Service function recommendation method and device, storage medium and processor

Abstract

The embodiment of the invention provides a service function recommendation method and device, a storage medium and a processor. The method comprises the following steps: acquiring historical burying point data representing jumping of a user among business functions in a business system and a function page of a current business function where the user is located; selecting one service function from all other service functions except the current service function in sequence; obtaining the historical jump probability of the current service function jumping to the selected service function and the number of service functions capable of jumping to the selected service function in all service functions; determining the current jump probability of jumping from the current service function to the selected service function according to the attribute of the function page, the historical burying point data, the historical jump probability and the number; and determining to recommend the target service function to which the current service function jumps to the user according to all the current jump probabilities, thereby improving the recommendation effect, preventing the user from entering an'information cocoon house ', and improving the user experience.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method for recommending a business function, a recommendation device, a storage medium, a processor, and a computer program product. Background Art

[0002] Current business systems, such as banking business systems, have been equipped with many business functions over time. When using the business system, users may need to click on the function menu or page multiple times to enter the page of the business function they really want to use, which causes great inconvenience to the user. Therefore, there is an urgent need for a business recommendation method based on user usage habits to improve the user experience.

[0003] Existing recommendation schemes generally use random recommendations or make recommendations based on user clicks or historical references, which makes the recommended functions too similar, causing users to enter an "information cocoon", resulting in poor recommendation effects and reduced user experience. Summary of the invention

[0004] The purpose of the embodiments of the present application is to provide a service function recommendation method, recommendation device, storage medium, processor and computer program product.

[0005] In order to achieve the above-mentioned purpose, the first aspect of the present application provides a method for recommending a service function, the method comprising:

[0006] Obtain historical tracking data that represents the user's jumps between various business functions in the business system and the function page of the current business function that the user is in;

[0007] Select one business function from all business functions except the current business function in turn;

[0008] Obtain the historical jump probability of the current business function jumping to the selected business function and the number of business functions that can jump to the selected business function among all business functions;

[0009] Determine the current jump probability of the current business function jumping to the selected business function based on the attributes of the function page, historical tracking data, historical jump probability and quantity;

[0010] The target service function to be recommended to the user to jump from the current service function is determined based on all current jump probabilities.

[0011] In an embodiment of the present application, the current jump probability of the current business function jumping to the selected business function is determined based on the attributes of the function page, historical tracking data, historical jump probability and quantity, including: processing the attributes of the function page, historical tracking data and historical jump probability based on a preset algorithm to obtain the conditional probability of the current business function jumping to the selected business function; and determining the product of the conditional probability and the quantity as the current jump probability.

[0012] In an embodiment of the present application, the attributes, historical tracking data and historical jump probabilities of the function page are processed based on a preset algorithm to obtain the conditional probability of the current business function jumping to the selected business function, including: preprocessing the historical tracking data, and extracting data features that meet preset conditions from the preprocessed historical tracking data; converting the data features into numerical data; processing the attributes, numerical data and historical jump probabilities of the function page based on a preset algorithm to obtain the conditional probability.

[0013] In an embodiment of the present application, the recommendation method also includes: after obtaining the conditional probability of the current business function jumping to the selected business function, generating a probability transition graph for the user's jump behavior based on all business functions and all conditional probabilities, wherein each node in the probability transition graph corresponds to a business function, and the connecting edge between each two nodes represents the jump direction and conditional probability between the corresponding two business functions.

[0014] In an embodiment of the present application, determining the target business function to recommend to the user to jump from the current business function based on all current jump probabilities includes: arranging each business function among all other business functions in descending order according to all current jump probabilities; selecting a preset number of business functions from the arranged business functions in order from high to low as target business functions, and recommending the target business functions to the user.

[0015] In an embodiment of the present application, the recommendation method also includes: after recommending the target business function to the user, obtaining the target business function selected by the user; using the target business function selected by the user as the new current business function, and determining the product of the current jump probability of the target business function selected by the user and a preset number as the current jump probability of the new current business function; determining the target business function recommended to the user to jump from the new current business function based on the current jump probability of the new current business function and the current jump probabilities of business functions in each business function except the new current business function.

