and historical purchase records, determining the target user's preference for different target commodities includes: Clustering is performed based on the target user's transaction data, behavior data, and persona data to obtain the classification results of the target user; Based on the classification results of the target users, determine the weight coefficients corresponding to the residence time and historical purchase records of the target users respectively; Based on the residence time, historical purchase records and weight coefficients of the target users, determine the preference degrees of the target users for different target commodities.

[0042] In this embodiment, the transaction data may include purchase frequency, purchase amount, and types of purchased commodities; The behavior data may include the residence time of the target user's line of sight in the commodity display area and the number of times of touching the commodity; The portrait data of the person may include age and gender.

[0043] These data depict the user characteristics from different perspectives.

[0044] Use the clustering algorithm to analyze and process the above data. The clustering algorithm can discover the natural grouping patterns in the data, classify the users with similar characteristics into one category, so as to obtain the classification results of the target users. For example, the users can be classified into different categories such as young high-frequency consumer groups and elderly low-frequency consumer groups.

[0045] In the purchase decision-making process of users in different categories, the influence degrees of the residence time and historical purchase records on their preferences are different. For example, young users are more easily influenced by current behaviors (such as residence time), while elderly users tend to follow past purchase habits (historical purchase records).

[0046] Based on the classification results of the target users, determine the weight coefficients corresponding to the residence time and historical purchase records for each category of users respectively. The weight coefficients reflect the emphasis degrees of different categories of users on the residence time and historical purchase records.

[0047] On the basis of having obtained the residence time, historical purchase records and corresponding weight coefficients of the target users, through weighted summation, these factors are combined to determine the preference degrees of the target users for different target commodities. The preference degrees obtained in this way can more accurately reflect the preference degrees of different categories of users for various commodities.

[0048] It can be concluded from the above that in this embodiment, through multi-dimensional data clustering, the target users are classified, and then the weight coefficients of the residence time and historical purchase records are determined according to the categories, and the preference degrees are accurately calculated. It can provide more personalized commodity preference analysis according to the characteristics of different user groups, so as to enable the vending machine to achieve accurate recommendation and improve the user shopping experience and satisfaction.

[0049] In an embodiment of the present disclosure, determining the preference degrees of the target users for different target commodities based on the residence time, historical purchase records and weight coefficients of the target users includes: Determine the preference degrees of the target users for different target commodities based on the first formula; The first formula is:

[0050] Among them, represents the preference degree of the target user for the target product k, represents the weight coefficient corresponding to the dwell time of the target user's line of sight in different target product display areas, both represent the weight coefficients corresponding to the target user's historical purchase records, represents the dwell time of the target user's line of sight in the i-th target product display area, n represents the total number of target product display areas, represents the judgment function of the i-th target product display area and the corresponding target product k, represents the product corresponding to the m-th purchase behavior in the historical purchase record list, s represents the total number of the target user's historical purchase records, represents the judgment function of the product corresponding to the m-th purchase behavior and the corresponding target product k.

[0051] In this embodiment, As the final calculation result, it represents the preference degree of the target user for the target product k. The higher the value, the stronger the user's preference for this product.

[0052] The weight coefficient is used to measure the influence degree of the dwell time of the target user's line of sight in different target product display areas on the preference degree. If is relatively large, it indicates that the dwell time accounts for a relatively high proportion in the preference degree calculation, that is, the dwell time is more important for the user's preference judgment.

[0053] The weight coefficient represents the influence weight of the target user's historical purchase records on the preference degree, the larger it is, the more significant the role of the historical purchase behavior in reflecting the user's preference.

[0054] represents the dwell time part, and calculates the preference degree based on the dwell time. represents the total dwell time of the target user's line of sight in the display area related to the target product k. represents the total dwell time of all display areas. The two are divided to obtain the proportion of the dwell time of the target user for the target product k in the total dwell time, and then multiplied by the weight coefficient corresponding to the dwell time to obtain the preference degree of the target user for the target product k based on the dwell time.

[0055] represents the historical purchase record part, The sum of the relevant behaviors of the target user in purchasing the target product k in the historical purchase records is counted (by using the judgment function to determine whether each purchase behavior is related to the target product k). s is the total number of historical purchase records. After division, the appearance ratio of the target product k in the historical purchase records is obtained, and then multiplied by the weight coefficient corresponding to the historical purchase records to obtain the preference degree of the target user for the target product k based on the historical purchase records.

[0056] Finally, the preference degrees based on the stay time and historical purchase records are added together to obtain the comprehensive preference degree of the target user for the target product k. . By adjusting and values, the relative importance of the stay time and historical purchase records in determining the preference degree can be flexibly adjusted according to the actual situation, so as to more accurately reflect the true preference degree of the target user for different target products.

