Information recommendation method and device, electronic equipment and storage medium

Abstract

The invention provides an information recommendation method and device, electronic equipment and a storage medium, and relates to the technical field of data processing. The method comprises the following steps: determining a first set associated with an enterprise; determining a second set and a first application scene corresponding to the policy information to be recommended; matching the business targets in the first set and the second set to generate a third set; determining multiple pieces of candidate policy information corresponding to a third set and a second application scene of the candidate policy information from the policy information to be recommended; determining a second priority of a service target in the third set according to the first priority of the candidate policy information, and determining a target recommendation algorithm according to the second priority and a second application scene; and determining at least one piece of target policy information recommended to the enterprise from the candidate policy information based on a target recommendation algorithm. Therefore, according to the scheme, the most suitable recommendation algorithm can be intelligently selected for different business targets, and the flexibility and effect of information recommendation for enterprises are remarkably improved.

Description

Technical Field

[0001] The present disclosure relates to the field of data processing technology, and in particular to an information recommendation method, device, electronic device and storage medium. Background Art

[0002] The main problem in the promotion and application of current policies is that many enterprises, especially small and micro enterprises, often do not know about the policies that are beneficial to them, resulting in low policy coverage and exposure. In addition, even if enterprises know about these policies, the success rate of applying for policies is unsatisfactory, largely because of the lack of a mechanism to accurately match policies with enterprise needs. Summary of the invention

[0003] The present invention provides an information recommendation method, device, electronic device and storage medium to solve the problem of being unable to accurately match enterprise needs and policies.

[0004] To this end, an object of the present disclosure is to propose an information recommendation method.

[0005] The second objective of the present disclosure is to provide an information recommendation device.

[0006] A third objective of the present disclosure is to provide an electronic device.

[0007] A fourth object of the present disclosure is to provide a non-transitory computer-readable storage medium.

[0008] A fifth object of the present disclosure is to provide a computer program product.

[0009] To achieve the above-mentioned purpose, the first aspect of the present disclosure proposes an information recommendation method, including: determining a first set associated with an enterprise, the first set including multiple first business objectives; obtaining multiple policy information to be recommended, and determining a second set and a first application scenario corresponding to each policy information to be recommended, the second set including multiple second business objectives; performing similarity matching on the business objectives in the first set and the second set, and generating a third set based on the successfully matched second business objectives; determining multiple candidate policy information corresponding to the third set and the second application scenario corresponding to the candidate policy information from the policy information to be recommended; determining the second priority of each business objective in the third set based on the first priority of the candidate policy information, and determining the target recommendation algorithm corresponding to the third set from an algorithm library based on the second priority and the second application scenario; based on the target recommendation algorithm, determining at least one target policy information recommended to the enterprise from the candidate policy information.

[0010] According to one embodiment of the present disclosure, determining the second priority of each business objective in the third set based on the first priority of the candidate policy information includes: for candidate policy information i, determining at least one second business objective j corresponding to the candidate policy information i from the third set; determining the second priority of the second business objective j based on the first priority of the candidate policy information i, wherein i and j are natural numbers greater than 1.

[0011] According to one embodiment of the present disclosure, determining the first set associated with an enterprise includes: obtaining historical operation information of the enterprise on the multiple policy information to be recommended; determining the operation type of the enterprise based on the historical operation information, and determining one or more historical policy information browsed by the enterprise based on the operation type; determining a corresponding fourth set of the historical policy information; and filtering out multiple repeated business goals from the fourth set as the first business goal in the first set.

[0012] According to one embodiment of the present disclosure, the similarity matching of the business targets in the first set and the second set, and generating a third set based on the successfully matched second business targets, includes: for any first business target in the first set, calculating the similarity between the any first business target and each second business target to obtain the similarity between the first business target and the second business target; determining the second business target whose similarity is greater than a set similarity threshold as the successfully matched second business target, and using the successfully matched second business target as the third business target to generate the third set.

[0013] According to one embodiment of the present disclosure, determining multiple candidate policy information corresponding to the third set from the policy information to be recommended includes: determining a second business goal that is the same as the third business goal from the second set, and using the policy information to be recommended corresponding to the second business goal as the candidate policy information.

[0014] According to one embodiment of the present disclosure, determining the target recommendation algorithm corresponding to the third set from the algorithm library based on the second priority and the second application scenario includes: obtaining the candidate priority and candidate application scenario of each candidate recommendation algorithm in the algorithm library; determining, from the candidate recommendation algorithms, a first candidate recommendation algorithm whose candidate priority is the same as the second priority; and determining, from the first candidate recommendation algorithms, a second candidate recommendation algorithm whose candidate application scenario is the same as the second application scenario as the target recommendation algorithm.

[0015] According to one embodiment of the present disclosure, after determining at least one target policy information recommended to the enterprise from the candidate policy information based on the target recommendation algorithm, it also includes: monitoring the operation information of the enterprise, and monitoring the information recommendation effect based on the operation information; in response to the monitoring result indicating that the information recommendation effect does not meet the set conditions, optimizing the parameters of the target recommendation algorithm; in response to the monitoring result indicating that the information recommendation effect meets the set conditions, using the operation information as the user's historical operation information to determine the first set based on the historical operation information.

[0016] According to one embodiment of the present disclosure, in response to the monitoring result indicating that the recommendation effect of the information does not meet the set conditions, the parameters of the target recommendation algorithm are optimized, including: determining a data set for the optimization process based on the operation information, and iteratively optimizing the parameters of the target recommendation algorithm according to the data set and the set optimization target, until the optimized target recommendation algorithm reaches the optimization target.