[0016] A second aspect of the present application provides a device for recommending a service function, the device comprising:

[0017] The first acquisition module is used to acquire historical tracking data representing the user's jumps between various business functions in the business system and the function page of the current business function where the user is located;

[0018] A selection module is used to select one business function from all business functions except the current business function in sequence;

[0019] The second acquisition module is used to acquire the historical jump probability of the current business function jumping to the selected business function and the number of business functions that can jump to the selected business function among all business functions;

[0020] The first determination module is used to determine the current jump probability of the current business function jumping to the selected business function according to the attributes of the function page, historical embedding data, historical jump probability and quantity;

[0021] The second determination module is used to determine the target service function to be jumped from the current service function and recommended to the user according to all current jump probabilities.

[0022] A third aspect of the present application provides a processor configured to execute the above-mentioned recommendation method for the business function.

[0023] A fourth aspect of the present application provides a machine-readable storage medium having instructions stored thereon, which, when executed by a processor, configures the processor to execute the above-mentioned recommendation method for the business function.

[0024] A fifth aspect of the present application provides a computer program product, including a computer program, which implements the above-mentioned method for recommending business functions when executed by a processor.

[0025] Through the above technical solution, the current jump probability of the user from the current business function to other business functions in the business system can be determined, so as to determine the target business function to be recommended to the user to jump from the current business function, improve the recommendation effect, avoid the user from entering the "information cocoon", and enhance the user experience.

[0026] Other features and advantages of the embodiments of the present application will be described in detail in the subsequent specific implementation section. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present application, but do not constitute a limitation on the embodiments of the present application. In the accompanying drawings:

[0028] Figure 1 A schematic diagram of a process flow of a method for recommending a business function according to an embodiment of the present application is shown schematically;

[0029] Figure 2 A schematic diagram of a probability conversion diagram according to an embodiment of the present application is schematically shown;

[0030] Figure 3 Another flowchart of a method for recommending a business function according to an embodiment of the present application is schematically shown;

[0031] Figure 4 The following schematically shows a flow chart of constructing a user behavior probability matrix according to an embodiment of the present application;

[0032] Figure 5 A structural block diagram of a device for recommending business functions according to an embodiment of the present application is schematically shown;

[0033] Figure 6 The internal structure diagram of a computer device according to an embodiment of the present application is schematically shown. DETAILED DESCRIPTION

[0034] In order to make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the specific implementation methods described herein are only used to illustrate and explain the embodiments of the present application, and are not used to limit the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0035] It should be noted that if the embodiments of the present application involve directional indications (such as up, down, left, right, front, back...), the directional indications are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0036] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present application, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or suggesting their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0037] The acquisition, transmission, storage, use, and processing of data in the technical solution of this application are in compliance with the relevant provisions of national laws and regulations. In addition, it should be noted that in the embodiments of this application, some existing solutions in the industry such as certain software, components, and models may be mentioned, which should be considered as exemplary, and their purpose is only to illustrate the feasibility of the implementation of the technical solution of this application, but it does not mean that the applicant has or will necessarily use the solution.

[0038] Figure 1 The flowchart of the method for recommending a service function according to an embodiment of the present application is schematically shown. Figure 1 As shown, in one embodiment of the present application, a method for recommending a business function is provided, comprising the following steps:

[0039] Step 101, obtaining historical tracking data representing the user's jumps between various business functions in the business system and the function page of the current business function where the user is located.

[0040] Step 102: Select one business function from all business functions except the current business function in sequence.

[0041] Step 103 : Obtain the historical jump probability of the current service function jumping to the selected service function and the number of service functions that can jump to the selected service function among all service functions.

[0042] Step 104, determine the current jump probability of the current business function jumping to the selected business function according to the attributes of the function page, historical tracking data, historical jump probability and quantity.

[0043] Step 105 : Determine a target service function to be recommended to the user to jump from the current service function according to all current jump probabilities.

