Business display method and device, computer equipment and storage medium

Abstract

The invention relates to a business display method and device, computer equipment and a storage medium, and relates to the technical field of artificial intelligence. The method comprises the following steps: determining a prediction service list according to eye movement data and historical service data of a user, determining an attention coefficient of each display area according to position information, size information and eye movement data of each display area in a display page, and further determining the attention coefficient of each display area according to the prediction service list and the attention coefficient of each display area. Displaying each piece of prediction service information in the prediction service list; the attention coefficient is used for representing the attention degree of the user to each display area. Compared with a method for determining the prediction service only according to the historical service of the user, the method improves the accuracy of the displayed prediction service through the combination of the eye movement data and the historical service data.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, and particularly to a business display method, apparatus, computer device, and storage medium. Background Art

[0002] With the rapid development of Internet technology, more and more Internet, financial institutions, or other third-party platforms have begun to explore technologies for intelligently displaying business information pages, giving priority to presenting content that users are interested in. In particular, financial institutions will predict user preferences and display various financial products or financial information to users.

[0003] However, in related technologies, the method of financial institutions presenting information to users has the problem of inaccuracy. Summary of the Invention

[0004] Based on this, in view of the above technical problems, it is necessary to provide a business display method, apparatus, computer device, and storage medium that can solve the problem of inaccuracy in the method of presenting information to users.

[0005] In a first aspect, this application provides a business display method, including:

[0006] Determine a predicted business list according to the user's eye movement data and historical business data;

[0007] Determine the attention coefficient of each display area in the display page according to the position information, size information, and the eye movement data of each display area in the display page; the attention coefficient is used to characterize the attention degree of the user to each display area;

[0008] Display each predicted business information in the predicted business list according to the predicted business list and the attention coefficient of each display area.

[0009] In one embodiment, the step of displaying each predicted business information in the predicted business list according to the predicted business list and the attention coefficient of each display area includes:

[0010] Determine the display position of each predicted business information according to the attention coefficient of each display area and the arrangement order of each predicted business information in the predicted business list;

[0011] Display each predicted business information in the predicted business list according to the predicted business list and the display position of each predicted business information.

[0012] In one embodiment, the step of determining the attention coefficient of each display area in the display page according to the position information, size information, and the eye movement data of each display area in the display page includes:

[0013] Determine the initial attention coefficients of the display areas according to the position information and size information of the display areas;

[0014] Determine the reference coefficients of the display areas according to the eye movement data;

[0015] Adjust the initial attention coefficients according to the reference coefficients to obtain the attention coefficients.

[0016] In one embodiment, the determining the reference coefficients of the display areas according to the eye movement data includes:

[0017] Determine the residence time of the user in each display area according to the eye movement data;

[0018] Determine the ratio of the residence time of each display area to the total residence time of the user on the display page as the reference coefficient of each display area.

[0019] In one embodiment, the determining the predicted service list according to the eye movement data and historical service data of the user includes:

[0020] Construct a knowledge graph according to the eye movement data and historical service data of the user; the knowledge graph is used to represent the relationship between the user and the services;

[0021] Determine the predicted service list according to the knowledge graph and a preset prediction model.

[0022] In one embodiment, the determining the predicted service list according to the knowledge graph and a preset prediction model includes:

[0023] Determine the relationships and relationship weights between the entities in the knowledge graph; the entities include the user and the services corresponding to the user;

[0024] Form a weight matrix according to the relationships and relationship weights between the entities;

[0025] Input the weight matrix into the preset prediction model to determine the predicted service list.

[0026] In one embodiment, the determining the relationships and relationship weights between the entities in the knowledge graph includes:

[0027] Determine the first correspondence between the user and each service in the knowledge graph, and the second correspondence between each service and each service;

[0028] Determine the first relationship weight of the first correspondence and the second relationship weight of the second correspondence.

[0029] In a second aspect, the present application further provides a service display device, including:

[0030] A first determination module, configured to determine a predicted service list according to the user's eye movement data and historical service data;

[0031] A second determination module, configured to determine the attention coefficient of each display area according to the position information, size information of each display area in the display page and the eye movement data; the attention coefficient is used to characterize the user's attention degree to each display area;

[0032] A display module, configured to display each predicted service information in the predicted service list according to the predicted service list and the attention coefficient of each display area.

[0033] In a third aspect, the present application further provides a computer device, including a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0034] Determine a predicted service list according to the user's eye movement data and historical service data;

[0035] Determine the attention coefficient of each display area according to the position information, size information of each display area in the display page and the eye movement data; the attention coefficient is used to characterize the user's attention degree to each display area;

[0036] Display each predicted service information in the predicted service list according to the predicted service list and the attention coefficient of each display area.