[0057] Among them, is the judgment function. When the product corresponding to the product display area i is k, value is 1; otherwise it is 0. Its function is to filter out the data related to product k in the summation operation.

[0058] is also a judgment function. When the product corresponding to the mth purchase behavior of the customer (i.e., the product represented by h m ) is product k, value is 1; if it is not product k, its value is 0.

[0059] In practical applications, considering the complexity of user purchase behaviors, in addition to judging whether to purchase the target product k, factors such as the purchase time interval and the purchase quantity can also be incorporated. Assume that t m is the time of the mth purchase behavior, q m is the quantity of the product in the mth purchase behavior, and T is the set reference time interval. can be expressed as:

[0060] Among them is the time of the previous purchase of the target product k. In the formula, when purchasing the target product k, the larger the purchase quantity and the closer the time interval from the previous purchase to the reference time interval T, value is, highlighting the importance and timeliness of the purchase behavior.

[0061] For , in addition to judging whether the display area corresponds to the target product k, the position of the display area and the user browsing order can also be considered. Assume that p iis the location priority of the ith display area (for example, the golden location has a high priority), o i is the order in which the user browses the i-th display area, O is the total number of browsed display areas, It can be expressed as:

[0062] When the display area corresponds to the target product k, the higher the position priority, the higher the browsing order. The larger the value is, the more it reflects the influence of the position of the display area and the user's browsing order on the preference calculation.

[0063] In one embodiment of the present disclosure, clustering is performed based on the transaction data, behavior data, and character portrait data of the target user to obtain a classification result of the target user, including: Determine multiple cluster centers based on the target user's transaction data, behavior data, and persona data; Encode the coordinates of multiple cluster centers to obtain the characteristic value of each cluster center; The eigenvalues of each cluster center are concatenated to obtain multiple chromosomes; Based on the error of the clustering result corresponding to each chromosome, multiple chromosomes are iteratively optimized to obtain the target cluster center; The classification result of the target user is obtained based on the target cluster center.

[0064] In this embodiment, the transaction data, behavior data and character portrait data of the target user can be clustered by the K-means algorithm to obtain multiple cluster centers. Multiple cluster centers (assuming K) can be set in advance, and each cluster center has corresponding coordinates in the feature space composed of the above multiple data. These coordinates are encoded, and the coordinate values of each dimension of each cluster center are converted into corresponding feature values.

[0065] For example, if the feature space is composed of three dimensions: age, consumption amount, and purchase frequency, the coordinates of each cluster center (age value, consumption amount value, purchase frequency value) are encoded as corresponding feature values.

[0066] The eigenvalues of each cluster center are connected in series in order to form a long code string, which can be regarded as a chromosome. Each chromosome represents a combination of a group of cluster centers. In this way, the problem of setting cluster centers is transformed into the problem of chromosome representation.

[0067] Calculate the error of the clustering result corresponding to each chromosome (i.e. a set of cluster centers). The error can be measured by clustering evaluation indicators, such as the sum of squared errors, which is to calculate the sum of squared errors of the distance from each data point to its cluster center. The smaller the sum of squared errors, the better the clustering effect.

[0068] Based on the error situation of each chromosome, these chromosomes are iteratively optimized. The optimization process includes genetic operations such as selection, crossover, and mutation. The selection operation selects some chromosomes from the current population (i.e., a set of multiple chromosomes) as the parents of the next generation according to the fitness of the chromosomes; the crossover operation exchanges some genes (i.e., some segments of the coding string) of two parent chromosomes to generate new offspring chromosomes; the mutation operation randomly changes some genes of the chromosomes to introduce new genetic diversity.

[0069] After multiple rounds of iterative optimization, a set of clustering centers with smaller errors, that is, the target clustering centers, are gradually found.

[0070] After obtaining the target clustering centers, according to the distance (such as the Euclidean distance) from each data point of the target user to each clustering center, the target users are divided into the clusters corresponding to the nearest clustering center. All target users are divided into different clusters, thus obtaining the classification result of the target users.

[0071] For example, if the distance from a user's data point to a certain clustering center is the closest among all clustering centers, this user can be classified into the category represented by this clustering center.

[0072] It can be concluded from the above that in this embodiment, by encoding the clustering centers as chromosomes and using genetic operations for iterative optimization, the clustering is effectively prevented from falling into local optima. The target clustering centers can be accurately found, and then classification can be achieved based on the distance between the user data points and the clustering centers, improving the clustering accuracy.