[0044] The business system refers to the business links required for an enterprise to achieve its positioning, the roles played by each partner, and the ways and contents of cooperation and transactions between stakeholders. The business system may be a banking system, including a series of banking business systems. It can be understood that business functions may include financial management, business management, inventory management, exchange rate risk management, and service management, etc., and the jump may refer to jumping from the financial management function to business management or inventory management, etc. The processor may obtain historical point-of-sale data representing the jump between various business functions in the business system and the function page of the current business function where the user is located. The historical point-of-sale data may include data such as user ID, user position, and function page residence time. The function page may include various business positions, business types, etc. In an optional embodiment, the historical point-of-sale data of the various business functions of the business system and the jump between various business functions may be pre-stored in a database, and the processor may directly obtain the historical point-of-sale data of the jump between various business functions from the database. After obtaining the function page of the current business function where the user is located, the processor may select a business function from all business functions except the current business function in turn. The processor may obtain the historical jump probability of the current service function jumping to the selected service function and the number of service functions that can jump to the selected service function among all service functions.

[0045] For example, the business system includes M business functions, and the current business function of the user is business function 1, then there are (M-1) business functions left. The processor can select one business function from the remaining (M-1) business functions in turn, assuming that business function 2 to business function M can be selected in turn according to the sequence number of the business function. Then the processor can obtain the historical jump probability of business function 1 jumping to business function 2 and the number of business functions that can jump to business function 2 among the M business functions. Assuming that business function 1 and business function 3 can jump to business function 2, the number is 2. In an optional embodiment, a storage module may be provided, and a plurality of probability jump graphs may be stored in the storage module, and each probability jump graph corresponds to the historical jump probability of the user jumping from one function to other functions. Alternatively, a probability jump graph may be stored in the storage module, and the probability jump graph includes each business function and the historical jump probability between business functions that can jump.

[0046] After obtaining the historical jump probability of the current business function jumping to the selected business function and the number of business functions that can jump to the selected business function among all business functions, the processor can determine the current jump probability of the current business function jumping to the selected business function based on the attributes of the function page of the current business function, such as the job type, function type, page status, etc. of the functional business, historical buried data, historical jump probability and number. After determining the current jump probability of the user jumping from the current business function to other business functions, the processor can determine to recommend to the user the target business function to jump from the current business function based on all the current jump probabilities, so as to reduce the number of recommendations to the user, improve the recommendation accuracy, and enhance the user experience.

[0047] In an embodiment of the present application, the current jump probability of the current business function jumping to the selected business function is determined based on the attributes of the function page, historical tracking data, historical jump probability and quantity, including: processing the attributes of the function page, historical tracking data and historical jump probability based on a preset algorithm to obtain the conditional probability of the current business function jumping to the selected business function; and determining the product of the conditional probability and the quantity as the current jump probability.

[0048] The processor can determine the current jump probability of the current business function jumping to the selected business function based on the attributes of the function page, historical buried data, historical jump probability and quantity. Specifically, the processor can process the attributes of the function page, historical buried data and historical jump probability based on a preset algorithm such as the Naive Bayes algorithm to obtain the conditional probability of the current business function jumping to the selected business function. After obtaining the conditional probability of the current business function jumping to the selected business function, the processor can determine the current jump probability as the product of the conditional probability and quantity of the current business function jumping to the selected business function, so that the current jump probability obtained is more accurate, providing better support for subsequent business function recommendations.

[0049] In an optional embodiment, the processor may also input the attributes, historical embedding data, historical jump probability and quantity of the function page into the probability model to output the current jump probability of the user jumping from the current business function to the selected business function through the probability model. The probability model may be constructed based on the page attributes, historical embedding data, historical jump data of the pages of multiple business functions and the number of business functions that can be jumped into corresponding to each of the multiple business functions.

[0050] In an embodiment of the present application, the attributes, historical tracking data and historical jump probabilities of the function page are processed based on a preset algorithm to obtain the conditional probability of the current business function jumping to the selected business function, including: preprocessing the historical tracking data, and extracting data features that meet preset conditions from the preprocessed historical tracking data; converting the data features into numerical data; processing the attributes, numerical data and historical jump probabilities of the function page based on a preset algorithm to obtain the conditional probability.

[0051] The processor can process the attributes, historical buried data and historical jump probabilities of the function page based on a preset algorithm to obtain the conditional probability that the current business function jumps to the selected business function. Specifically, the processor can preprocess the historical buried data, such as data cleaning, removing outliers and missing values, etc. And extract data features that meet the preset conditions from the preprocessed historical buried data. The preset conditions can be determined by the user based on the processing requirements of the preset algorithm, such as determined based on the computing requirements of the naive Bayes algorithm. After extracting the data features that meet the preset conditions, the processor can convert the data features into numerical data. After obtaining the converted numerical data, the processor can process the attributes, numerical data and historical jump probabilities of the function page based on the preset algorithm to obtain the conditional probability that the current business function jumps to the selected business function, so that the obtained conditional probability is more accurate.