[0037] In a fourth aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0038] Determine a predicted service list according to the user's eye movement data and historical service data;

[0039] Determine the attention coefficient of each display area according to the position information, size information of each display area in the display page and the eye movement data; the attention coefficient is used to characterize the user's attention degree to each display area;

[0040] Display each predicted service information in the predicted service list according to the predicted service list and the attention coefficient of each display area.

[0041] In a fifth aspect, the present application further provides a computer program product, including a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0042] Determine a predicted service list according to the user's eye movement data and historical service data;

[0043] Determine the attention coefficient of each display area in the display page according to the position information, size information of each display area in the display page and the eye movement data; the attention coefficient is used to characterize the attention degree of the user to each display area;

[0044] Display each predicted service information in the predicted service list according to the predicted service list and the attention coefficient of each display area.

[0045] The above service display method, device, computer device and storage medium determine a predicted service list according to the user's eye movement data and historical service data, and thus determine the attention coefficient of each display area according to the position information, size information and eye movement data of each display area in the display page, and then display each predicted service information in the predicted service list according to the predicted service list and the attention coefficient of each display area; the attention coefficient is used to characterize the attention degree of the user to each display area. Compared with only determining the predicted service according to the user's historical service, the predicted service list determined by combining the eye movement data and historical service data has higher accuracy, thereby improving the accuracy of the displayed predicted service. By analyzing the position information, size information and eye movement data of the display area, the attention degree of the user to each display area is also more accurate. Displaying each predicted service information in the predicted service list according to the predicted service list and the attention coefficient of each display area further improves the accuracy of the display. Brief Description of the Drawings

[0046] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following will briefly introduce the drawings required for use in the description of the embodiments or related technologies. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0047] Figure 1 It is an application environment diagram of the service display method in an embodiment;

[0048] Figure 2 It is a flow schematic diagram of the service display method in an embodiment;

[0049] Figure 3 It is a flow schematic diagram of the service display method in another embodiment;

[0050] Figure 4 It is a flow schematic diagram of the service display method in another embodiment;

[0051] Figure 5 It is a schematic flowchart of a service display method in another embodiment;

[0052] Figure 6 It is a schematic flowchart of a service display method in another embodiment;

[0053] Figure 7 It is a schematic flowchart of a service display method in another embodiment;

[0054] Figure 8 It is a schematic flowchart of a service display method in another embodiment;

[0055] Figure 9 It is a structural block diagram of a service display device in one embodiment. Detailed implementation manners

[0056] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, and are not used to limit the present application.

[0057] The service display method provided by the embodiments of the present application can be applied to an application environment as Figure 1 shown. Among them, the computer device can be a server, and its internal structural diagram can be as Figure 1 shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store service display data. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it realizes a service display method.

[0058] Those skilled in the art can understand that Figure 1 the structure shown in

[0059] In one embodiment, as Figure 2 shown, a service display method is provided. Taking the server in Figure 1 as an example for illustration, it includes:

[0060] S201. Determine a predicted service list according to the user's eye movement data and historical service data.

[0061] Among them, the user's eye movement data may include the number of gazes, gaze duration, movement trajectory, transition duration, and stay duration, etc.; the historical service data may include historical browsing service data and historical processed service data.

[0062] In the embodiment of the present application, with the user's permission, the user terminal collects the user's eye movement data when browsing the display page by calling the eye tracking component, and extracts the user's historical service data from the preset database, so as to determine multiple predicted services corresponding to the user according to the user's eye movement data and historical service data. The predicted services can be characterized as the services that the user is interested in, and thus a predicted service list is formed according to the multiple predicted services and the attention degree of each service.

[0063] It should be noted that the eye tracking component can be the front camera of the user terminal. After the terminal runs the application program of the mobile bank, the eye tracking component collects the gaze actions of the user's eyes during the browsing process of the display page, records the number of gazes, gaze duration, movement trajectory, transition duration, and stay duration. Among them, the movement trajectory refers to the sequential logic of the user's eyes moving from area i to area j. When the duration of the gaze action is not less than the preset threshold, the user's gaze area i and the stay duration t are recorded i .

[0064] S202. Determine the attention coefficient of each display area according to the position information, size information, and eye movement data of each display area in the display page; the attention coefficient is used to characterize the attention degree of the user to each display area.

[0065] In the embodiment of the present application, the sequential attention coefficient of each display area can be determined according to the position information of each display area, the size attention coefficient of each display area can be determined according to the size information of each display area, and the reference coefficient corresponding to each display area can be determined according to the eye movement data, so as to determine the attention coefficient of each display area according to the sequential attention coefficient, size attention coefficient, and eye movement data.