[0017] To achieve the above-mentioned purpose, the second aspect of the present disclosure proposes an information recommendation device, including: a first determination module, used to determine a first set associated with an enterprise, the first set including multiple first business objectives; a second determination module, used to obtain multiple policy information to be recommended, and determine a second set and a first application scenario corresponding to each policy information to be recommended, the second set including multiple second business objectives; a matching module, used to perform similarity matching on the business objectives in the first set and the second set, and generate a third set based on the successfully matched second business objectives; a third determination module, used to determine, from the policy information to be recommended, multiple candidate policy information corresponding to the third set, and a second application scenario corresponding to the candidate policy information; a fourth determination module, used to determine the second priority of each business objective in the third set based on the first priority of the candidate policy information, and determine the target recommendation algorithm corresponding to the third set from an algorithm library based on the second priority and the second application scenario; a recommendation module, used to determine at least one target policy information recommended to the enterprise from the candidate policy information based on the target recommendation algorithm.

[0018] According to one embodiment of the present disclosure, the fourth determination module is also used to: for candidate policy information i, determine at least one second business objective j corresponding to the candidate policy information i from the third set; determine the second priority of the second business objective j based on the first priority of the candidate policy information i, where i and j are natural numbers greater than 1.

[0019] According to one embodiment of the present disclosure, the first determination module is also used to: obtain historical operation information of the enterprise on the multiple policy information to be recommended; determine the operation type of the enterprise based on the historical operation information, and determine one or more historical policy information browsed by the enterprise based on the operation type; determine the corresponding fourth set of the historical policy information; and filter out multiple repeated business goals from the fourth set as the first business goal in the first set.

[0020] According to one embodiment of the present disclosure, the matching module is also used to: for any first business target in the first set, calculate the similarity between the any first business target and each second business target to obtain the similarity between the first business target and the second business target; determine the second business target whose similarity is greater than the set similarity threshold as the successfully matched second business target, and use the successfully matched second business target as the third business target to generate the third set.

[0021] According to one embodiment of the present disclosure, the third determination module is further used to: determine a second business goal that is the same as the third business goal from the second set, and use the policy information to be recommended corresponding to the second business goal as the candidate policy information.

[0022] According to one embodiment of the present disclosure, the fourth determination module is also used to: obtain the candidate priority and candidate application scenario of each candidate recommendation algorithm in the algorithm library; determine, from the candidate recommendation algorithms, a first candidate recommendation algorithm whose candidate priority is the same as the second priority; and determine, from the first candidate recommendation algorithms, a second candidate recommendation algorithm whose candidate application scenario is the same as the second application scenario as the target recommendation algorithm.

[0023] According to one embodiment of the present disclosure, the recommendation module is also used to: monitor the operation information of the enterprise, and monitor the information recommendation effect based on the operation information; in response to the monitoring result indicating that the information recommendation effect does not meet the set conditions, optimize the parameters of the target recommendation algorithm; in response to the monitoring result indicating that the information recommendation effect meets the set conditions, use the operation information as the user's historical operation information to determine the first set based on the historical operation information.

[0024] According to one embodiment of the present disclosure, the recommendation module is also used to: determine a data set for the optimization process based on the operation information, and iteratively optimize the parameters of the target recommendation algorithm according to the data set and the set optimization target until the optimized target recommendation algorithm reaches the optimization target.

[0025] To achieve the above-mentioned purpose, the third aspect embodiment of the present disclosure proposes an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to implement the information recommendation method as described in the first aspect embodiment of the present disclosure.

[0026] To achieve the above-mentioned purpose, the fourth aspect embodiment of the present disclosure proposes a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to implement the information recommendation method as described in the first aspect embodiment of the present disclosure.

[0027] To achieve the above-mentioned purpose, the fifth aspect of the present disclosure provides a computer program product, including a computer program, which, when executed by a processor, is used to implement the information recommendation method as described in the first aspect of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0029] Figure 1 An example flow chart of an information recommendation method provided in an embodiment of the present disclosure;

[0030] Figure 2 A flowchart of another information recommendation method provided by an embodiment of the present disclosure;

[0031] Figure 3 A flowchart of another information recommendation method provided by an embodiment of the present disclosure;

[0032] Figure 4 An example diagram of a process for recommending policy information provided by an embodiment of the present disclosure;

[0033] Figure 5 A structural example diagram of an information recommendation device provided by an embodiment of the present disclosure;

[0034] Figure 6 This is a diagram showing an example structure of an electronic device provided in an embodiment of the present disclosure.

[0035] The above drawings show clear embodiments of the present disclosure, which will be described in more detail below. These drawings and text descriptions are not intended to limit the scope of the present disclosure in any way, but to illustrate the concepts of the present disclosure to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0036] In order to enable ordinary persons in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings.

[0037] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0038] It should be noted that the acquisition, storage, use, and processing of data in the technical solution of this application are in compliance with the provisions of relevant laws and regulations.

[0039] It should be noted that the information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, stored data, displayed data, etc.) and signals involved in this application are all authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards.

[0040] It should be noted that in the embodiments of the present application, certain software, components, models and other existing solutions in the industry may be mentioned, and they should be regarded as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of the present application, but it does not mean that the applicant has or will necessarily use the relevant content of the solution.

[0041] Figure 1 This is an example flow chart of the information recommendation method provided by the embodiment of the present disclosure. Figure 1 As shown, the information recommendation method includes:

[0042] S101, determining a first set of enterprise associations, where the first set includes a plurality of first business objectives.