[0052] For example, the current business function of the user is function 1, and the selected business function is function 2. The processor can obtain the attributes of the page function of function 1, including position type and function type. The position type is position a and the function type is function type a. The processor can also pre-process historical buried data such as user ID, user position, function page residence time and other data, and extract data features that meet the preset conditions from the pre-processed historical buried data, such as function category, process link, current position, processing opinion, page residence time, etc. After obtaining the data features, the processor can convert the data features into numerical data such as the processing duration type of function 1 is duration type a. The processor can process position a, function type a, duration type a and the historical jump probability P (jump) of function 1 jumping to function 2 based on the naive Bayes algorithm to obtain the conditional probability P (jump│position a, function type a, duration type a) of function 1 jumping to function 2. Specifically, P(jump│position a, function type a, duration type a)=(P(position a, function type a, duration type a│jump)*P(jump)) / (P(position a, function type a, duration type a)). Based on the Naive Bayesian assumption that features are independent of each other, P(position a, function type a, duration type a│jump)=P(position a|jump)*P(function type a|jump)*P(duration type a|jump). Finally, it can be determined that P(jump│position a, function type a, duration type a)=(P(position a, function type a, duration type a│jump)*P(jump)) / P(position a, function type a, duration type a)=(P(position a|jump)*P(function type a|jump)*P(duration type a|jump)*P(jump)) / (P(position a)*P(function type a)*P(duration type a)).

[0053] In an embodiment of the present application, the recommendation method also includes: after obtaining the conditional probability of the current business function jumping to the selected business function, generating a probability transition graph for the user's jump behavior based on all business functions and all conditional probabilities, wherein each node in the probability transition graph corresponds to a business function, and the connecting edge between each two nodes represents the jump direction and conditional probability between the corresponding two business functions.

[0054] After obtaining the conditional probability of the current business function jumping to the selected business function, the processor can generate a probability transition graph for the user's jump behavior based on all business functions and all conditional probabilities. In the probability transition graph, each node corresponds to a business function, and the connection edge between each two nodes represents the jump direction and conditional probability between the corresponding two business functions, so as to intuitively display the jump relationship and conditional probability between each business function, and improve the efficiency of recommending business functions to users in the future. Figure 2As shown, the business system may include 9 functions, namely function 1, function 2, function 3, function 4, function 5, function 6, function 7, function 8, and function 9. The conditional probability of function 1 jumping to function 5 is 0.1, the conditional probability of function 1 jumping to function 2 is 0.3, the conditional probability of function 1 jumping to function 3 is 0.1, the conditional probability of function 1 jumping to function 7 is 0.4, the conditional probability of function 1 jumping to function 4 is 0.1, the conditional probability of function 2 jumping to function 5 is 0.3, the conditional probability of function 2 jumping to function 6 is 0.4, the conditional probability of function 2 jumping to function 7 is 0.3, the conditional probability of function 3 jumping to function 6 is 0.4, the conditional probability of function 3 jumping to function 7 is 0.6, the conditional probability of function 5 jumping to function 8 is 0.6, the conditional probability of function 5 jumping to function 9 is 0.4, and the conditional probability of function 6 jumping to function 9 is 1.

[0055] In an embodiment of the present application, determining the target business function to recommend to the user to jump from the current business function based on all current jump probabilities includes: arranging each business function among all other business functions in descending order according to all current jump probabilities; selecting a preset number of business functions from the arranged business functions in order from high to low as target business functions, and recommending the target business functions to the user.

[0056] The processor may determine the target business function to be jumped from the current business function to be recommended to the user according to all current jump probabilities. Specifically, the processor may arrange each business function among all other business functions in descending order according to all current jump probabilities. A preset number of business functions are selected from the arranged business functions in descending order as target business functions, and the target business functions are recommended to the user to improve the rationality of the recommendation. The preset number may be determined by the user according to demand.