[0066] Optionally, the weight values corresponding to the position information, size information, and eye movement data can be preset, so that the sequential attention coefficient, size attention coefficient, and reference coefficient can be weighted and summed to determine the attention coefficient of each display area.

[0067] S203. Display the prediction service information in the prediction service list according to the prediction service list and the attention coefficients of each display area.

[0068] In the embodiment of the present application, according to the attention coefficients of each display area and the prediction service list, determine the corresponding relationship between each prediction service in the prediction service list and each display area, so as to display each prediction service in the corresponding display area.

[0069] In the above service display method, according to the user's eye movement data and historical service data, determine the prediction service list, and then according to the position information, size information and eye movement data of each display area in the display page, determine the attention coefficients of each display area. Furthermore, according to the prediction service list and the attention coefficients of each display area, display the prediction service information in the prediction service list; the attention coefficient is used to characterize the attention degree of the user to each display area. Compared with only determining the prediction service according to the user's historical service, the prediction service list determined by combining the eye movement data and historical service data has higher accuracy, thus improving the accuracy of the displayed prediction service. By analyzing the position information, size information and eye movement data of the display area, the attention degree of the user to each display area is also more accurate. Displaying the prediction service information in the prediction service list according to the prediction service list and the attention coefficients of each display area further improves the display accuracy.

[0070] In one embodiment, an implementation manner of the above S203 is improved, as Figure 3 shown, the above "display the prediction service information in the prediction service list according to the prediction service list and the attention coefficients of each display area" includes:

[0071] S301. Determine the display positions of each prediction service information according to the attention coefficients of each display area and the arrangement order of each prediction service information in the prediction service list.

[0072] In the embodiment of the present application, the number of display areas is the same as the number of prediction service information. The earlier the arrangement order of the prediction service information in the prediction service list, the higher the probability that the user is interested in the prediction service information. Further, arrange each display area according to the attention coefficients of each display area to obtain the arrangement order of each display area. For example, arrange each display area in descending order of the attention coefficients of the display area to obtain the arrangement order of each display area. Then, according to the arrangement order of each display area and the arrangement order of each prediction service information, determine the corresponding relationship between the prediction service information and the display area. The display position of each prediction service information is the position where the display area corresponding to each prediction service information is located.

[0073] S302. Display each prediction service information in the prediction service list according to the prediction service list and the display positions of each prediction service information.

[0074] In an embodiment of the present application, according to the prediction service list and the display positions of each prediction service information, each service information is displayed on the corresponding display position through a display page.

[0075] In this embodiment, according to the attention coefficients of each display area and the arrangement order of each prediction service information in the prediction service list, the display positions of each prediction service information are determined, so that users can preferentially view the prediction service information with a higher probability of interest.

[0076] In one embodiment, an implementation manner of the above S202 is provided, as Figure 4 shown, the above "determine the attention coefficient of each display area according to the position information, size information and eye movement data in the display page" includes:

[0077] S401. Determine the initial attention coefficient of each display area according to the position information and size information of each display area.

[0078] In an embodiment of the present application, the position information of each display area is determined in the order from top to bottom, and the attention coefficient is initialized according to the position information and size information. The sequential attention coefficient is the ratio of the sequential number from top to bottom to the total number of areas. For example, the sequential number from top to bottom can be expressed as order, and the total number of areas can be expressed as N, then the sequential attention coefficient is order / N; the size attention coefficient is the ratio of the size information of the display area to the total size information of the page. For example, the size information of the display area can be expressed as size, and the total size information of the page can be expressed as M, then the size attention coefficient is size / M. Further, the product of the sequential attention coefficient and the size attention coefficient is determined as the initial attention coefficient.

[0079] S402. Determine the reference coefficient of each display area according to the eye movement data.

[0080] In an embodiment of the present application, the eye tracking technology is used to identify the stay time of the user in each display area when browsing the display page, so as to determine the reference coefficient of each display area according to the stay time of each display area.

[0081] S403. Adjust the initial attention coefficient according to the reference coefficient to obtain the attention coefficient.

[0082] Optionally, the product of the reference coefficient and the initial attention coefficient can be used as the attention coefficient; or, the sum of the reference coefficient and the initial attention coefficient can be used as the attention coefficient.

[0083] Optionally, as Figure 5As shown above, "determining the reference coefficients of each display area according to the eye movement data" includes:

[0084] S501, determining the residence time of the user in each display area according to the eye movement data.

[0085] S502, determining the ratio of the residence time of each display area to the total residence time of the user on the display page as the reference coefficient of each display area.

[0086] In the embodiment of the present application, the residence duration of each display area is identified and obtained through eye tracking technology, and the ratio of the residence duration of each display area to the residence duration of all areas is determined, and this ratio is determined as the attention coefficient.

