Digital application recommendation method and device, equipment and storage medium

Abstract

The invention relates to the technical field of precision marketing, and provides a digital application recommendation method, device and equipment and a storage medium, and the method comprises the steps: obtaining application basic data of an existing application of a user, carrying out the evaluation and analysis of the application basic data based on a preset index evaluation system, and obtaining an evaluation result of the existing application; determining a scheme recommendation rule according to the evaluation result; performing query matching on applications in a preset application resource pool according to the scheme recommendation rule to obtain a required application list and a to-be-selected application list; and based on constraint conditions in the scheme recommendation rule, screening out a target application from the to-be-selected application list, adding the target application into a required application list, combining the target application with the required application, and obtaining an application combination scheme to be recommended to the user. Existing applications of a user are evaluated and analyzed by constructing an index evaluation system, and user requirements are quickly mined, so that an application combination scheme meeting the requirements of the user is recommended to the user, and the application cost of the user is reduced while the application recommendation efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the field of precision marketing technology, and in particular to a digital application recommendation method, device, equipment and storage medium. Background Art

[0002] With the rapid development of artificial intelligence and big data technologies, the importance of data assets has become increasingly prominent. Digital transformation is becoming a key component of corporate competitiveness. Most companies have gradually integrated digital capabilities into production and operations to improve production capacity and efficiency. As an important component of realizing digital capabilities, the selection and use of digital applications by enterprises is particularly important. However, due to the wide variety and different functions of digital applications, enterprises are unable to select applications that meet their own needs from a large number of digital applications in a self-service manner. The existing recommendation methods for digital applications are mainly based on typical cases for specific users and solutions for industries or scenarios. They are extensive application combination recommendation models. For different users in different industries, a large amount of preliminary research, analysis and verification are required to customize application solutions, which have problems such as high cost and low efficiency. Summary of the invention

[0003] The present invention provides a digital application recommendation method, device, equipment and storage medium, which are used to solve the defects of high cost and low efficiency in the existing extensive application combination recommendation mode.

[0004] The present invention provides a digital application recommendation method, comprising: Obtaining application basic data of the user's existing applications, and evaluating and analyzing the application basic data based on a preset indicator evaluation system to obtain an evaluation result of the existing applications; Determine a solution recommendation rule according to the evaluation result; the solution recommendation rule includes a constraint condition; According to the solution recommendation rule, the applications in the preset application resource pool are queried and matched to obtain a list of required applications and a list of to-be-selected applications; Based on the constraint condition, a target application is screened out from the candidate application list, added to the mandatory application list, and combined with each mandatory application in the mandatory application list to obtain an application combination solution, and the application combination solution is recommended to the user.

[0005] According to the digital application recommendation method provided by the present invention, based on the constraint condition, the target application is screened out from the candidate application list, added to the mandatory application list, and combined with each mandatory application in the mandatory application list to obtain an application combination scheme, including: Determine, according to the evaluation result, a first evaluation score of each indicator of each mandatory application in the mandatory application list under the indicator evaluation system; Based on the first evaluation score and the preset full score values ​​of each indicator under the indicator evaluation system, calculating the full score difference of each indicator under the indicator evaluation system for each required application in the required application list; Determine the target indicator with the largest full score difference, and calculate the recommendation score of each candidate application in the candidate application list under the target indicator; Sort the applications to be selected in the list of applications to be selected in descending order according to the recommendation score; Selecting a target application according to the sorting order of each candidate application in the candidate application list, and combining the target application with each mandatory application in the mandatory application list to obtain an application combination scheme; the target application is a candidate application marked as unselected; Calculating a solution score of the application combination solution, and determining whether the application combination solution satisfies the constraint condition according to the solution score; If the application solution does not satisfy the constraint condition, the target application is removed from the list of candidate applications, and the process returns to and executes the step of selecting the target application according to the sorting order of the candidate applications in the list of candidate applications; If the application combination scheme satisfies the constraint condition, the target application is marked as selected and added to the required application list, and the step of selecting the target application according to the sorting order of the to-be-selected applications in the to-be-selected application list is returned and executed until the target application is the last to-be-selected application in the to-be-selected application list, or the number of target applications added to the required application list reaches the preset number of applications.

[0006] According to the digital application recommendation method provided by the present invention, the step of calculating the solution score of the application combination solution includes: Determine, according to the evaluation result, a second evaluation score for each indicator of the target application under the indicator evaluation system; Calculating target evaluation scores of various indicators of the application combination solution under the indicator evaluation system based on the first evaluation score and the second evaluation score; The target evaluation scores are summed to obtain a solution score of the application combination solution.

[0007] According to the digital application recommendation method provided by the present invention, determining the first evaluation score of each indicator of each mandatory application in the mandatory application list under the indicator evaluation system according to the evaluation result includes: According to the evaluation result, determine the indicator value and indicator score of each mandatory application in the mandatory application list under the first indicator; the first indicator is any one of the indicators under the indicator evaluation system; Obtaining a preset indicator weight for the first indicator, and weighting the indicator value of the first indicator based on the indicator weight to obtain a weighted indicator value; The sum of the weighted index value and the index score of the first index is calculated to obtain a first evaluation score of each mandatory application in the mandatory application list under the first index.