[0057] In an optional embodiment, the processor may select a preset number of business functions from all current jump probabilities as target business functions according to a preset selection rule, and recommend the target functions to the user. The preset selection rule may define selection conditions such as the range of the current jump probability and the selection order such as from high to low.

[0058] In a specific embodiment, assuming that the user is currently in function 1, the processor can process the attributes of the function page of function 1, the numerical data, and the historical jump probability of function 1 jumping to function 2 to function 9 based on the naive Bayes algorithm to determine that the conditional probability of the user jumping from function 1 to function 2 to function 9 is 0.3, 0.1, 0.1, 0.09, 0.04, 0.55, 0.054, 0.076 respectively. And generate a jump matrix IP1 = [0, 0.3, 0.1, 0.1, 0.09, 0.04, 0.55, 0.054, 0.076], where 0 represents no jump in function 1. The processor can obtain that the number of functions that can jump to function 2 among the 9 functions is 1, the number of functions that can jump to function 3 is 1, the number of functions that can jump to function 4 is 1, the number of functions that can jump to function 5 is 2, the number of functions that can jump to function 6 is 2, the number of functions that can jump to function 7 is 3, the number of functions that can jump to function 8 is 1, and the number of functions that can jump to function 9 is 2. After obtaining each number, the processor can determine the product of the conditional probability and the number of each function as the current jump probability of each function, and generate a new jump matrix RP1 = [0, 0.3, 0.1, 0.1, 0.09*2, 0.04*2, 0.55*3, 0.054, 0.076*2] = [0, 0.3, 0.1, 0.1, 0.18, 0.08, 1.65, 0.054, 0.152].

[0059] After obtaining the current jump probability of each function, the processor can arrange the functions in descending order based on the current jump probability of each function, and the arranged functions are function 7, function 2, function 5, function 9, function 3, function 4, function 6, and function 8. After obtaining the sorted functions, the processor can recommend the first three functions to the user in descending order, that is, recommend to the user that it is possible to jump from function 1 to function 7, function 2, and function 5, and give a limited number of recommended functions to improve the user experience.

[0060] In an embodiment of the present application, the recommendation method also includes: after recommending the target business function to the user, obtaining the target business function selected by the user; using the target business function selected by the user as the new current business function, and determining the product of the current jump probability of the target business function selected by the user and a preset number as the current jump probability of the new current business function; determining the target business function recommended to the user to jump from the new current business function based on the current jump probability of the new current business function and the current jump probabilities of business functions in each business function except the new current business function.

[0061] After recommending the target business function to the user, the processor can obtain the target business function selected by the user, that is, a target business function that the user chooses to jump to from the current business function. After obtaining the target business function selected by the user, the processor can use the target business function selected by the user as the new current business function, and determine the product of the current jump probability of the target business function selected by the user and a preset number as the current jump probability of the new current business function. After obtaining the current jump probability of the new current business function, the processor can determine the target business function recommended to the user to jump to from the new current business function based on the current jump probability of the new current business function and the current jump probabilities of business functions other than the new current business function in each business function, so as to update the current probability of each business function based on the real-time selection of the user, and improve the accuracy of subsequent function recommendations.

[0062] In an optional embodiment, after recommending the target business function to the user, the processor may obtain the target business function selected by the user, and use the target business function selected by the user as the new current business function, and then return to the step of selecting a business function from all business functions except the current business function in sequence, until the target business function to be recommended to the user to jump to from the current business function is determined.

[0063] like Figure 3 As shown in FIG. 1 , for a banking system, the processor can read the corresponding position matrix into the cache, and find the N functions with the highest probability according to the user behavior probability matrix according to the different functions of the current user, where N is a natural number. Specifically, the processor can construct a user behavior probability matrix according to each position of the banking system. Figure 4 As shown, the processor can obtain the tracking data from the tracking table. Then determine whether the job polling is over. If the job polling is not over, the processor can obtain the corresponding tracking set according to the job, and then obtain the probability of each edge according to the user's historical behavior in the tracking table, that is, the jump probability between two functions. When the job polling is over, the processor can construct a user behavior probability matrix according to the job. After obtaining the user behavior probability matrix, the processor can find the N functions with the highest probability according to the user behavior probability matrix. After finding the N functions with the highest probability, the processor can recommend N functions to the user and adjust the weights of the corresponding functions according to the function that the user finally clicked.