[0087] In this embodiment, the initial attention coefficient is determined according to the position information and size information of the display area, and then the initial attention coefficient is adjusted by using the reference coefficient corresponding to the eye movement data, so that the accuracy of the attention coefficient is higher.

[0088] In one embodiment, an implementation manner of the above S201 is provided, as Figure 6 shown above, "determining the predicted service list according to the user's eye movement data and historical service data" includes:

[0089] S601, constructing a knowledge graph according to the user's eye movement data and historical service data; the knowledge graph is used to represent the relationship between the user and the service.

[0090] In the embodiment of the present application, the logistic regression algorithm is used to identify the relationship of the service information that the user is interested in. For example, the service information 2 that the user may be interested in next after browsing the service information 1. First, identify the service information that the user is interested in, use the eye movement indicators of the user in each service information as the model input. If the user successfully clicks on this service information, mark the interested label of this service information as 1, otherwise mark it as 0. Use the interested label as the model output, use the eye movement data and click data of the user in the previous stage as the training samples, use the recent eye movement data of the user as the model input to predict whether the user is interested in the service, and if the output function value is less than or equal to 0.5, it belongs to 0, representing not interested, and if it is greater than 0.5, it represents interested. Further, identify the relationship of the interested service information, use the user and the service as the nodes of the knowledge graph, and use the relationship output by the model as the edge of the knowledge graph to construct the user interest knowledge graph, for example, record it as a triple of (user 1, interested, service 1), (service 1, interested, service 2).

[0091] In the embodiments of the present application, business scenarios and business entities are extracted respectively from business document data and operation specification document data by means of named entity recognition. The relationships between entities are extracted by means of relationship extraction as the edges of the knowledge graph, and business information is associated unidirectionally. Business information relationships that conform to business logic and process significance are extracted from semi-structured data to construct a business process knowledge graph, which is denoted as, for example, a triple (Business 1, Business Process, Business 1).

[0092] In the embodiments of the present application, the historical business association relationships of the user are extracted according to the user dimension to construct a user historical business knowledge graph. The historical business includes a time attribute, and the historical businesses of the user are associated according to time sequence. Exemplarily, the set time period with an association relationship is 30 minutes. If the user first completes Business 1 and then does Business 2 within 30 minutes, then Business 1 and Business 2 are associated unidirectionally to construct a historical business knowledge graph, which is denoted as, for example, triples (User 1, Association, Business 2) and (Business 1, Association, Business 2), indicating that the user will perform Business 2 within a certain time after completing Business 1.

[0093] Further, in this embodiment, knowledge extraction is performed on the above user interest knowledge graph, business process knowledge graph, and historical business knowledge graph. Knowledge extraction includes entity, relationship, and attribute extraction. An entity relationship graph is constructed based on the extracted entities and relationships. Among them, entity extraction refers to identifying user and business named entities; relationship extraction refers to extracting semantic relationships between multiple entities from the basic data, including user historical business relationships, user interested business relationships, business logic relationships, etc., such as (User 1, Has Done, Business 1) and (User 1, Is Interested In, Business 2); attribute extraction refers to extracting attribute values of entities, such as the user name, user gender, user resources, etc. of the user entity, and the processing time of the business entity, etc. Further, knowledge fusion is performed, and the LPA label propagation algorithm is used to connect user entities with user entities.

[0094] Optionally, a user status recognition model is constructed. The dates, weeks, time periods, and usage statuses of the user's historical use of mobile banking applications within a preset time period are used as training samples and trained using the Convolutional Neural Networks (CNN) algorithm. The usage status includes "browse" and "execute". If the usage result is that a certain business is completed, the usage result is recorded as "execute". If the usage result is a series of browsing without any business operation, the usage result is recorded as "browse". The usage status will be used as an attribute of the business entity.

[0095] S602. Determine a predicted business list according to the knowledge graph and a preset prediction model.

[0096] In the embodiment of the present application, an initial prediction model is trained according to the historical business data and historical eye movement data of multiple users to obtain a trained prediction model. Then, input data is determined according to the knowledge graph, and the input data is input into the prediction model to output a predicted business list.

[0097] In this embodiment, first, a knowledge graph is constructed according to the eye movement data and historical business data of users, so as to more intuitively and accurately obtain the association between users and business data. Then, the knowledge graph is used to determine the predicted business list, improving the accuracy of the predicted business list.

[0098] In one embodiment, an implementation manner of the above S602 is improved. As Figure 7 shown, the above "determining the predicted business list according to the knowledge graph and a preset prediction model" includes:

[0099] S701, determining the relationships and relationship weights between entities in the knowledge graph; the entities include users and the corresponding services of users.