[0008] According to the digital application recommendation method provided by the present invention, the calculation of the recommendation score of each candidate application in the candidate application list under the target indicator includes: Determine the target indicator value of each candidate application in the candidate application list under the target indicator according to the evaluation result, obtain the recommendation weight of each candidate application in the candidate application list, and the target full score value preset for the target indicator; The ratio of the target indicator value to the target full score value is calculated, and the ratio and the recommendation weight are weightedly summed to obtain the recommendation score of each candidate application in the candidate application list under the target indicator.

[0009] According to the digital application recommendation method provided by the present invention, the application in the preset application resource pool is queried and matched according to the solution recommendation rule to obtain a required application list and a to-be-selected application list, including: According to the mandatory application configuration in the solution recommendation rule, query and match the applications in the preset application resource pool to obtain an initial mandatory application list; Deduplication of the initial mandatory application list is performed based on the existing applications to obtain a mandatory application list; According to the optional application configuration in the solution recommendation rule, query and match the applications in the application resource pool to obtain an initial list of candidate applications; The initial list of to-be-selected applications is deduplicated based on the existing applications to obtain a list of to-be-selected applications.

[0010] According to the digital application recommendation method provided by the present invention, the application basic data is evaluated and analyzed based on a preset indicator evaluation system to obtain an evaluation result of the existing application, including: Based on the finest-grained indicator in the preset indicator evaluation system, the application basic data is evaluated and analyzed to determine the indicator value of the finest-grained indicator; Determining an indicator score of the finest-grained indicator according to the indicator value of the finest-grained indicator; Based on the indicator value and indicator score of the finest-grained indicator, the multi-level indicators in the indicator evaluation system are evaluated level by level to obtain the evaluation result of the existing application; wherein, the indicator value of any N-th level indicator in the indicator evaluation system is the sum of the indicator values ​​of the N+1-th level indicators under the N-th level indicator, and the indicator score of the N-th level indicator is the sum of the indicator scores of the N+1-th level indicators under the N-th level indicator.

[0011] The present invention also provides a digital application recommendation device, comprising the following modules: An indicator evaluation module is used to obtain application basic data of the user's existing applications, and based on a preset indicator evaluation system, evaluate and analyze the application basic data to obtain an evaluation result of the existing application; A rule determination module, used to determine a solution recommendation rule according to the evaluation result; the solution recommendation rule includes a constraint condition; An application matching module, used to query and match applications in a preset application resource pool according to the solution recommendation rule, and obtain a list of required applications and a list of to-be-selected applications; The application recommendation module is used to filter out target applications from the candidate application list based on the constraint conditions, add the target applications to the mandatory application list, combine them with the mandatory applications in the mandatory application list, obtain an application combination solution, and recommend the application combination solution to the user.

[0012] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of any one of the digital application recommendation methods described above are implemented.

[0013] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of any of the digital application recommendation methods described above are implemented.

[0014] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the steps of any one of the digital application recommendation methods described above are implemented.

[0015] The digital application recommendation method, device, equipment and storage medium provided by the present invention determine the solution recommendation rules by evaluating and analyzing the user's existing applications, thereby querying and matching the required application list and the candidate application list, and according to the constraints in the solution recommendation rules, screen out the target applications that meet the constraints from the candidate application list and add them to the required application list, and combine them with the required applications in the required application list to obtain an application combination solution and recommend it to the user. By constructing an indicator evaluation system to evaluate and analyze the user's existing applications, the user's actual needs for digital applications can be quickly explored, so as to recommend application combination solutions that meet their needs to the user, thereby improving the efficiency of application recommendation and reducing the user's application costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 It is a flow chart of the digital application recommendation method provided by the present invention.

[0018] Figure 2 It is a structural schematic diagram of the indicator evaluation system provided by the present invention.

[0019] Figure 3 It is a structural schematic diagram of the digital application recommendation device provided by the present invention.

[0020] Figure 4 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0021] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0022] Figure 1 is a flow chart of the digital application recommendation method provided by the present invention, such as Figure 1 As shown, the method comprises the following steps: Step 100, obtaining application basic data of the user's existing applications, and evaluating and analyzing the application basic data based on a preset indicator evaluation system to obtain an evaluation result of the existing applications; Step 200, determining a solution recommendation rule according to the evaluation result; the solution recommendation rule includes a constraint condition; Step 300, query and match applications in a preset application resource pool according to the solution recommendation rule to obtain a required application list and a to-be-selected application list; Step 400 , based on the constraint condition, select a target application from the candidate application list, add the target application to the mandatory application list, combine the target application with the mandatory applications in the mandatory application list, obtain an application combination solution, and recommend the application combination solution to the user.

[0023] When recommending digital applications to users, we first obtain the basic application data of the user's existing applications. It should be noted that digital applications are software or hardware systems applied by users to production and operation links. For the convenience of calculation, digital applications have inherent attributes such as application type, application function and application effect, as well as additional attributes such as recommendation weight and price. The user here can be an enterprise, unit or individual, and the basic application data includes data such as application type, usage and user behavior of existing applications.

[0024] Based on the preset indicator evaluation system, the application basic data is evaluated and analyzed to obtain the evaluation results of the existing applications. The solution recommendation rules are determined based on the evaluation results. The solution recommendation rules contain constraints on application recommendations, which include but are not limited to the types of applications that can be recommended, the number of recommendations, and the types of applications that must be selected.