[0064] For example, the current business function of the user is function 1, and the processor determines that the current jump probabilities of jumping from function 1 to other business functions including function 2, function 3, function 4, function 5, function 6, function 7, function 8, and function 9 are 0.3, 0.1, 0.1, 0.18, 0.08, 1.65, 0.054, and 0.152 respectively. The target business functions recommended by the processor to the user are function 7, function 2, and function 5 respectively, that is, the user can jump from function 1 to function 7, function 2, and function 5. Assume that the user selects function 5, that is, the user chooses to jump from function 2 to function 5. The processor can determine the product of the current jump probability of function 5, 0.18, and the recommendation quantity 3, 0.54, as the new current jump probability of function 5, that is, the current jump probability of each function is converted into 0.3, 0.1, 0.1, 0.54, 0.08, 1.65, 0.054, and 0.152. The processor can determine that when the user jumps to function 5, the recommended order of the functions recommended to the user is function 7, function 5, function 2, function 9, function 3, function 4, function 6, and function 8 based on the current jump probability of each function converted into 0.3, 0.1, 0.1, 0.54, 0.08, 1.65, 0.054, and 0.152.

[0065] Through the above technical solution, the current jump probability of the user from the current business function to other business functions in the business system can be determined, so as to determine the target business function to be recommended to the user to jump from the current business function, improve the recommendation effect, avoid the user from entering the "information cocoon", and enhance the user experience.

[0066] Figure 1 and Figure 3 FIG. 1 is a flowchart of a method for recommending a business function in an embodiment. It should be understood that although Figure 1 and Figure 3 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 1 and Figure 3 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0067] In one embodiment, Figure 5As shown, a device for recommending business functions is provided, comprising a first acquisition module, a selection module, a second acquisition module, a first determination module and a second determination module, wherein:

[0068] The first acquisition module 501 is used to acquire historical tracking data representing the user's jumps between various business functions in the business system and the function page of the current business function where the user is located.

[0069] The selection module 502 is used to sequentially select a business function from all business functions except the current business function.

[0070] The second acquisition module 503 is used to acquire the historical jump probability of the current service function jumping to the selected service function and the number of service functions that can jump to the selected service function among all service functions.

[0071] The first determination module 504 is used to determine the current jump probability of the current business function jumping to the selected business function according to the attributes of the function page, historical tracking data, historical jump probability and quantity.

[0072] The second determination module 505 is used to determine the target service function to be jumped from the current service function and recommended to the user according to all current jump probabilities.

[0073] In one embodiment, the first determination module 504 is used to determine the current jump probability of the current business function jumping to the selected business function based on the attributes of the function page, historical tracking data, historical jump probability, and quantity. Specifically, the first determination module 504 can process the attributes of the function page, historical tracking data, and historical jump probability based on a preset algorithm to obtain the conditional probability of the current business function jumping to the selected business function. After obtaining the conditional probability of the current business function jumping to the selected business function, the first determination module 504 can determine the product of the conditional probability and the quantity as the current jump probability.

[0074] In one embodiment, the first determination module 504 can process the attributes, historical tracking data, and historical jump probability of the function page based on a preset algorithm to obtain the conditional probability of the current business function jumping to the selected business function. Specifically, the first determination module 504 can pre-process the historical tracking data and extract data features that meet the preset conditions from the pre-processed historical tracking data. After obtaining the data features, the first determination module 504 can convert the data features into numerical data; and process the attributes, numerical data, and historical jump probability of the function page based on a preset algorithm to obtain the conditional probability.

[0075] In one embodiment, after obtaining the conditional probability of the current business function jumping to the selected business function, the first determination module 504 can also generate a probability transition graph for the user's jump behavior based on all business functions and all conditional probabilities, wherein each node in the probability transition graph corresponds to a business function, and the connecting edge between each two nodes represents the jump direction and conditional probability between the corresponding two business functions.

[0076] In one embodiment, the second determination module 505 is used to determine the target business function to be jumped from the current business function to be recommended to the user according to all current jump probabilities. Specifically, the second determination module 505 can arrange each business function among all other business functions in descending order according to all current jump probabilities. After obtaining the sorted business functions, the second determination module 505 can select a preset number of business functions from the sorted business functions in descending order as target business functions, and recommend the target business functions to the user.