[0073] In an embodiment of the present disclosure, a human-computer interaction method further includes: Determining a change rate threshold of the target user behavior characteristics based on the historical purchase records, and the behavior characteristics of the target user are obtained by extracting features from the behavior data; In response to the change rate of the target user behavior data being greater than the change rate threshold, updating the number of clustering centers.

[0074] In this embodiment, the vending machine continuously records the historical purchase records of the target user, and based on the collected historical purchase records, determines the change rate threshold of the target user behavior characteristics through statistical analysis methods.

[0075] For example, by analyzing the fluctuation of the user's purchase frequency over a period of time, a reasonable change rate threshold is calculated. When the change rate of the behavior characteristics exceeds this threshold, it indicates that the user's behavior pattern has changed.

[0076] During the operation of the vending machine, it collects the behavioral data of the target user in real time and calculates the change rate of these behavioral data relative to the previous state. For example, calculate the change rate of the user's purchase frequency, the change rate of the proportion of new product purchases, etc. once a day.

[0077] Compare the calculated change rate of the behavioral data with a pre-determined change rate threshold. If it is found that the change rate of the target user's behavioral data is greater than the change rate threshold, it indicates that the user's behavior pattern has changed significantly, and the current clustering result cannot accurately reflect the user's latest characteristics.

[0078] When the change rate of the target user's behavioral data is greater than the change rate threshold, the vending machine triggers an update operation on the number of clustering centers. Because the change in the user's behavior pattern can cause the original clustering method to become inapplicable, and it is necessary to re-divide the clusters to better classify the users.

[0079] Increase or decrease the number of clustering centers according to specific algorithms and strategies.

[0080] For example, if it is found that there has emerged a user behavior pattern with significant differences from the existing clustering characteristics, the number of clustering centers can be increased to cluster these new behavior patterns separately; if the number of users in some clusters gradually decreases and the behavioral characteristics of these users become more and more similar to those of other clusters, then the number of clustering centers can be considered to be reduced. By updating the number of clustering centers and re-performing clustering analysis, the clustering result can better adapt to the dynamic changes of the target user's behavior, improving the vending machine's personalized service ability for users and the accuracy of product recommendations.

[0081] It can be concluded from the above that in this embodiment, the change rate threshold of the behavioral characteristics is determined through historical purchase records, and the number of clustering centers is updated when the change rate of the target user's behavioral data exceeds the threshold. This can enable the clustering analysis of the vending machine to closely follow the dynamic changes of the user's behavior, accurately grasp the user's characteristics, provide product recommendations and services that better meet the user's current needs, and improve the interaction experience and sales efficiency.

[0082] Corresponding to the human-computer interaction method in the above embodiment, Figure 2 This is a structural block diagram of a human-computer interaction device provided by an embodiment of the present disclosure. For the sake of convenience of description, only the parts related to the embodiment of the present disclosure are shown. Refer to Figure 2 This human-computer interaction device 20, for a vending machine, includes: a preference calculation module 21, a priority calculation module 22, and a product display module 23.

[0083] Among them, the preference calculation module 21 is used to determine the preference degrees of the target user for different target commodities based on the residence time of the target user and the historical purchase records. The target user is the user who interacts with the vending machine, the target commodities are the commodities sold by the vending machine, and the residence time is the residence time of the target user's line of sight in the display areas of different target commodities. The priority calculation module 22 is used to update the preference degrees based on the inventory statuses of different target commodities to obtain the recommended priorities of different target commodities. The commodity display module 23 is used to sort and display the target commodities based on the recommended priorities or historical purchase frequencies of the target commodities.

[0084] In an embodiment of the present disclosure, the commodity display module 23 is specifically configured to: In response to the passenger flow being greater than the passenger flow threshold, sort and display the target commodities based on the target commodities corresponding to the historical purchase frequency being greater than the purchase frequency threshold: In response to the passenger flow being less than or equal to the passenger flow threshold, sort and display the target commodities based on the recommended priorities.

[0085] In an embodiment of the present disclosure, the preference calculation module 21 is specifically configured to: Cluster based on the transaction data, behavior data, and portrait data of the target user to obtain the classification result of the target user; Based on the classification result of the target user, respectively determine the weight coefficients corresponding to the residence time and historical purchase records of the target user; Based on the residence time, historical purchase records, and weight coefficients of the target user, determine the preference degrees of the target user for different target commodities.