[0025] In one embodiment, the solution recommendation rules are the rules used when recommending applications. When determining the solution recommendation rules based on the evaluation results, the application scenarios are determined based on the evaluation results of existing applications, and the solution recommendation rules are determined based on the application scenarios. Different scenarios correspond to different solution recommendation rules. Furthermore, different solution recommendation rules are distinguished based on the rule content, which specifically includes the rule name, applicable scenario, and constraint conditions.

[0026] According to the solution recommendation rules, the applications in the preset application resource pool are queried and matched to obtain a list of mandatory applications and a list of candidate applications, wherein the application resource pool contains a large number of digital applications, and the applications in the application resource pool have unique application identifiers for distinguishing different applications. The mandatory application list includes one or more mandatory applications, and the candidate application list includes one or more candidate applications.

[0027] When making application recommendations, the recommendation is made in the form of an application combination scheme, which is a recommendation scheme generated based on the combination of multiple applications. Specifically, based on the constraints in the scheme recommendation rules, the target application is screened out from the list of candidate applications and added to the list of required applications, the screened target application is combined with each required application in the list of required applications to generate an application combination scheme, and the generated application combination scheme is recommended to the user.

[0028] Optionally, the target application added to the mandatory application list includes one or more target applications, and the number of target applications added to the mandatory application list can be determined according to the number of recommended applications configured in the constraint condition and / or the number of to-be-selected applications in the to-be-selected application list.

[0029] In this embodiment, by evaluating and analyzing the user's existing applications, the solution recommendation rules are determined, so as to query and match the required application list and the candidate application list. According to the constraints in the solution recommendation rules, the target applications that meet the constraints are screened from the candidate application list and added to the required application list, and combined with the required applications in the required application list to obtain an application combination solution and recommend it to the user. By building an indicator evaluation system to evaluate and analyze the user's existing applications, the user's actual needs for digital applications can be quickly discovered, so as to recommend application combination solutions that meet their needs to the user, thereby improving the efficiency of application recommendation and reducing the user's application costs.

[0030] In one embodiment, the preset index evaluation system includes multiple levels of indicators. In the index evaluation system, each indicator item in the first-level indicator is subdivided into one or more second-level indicators, and each indicator item in the second-level indicator is subdivided into one or more third-level indicators, and so on, and finally the most fine-grained indicator items are subdivided as leaf nodes. Furthermore, the sum of the full score values ​​of the indicators of the finest-grained indicator items is a preset value, and the preset value is, for example, 100. In any two adjacent levels of indicators, the full score value of the upper-level indicator is the sum of the full score values ​​of the lower-level indicators. The digital application sets the indicator value of the most fine-grained indicator item according to the application effect and functional characteristics.

[0031] Optional, Figure 2 The three-level indicator evaluation system of digital application is given as an example. Figure 2In the first-level index, there are three index items: first-level index 1, first-level index 2 and first-level index 3. Further, first-level index 1 is subdivided into three index items: second-level index 1, second-level index 2 and second-level index 3, first-level index 2 is subdivided into two index items: second-level index 4 and second-level index 5, and first-level index 3 is subdivided into two index items: second-level index 6 and second-level index 7. Further, second-level index 1 is subdivided into three index items: third-level index 1, third-level index 2 and third-level index 3, and second-level index 7 is subdivided into three index items: third-level index n-2, third-level index n-1 and third-level index n. If the third-level indicator is the finest-grained indicator, then in the indicator evaluation system of digital applications, the third-level indicator includes n finest-grained indicators, the full marks of the n finest-grained indicators are preset values, the full mark of the second-level indicator 7 is the sum of the full marks of the three indicator items of the third-level indicator n-2, the third-level indicator n-1 and the third-level indicator n, the full mark of the second-level indicator 1 is the sum of the full marks of the three indicator items of the third-level indicator 1, the third-level indicator 2 and the third-level indicator 3, the full mark of the first-level indicator 1 is the sum of the full marks of the three indicator items of the second-level indicator 1, the second-level indicator 2 and the second-level indicator 3, the full mark of the second-level indicator 2 is the sum of the full marks of the two indicator items of the second-level indicator 4 and the second-level indicator 5, and the full mark of the first-level indicator 3 is the sum of the full marks of the two indicator items of the second-level indicator 6 and the second-level indicator 7.

[0032] Based on this, in step 100, based on a preset indicator evaluation system, the application basic data of the existing application is evaluated and analyzed to obtain the evaluation results of the existing application, including: Step 101, based on the finest-grained indicator in the preset indicator evaluation system, the application basic data is evaluated and analyzed to determine the indicator value of the finest-grained indicator; Step 102, determining the indicator score of the finest-grained indicator according to the indicator value of the finest-grained indicator; Step 103, based on the indicator value and indicator score of the finest-grained indicator, the multi-level indicators in the indicator evaluation system are evaluated step by step to obtain the evaluation result of the existing application; wherein, the indicator value of any N-th level indicator in the indicator evaluation system is the sum of the indicator values ​​of the N+1-th level indicators under the N-th level indicator, and the indicator score of the N-th level indicator is the sum of the indicator scores of the N+1-th level indicators under the N-th level indicator.

[0033] When evaluating and analyzing the application basic data of existing applications, the application basic data is evaluated and analyzed based on the finest-grained indicators in the indicator evaluation system, the indicator value of the finest-grained indicator of the finest-grained indicator is determined, and the indicator score of the finest-grained indicator is determined based on the indicator value of the finest-grained indicator.