[0100] S702, forming a weight matrix according to the relationships and relationship weights between the entities.

[0101] S703, inputting the weight matrix into the preset prediction model to determine the predicted business list.

[0102] In the embodiment of the present application, the relationships and relationship weights between entities in the knowledge graph are determined; the entities include users and the corresponding services of users, and a weight matrix is formed according to the relationships and relationship weights between the entities.

[0103] In the embodiment of the present application, since the knowledge graph data rolls to obtain recent data and a graph will be generated in each time period, a deep learning recurrent neural network model is constructed. The calculation formula of the hidden layer is , where U is the weight matrix of the input x, W is the value of the previous hidden layer as the weight matrix of the input this time, f is the activation function, and the calculation formula of the output layer is , where V is the weight matrix of the output layer, g is the activation function, and B1 and B2 are biases assumed to be 0. The graph generated in the previous time period T - n and the usage status and usage results of the actual operations of the customers on the Tth day are used as training samples. The usage status of the actual operations of the customers on the Tth day on the application program refers to the predicted "browse" and "execute" statuses. The graph generated in the preset time period and the usage status are used as inputs to predict the services that the user may click on and handle and the probabilities, and they are sorted from high to low according to the probabilities, and the top N items are taken as the predicted business list.

[0104] In this embodiment, according to the relationships and relationship weights between entities, a weight matrix is formed and used as the input of the prediction model. Since the weight values of the relationships between entities are combined, the obtained predicted service list is more accurate.

[0105] In one embodiment, an implementation manner of the above S701 is provided. As Figure 8 shown, the above "determine the relationships and relationship weights between entities in the knowledge graph" includes:

[0106] S801, determine the first correspondence between the user and each service in the knowledge graph, and the second correspondence between each service and each other service.

[0107] In the embodiment of the present application, the second correspondence includes historical service processing relationships, interested service relationships, service logic relationships, etc. According to the relevance of each node in the knowledge graph, the first correspondence between the user and each service, and the second correspondence between each service and each other service are extracted.

[0108] S802, determine the first relationship weight of the first correspondence and the second relationship weight of the second correspondence.

[0109] In the embodiment of the present application, methods such as Euclidean distance, cosine similarity, and Jackson similarity formula are used to determine the similarity between entities. Further, the PageRank algorithm is used to assign weights to entity relationships according to the importance between entities. Finally, the entity similarity and the entity relationship weight are multiplied for the entity to obtain the total weight of the entity relationship.

[0110] Further, in the embodiments of the present application, the first relationship weight is mined by using the association rule algorithm. Specifically, first, the weights of business nodes in the knowledge graph are initialized, and the historical services, interested services, and service frequencies of business logic types of user entities and their neighboring similar user entities within a preset cycle range are counted. For example, the proportion of service type 1 in all historical services and interested frequencies of the user within the cycle is used to initialize the service frequency as the initial weight of the service type, which is also used as the weight of the edge between the user entity and the service type 1 node. For example, the initial weight of the edge between service 1 and service 2 is 0.3. Secondly, the confidence and lift of the implication of service 1 and service 2 are obtained by combining the Apriori association rule algorithm. The confidence specifically refers to the probability of the occurrence of service type 2 after the occurrence of service type 1, and the lift specifically refers to the improvement of the probability of the occurrence of service type 2 after the occurrence of service type 1. The lift is the ratio of the confidence to the support. Finally, according to the historical service / interested service types of all users and the association rules in the most recent cycle, the service type list and its weights are adjusted. If the matching association rules include new service types, the new service types are added to the adjusted service list and the weights are initialized as their service frequencies within the cycle interval of similar user entities. The adjusted weight is the product of the initialized weight and the lift.

[0111] In the embodiments of the present application, when determining the second relationship weight of the second corresponding relationship and according to the customer usage status, a two-layer graph neural network model is constructed, the customer service knowledge graph G is transformed into a feature matrix, and the feature matrix and the adjacency matrix are input into the two-layer graph neural network model. The relationship weight between the user entity and the business entity is set as a learnable weight parameter, and the interested relationship weight is uniformly set to , and the historical service relationship weight is uniformly set to . The update of each node is jointly determined by its own features and the features of neighboring nodes. The update calculation formula for each node is:

[0112] (Equation 1)

[0113] Construct a two-layer graph convolutional neural network, and the activation functions adopt ReLU and Softmax respectively. Then the overall forward propagation formula is: , is the result of the normalization process of the adjacency matrix. The loss function is calculated and iteratively updated for all labeled nodes, and two sets of weights are trained respectively.