[0077] In one embodiment, after recommending the target business function to the user, the second determination module 505 may further obtain the target business function selected by the user. After obtaining the target business function selected by the user, the second determination module 505 may use the target business function selected by the user as the new current business function, and determine the product of the current jump probability of the target business function selected by the user and the preset number as the current jump probability of the new current business function. After obtaining the current jump probability of the new current business function, the second determination module 505 may determine the target business function recommended to the user to jump from the new current business function based on the current jump probability of the new current business function and the current jump probabilities of business functions other than the new current business function in each business function.

[0078] The business function recommendation device includes a processor and a memory. The first acquisition module, selection module, second acquisition module, first determination module and second determination module are all stored in the memory as program units, and the processor executes the program modules stored in the memory to implement corresponding functions.

[0079] The processor includes a kernel, which calls the corresponding program unit from the memory. One or more kernels can be set, and the recommended method for business functions can be implemented by adjusting kernel parameters.

[0080] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0081] An embodiment of the present application provides a storage medium on which a program is stored. When the program is executed by a processor, a recommendation method for implementing the above-mentioned business function is implemented.

[0082] An embodiment of the present application provides a processor, which is used to run a program, wherein the program executes the recommended method of the above-mentioned business function when running.

[0083] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 6 As shown. The computer device includes a processor A01, a network interface A02, a memory (not shown in the figure) and a database (not shown in the figure) connected via a system bus. Among them, the processor A01 of the computer device is used to provide computing and control capabilities. The memory of the computer device includes an internal memory A03 and a non-volatile storage medium A04. The non-volatile storage medium A04 stores an operating system B01, a computer program B02 and a database (not shown in the figure). The internal memory A03 provides an environment for the operation of the operating system B01 and the computer program B02 in the non-volatile storage medium A04. The database of the computer device is used to store data such as attributes of the function page, historical buried point data, historical jump probability, quantity and current jump probability. The network interface A02 of the computer device is used to communicate with an external terminal through a network connection. When the computer program B02 is executed by the processor A01, a method for recommending a business function is implemented.

[0084] Those skilled in the art will understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0085] An embodiment of the present application provides a device, which includes a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, the following steps are implemented: obtaining historical tracking data representing the user's jumps between various business functions in the business system and the function page of the current business function where the user is located; selecting one business function from all business functions except the current business function in turn; obtaining the historical jump probability of the current business function jumping to the selected business function and the number of business functions that can jump to the selected business function from all business functions; determining the current jump probability of the current business function jumping to the selected business function based on the attributes of the function page, the historical tracking data, the historical jump probability and the number; and determining the target business function to be recommended to the user to jump from the current business function based on all the current jump probabilities.

[0086] In one embodiment, the current jump probability of the current business function jumping to the selected business function is determined based on the attributes of the function page, historical tracking data, historical jump probability and quantity, including: processing the attributes of the function page, historical tracking data and historical jump probability based on a preset algorithm to obtain the conditional probability of the current business function jumping to the selected business function; and determining the product of the conditional probability and the quantity as the current jump probability.

[0087] In one embodiment, the attributes, historical tracking data and historical jump probabilities of the function page are processed based on a preset algorithm to obtain the conditional probability of the current business function jumping to the selected business function, including: preprocessing the historical tracking data, and extracting data features that meet preset conditions from the preprocessed historical tracking data; converting the data features into numerical data; processing the attributes, numerical data and historical jump probabilities of the function page based on a preset algorithm to obtain the conditional probability.

[0088] In one embodiment, the recommendation method also includes: after obtaining the conditional probability of the current business function jumping to the selected business function, generating a probability transition graph for the user's jump behavior based on all business functions and all conditional probabilities, wherein each node in the probability transition graph corresponds to a business function, and the connecting edge between each two nodes represents the jump direction and conditional probability between the corresponding two business functions.

[0089] In one embodiment, determining a target business function to recommend to a user to jump from a current business function based on all current jump probabilities includes: arranging each business function among all other business functions in descending order based on all current jump probabilities; selecting a preset number of business functions from the arranged business functions in order from high to low as target business functions, and recommending the target business functions to the user.