[0043] It should be noted that the execution subject of the information recommendation method provided in the embodiment of the present disclosure is an electronic device, and the electronic device may be a terminal device. Optionally, the terminal device may be a mobile electronic device or a non-mobile electronic device. Exemplarily, the mobile electronic device may be a mobile phone, a tablet computer, a laptop computer, a PDA, an in-vehicle electronic device, a wearable device, an ultra-mobile personal computer (UMPC), a netbook or a personal digital assistant (PDA), etc., and the non-mobile electronic device may be a network attached storage (NAS), a personal computer (PC), a television (TV), a teller machine or a self-service machine, etc. The embodiment of the present disclosure does not make specific limitations.

[0044] In some implementations, policy information that has been browsed by the enterprise in the past may be obtained, and the business goal corresponding to the policy information may be used as the first business goal in the first set associated with the enterprise. Input information of the enterprise may also be obtained, and business goals may be identified from the input information, and the identified multiple business goals may be used as the first business goal.

[0045] Optionally, business objectives include, but are not limited to: increasing policy awareness and exposure, improving the success rate of policy applications, optimizing policy resource allocation efficiency, strengthening the match between enterprises and policies, and improving enterprise experience and satisfaction.

[0046] S102, obtaining a plurality of policy information to be recommended, and determining a second set and a first application scenario corresponding to each piece of policy information to be recommended, wherein the second set includes a plurality of second business objectives.

[0047] In some implementations, the latest released policy information can be obtained as policy information to be recommended to the enterprise. Based on the enterprise's historical browsing information, policy information that has not been browsed by the enterprise can also be used as policy information to be recommended.

[0048] Furthermore, the business goal of each information to be recommended is determined, and the business goal is used as the second business goal in the second set. That is, each policy information itself carries its corresponding business goal.

[0049] Optionally, the policy information is located to determine the first application scenario corresponding to the policy information to be recommended. The first application scenario of the policy information to be recommended can be clarified based on the fields, industries, etc. involved in the policy information to ensure the accuracy and effectiveness of the policy application scenario.

[0050] S103, performing similarity matching on the business objectives in the first set and the second set, and generating a third set according to the successfully matched second business objectives.

[0051] In some implementations, based on the similarity between the first business goal and the second business goal and based on the magnitude of the similarity, a successfully matched second business goal can be determined, and the successfully matched second business goal can be used as an element in a third set to generate a third set.

[0052] Optionally, for any first business target in the first set, by calculating the similarity between it and each second business target in the second set, and sorting them in descending order according to the similarity, the second business target corresponding to the top similarity can be selected as the second business target that has been successfully matched. For example, the first business targets and the second business targets corresponding to the first three similarities can be considered to have been successfully matched, and then the third set is generated based on the successfully matched second business targets.

[0053] Optionally, a similarity threshold may be set, and a second business target with a similarity greater than the similarity threshold is taken as a successfully matched second business target.

[0054] S104: Determine, from the policy information to be recommended, a plurality of candidate policy information corresponding to the third set and a second application scenario corresponding to the candidate policy information.

[0055] It can be understood that the second set corresponding to the policy information to be recommended contains the third set, that is, the second business goal in the third set also exists in the second set. It is possible to determine the information to be recommended corresponding to the second business goal in the third set, and use the policy information to be recommended as candidate policy information, and use the application scenario corresponding to the candidate policy information as the second application scenario.

[0056] S105, determining the second priority of each business goal in the third set according to the first priority of the candidate policy information, and determining the target recommendation algorithm corresponding to the third set from the algorithm library according to the second priority and the second application scenario.

[0057] In some implementations, different policy information has different priorities, and the first priority of each candidate policy information can be obtained and used as the first priority of the business objective corresponding to the candidate policy information.

[0058] It can be understood that each business objective in the third set is the same as the business objective corresponding to the candidate policy information, and the first priority of the business objective corresponding to the candidate policy information can be used as the second priority of each business objective in the third set.

[0059] In some implementations, the algorithm library has multiple candidate recommendation algorithms, and each candidate recommendation algorithm has a corresponding priority and application scenario. That is, the target recommendation algorithm can be determined based on the second priority and the second application scenario, and the candidate priority and the candidate application scenario corresponding to the candidate recommendation algorithm.

[0060] Optionally, a candidate priority level that is the same as the second priority level and a candidate application scenario that is the same as the second application scenario may be obtained, and the candidate priority level and the candidate recommendation algorithm corresponding to the candidate application scenario may be determined as the target recommendation algorithm.

[0061] By way of example, the candidate recommendation algorithms in the algorithm library include, but are not limited to: a content-based recommendation (CBR) algorithm, which can make accurate recommendations based on the needs of the enterprise and the details of the policy information; a collaborative filtering (CF) algorithm, which can use historical data to make policy recommendations; and an upper confidence bound (UCB) algorithm, which finds the most promising match between enterprises and policy information through a balance between exploration and utilization, thereby allocating resources reasonably.

[0062] Among them, the priority corresponding to the CBR algorithm is priority A, and the application scenario is scenario 1; the priority corresponding to the CF algorithm is priority A, and the application scenario is scenario 2; the priority corresponding to the UCB algorithm is priority B, and the application scenario is scenario 3.

[0063] If the second priority and the second application scenario are priority A and scenario 2 respectively, the CF algorithm is used as the target recommendation algorithm; if the second priority and the second application scenario are priority B and scenario 3 respectively, the UCB algorithm is used as the target recommendation algorithm.