[0086] In an embodiment of the present disclosure, the preference calculation module 21 is specifically further configured to: Determine the preference degrees of the target user for different target commodities based on the first formula; The first formula is:

[0087] Wherein, represents the preference degree of the target user for the target commodity k, represents the weight coefficient corresponding to the residence time of the target user's line of sight in the display areas of different target commodities, both represent the weight coefficients corresponding to the historical purchase records of the target user, represents the residence time of the target user's line of sight in the i-th target commodity display area, n represents the total number of target commodity display areas, represents the judgment function of the i-th target commodity display area and the corresponding target commodity k, denote the products corresponding to the m-th purchase behavior in the historical purchase record list, s denote the total number of the target user's historical purchase records, denote the judgment function of the product corresponding to the m-th purchase behavior and the corresponding target product k.

[0088] In an embodiment of the present disclosure, the preference calculation module is further specifically configured to: determine multiple clustering centers based on the transaction data, behavior data and portrait data of the target user; encode the coordinates of the multiple clustering centers to obtain the eigenvalue of each clustering center; concatenate the eigenvalues of each clustering center to obtain multiple chromosomes; iteratively optimize the multiple chromosomes based on the error of the clustering result corresponding to each chromosome to obtain the target clustering center; obtain the classification result of the target user based on the target clustering center.

[0089] In an embodiment of the present disclosure, the preference calculation module is further specifically configured to: determine the change rate threshold of the target user's behavior characteristics based on the historical purchase record, and the behavior characteristics of the target user are obtained by feature extraction of the behavior data; in response to the change rate of the target user's behavior data being greater than the change rate threshold, update the number of clustering centers.

[0090] See Figure 3 , Figure 3 is a structural block diagram of a human-computer interaction system provided by an embodiment of the present disclosure. For the sake of convenience of description, only the parts related to the embodiment of the present disclosure are shown. Refer to Figure 3 This human-computer interaction system 30 for a vending machine includes: a display unit 31, an image acquisition unit 32 and an electronic device 300; The display unit 31 is used to display the target product; The image acquisition unit 32 is used to acquire the behavior data and portrait data of the target user; The electronic device 300 is used to process or store the program instructions for executing the human-computer interaction method.

[0091] See Figure 4 , Figure 4 is a schematic block diagram of an electronic device provided by an embodiment of the present disclosure. As Figure 4The electronic device 300 in the present embodiment shown may include: one or more processors 301, one or more input devices 302, one or more output devices 303, and one or more memories 304. The above-mentioned processors 301, input devices 302, output devices 303, and memories 304 communicate with each other through a communication bus 305. The memory 304 is used to store computer programs, and the computer programs include program instructions. The processor 301 is used to execute the program instructions stored in the memory 304. Among them, the processor 301 is configured to call the program instructions to execute the functions of each module in the above-mentioned device embodiments, for example Figure 2 the functions of the preference calculation module 21, the priority calculation module 22, and the commodity display module 23 shown.

[0092] It should be understood that in the embodiments of the present disclosure, the so-called processor 301 may be a central processing unit (CPU), and this processor may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or this processor may also be any conventional processor, etc.

[0093] The input device 302 may include a touchpad, a fingerprint acquisition sensor (for acquiring the fingerprint information and the direction information of the fingerprint of the user), a microphone, etc., and the output device 303 may include a display (such as an LCD), a speaker, etc.

[0094] The memory 304 may include a read-only memory and a random access memory, and provide instructions and data to the processor 301. A part of the memory 304 may also include a non-volatile random access memory. For example, the memory 304 may also store information about the device type.

[0095] In specific implementation, the processors 301, input devices 302, and output devices 303 described in the embodiments of the present disclosure may execute the implementation manners described in the first embodiment and the second embodiment of a human-computer interaction method provided by the embodiments of the present disclosure, and may also execute the implementation manner of the electronic device described in the embodiments of the present disclosure, which will not be elaborated here.

[0096] In another embodiment of the present disclosure, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program, and the computer program includes program instructions. When the program instructions are executed by a processor, all or part of the processes in the methods of the above embodiments are implemented. It can also be completed by instructing relevant hardware through the computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc.

[0097] The computer-readable storage medium can be an internal storage unit of the electronic device in any of the foregoing embodiments, such as the hard disk or memory of the electronic device. The computer-readable storage medium can also be an external storage device of the electronic device, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device. Further, the computer-readable storage medium can also include both the internal storage unit and the external storage device of the electronic device. The computer-readable storage medium is used to store the computer program and other programs and data required by the electronic device. The computer-readable storage medium can also be used to temporarily store the data that has been output or will be output.

[0098] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the components and steps of the examples have been generally described according to their functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present disclosure.

[0099] Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the above-described electronic devices and units can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0100] In several embodiments provided by this application, it should be understood that the disclosed electronic devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed coupling, direct coupling, or communication connection between each other can be an indirect coupling or communication connection through some interfaces or units, or can also be in the form of electrical, mechanical, or other connections.