[0090] In one embodiment, the recommendation method also includes: after recommending the target business function to the user, obtaining the target business function selected by the user; using the target business function selected by the user as the new current business function, and determining the product of the current jump probability of the target business function selected by the user and a preset number as the current jump probability of the new current business function; determining the target business function recommended to the user to jump from the new current business function based on the current jump probability of the new current business function and the current jump probabilities of business functions in each business function except the new current business function.

[0091] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing the recommended method steps for initializing a business function.

[0092] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0093] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0094] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0095] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0096] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0097] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0098] Computer readable media include permanent and non-permanent, removable and non-removable media, and can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0099] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0100] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for recommending a business function, characterized in that: The recommended methods include: Obtain historical tracking data representing the user's jumps between various business functions in the business system and the function page of the current business function where the user is located; Selecting one business function from all business functions except the current business function in sequence; Obtaining a historical jump probability of the current service function jumping to the selected service function and the number of service functions that can jump to the selected service function among all service functions; Determine the current jump probability of the current business function jumping to the selected business function according to the attribute of the function page, the historical tracking data, the historical jump probability and the quantity; Determine, according to all current jump probabilities, a target service function to be jumped from the current service function and recommended to the user.

2. The method for recommending business functions according to claim 1, characterized in that: Determining the current jump probability of the current business function jumping to the selected business function according to the attribute of the function page, the historical tracking data, the historical jump probability and the quantity includes: Processing the attributes of the function page, the historical tracking data, and the historical jump probability based on a preset algorithm to obtain a conditional probability of the current business function jumping to the selected business function; The product of the conditional probability and the number is determined as the current jump probability.

3. The method for recommending business functions according to claim 2, characterized in that: Processing the attributes of the function page, the historical tracking data, and the historical jump probability based on a preset algorithm to obtain the conditional probability of the current business function jumping to the selected business function includes: Preprocessing the historical point-of-sale data, and extracting data features that meet preset conditions from the preprocessed historical point-of-sale data; Converting the data features into numerical data; The attribute of the function page, the numerical data and the historical jump probability are processed based on the preset algorithm to obtain the conditional probability.

4. The method for recommending business functions according to claim 2, characterized in that: The recommended method also includes: After obtaining the conditional probability of the current business function jumping to the selected business function, a probability transition graph for the user's jump behavior is generated based on all business functions and all conditional probabilities, wherein each node in the probability transition graph corresponds to a business function, and the connecting edge between each two nodes represents the jump direction and conditional probability between the corresponding two business functions.

5. The method for recommending business functions according to claim 1, characterized in that: Determining, according to all current jump probabilities, to recommend to the user a target service function to jump from the current service function comprises: Arrange each of the other business functions in descending order according to all the current jump probabilities; A preset number of business functions are selected from the arranged business functions in descending order as target business functions, and the target business functions are recommended to the user.

6. The method for recommending business functions according to claim 5, characterized in that: The recommended method also includes: After recommending the target service function to the user, obtaining the target service function selected by the user; Taking the target service function selected by the user as the new current service function, and determining the product of the current jump probability of the target service function selected by the user and the preset number as the current jump probability of the new current service function; A target service function to be recommended to the user to jump from the new current service function is determined according to the current jump probability of the new current service function and the current jump probabilities of service functions other than the new current service function among the service functions.

7. A device for recommending business functions, characterized in that: The recommended devices include: The first acquisition module is used to acquire historical tracking data representing the user's jumps between various business functions in the business system and the function page of the current business function where the user is located; A selection module, used to select one business function from all business functions except the current business function in sequence; A second acquisition module is used to acquire a historical jump probability of the current service function jumping to the selected service function and the number of service functions that can jump to the selected service function among all service functions; A first determination module is used to determine the current jump probability of the current business function jumping to the selected business function according to the attributes of the function page, the historical tracking data, the historical jump probability and the quantity; The second determining module is used to determine, according to all current jump probabilities, a target service function to be jumped from the current service function and recommended to the user.

8. A processor, characterized in that: A method for recommending a service function configured to execute the service function according to any one of claims 1 to 6.

9. A machine-readable storage medium having instructions stored thereon, characterized in that: When the instruction is executed by a processor, the processor is configured to execute the method for recommending a business function according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the computer program implements the method for recommending a business function according to any one of claims 1 to 6.

Images