[0064] S106: Determine at least one target policy information recommended to the enterprise from the candidate policy information based on the target recommendation algorithm.

[0065] In some implementations, after determining the target recommendation algorithm, the target recommendation algorithm can be used to determine one or more target policy information from the candidate policy information, and the target policy information can be recommended to the enterprise. For example, if the target recommendation algorithm is a CF algorithm, the interest of the enterprise in the policy information can be predicted, and the candidate policy information with an interest greater than an interest threshold can be used as the target policy information to determine at least one target policy information.

[0066] Optionally, the interest level can be calculated based on the similarity between the enterprise and other enterprises. The formula for calculating the interest level of an enterprise in the candidate policy information is as follows:

[0067] Interest(u,p)=∑v∈Usim(u,v)·rating(v,p)(1)

[0068] Among them, Interest represents interest, u represents the enterprise, p represents the candidate policy information, v represents other enterprises, sim(u,v) represents the similarity between enterprise u and enterprise v, and rating(v,p) represents the evaluation of enterprise v on the candidate policy information p.

[0069] By way of example, if the target recommendation algorithm is a CBR algorithm, the feature vectors of the candidate policy information and the enterprise can be obtained, and based on the similarity of the feature vectors, at least one target policy information can be determined. The candidate policy information with a similarity greater than a set threshold can be used as the target policy information.

[0070] Optionally, the formula for calculating the similarity of feature vectors is as follows:

[0071] Match(e,p)=vec(e)·vec(p) / vec(e).vec(p)(2)

[0072] Among them, Match represents similarity, vec(e) represents the feature vector of the enterprise, and vec(p) represents the feature vector of the candidate policy information.

[0073] If the target recommendation algorithm is the UCB algorithm, the UCB value of the candidate policy information can be calculated, and at least one target policy information can be determined based on the UCB value. The candidate policy information with a UCB value greater than a set threshold can be used as the target policy information.

[0074] Optionally, the formula for calculating the UCB value of the candidate policy information is as follows:

[0075]

[0076] Among them, UCB(p) represents the UCB value of candidate policy information p, represents the average reward of candidate policy information p, n is the total number of attempts, n p is the number of times the candidate policy information p is tried.

[0077] In the information recommendation method provided by the embodiment of the present disclosure, the first business goal of the enterprise is determined, and a first set is generated. The second business goal and the first application scenario of the policy information to be recommended are determined, and a second set is generated. Further, matching business goals are determined from the first set and the second set to generate a third set, and candidate policy information and the second application scenario of the candidate policy information are determined from the policy information to be recommended according to the third set, and then the priority of the business goal is determined to determine the target recommendation algorithm according to the priority and the application scenario. Furthermore, using the target recommendation algorithm, at least one target policy information is determined from the candidate policy information to be recommended to the enterprise, and the most suitable recommendation algorithm can be intelligently selected for different business goals, which significantly improves the flexibility and effect of information recommendation to the enterprise, and also improves the efficiency of policy communication, making the policy communication more targeted and effective.

[0078] Figure 2 This is an example flow chart of the information recommendation method provided by the embodiment of the present disclosure. Figure 2 As shown, the information recommendation method includes:

[0079] S201, determining a first set of enterprise associations, where the first set includes a plurality of first business objectives.

[0080] In some implementations, a first business goal can be determined based on the enterprise's historical data to generate a first set based on the first business goal, which enhances the scientific nature of determining business goals and helps the enterprise clarify its own business direction.

[0081] Optionally, by obtaining historical operation information of the enterprise on multiple policy information to be recommended, such as operations such as clicking on the policy information to be recommended, and determining the operation type of the enterprise based on the historical operation information, and determining one or more historical policy information browsed by the enterprise based on the operation type. For example, if the enterprise's operation type on a policy information is operations such as clicking, browsing, etc., it can be determined that the enterprise has browsed the policy information.

[0082] Further, after determining one or more historical policy information browsed by the enterprise, a fourth set corresponding to the historical policy information is determined, and multiple repeated business objectives are screened out from the fourth set as the first business objectives in the first set. The fourth set includes multiple business objectives.

[0083] S202, obtaining a plurality of policy information to be recommended, and determining a second set and a first application scenario corresponding to each piece of policy information to be recommended, wherein the second set includes a plurality of second business objectives.

[0084] S203, performing similarity matching on the business objectives in the first set and the second set, and generating a third set according to the successfully matched second business objectives.

[0085] S204: Determine, from the policy information to be recommended, a plurality of candidate policy information corresponding to the third set and a second application scenario corresponding to the candidate policy information.

[0086] The relevant contents of step S202 to step S204 can be found in the above embodiment and will not be repeated here.

[0087] S205 : For the candidate policy information i, determine at least one second business objective j corresponding to the candidate policy information i from the third set.

[0088] S206: Determine the second priority of the second business goal j according to the first priority of the candidate policy information i, where i and j are natural numbers greater than 1.

[0089] In some implementations, the first priority of candidate policy information can be determined and used as the second priority of the second business goal to ensure that the importance of policy information is taken into consideration, optimize resources based on priority, achieve efficient resource allocation, reduce resource waste, and reduce enterprise operating costs.

[0090] In some implementations, the second business objectives in the third set correspond to the business objectives of the candidate policy information one by one, that is, one candidate policy information can correspond to at least one second business objective. By determining the second business objective j corresponding to the candidate policy information i and determining the first priority of the candidate policy information i, the first priority is used as the second priority of the second business objective j, where i and j are natural numbers greater than 1.