[0034] Furthermore, based on the indicator value and indicator score of the finest granularity indicator, the multi-level indicators in the indicator evaluation system are evaluated level by level to obtain the evaluation results of the existing applications. During the level-by-level evaluation, the indicator value of any N-th level indicator in the indicator evaluation system is the sum of the indicator values ​​of the N+1-th level indicators under the N-th level indicator, and the indicator score of the N-th level indicator is the sum of the indicator scores of the N+1-th level indicators under the N-th level indicator.

[0035] For example, Figure 2 In the indicator evaluation system shown in the figure, the index value of the first-level indicator is the sum of the index values ​​of the second-level indicators, the index value of the first-level indicator 1 is the sum of the index values ​​of the three indicator items of second-level indicators 1, second-level indicators 2 and second-level indicators 3, and the index score of the first-level indicator 1 is the sum of the index scores of the three indicator items of second-level indicators 1, second-level indicators 2 and second-level indicators 3.

[0036] Among them, the indicator score of the most fine-grained indicator can be obtained by scoring the indicator value, and the scoring method includes but is not limited to scoring the indicator value based on scoring rules, or scoring the indicator value based on an AI model.

[0037] In one embodiment, the mandatory application list and the candidate application list are obtained by querying and matching the solution recommendation rules with the applications in the application resource pool, and then deduplicating the queried applications based on the user's existing applications.

[0038] Specifically, step 300 also includes: Step 301, according to the mandatory application configuration in the solution recommendation rule, query and match the applications in the preset application resource pool to obtain an initial mandatory application list; Step 302, deduplicating the initial mandatory application list based on the existing applications to obtain a mandatory application list; Step 303, query and match the applications in the application resource pool according to the optional application configuration in the solution recommendation rule to obtain an initial list of candidate applications; Step 304: De-duplicate the initial list of applications to be selected based on the existing applications to obtain a list of applications to be selected.

[0039] The solution recommendation rules include mandatory application configurations and optional application configurations. When querying and matching the application resource pool, the preset application resource pool is queried and matched according to the mandatory application configurations in the solution recommendation rules to obtain an initial mandatory application list. Then, based on the user's existing applications, the mandatory applications in the initial mandatory application list are deduplicated, and the user's existing applications are filtered out from the initial mandatory application list to obtain a mandatory application list.

[0040] Furthermore, according to the optional application configuration in the solution recommendation rules, the applications in the application resource pool are queried and matched to obtain an initial list of candidate applications. Then, based on the user's existing applications, the candidate applications in the initial list of candidate applications are deduplicated, and the user's existing applications are filtered out from the initial list of candidate applications to obtain a list of candidate applications.

[0041] The solution recommendation rules also include constraints, which include application type and recommended quantity. Based on the constraints, without exceeding the recommended number of digital applications, the target application is screened from the list of candidate applications and added to the list of required applications, and combined with the required applications in the list of required applications to obtain an application combination solution.

[0042] In step 400, based on the constraint condition, the target application is selected from the list of candidate applications and added to the list of required applications, and combined with each required application in the list of required applications to obtain an application combination solution, which specifically includes: Step 401, determining, according to the evaluation result, a first evaluation score of each indicator of each mandatory application in the mandatory application list under the indicator evaluation system; Step 402, based on the first evaluation score and the preset full score values ​​of each indicator under the indicator evaluation system, calculate the full score difference of each indicator of each required application in the required application list under the indicator evaluation system; Step 403, determining the target indicator with the largest full score difference, and calculating the recommendation score of each candidate application in the candidate application list under the target indicator; Step 404, sorting the candidate applications in the candidate application list in descending order according to the recommendation score; Step 405, selecting a target application according to the sorting order of each candidate application in the candidate application list, and combining the target application with each required application in the required application list to obtain an application combination solution; the target application is a candidate application marked as unselected; Step 406, calculating a solution score of the application combination solution, and determining whether the application combination solution satisfies the constraint condition according to the solution score; Step 407, if the application solution does not satisfy the constraint condition, the target application is removed from the list of candidate applications, and the process returns to and executes the step of selecting the target application according to the sorting order of the candidate applications in the list of candidate applications; Step 408: If the application combination scheme satisfies the constraint condition, the target application is marked as selected and added to the required application list, and the step of selecting the target application according to the sorting order of the to-be-selected applications in the to-be-selected application list is returned and executed until the target application is the last to-be-selected application in the to-be-selected application list, or the number of target applications added to the required application list reaches the preset number of applications.

[0043] When screening each candidate application in the candidate application list, determine the evaluation score of each indicator of each mandatory application in the mandatory application list under the indicator evaluation system according to the evaluation result, and obtain the first evaluation score of each indicator of the mandatory application. Further, based on the first evaluation score and the preset full score of each indicator under the indicator evaluation system, calculate the full score difference of each indicator of each mandatory application in the mandatory application list under the indicator evaluation system. For any mandatory application, subtract the full score of each indicator under the indicator evaluation system from the corresponding first evaluation score to obtain the full score difference.

[0044] The indicators are sorted according to their full score differences under the indicator evaluation system, so as to select the target indicator with the largest full score difference, calculate the recommended score of each candidate application in the candidate application list under the target indicator, and sort the candidate applications in descending order according to the recommended score.