[0114] In this embodiment, the corresponding relationships between entities are first determined, and then different methods are used to determine the weight values of each corresponding relationship according to the type of the corresponding relationship, improving the accuracy of the relationship weight.

[0115] In combination with all the above embodiments, a service display method is further provided. The method includes:

[0116] S1. Construct a knowledge graph based on the user's eye movement data and historical business data; the knowledge graph is used to represent the relationship between the user and the business.

[0117] S2. Determine the first correspondence between the user and each business in the knowledge graph, and the second correspondence between each business and each other business.

[0118] S3. Determine the first relationship weight of the first correspondence and the second relationship weight of the second correspondence.

[0119] S4. Form a weight matrix according to the relationships and relationship weights between entities.

[0120] S5. Input the weight matrix into a preset prediction model to determine a predicted business list.

[0121] S6. Determine the initial attention coefficient of each display area according to the position information and size information of each display area; the attention coefficient is used to represent the degree of attention of the user to each display area.

[0122] S7. Determine the residence time of the user in each display area according to the eye movement data.

[0123] S8. Determine the ratio of the residence time of each display area to the total residence time of the user on the display page as the reference coefficient of each display area.

[0124] S9. Adjust the initial attention coefficient according to the reference coefficient to obtain the attention coefficient.

[0125] S10. Determine the display position of each predicted business information according to the attention coefficient of each display area and the arrangement order of each predicted business information in the predicted business list.

[0126] S11. Display each predicted business information in the predicted business list according to the predicted business list and the display position of each predicted business information.

[0127] In the above business display method, according to the user's eye movement data and historical business data, a predicted business list is determined. Then, according to the position information, size information, and eye movement data of each display area in the display page, the attention coefficient of each display area is determined. Furthermore, according to the predicted business list and the attention coefficients of each display area, each predicted business information in the predicted business list is displayed; the attention coefficient is used to represent the degree of attention of the user to each display area. Compared with determining the predicted business only based on the user's historical business, the predicted business list determined by combining the eye movement data and historical business data has a higher accuracy, thus improving the accuracy of the displayed predicted business. By analyzing the position information, size information, and eye movement data of the display area, the degree of attention of the user to each display area is also more accurate. Displaying each predicted business information in the predicted business list according to the predicted business list and the attention coefficients of each display area further improves the accuracy of the display.

[0128] It should be understood that although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or steps or stages in other steps.

[0129] Based on the same inventive concept, an embodiment of the present application further provides a business display device for implementing the above-mentioned business display method. The implementation solution provided by this device to solve the problem is similar to the implementation solution described in the above method. Therefore, the specific limitations in one or more embodiments of the business display device provided below can refer to the limitations on the business display method in the above text and will not be repeated here.

[0130] In one embodiment, as Figure 9 shown, a business display device is provided, including: a first determination module 10, a second determination module 11, and a display module 12, where:

[0131] The first determination module 10 is configured to determine a predicted business list according to the user's eye movement data and historical business data.

[0132] The second determination module 11 is configured to determine the attention coefficients of each display area according to the position information, size information, and eye movement data of each display area in the display page; the attention coefficient is used to characterize the degree of attention of the user to each display area.

[0133] The display module 12 is configured to display each predicted service information in the predicted service list according to the predicted service list and the attention coefficients of each display area.

[0134] In one embodiment, the above display module 12 includes: a first determination unit and a display unit, where:

[0135] The first determination unit is configured to determine the display positions of each predicted service information according to the attention coefficients of each display area and the arrangement order of each predicted service information in the predicted service list.

[0136] The display unit is configured to display each predicted service information in the predicted service list according to the predicted service list and the display positions of each predicted service information.

[0137] In one embodiment, the above second determination module 11 includes: a second determination unit, a third determination unit, and a fourth determination unit, where:

[0138] The second determination unit is configured to determine the initial attention coefficients of each display area according to the position information and size information of each display area.

[0139] The third determination unit is configured to determine the reference coefficients of each display area according to the eye movement data.

[0140] The fourth determination unit is configured to adjust the initial attention coefficients according to the reference coefficients to obtain the attention coefficients.

[0141] In one embodiment, the above third determination unit is specifically configured to determine the residence time of the user in each display area according to the eye movement data; and determine the ratio of the residence time of each display area to the total residence time of the user on the display page as the reference coefficient of each display area.

[0142] In one embodiment, the above first determination module includes: a construction unit and a fifth determination unit, where:

[0143] The construction unit is configured to construct a knowledge graph according to the eye movement data and historical service data of the user; the knowledge graph is used to characterize the relationship between the user and the service.

[0144] The fifth determination unit is configured to determine the predicted service list according to the knowledge graph and a preset prediction model.