[0091] S207: Determine a target recommendation algorithm corresponding to the third set from the algorithm library according to the second priority and the second application scenario.

[0092] S208: Determine at least one target policy information recommended to the enterprise from the candidate policy information based on the target recommendation algorithm.

[0093] The relevant contents of step S207 to step S208 can be found in the above embodiment and will not be repeated here.

[0094] In the information recommendation method provided by the embodiment of the present disclosure, the first business goal of the enterprise is determined and a first set is generated. The second business goal and the first application scenario of the policy information to be recommended are determined and a second set is generated. Further, matching business goals are determined from the first set and the second set to generate a third set, and candidate policy information and the second application scenario of the candidate policy information are determined from the policy information to be recommended according to the third set. The first priority of the candidate policy information is determined, and the second priority of the business goals in the third set is determined to determine a target recommendation algorithm according to the second priority and the second application scenario. Furthermore, using the target recommendation algorithm, at least one target policy information is determined from the candidate policy information to be recommended to the enterprise, and the most suitable recommendation algorithm can be intelligently selected for different business goals, which significantly improves the flexibility and effect of information recommendation to the enterprise, and also improves the efficiency of policy communication, making the policy communication more targeted and effective.

[0095] Figure 3 This is an example flow chart of the information recommendation method provided by the embodiment of the present disclosure. Figure 3 As shown, the information recommendation method includes:

[0096] S301, determining a first set of enterprise associations, where the first set includes a plurality of first business objectives.

[0097] S302, obtaining a plurality of policy information to be recommended, and determining a second set and a first application scenario corresponding to each piece of policy information to be recommended, wherein the second set includes a plurality of second business objectives.

[0098] The relevant contents of step S301 to step S302 can be found in the above embodiment and will not be repeated here.

[0099] S303: For any first business goal in the first set, calculate the similarity between any first business goal and each second business goal to obtain the similarity between the first business goal and the second business goal.

[0100] In some implementations, by calculating the similarity between each first business goal in the first set and each second business goal in the second set, the similarity between the first business goal and the second business goal can be obtained.

[0101] Optionally, the pre-similarity between the first business goal and the second business goal may be calculated, and the Euclidean distance between the first business goal and the second business goal may be calculated and used as the similarity. The embodiment of the present disclosure does not specifically limit the method for calculating the similarity.

[0102] S304: Determine a second business target whose similarity is greater than a set similarity threshold as the successfully matched second business target, and use the successfully matched second business target as the third business target to generate a third set.

[0103] Optionally, by setting a similarity threshold to determine whether the second business goal matches the first business goal based on the threshold, second business goals that are highly similar to the first business goal can be screened out, thereby helping the enterprise to accurately locate potential business goals, and then achieve more targeted resource allocation and improve the enterprise's resource utilization efficiency.

[0104] Optionally, if the similarity is greater than a set similarity threshold, the second business target greater than the set similarity threshold is used as the successfully matched second business target, and the successfully matched second business target is used as the third business target.

[0105] That is, a plurality of successfully matched second business objectives are obtained from the second set as the third business objectives, and the third business objectives are used as elements in the initial set to generate the third set.

[0106] S305: Determine, from the policy information to be recommended, a plurality of candidate policy information corresponding to the third set and a second application scenario corresponding to the candidate policy information.

[0107] It can be understood that the second set corresponding to the policy information to be recommended contains the third set, that is, the third business goal in the third set also exists in the second set. The second business goal that is the same as the third business goal can be determined from the second set, and the policy information to be recommended corresponding to the second business goal can be used as candidate policy information to improve the accuracy of policy recommendations and concentrate limited resources on the most valuable policy information, which can significantly improve resource utilization efficiency.

[0108] S306, determining the second priority of each business goal in the third set according to the first priority of the candidate policy information, and determining the target recommendation algorithm corresponding to the third set from the algorithm library according to the second priority and the second application scenario.

[0109] For the relevant contents of determining the second priority in step S306, reference may be made to the above embodiment and will not be repeated here.

[0110] In some implementations, appropriate target recommendation algorithms are matched to enterprises from the algorithm library based on priorities and application scenarios. Based on the business goals of the enterprise, policies that may be of interest to the enterprise can be accurately pushed, thereby improving the satisfaction of the enterprise.

[0111] Optionally, by obtaining the candidate priority and candidate application scenario of each candidate recommendation algorithm in the algorithm library, a first candidate recommendation algorithm whose candidate priority is the same as the second priority is determined from the candidate recommendation algorithms. Further, a second candidate recommendation algorithm whose candidate application scenario is the same as the second application scenario is determined from the first candidate recommendation algorithm as the target recommendation algorithm.

[0112] S307: Determine at least one target policy information recommended to the enterprise from the candidate policy information based on the target recommendation algorithm.

[0113] The relevant contents of step S307 can be found in the above embodiment and will not be described again here.

[0114] In some implementations, after recommending target policy information to an enterprise, the enterprise's operational information can be monitored, and based on the operational information, the effectiveness of the information recommendation can be monitored to obtain monitoring results, and the information recommendation process can be adjusted and optimized based on the monitoring results to ensure that business goals are optimally achieved.