[0045] Further, according to the ranking order of the candidate applications, the target application with the highest recommendation score is selected, and the target application is combined with each mandatory application in the mandatory application list to generate an application combination solution. It should be noted that the selected target application is the candidate application marked as unselected.

[0046] For the generated application combination solution, calculate the solution score of the application combination solution, and determine whether the generated application combination solution meets the constraints in the solution recommendation rules based on the solution score. If the application combination solution meets the constraints, mark the target application as selected and add it to the list of required applications, and then reselect the next candidate application marked as unselected as the target application according to the sorting order of the candidate applications, and repeat the above steps. If the generated application combination solution does not meet the constraints, remove the current target application from the list of candidate applications, and then reselect the next candidate application marked as unselected as the target application according to the sorting order of the candidate applications, and repeat the above steps. Until the selected target application is the last candidate application in the list of candidate applications, or the number of target applications added to the list of required applications reaches the preset number of applications, where the preset number of applications is included in the constraints.

[0047] Optionally, in step 403, calculating the recommendation score of each candidate application in the candidate application list under the target indicator includes: Step 413, determining the target indicator value of each candidate application in the candidate application list under the target indicator according to the evaluation result, obtaining the recommendation weight of each candidate application in the candidate application list, and the target full score value preset for the target indicator; Step 423 , calculate the ratio of the target indicator value to the target full score value, and perform weighted summation on the ratio and the recommendation weight to obtain the recommendation score of each candidate application in the candidate application list under the target indicator.

[0048] When calculating the recommended score of each candidate application in the candidate application list under the target indicator, first determine the target indicator value of each candidate application in the candidate application list under the target indicator according to the evaluation result, obtain the recommendation weight of each candidate application in the candidate application list, and the preset target full score value of the target indicator.

[0049] Then, the ratio of the target indicator value to the target full score value is calculated, and the ratio is weighted and summed with the recommendation weight to obtain the recommendation score of each candidate application in the candidate application list under the target indicator.

[0050] For example, for the candidate application a, its corresponding recommendation weight is , whose index value under target index i is , the target full score of target indicator i is , calculate the recommended score of the candidate application under target indicator i according to the following formula 1 : ; (1)

[0051] in, , , , is a configurable constant coefficient, is the price in the additional attributes of application a, is the maximum price of similar applications in the list of applications to be selected. In this embodiment, when the index value of the application to be selected is scored, additional attributes such as the price of the application are combined.

[0052] Furthermore, in step 401, according to the evaluation result, determining the first evaluation score of each indicator of each required application in the required application list under the indicator evaluation system also includes: Step 411, determining the index value and index score of each mandatory application in the mandatory application list under the first index according to the evaluation result; the first index is any one of the various indexes under the index evaluation system; Step 421, obtaining a preset indicator weight of the first indicator, and weighting the indicator value of the first indicator based on the indicator weight to obtain a weighted indicator value; Step 431 , calculating the sum of the weighted index value and the index score of the first index, and obtaining a first evaluation score of each mandatory application in the mandatory application list under the first index.

[0053] When calculating the evaluation scores of each required application in the required application list under the indicator evaluation system, first determine the indicator value and indicator score of each required application in the selected application list under the first indicator according to the evaluation results. The first indicator is any one of the indicators under the indicator evaluation system.

[0054] Further, the indicator weight preset for the first indicator is obtained, and the indicator value of the first indicator is weighted based on the indicator weight to obtain a weighted indicator value, and the sum of the weighted indicator value and the indicator score of the first indicator is calculated to obtain the first evaluation score of each required application in the required application list under the first indicator. In this way, the first evaluation score of each required application under the indicator evaluation system can be calculated.

[0055] For example, is the indicator score of the mandatory application a under the first indicator I, is the index value of the mandatory application a under the first index I, is the indicator weight of the first indicator I, which is a configurable constant coefficient. The first evaluation score of a under the first indicator must be applied. It can be calculated according to the following formula 2: ; (2)

[0056] For the application combination solution, its solution score is the sum of all indicator evaluation scores under the indicator evaluation system. , if the indicator evaluation score of any indicator is greater than its full score, the evaluation score of the indicator is set to the full score, that is, ,but .

[0057] Based on this, in step 406, calculating the solution score of the application combination solution may also include: Step 416, determining a second evaluation score of each indicator of the target application under the indicator evaluation system according to the evaluation result; Step 426, calculating the target evaluation score of each indicator of the application combination solution under the indicator evaluation system based on the first evaluation score and the second evaluation score; Step 436: sum the target evaluation scores to obtain a solution score for the application combination solution.

[0058] The second evaluation score of each indicator of the target application under the indicator evaluation system is determined according to the evaluation result. The calculation method of the second evaluation score can be the same as the calculation method of the first evaluation score, which will not be repeated here.

[0059] Furthermore, based on the first evaluation score and the second evaluation score, the target evaluation score of each indicator of the application combination scheme under the indicator evaluation system is calculated, and the first evaluation score and the second evaluation score of the same indicator under the indicator evaluation system are added to obtain the target evaluation score of the indicator. That is, the evaluation scores of the same indicator of different applications in the application combination scheme under the indicator evaluation system are added to obtain the target evaluation score of the same indicator, and the target evaluation scores of each indicator are summed to obtain the scheme score of the application combination scheme.