[0101] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place, or can also be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiments of the present disclosure.

[0102] In addition, each functional unit in various embodiments of the present disclosure can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0103] The above is only the specific implementation manner of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present disclosure can easily think of various equivalent modifications or substitutions, and these modifications or substitutions should all be covered within the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be subject to the protection scope of the claims.

Claims

1. A human-computer interaction method for a vending machine, characterized in that, Including: Based on the residence time and historical purchase records of the target user, determine the preference degrees of the target user for different target commodities, where the target user is a user interacting with the vending machine, the target commodities are the commodities sold by the vending machine, and the residence time is the residence time of the target user's line of sight in different target commodity display areas; Update the preference degrees based on the inventory status of different target commodities to obtain the recommended priorities of different target commodities; Sort and display the target commodities based on the recommended priorities or historical purchase frequencies of the target commodities.

2. The human-computer interaction method according to claim 1, wherein The sorting and displaying of the target commodities based on the recommended priorities or historical purchase frequencies of the target commodities includes: In response to the passenger flow being greater than the passenger flow threshold, sort and display the target commodities based on the target commodities corresponding to the historical purchase frequency being greater than the purchase frequency threshold: In response to the passenger flow being less than or equal to the passenger flow threshold, sort and display the target commodities based on the recommended priorities.

3. The human-computer interaction method according to claim 1, characterized in that, The determining of the preference degrees of the target user for different target commodities based on the residence time and historical purchase records of the target user includes: Perform clustering based on the transaction data, behavior data, and portrait data of the target user to obtain the classification result of the target user; Based on the classification result of the target user, respectively determine the weight coefficients corresponding to the residence time and historical purchase records of the target user; Based on the residence time, historical purchase records, and weight coefficients of the target user, determine the preference degrees of the target user for different target commodities.

4. The human-computer interaction method according to claim 3, wherein, The determining of the preference degrees of the target user for different target commodities based on the residence time, historical purchase records, and weight coefficients of the target user includes: Determine the preference degrees of the target user for different target commodities based on the first formula; The first formula is: Among them, represents the preference degree of the target user for the target commodity k, represents the weight coefficient corresponding to the residence time of the target user's line of sight in different target commodity display areas, both represent the weight coefficients corresponding to the target user's historical purchase records, represents the residence time of the target user's line of sight in the i-th target commodity display area, and n represents the total number of target commodity display areas, represents the judgment function of the i-th target commodity display area and the corresponding target commodity k, represents the commodity corresponding to the m-th purchase behavior in the historical purchase record list, and s represents the total number of the target user's historical purchase records, represents the judgment function of the commodity corresponding to the m-th purchase behavior and the corresponding target commodity k.

5. The human-computer interaction method according to claim 3, characterized in that, The performing of clustering based on the transaction data, behavior data, and portrait data of the target user to obtain the classification result of the target user includes: Determine multiple clustering centers based on the transaction data, behavior data, and portrait data of the target user; Encode the coordinates of the multiple clustering centers to obtain the eigenvalue of each clustering center; Concatenate the eigenvalues of each clustering center to obtain multiple chromosomes; Based on the error of the clustering result corresponding to each chromosome, perform iterative optimization on the multiple chromosomes to obtain the target clustering center; Based on the target clustering center, obtain the classification result of the target user.

6. The human-computer interaction method according to claim 5, wherein, It further includes: Based on the historical purchase records, determine the change rate threshold of the behavior characteristics of the target user, where the behavior characteristics of the target user are obtained by performing feature extraction on the behavior data; In response to the change rate of the target user's behavior data being greater than the change rate threshold, update the number of the clustering centers.

7. A human-machine interaction device for a vending machine, characterized in that, Including: A preference degree calculation module, configured to determine the preference degrees of the target user for different target commodities based on the residence time and historical purchase records of the target user, where the target user is a user interacting with the vending machine, the target commodities are the commodities sold by the vending machine, and the residence time is the residence time of the target user's line of sight in different target commodity display areas; A priority calculation module, configured to update the preference degree based on the inventory status of different target commodities to obtain the recommendation priorities of different target commodities; A commodity display module, configured to sort and display target commodities based on the recommendation priorities or historical purchase frequencies of the target commodities.

8. An electronic device, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A human-computer interaction system, characterized in that, Comprising: A display unit, an image acquisition unit and an electronic device; The display unit is configured to display target commodities; The image acquisition unit is configured to acquire the behavior data and portrait data of a target user; The electronic device includes a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images