[0115] Optionally, in response to the monitoring result indicating that the information recommendation effect does not meet the set conditions, the parameters of the target recommendation algorithm are optimized to recommend policy information according to the optimized target recommendation algorithm, thereby improving the recommendation effect and making the recommended content more in line with the business goals of the enterprise. The data set of the optimization process can be determined based on the operation information, and the parameters of the target recommendation algorithm can be iteratively optimized according to the data set and the set optimization goal until the optimized target recommendation algorithm reaches the optimization goal, and then the optimized target recommendation algorithm is used to recommend policy information.

[0116] Optionally, in response to the monitoring result indicating that the recommendation effect of the information meets the set condition, the operation information is used as the user's historical operation information to determine the first set based on the historical operation information.

[0117] In the information recommendation method provided by the embodiment of the present disclosure, the first business goal of the enterprise is determined, and a first set is generated. The second business goal and the first application scenario of the policy information to be recommended are determined, and a second set is generated. Further, matching business goals are determined from the first set and the second set to generate a third set, and candidate policy information and the second application scenario of the candidate policy information are determined from the policy information to be recommended according to the third set, and then the priority of the business goal is determined to determine the target recommendation algorithm according to the priority and the application scenario. Furthermore, using the target recommendation algorithm, at least one target policy information is determined from the candidate policy information to be recommended to the enterprise, and the most suitable recommendation algorithm can be intelligently selected for different business goals, which significantly improves the flexibility and effect of information recommendation to the enterprise, and also improves the efficiency of policy communication, making the policy communication more targeted and effective.

[0118] like Figure 4 A flow chart of the recommended policy information is shown. Figure 4 The policy recommendation system is used to recommend policies to enterprises, and the system uses the information recommendation method proposed in the present disclosure to recommend policies. By setting the first business goal of the enterprise, the system can recommend business goals for the enterprise based on the historical operation information of the enterprise, such as improving policy awareness, and then setting the first business goal, such as policy awareness, policy application success rate, policy coverage, etc.

[0119] Furthermore, the target recommendation algorithm is determined from the algorithm library, which has multiple candidate recommendation algorithms, and each candidate recommendation algorithm is equipped with a model operator to use the model operator of the target recommendation algorithm to recommend policies. The model operators include: model operator A: CF algorithm, model operator B: CBR algorithm, model operator C: UBC algorithm, model operator D: whitelist recommendation algorithm, etc.

[0120] Furthermore, after recommending at least one target policy information to an enterprise, the enterprise's operating information can be monitored to determine the recommendation effect of the policy information from the operating information, and the parameters of the model operator can be optimized according to the recommendation effect, or different model operators can be switched to recommend the target policy information to the enterprise.

[0121] Corresponding to the information recommendation methods provided in the above-mentioned embodiments, an embodiment of the present disclosure further provides an information recommendation device. Since the information recommendation device provided in the embodiment of the present disclosure corresponds to the information recommendation methods provided in the above-mentioned embodiments, the implementation methods of the above-mentioned information recommendation methods are also applicable to the information recommendation device provided in the embodiment of the present disclosure and will not be described in detail in the following embodiments.

[0122] Figure 5 This is a structural example diagram of the information recommendation device provided by the embodiment of the present disclosure. Figure 5 As shown, the information recommendation device includes: a first determination module 501, a second determination module 502, a matching module 503, a third determination module 504, a fourth determination module 505 and a recommendation module 506.

[0123] A first determination module 501 is used to determine a first set of enterprise associations, where the first set includes a plurality of first business objectives;

[0124] A second determination module 502 is used to obtain a plurality of policy information to be recommended, and determine a second set and a first application scenario corresponding to each policy information to be recommended, wherein the second set includes a plurality of second business objectives;

[0125] A matching module 503, configured to perform similarity matching on the business objectives in the first set and the second set, and generate a third set according to the successfully matched second business objectives;

[0126] A third determination module 504 is used to determine, from the policy information to be recommended, a plurality of candidate policy information corresponding to the third set and a second application scenario corresponding to the candidate policy information;

[0127] A fourth determination module 505 is used to determine the second priority of each business goal in the third set according to the first priority of the candidate policy information, and determine the target recommendation algorithm corresponding to the third set from an algorithm library according to the second priority and the second application scenario;

[0128] The recommendation module 506 is used to determine at least one target policy information recommended to the enterprise from the candidate policy information based on the target recommendation algorithm.

[0129] According to one embodiment of the present disclosure, the fourth determination module 505 is also used to: for candidate policy information i, determine at least one second business objective j corresponding to the candidate policy information i from the third set; determine the second priority of the second business objective j based on the first priority of the candidate policy information i, where i and j are natural numbers greater than 1.

[0130] According to one embodiment of the present disclosure, the first determination module 501 is also used to: obtain historical operation information of the enterprise on the multiple policy information to be recommended; determine the operation type of the enterprise based on the historical operation information, and determine one or more historical policy information browsed by the enterprise based on the operation type; determine the corresponding fourth set of the historical policy information; and filter out multiple repeated business goals from the fourth set as the first business goal in the first set.

[0131] According to one embodiment of the present disclosure, the matching module 503 is also used to: for any first business target in the first set, calculate the similarity between the any first business target and each second business target to obtain the similarity between the first business target and the second business target; determine the second business target whose similarity is greater than the set similarity threshold as the second business target that has been matched successfully, and use the second business target that has been matched successfully as the third business target to generate the third set.

[0132] According to an embodiment of the present disclosure, the third determination module 504 is further used to: determine a second business goal that is the same as the third business goal from the second set, and use the policy information to be recommended corresponding to the second business goal as the candidate policy information.