[0060] Optionally, the full score difference of each indicator is calculated as shown in the following formula 3: ; (3)

[0061] in, Indicates the full score difference of indicator I, represents the evaluation score of indicator I, Indicates the full score of indicator I.

[0062] Optionally, when selecting the target application from the candidate applications in the candidate application list, sort the various indicators under the indicator evaluation system in descending order according to the full score difference, and then select the indicator j with the largest full score difference according to the sorting order, and then calculate the recommended score of each candidate application under indicator j. Among them, the indicator with the largest full score difference is the part that needs to be improved in the digital application, and according to the recommended score of the candidate application under the indicator with the largest full score difference, the candidate application with the largest recommended score is selected as the target application and combined with the required application. The obtained application combination scheme can improve the indicator with the largest full score difference, thereby improving the digital effect.

[0063] Optionally, when determining whether the application combination solution satisfies the constraint condition, the application combination solution score is compared with a score threshold preset in the constraint condition. Compare, if the solution scores If the application combination plan satisfies the constraint condition, otherwise, the application combination plan does not satisfy the constraint condition. The score threshold in the constraint condition is the target score of the application combination plan set according to user needs.

[0064] It should be noted that for indicator j with the largest full score difference, if there is no target application that meets the constraint conditions in the list of candidate applications, indicator j will be marked as an invalid indicator, and then the next indicator will be selected for screening according to the sorting order of the full score difference of each indicator under the indicator evaluation system until the generated application combination solution meets the constraint conditions.

[0065] In this embodiment, in order to solve the problem that users cannot reasonably choose digital applications according to their own needs among a wide variety of digital applications with different functions, the user's existing applications are evaluated and analyzed through an indicator evaluation system to determine the required applications and candidate applications required by the user. Then, according to the configurable constraints in the user's needs, the target applications that meet the constraints are screened out from the candidate applications, combined with the required applications, and an application combination plan is generated and recommended to the user, which is conducive to improving the user's selection efficiency of digital applications and meeting the user's digital construction needs.

[0066] Furthermore, when screening target applications that meet the constraints from the candidate applications, the recommendation score of each candidate application under the indicator with the largest gap between the expected target and the user's needs under the required application combination scheme is calculated, thereby screening out the applications that contribute most to the improvement of the indicator, improving the compatibility of the selected digital applications with user needs and the rationality of the combination scheme of digital applications, which is conducive to reducing the user's investment cost in digital applications and increasing the user's digital benefits.

[0067] The digital application recommendation device provided by the present invention is described below. The digital application recommendation device described below and the digital application recommendation method described above can be referred to each other.

[0068] Reference Figure 3 , the digital application recommendation device provided by the embodiment of the present invention includes: The indicator evaluation module 10 is used to obtain the application basic data of the user's existing application, and evaluate and analyze the application basic data based on a preset indicator evaluation system to obtain an evaluation result of the existing application; A rule determination module 20 is used to determine a solution recommendation rule according to the evaluation result; the solution recommendation rule includes a constraint condition; An application matching module 30 is used to query and match applications in a preset application resource pool according to the solution recommendation rule to obtain a required application list and a candidate application list; The application recommendation module 40 is used to filter out target applications from the candidate application list based on the constraint conditions, add the target applications to the mandatory application list, combine them with the mandatory applications in the mandatory application list, obtain an application combination solution, and recommend the application combination solution to the user.

[0069] In one embodiment, the application recommendation module 40 is further configured to: Determine, according to the evaluation result, a first evaluation score of each indicator of each mandatory application in the mandatory application list under the indicator evaluation system; Based on the first evaluation score and the preset full score values ​​of each indicator under the indicator evaluation system, calculating the full score difference of each indicator under the indicator evaluation system for each required application in the required application list; Determine the target indicator with the largest full score difference, and calculate the recommendation score of each candidate application in the candidate application list under the target indicator; Sort the applications to be selected in the list of applications to be selected in descending order according to the recommendation score; Selecting a target application according to the sorting order of each candidate application in the candidate application list, and combining the target application with each mandatory application in the mandatory application list to obtain an application combination scheme; the target application is a candidate application marked as unselected; Calculating a solution score of the application combination solution, and determining whether the application combination solution satisfies the constraint condition according to the solution score; If the application solution does not satisfy the constraint condition, the target application is removed from the list of candidate applications, and the process returns to and executes the step of selecting the target application according to the sorting order of the candidate applications in the list of candidate applications; If the application combination scheme satisfies the constraint condition, the target application is marked as selected and added to the required application list, and the step of selecting the target application according to the sorting order of the to-be-selected applications in the to-be-selected application list is returned and executed until the target application is the last to-be-selected application in the to-be-selected application list, or the number of target applications added to the required application list reaches the preset number of applications.

[0070] In one embodiment, the application recommendation module 40 is further configured to: Determine, according to the evaluation result, a second evaluation score for each indicator of the target application under the indicator evaluation system; Calculating target evaluation scores of various indicators of the application combination solution under the indicator evaluation system based on the first evaluation score and the second evaluation score; The target evaluation scores are summed to obtain a solution score of the application combination solution.