[0145] In one embodiment, the above-mentioned fifth determination unit is specifically configured to determine the relationships and relationship weights between entities in the knowledge graph; the entities include users and the services corresponding to the users; form a weight matrix according to the relationships and relationship weights between the entities; and input the weight matrix into a preset prediction model to determine a predicted service list.

[0146] In one embodiment, the above-mentioned fifth determination unit is specifically configured to determine a first correspondence between a user and each service in the knowledge graph, and a second correspondence between each service and each service; determine a first relationship weight for the first correspondence and a second relationship weight for the second correspondence.

[0147] Each module in the above-mentioned service display device can be implemented in whole or in part by software, hardware, and their combination. Each of the above modules can be embedded in or independent of a processor in a computer device in the form of hardware, or stored in a memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0148] In one embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory. When the processor executes the computer program, the following steps are implemented:

[0149] Determine a predicted service list according to the user's eye movement data and historical service data;

[0150] Determine the attention coefficient of each display area according to the position information, size information, and eye movement data of each display area in the display page; the attention coefficient is used to characterize the degree of attention of the user to each display area;

[0151] Display each predicted service information in the predicted service list according to the predicted service list and the attention coefficient of each display area.

[0152] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0153] Determine the display position of each predicted service information according to the attention coefficient of each display area and the arrangement order of each predicted service information in the predicted service list;

[0154] Display each predicted service information in the predicted service list according to the predicted service list and the display position of each predicted service information.

[0155] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0156] Determine the initial attention coefficient of each display area according to the position information and size information of each display area;

[0157] Determine the reference coefficients of each display area according to the eye movement data;

[0158] Adjust the initial attention coefficient according to the reference coefficient to obtain the attention coefficient.

[0159] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0160] Determine the residence time of the user in each display area according to the eye movement data;

[0161] Determine the ratio of the residence time of each display area to the total residence time of the user on the display page as the reference coefficient of each display area.

[0162] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0163] Construct a knowledge graph according to the user's eye movement data and historical business data; the knowledge graph is used to represent the relationship between the user and the business;

[0164] Determine the predicted business list according to the knowledge graph and the preset prediction model.

[0165] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0166] Determine the relationships and relationship weights between the entities in the knowledge graph; the entities include users and the corresponding businesses of the users;

[0167] Form a weight matrix according to the relationships and relationship weights between the entities.

[0168] Input the weight matrix into the preset prediction model to determine the predicted business list.

[0169] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0170] Determine the first correspondence between the user and each business in the knowledge graph, and the second correspondence between each business and each business;

[0171] Determine the first relationship weight of the first correspondence and the second relationship weight of the second correspondence.

[0172] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0173] Determine the predicted business list according to the user's eye movement data and historical business data;

[0174] Determine the attention coefficient of each display area according to the position information, size information, and eye movement data of each display area in the display page; the attention coefficient is used to characterize the degree of attention of the user to each display area;

[0175] According to the prediction service list and the attention coefficient of each display area, display each prediction service information in the prediction service list.

[0176] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented:

[0177] Determine the display position of each prediction service information according to the attention coefficient of each display area and the arrangement order of each prediction service information in the prediction service list;

[0178] According to the prediction service list and the display position of each prediction service information, display each prediction service information in the prediction service list.

[0179] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented:

[0180] Determine the initial attention coefficient of each display area according to the position information and size information of each display area;

[0181] Determine the reference coefficient of each display area according to the eye movement data;

[0182] Adjust the initial attention coefficient according to the reference coefficient to obtain the attention coefficient.

[0183] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented:

[0184] Determine the residence time of the user in each display area according to the eye movement data;

[0185] Determine the ratio of the residence time of each display area to the total residence time of the user on the display page as the reference coefficient of each display area.

[0186] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented:

[0187] Construct a knowledge graph according to the eye movement data and historical service data of the user; the knowledge graph is used to characterize the relationship between the user and the service;

[0188] Determine the prediction service list according to the knowledge graph and the preset prediction model.

[0189] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented:

[0190] Determine the relationship and relationship weight between the entities in the knowledge graph; the entities include the user and the services corresponding to the user;

[0191] Form a weight matrix according to the relationships between entities and the relationship weights.

[0192] Input the weight matrix into a preset prediction model to determine a predicted service list.

[0193] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0194] Determine the first correspondence between the user and each service in the knowledge graph, as well as the second correspondence between each service and each other service.

[0195] Determine the first relationship weight of the first correspondence and the second relationship weight of the second correspondence.

[0196] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the following steps:

[0197] Determine a predicted service list according to the user's eye movement data and historical service data.