[0133] According to one embodiment of the present disclosure, the fourth determination module 505 is also used to: obtain the candidate priority and candidate application scenario of each candidate recommendation algorithm in the algorithm library; determine, from the candidate recommendation algorithms, a first candidate recommendation algorithm whose candidate priority is the same as the second priority; and determine, from the first candidate recommendation algorithms, a second candidate recommendation algorithm whose candidate application scenario is the same as the second application scenario as the target recommendation algorithm.

[0134] According to one embodiment of the present disclosure, the recommendation module 506 is also used to: monitor the operation information of the enterprise, and monitor the information recommendation effect based on the operation information; in response to the monitoring result indicating that the information recommendation effect does not meet the set conditions, optimize the parameters of the target recommendation algorithm; in response to the monitoring result indicating that the information recommendation effect meets the set conditions, use the operation information as the user's historical operation information to determine the first set based on the historical operation information.

[0135] According to one embodiment of the present disclosure, the recommendation module 506 is also used to: determine a data set for the optimization process based on the operation information, and iteratively optimize the parameters of the target recommendation algorithm according to the data set and the set optimization target until the optimized target recommendation algorithm reaches the optimization target.

[0136] In the information recommendation device provided by the embodiment of the present disclosure, the first business goal of the enterprise is determined and a first set is generated. The second business goal and the first application scenario of the policy information to be recommended are determined and a second set is generated. Further, matching business goals are determined from the first set and the second set to generate a third set, and candidate policy information and the second application scenario of the candidate policy information are determined from the policy information to be recommended according to the third set, and then the priority of the business goal is determined to determine the target recommendation algorithm according to the priority and the application scenario. Furthermore, using the target recommendation algorithm, at least one target policy information is determined from the candidate policy information to be recommended to the enterprise, and the most suitable recommendation algorithm can be intelligently selected for different business goals, which significantly improves the flexibility and effect of information recommendation to the enterprise, and also improves the efficiency of policy communication, making the policy communication more targeted and effective.

[0137] Figure 6 This is a diagram showing an example of the structure of an electronic device provided in an embodiment of the present disclosure. Figure 6As shown, the electronic device 600 may include: a transceiver 601 , a processor 602 , and a memory 603 .

[0138] The processor 602 executes the computer execution instructions stored in the memory, so that the processor 602 executes the scheme in the above embodiment. The processor 602 can be a general-purpose processor, including a central processing unit CPU, a network processor (network processor, NP), etc.; it can also be a digital signal processor DSP, an application-specific integrated circuit ASIC, a field programmable gate array FPGA or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components.

[0139] The memory 603 is connected to the processor 602 via a system bus and completes communication between them. The memory 603 is used to store computer program instructions.

[0140] The transceiver 601 may be used to obtain tasks to be executed and configuration information of the tasks to be executed.

[0141] The system bus can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The system bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus. The transceiver is used to realize the communication between the database access device and other computers (such as clients, read-write libraries, and read-only libraries). The memory may include random access memory (RAM) and may also include non-volatile memory.

[0142] The electronic device provided in the embodiments of the present disclosure may be the terminal device of the above embodiments.

[0143] The disclosed embodiment also provides a chip for executing instructions, and the chip is used to execute the technical solution of the information recommendation method in the above embodiment.

[0144] The embodiment of the present disclosure further provides a computer-readable storage medium, in which computer instructions are stored. When the computer instructions are executed on a computer, the computer executes the technical solution of the information recommendation method of the above embodiment.

[0145] The embodiments of the present disclosure also provide a computer program product, which includes a computer program stored in a computer-readable storage medium. At least one processor can read the computer program from the computer-readable storage medium. When the at least one processor executes the computer program, the technical solution of the information recommendation method in the above embodiments can be implemented.

[0146] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. The present disclosure is intended to cover any variations, uses or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The description and examples are to be considered exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.

[0147] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. An information recommendation method, characterized in that: include: determining a first set of enterprise associations, the first set comprising a plurality of first business objectives; Acquire multiple policy information to be recommended, and determine a second set and a first application scenario corresponding to each policy information to be recommended, wherein the second set includes multiple second business objectives; Performing similarity matching on the business objectives in the first set and the second set, and generating a third set according to the successfully matched second business objectives; Determining, from the policy information to be recommended, a plurality of candidate policy information corresponding to the third set and a second application scenario corresponding to the candidate policy information; Determine, according to the first priority of the candidate policy information, the second priority of each business goal in the third set, and determine, from an algorithm library, a target recommendation algorithm corresponding to the third set according to the second priority and the second application scenario; Based on the target recommendation algorithm, at least one target policy information recommended to the enterprise is determined from the candidate policy information.

2. The method according to claim 1, characterized in that The determining, according to the first priority of the candidate policy information, the second priority of each business objective in the third set includes: For the candidate policy information i, determining at least one second business objective j corresponding to the candidate policy information i from the third set; The second priority of the second business objective j is determined according to the first priority of the candidate policy information i, wherein i and j are natural numbers greater than 1.

3. The method according to claim 1, characterized in that The determining a first set of enterprise associations includes: Acquire historical operation information of the enterprise on the plurality of policy information to be recommended; Determine the operation type of the enterprise according to the historical operation information, and determine one or more historical policy information browsed by the enterprise based on the operation type; determining a corresponding fourth set of said historical policy information; A plurality of repeated business objectives are screened out from the fourth set as the first business objectives in the first set.