[0071] In one embodiment, the application recommendation module 40 is further configured to: According to the evaluation result, determine the indicator value and indicator score of each mandatory application in the mandatory application list under the first indicator; the first indicator is any one of the indicators under the indicator evaluation system; Obtaining a preset indicator weight for the first indicator, and weighting the indicator value of the first indicator based on the indicator weight to obtain a weighted indicator value; The sum of the weighted index value and the index score of the first index is calculated to obtain a first evaluation score of each mandatory application in the mandatory application list under the first index.

[0072] In one embodiment, the application recommendation module 40 is further configured to: Determine the target indicator value of each candidate application in the candidate application list under the target indicator according to the evaluation result, obtain the recommendation weight of each candidate application in the candidate application list, and the target full score value preset for the target indicator; The ratio of the target indicator value to the target full score value is calculated, and the ratio and the recommendation weight are weightedly summed to obtain the recommendation score of each candidate application in the candidate application list under the target indicator.

[0073] In one embodiment, the application matching module 30 is further used to: According to the mandatory application configuration in the solution recommendation rule, query and match the applications in the preset application resource pool to obtain an initial mandatory application list; Deduplication of the initial mandatory application list is performed based on the existing applications to obtain a mandatory application list; According to the optional application configuration in the solution recommendation rule, query and match the applications in the application resource pool to obtain an initial list of candidate applications; The initial list of to-be-selected applications is deduplicated based on the existing applications to obtain a list of to-be-selected applications.

[0074] In one embodiment, the indicator evaluation module 10 is further used to: Based on the finest-grained indicator in the preset indicator evaluation system, the application basic data is evaluated and analyzed to determine the indicator value of the finest-grained indicator; Determining an indicator score of the finest-grained indicator according to the indicator value of the finest-grained indicator; Based on the indicator value and indicator score of the finest-grained indicator, the multi-level indicators in the indicator evaluation system are evaluated level by level to obtain the evaluation result of the existing application; wherein, the indicator value of any N-th level indicator in the indicator evaluation system is the sum of the indicator values ​​of the N+1-th level indicators under the N-th level indicator, and the indicator score of the N-th level indicator is the sum of the indicator scores of the N+1-th level indicators under the N-th level indicator.

[0075] Figure 4 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 4 As shown, the electronic device may include: a processor 410, a communications interface 420, a memory 430 and a communication bus 440, wherein the processor 410, the communications interface 420 and the memory 430 communicate with each other via the communication bus 440. The processor 410 may call the logic instructions in the memory 430 to execute the steps of the digital application recommendation method, for example including: Obtaining application basic data of the user's existing applications, and evaluating and analyzing the application basic data based on a preset indicator evaluation system to obtain an evaluation result of the existing applications; Determine a solution recommendation rule according to the evaluation result; the solution recommendation rule includes a constraint condition; According to the solution recommendation rule, the applications in the preset application resource pool are queried and matched to obtain a list of required applications and a list of to-be-selected applications; Based on the constraint condition, a target application is screened out from the candidate application list, added to the mandatory application list, and combined with each mandatory application in the mandatory application list to obtain an application combination solution, and the application combination solution is recommended to the user.

[0076] In addition, the logic instructions in the above-mentioned memory 430 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0077] On the other hand, the present invention further provides a computer program product, the computer program product comprising a computer program, the computer program can be stored on a non-transitory computer-readable storage medium, and when the computer program is executed by a processor, the computer can perform the steps of the digital application recommendation method provided by the above methods, for example, including: Obtaining application basic data of the user's existing applications, and evaluating and analyzing the application basic data based on a preset indicator evaluation system to obtain an evaluation result of the existing applications; Determine a solution recommendation rule according to the evaluation result; the solution recommendation rule includes a constraint condition; According to the solution recommendation rule, the applications in the preset application resource pool are queried and matched to obtain a list of required applications and a list of to-be-selected applications; Based on the constraint condition, a target application is screened out from the candidate application list, added to the mandatory application list, and combined with each mandatory application in the mandatory application list to obtain an application combination solution, and the application combination solution is recommended to the user.

[0078] In another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the digital application recommendation method provided by the above methods, for example, including: Obtaining application basic data of the user's existing applications, and evaluating and analyzing the application basic data based on a preset indicator evaluation system to obtain an evaluation result of the existing applications; Determine a solution recommendation rule according to the evaluation result; the solution recommendation rule includes a constraint condition; According to the solution recommendation rule, the applications in the preset application resource pool are queried and matched to obtain a list of required applications and a list of to-be-selected applications; Based on the constraint condition, a target application is screened out from the candidate application list, added to the mandatory application list, and combined with each mandatory application in the mandatory application list to obtain an application combination solution, and the application combination solution is recommended to the user.

[0079] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0080] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0081] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A digital application recommendation method, characterized in that: include: Obtaining application basic data of the user's existing applications, and evaluating and analyzing the application basic data based on a preset indicator evaluation system to obtain an evaluation result of the existing applications; Determine a solution recommendation rule according to the evaluation result; the solution recommendation rule includes a constraint condition; According to the solution recommendation rule, the applications in the preset application resource pool are queried and matched to obtain a list of required applications and a list of to-be-selected applications; Based on the constraint condition, a target application is screened out from the candidate application list, added to the mandatory application list, and combined with each mandatory application in the mandatory application list to obtain an application combination solution, and the application combination solution is recommended to the user.