[0198] According to the position information, size information, and eye movement data of each display area in the display page, determine the attention coefficient of each display area; the attention coefficient is used to characterize the degree of attention of the user to each display area.

[0199] According to the predicted service list and the attention coefficients of each display area, display each predicted service information in the predicted service list.

[0200] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0201] According to the attention coefficients of each display area and the arrangement order of each predicted service information in the predicted service list, determine the display positions of each predicted service information.

[0202] According to the predicted service list and the display positions of each predicted service information, display each predicted service information in the predicted service list.

[0203] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0204] According to the position information and size information of each display area, determine the initial attention coefficient of each display area.

[0205] Determine the reference coefficient of each display area according to the eye movement data.

[0206] Adjust the initial attention coefficient according to the reference coefficient to obtain the attention coefficient.

[0207] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0208] Determine the residence time of the user in each display area according to the eye movement data;

[0209] Determine the ratio of the residence time of each display area to the total residence time of the user on the display page as the reference coefficient of each display area.

[0210] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0211] Construct a knowledge graph according to the user's eye movement data and historical business data; the knowledge graph is used to represent the relationship between the user and the business;

[0212] Determine a predicted business list according to the knowledge graph and a preset prediction model.

[0213] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0214] Determine the relationships and relationship weights between the entities in the knowledge graph; the entities include users and the corresponding businesses of the users;

[0215] Form a weight matrix according to the relationships and relationship weights between the entities.

[0216] Input the weight matrix into a preset prediction model to determine a predicted business list.

[0217] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0218] Determine the first correspondence between the user and each business in the knowledge graph, and the second correspondence between each business and each business;

[0219] Determine the first relationship weight of the first correspondence and the second relationship weight of the second correspondence.

[0220] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in the present application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in the present application can be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, data processing logics based on quantum computing, etc., without limitation.

[0221] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0222] The above-described embodiments merely represent several implementation manners of the present application. The description is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A business display method, characterized in that: The method includes: Determining a predicted service list according to the user's eye movement data and historical service data; Determining the attention coefficient of each display area according to the position information, size information of each display area in the display page and the eye movement data; the attention coefficient is used to characterize the attention degree of the user to each display area; Displaying each predicted service information in the predicted service list according to the predicted service list and the attention coefficient of each display area.

2. The method according to claim 1, characterized in that, The displaying each predicted service information in the predicted service list according to the predicted service list and the attention coefficient of each display area includes: Determining the display position of each predicted service information according to the attention coefficient of each display area and the arrangement order of each predicted service information in the predicted service list; Displaying each predicted service information in the predicted service list according to the predicted service list and the display position of each predicted service information.

3. The method according to claim 1, characterized in that, The determining the attention coefficient of each display area according to the position information, size information of each display area in the display page and the eye movement data includes: Determining the initial attention coefficient of each display area according to the position information and size information of each display area; Determining the reference coefficient of each display area according to the eye movement data; Adjusting the initial attention coefficient according to the reference coefficient to obtain the attention coefficient.

4. The method according to claim 3, characterized in that, The determining the reference coefficient of each display area according to the eye movement data includes: Determining the residence time of the user in each display area according to the eye movement data; Determining the ratio of the residence time of each display area to the total residence time of the user on the display page as the reference coefficient of each display area.

5. The method according to claim 1, wherein The determining a predicted service list according to the user's eye movement data and historical service data includes: Constructing a knowledge graph according to the user's eye movement data and historical service data; the knowledge graph is used to characterize the relationship between the user and the service; Determining the predicted service list according to the knowledge graph and a preset prediction model.

6. The method according to claim 5, characterized in that The determining the predicted service list according to the knowledge graph and a preset prediction model includes: Determining the relationship and relationship weight between each entity in the knowledge graph; the entities include the user and the services corresponding to the user; Forming a weight matrix according to the relationship and relationship weight between each entity; Inputting the weight matrix into the preset prediction model to determine the predicted service list.

7. The method according to claim 6, characterized in that, The determining the relationship and relationship weight between each entity in the knowledge graph includes: Determining the first corresponding relationship between the user and each service in the knowledge graph, and the second corresponding relationship between each service and each service; Determining the first relationship weight of the first corresponding relationship and the second relationship weight of the second corresponding relationship.

8. A service display device, characterized in that, The device includes: A first determination module, configured to determine a predicted service list according to the user's eye movement data and historical service data; A second determination module, configured to determine an attention coefficient of each of the display areas according to the position information, size information of each display area in the display page and the eye movement data; the attention coefficient is used to characterize the attention degree of the user to each of the display areas; A display module, configured to display each prediction service information in the prediction service list according to the prediction service list and the attention coefficient of each of the display areas.

9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, 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 7 are implemented.

Images