4. The method according to claim 1, characterized in that: The similarity matching of the business objectives in the first set and the second set, and generating a third set according to the successfully matched second business objectives, includes: For any first business objective in the first set, perform similarity calculation between the any first business objective and each second business objective to obtain the similarity between the first business objective and the second business objective; The second business target whose similarity is greater than a set similarity threshold is determined as the successfully matched second business target, and the successfully matched second business target is used as the third business target to generate the third set.

5. The method according to claim 4, characterized in that The step of determining, from the policy information to be recommended, a plurality of candidate policy information corresponding to the third set includes: A second business objective that is the same as the third business objective is determined from the second set, and the policy information to be recommended corresponding to the second business objective is used as the candidate policy information.

6. The method according to claim 1, characterized in that The determining, from an algorithm library according to the second priority and the second application scenario, a target recommendation algorithm corresponding to the third set includes: Obtaining a candidate priority and a candidate application scenario for each candidate recommendation algorithm in the algorithm library; Determine, from the candidate recommendation algorithms, a first candidate recommendation algorithm having the same candidate priority as the second priority; A second candidate recommendation algorithm whose candidate application scenario is the same as the second application scenario is determined from the first candidate recommendation algorithms as the target recommendation algorithm.

7. The method according to claim 1, characterized in that After determining at least one target policy information recommended to the enterprise from the candidate policy information based on the target recommendation algorithm, the method further includes: Monitoring the operation information of the enterprise, and based on the operation information, monitoring the effect of information recommendation; In response to the monitoring result indicating that the recommendation effect of the information does not meet the set conditions, optimizing the parameters of the target recommendation algorithm; In response to the monitoring result indicating that the recommendation effect of the information meets the set condition, the operation information is used as the user's historical operation information to determine the first set based on the historical operation information.

8. The method according to claim 7, characterized in that In response to the monitoring result indicating that the recommendation effect of the information does not meet the set conditions, optimizing the parameters of the target recommendation algorithm includes: A data set for the optimization process is determined based on the operation information, and parameters of the target recommendation algorithm are iteratively optimized according to the data set and the set optimization target, until the optimized target recommendation algorithm reaches the optimization target.

9. An information recommendation device, characterized in that: include: A first determination module, configured to determine a first set of enterprise associations, wherein the first set includes a plurality of first business objectives; A second determination module is used to obtain a plurality of policy information to be recommended, and determine a second set and a first application scenario corresponding to each policy information to be recommended, wherein the second set includes a plurality of second business objectives; A matching module, used to perform similarity matching on the business objectives in the first set and the second set, and generate a third set according to the successfully matched second business objectives; A third determination module, configured to determine, from the policy information to be recommended, a plurality of candidate policy information corresponding to the third set, and a second application scenario corresponding to the candidate policy information; a fourth determination module, configured to determine a second priority of each business objective in the third set according to the first priority of the candidate policy information, and determine a target recommendation algorithm corresponding to the third set from an algorithm library according to the second priority and the second application scenario; A recommendation module is used to determine at least one target policy information recommended to the enterprise from the candidate policy information based on the target recommendation algorithm.

10. The device according to claim 9, characterized in that The fourth determining module is further used for: For the candidate policy information i, determining at least one second business objective j corresponding to the candidate policy information i from the third set; The second priority of the second business objective j is determined according to the first priority of the candidate policy information i, wherein i and j are natural numbers greater than 1.

11. The device according to claim 9, characterized in that The first determining module is further used for: Acquire historical operation information of the enterprise on the plurality of policy information to be recommended; Determine the operation type of the enterprise according to the historical operation information, and determine one or more historical policy information browsed by the enterprise based on the operation type; determining a corresponding fourth set of said historical policy information; A plurality of repeated business objectives are screened out from the fourth set as the first business objectives in the first set.

12. The device according to claim 9, characterized in that The matching module is further used for: For any first business objective in the first set, perform similarity calculation between the any first business objective and each second business objective to obtain the similarity between the first business objective and the second business objective; The second business target whose similarity is greater than a set similarity threshold is determined as the successfully matched second business target, and the successfully matched second business target is used as the third business target to generate the third set.

13. The device according to claim 12, characterized in that The third determining module is further used for: A second business objective that is the same as the third business objective is determined from the second set, and the policy information to be recommended corresponding to the second business objective is used as the candidate policy information.

14. The device according to claim 9, characterized in that The fourth determining module is further used for: Obtaining a candidate priority and a candidate application scenario for each candidate recommendation algorithm in the algorithm library; Determine, from the candidate recommendation algorithms, a first candidate recommendation algorithm having the same candidate priority as the second priority; A second candidate recommendation algorithm whose candidate application scenario is the same as the second application scenario is determined from the first candidate recommendation algorithms as the target recommendation algorithm.

15. The device according to claim 9, characterized in that The recommendation module is also used to: Monitoring the operation information of the enterprise, and based on the operation information, monitoring the effect of information recommendation; In response to the monitoring result indicating that the recommendation effect of the information does not meet the set conditions, optimizing the parameters of the target recommendation algorithm; In response to the monitoring result indicating that the recommendation effect of the information meets the set condition, the operation information is used as the user's historical operation information to determine the first set based on the historical operation information.

16. The device according to claim 15, characterized in that The recommendation module is also used to: A data set for the optimization process is determined based on the operation information, and parameters of the target recommendation algorithm are iteratively optimized according to the data set and the set optimization target, until the optimized target recommendation algorithm reaches the optimization target.

17. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 8.

18. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 8 when executed by a processor.

19. A computer program product, characterized in that The invention comprises a computer program, which implements the method according to any one of claims 1 to 8 when being executed by a processor.

Images