2. The digital application recommendation method according to claim 1, characterized in that: The step of screening out a target application from the list of candidate applications based on the constraint condition, adding the target application to the list of mandatory applications, and combining the target application with each mandatory application in the list of mandatory applications to obtain an application combination solution includes: Determine, according to the evaluation result, a first evaluation score of each indicator of each mandatory application in the mandatory application list under the indicator evaluation system; Based on the first evaluation score and the preset full score values ​​of each indicator under the indicator evaluation system, calculating the full score difference of each indicator under the indicator evaluation system for each required application in the required application list; Determine the target indicator with the largest full score difference, and calculate the recommendation score of each candidate application in the candidate application list under the target indicator; Sort the applications to be selected in the list of applications to be selected in descending order according to the recommendation score; Selecting a target application according to the sorting order of each candidate application in the candidate application list, and combining the target application with each mandatory application in the mandatory application list to obtain an application combination scheme; the target application is a candidate application marked as unselected; Calculating a solution score of the application combination solution, and determining whether the application combination solution satisfies the constraint condition according to the solution score; If the application solution does not satisfy the constraint condition, the target application is removed from the list of candidate applications, and the process returns to and executes the step of selecting the target application according to the sorting order of the candidate applications in the list of candidate applications; If the application combination scheme satisfies the constraint condition, the target application is marked as selected and added to the required application list, and the step of selecting the target application according to the sorting order of the to-be-selected applications in the to-be-selected application list is returned and executed until the target application is the last to-be-selected application in the to-be-selected application list, or the number of target applications added to the required application list reaches the preset number of applications.

3. The digital application recommendation method according to claim 2, characterized in that: The calculating the solution score of the application combination solution includes: Determine, according to the evaluation result, a second evaluation score for each indicator of the target application under the indicator evaluation system; Calculating target evaluation scores of various indicators of the application combination solution under the indicator evaluation system based on the first evaluation score and the second evaluation score; The target evaluation scores are summed to obtain a solution score of the application combination solution.

4. The digital application recommendation method according to claim 2, characterized in that: Determining, according to the evaluation result, a first evaluation score of each indicator of each mandatory application in the mandatory application list under the indicator evaluation system comprises: According to the evaluation result, determine the indicator value and indicator score of each mandatory application in the mandatory application list under the first indicator; the first indicator is any one of the indicators under the indicator evaluation system; Obtaining a preset indicator weight for the first indicator, and weighting the indicator value of the first indicator based on the indicator weight to obtain a weighted indicator value; The sum of the weighted index value and the index score of the first index is calculated to obtain a first evaluation score of each mandatory application in the mandatory application list under the first index.

5. The digital application recommendation method according to claim 2, characterized in that: The calculating the recommendation score of each candidate application in the candidate application list under the target indicator includes: Determine the target indicator value of each candidate application in the candidate application list under the target indicator according to the evaluation result, obtain the recommendation weight of each candidate application in the candidate application list, and the target full score value preset for the target indicator; The ratio of the target indicator value to the target full score value is calculated, and the ratio and the recommendation weight are weightedly summed to obtain the recommendation score of each candidate application in the candidate application list under the target indicator.

6. The digital application recommendation method according to claim 1, characterized in that: The querying and matching of applications in a preset application resource pool according to the solution recommendation rule to obtain a mandatory application list and a candidate application list includes: According to the mandatory application configuration in the solution recommendation rule, query and match the applications in the preset application resource pool to obtain an initial mandatory application list; Deduplication of the initial mandatory application list is performed based on the existing applications to obtain a mandatory application list; According to the optional application configuration in the solution recommendation rule, query and match the applications in the application resource pool to obtain an initial list of candidate applications; The initial list of to-be-selected applications is deduplicated based on the existing applications to obtain a list of to-be-selected applications.

7. The digital application recommendation method according to claim 1, characterized in that: The evaluation results of the existing applications are obtained by evaluating and analyzing the application basic data based on the preset indicator evaluation system, including: Based on the finest-grained indicator in the preset indicator evaluation system, the application basic data is evaluated and analyzed to determine the indicator value of the finest-grained indicator; Determining an indicator score of the finest-grained indicator according to the indicator value of the finest-grained indicator; Based on the indicator value and indicator score of the finest-grained indicator, the multi-level indicators in the indicator evaluation system are evaluated level by level to obtain the evaluation result of the existing application; wherein, the indicator value of any N-th level indicator in the indicator evaluation system is the sum of the indicator values ​​of the N+1-th level indicators under the N-th level indicator, and the indicator score of the N-th level indicator is the sum of the indicator scores of the N+1-th level indicators under the N-th level indicator.

8. A digital application recommendation device, characterized in that: include: The indicator evaluation module is used to obtain the basic application data of the user's existing applications, and based on a preset indicator evaluation system, evaluate and analyze the basic application data to obtain an evaluation result of the existing application; A rule determination module, used to determine a solution recommendation rule according to the evaluation result; the solution recommendation rule includes a constraint condition; An application matching module, used to query and match applications in a preset application resource pool according to the solution recommendation rule, and obtain a list of required applications and a list of to-be-selected applications; The application recommendation module is used to filter out target applications from the candidate application list based on the constraint conditions, add the target applications to the mandatory application list, combine them with the mandatory applications in the mandatory application list, obtain an application combination solution, and recommend the application combination solution to the user.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the digital application recommendation method according to any one of claims 1 to 7 are implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the digital application recommendation method according to any one of claims 1 to 7 are implemented.

Images