Personalized recommendation method, device and equipment for office portal menu and storage medium

Abstract

The invention discloses an office portal menu personalized recommendation method, device and equipment and a storage medium, and relates to the technical field of office ports.The method comprises the steps that recommendation scores of all menus in an office portal system are determined based on historical menu operation information of a target user in the office portal system and a menu recommendation model, a plurality of scoring rules are stored in the menu recommendation model; determining a recommended menu of the target user based on the recommendation score of each menu in the office portal system; and pushing the recommended menu to the target user in a preset area in the office portal system. By means of the mode, according to the actual operation behavior of the user, the related content interested by the user and the related content required by the user are found, the personalized recommendation menu is made for the user, the user can rapidly obtain the wanted information based on the recommendation menu, the information obtaining efficiency is improved, meanwhile, the use experience of the user is guaranteed, and the user experience is improved. And the user satisfaction and the stickiness are improved.

Description

Technical Field

[0001] The present application relates to the technical field of office portals, and in particular to a method, device, equipment and storage medium for personalized recommendation of office portal menus. Background Art

[0002] In the office portal system, menu display is mainly based on content browsing, searching, filtering and other methods to achieve in-depth reading and interaction. Users decide whether to continue browsing or exit through feedback and interaction. However, the menu is less personalized. Users usually need to spend a certain amount of time to search and filter menus. It is difficult to quickly find the menu they want, and they cannot timely understand the relevant content of their interests and needs, which affects the efficiency of information acquisition and the user experience.

[0003] The above contents are only used to assist in understanding the technical solution of the present invention and do not constitute an admission that the above contents are prior art. Summary of the invention

[0004] The main purpose of the present application is to provide a method, device, equipment and storage medium for personalized recommendation of office portal menus, aiming to solve the technical problem in the prior art that the menu personalization level of the office portal system is low, which affects the efficiency of user information acquisition.

[0005] To achieve the above purpose, the present application provides a method for personalized recommendation of office portal menus, the method comprising:

[0006] Determining a recommendation score for each menu in the office portal system based on historical menu operation information of a target user in the office portal system and a menu recommendation model, wherein the menu recommendation model stores a plurality of scoring rules;

[0007] Determining a recommended menu for the target user based on the recommendation score of each menu in the office portal system;

[0008] The recommendation menu is pushed to the target user in a preset area in the office portal system.

[0009] In one embodiment, the step of determining the recommendation score of each menu in the office portal system based on the historical menu operation information of the target user in the office portal system and the menu recommendation model includes:

[0010] Based on the historical menu operation information of the target user, determining the effective feature data of each menu in the office portal system, wherein the effective feature data at least includes the number of visits, the collection time and the search keyword;

[0011] Based on the valid feature data and the recall strategy, the menus of the office portal system are divided into candidate menus and non-candidate menus, and the recall strategy at least includes a high-frequency use recall strategy, a collection time recall strategy, a search keyword recall strategy, a same category recall strategy, a same team recall strategy, a same department recall strategy, and a same-level organization recall strategy;

[0012] Determining the recommendation score of the candidate menu based on the scoring rule of the menu recommendation model;

[0013] A preset initial value is used as the recommendation score of the non-candidate menu.

[0014] In one embodiment, the step of dividing the menus of the office portal system into candidate menus and non-candidate menus based on the valid feature data and the recall strategy includes:

[0015] Based on the effective feature data, the menus of the office portal system are sorted, and the frequently used menus under the frequently used recall strategy, the recently collected menus under the collection time recall strategy, and the search-related menus under the search keyword recall strategy are respectively selected, and based on the frequently used menus, frequently used menus of the same type are determined;

[0016] Based on the basic information of the target user, determine the same category high-frequency use menu under the same category recall strategy, the same team high-frequency use menu under the same team recall strategy, the same department high-frequency use menu under the same department recall strategy, and the same level institution high-frequency use menu under the same level institution recall strategy, respectively, wherein the basic information includes at least personnel category, team information, department information, level institution information, and authority information;

[0017] Based on the frequently used menus, the frequently used menus of the same type, the recently collected menus, the search-related menus, the frequently used menus of the same category, the frequently used menus of the same team, the frequently used menus of the same department, and the frequently used menus of the same-level organization, the candidate menus are determined, and the menus in the office portal system other than the candidate menus are used as non-candidate menus.

[0018] In one embodiment, the step of determining the candidate menu based on the frequently used menu, the frequently used menu of the same type, the recently collected menu, the search-related menu, the frequently used menu of the same category, the frequently used menu of the same team, the frequently used menu of the same department, and the frequently used menu of the same level organization includes:

[0019] Based on the preference tag of the target user, determining the preference menu of the target user in the menu of the office portal system;

[0020] The preference menu, the frequently used menu, the frequently used menu of the same type, the recently collected menu, the search-related menu, the frequently used menu of the same category, the frequently used menu of the same team, the frequently used menu of the same department and the frequently used menu of the same-level organization are taken as the candidate menus.

[0021] In one embodiment, the step of determining the recommendation score of the candidate menu based on the scoring rule of the menu recommendation model includes:

[0022] Based on the scoring rules of the menu recommendation model, the associated scoring rules corresponding to the candidate menus are determined respectively, wherein the scoring rules at least include a preferred menu scoring rule, a frequently used menu scoring rule, a frequently used menu of the same type scoring rule, a recently collected menu scoring rule, a search-related menu scoring rule, a frequently used menu of the same category scoring rule, a frequently used menu of the same team scoring rule, a frequently used menu of the same department scoring rule, and a frequently used menu of the same level institution scoring rule;

[0023] Scoring the candidate menus based on the associated scoring rules and valid feature data corresponding to the candidate menus, and determining the initial recommendation scores of the candidate menus under each associated scoring rule;

[0024] The initial recommendation scores of the candidate menus under various associated scoring rules are added together to obtain the recommendation score of the candidate menus.

[0025] In one embodiment, the step of determining the recommended menu for the target user based on the recommendation score of each menu in the office portal system further includes:

[0026] Based on the recommendation scores of the menus in the office portal system, the menus are sorted in descending order to obtain a menu sequence;

[0027] Based on the preset recommendation quantity, a corresponding menu is selected from the menu sequence as a recommended menu for the target user.

[0028] In one embodiment, after the step of displaying the recommendation menu to the target user in the preset area of ​​the office portal system, the step further includes:

[0029] Obtaining visit volume change data and favorite volume change data of the recommended menu;

[0030] Based on the visit volume change data and the collection volume change data, the accuracy of the recommendation score is evaluated to obtain an evaluation result;

[0031] Based on the evaluation result, the menu recommendation model is optimized to optimize the recommended menu.

[0032] In addition, to achieve the above-mentioned purpose, the present application also proposes a personalized recommendation device for an office portal menu, which includes:

[0033] A menu scoring module, used to determine the recommendation score of each menu in the office portal system based on the historical menu operation information of the target user in the office portal system and a menu recommendation model, wherein the menu recommendation model stores a plurality of scoring rules;

[0034] A menu recommendation module, used to determine a recommended menu for the target user based on the recommendation score of each menu in the office portal system;

[0035] The menu recommendation module is further configured to push the recommended menu to the target user in a preset area in the office portal system.

[0036] In addition, to achieve the above-mentioned purpose, the present application also proposes an office portal menu personalized recommendation device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, and the computer program is configured to implement the steps of the office portal menu personalized recommendation method as described above.

[0037] In addition, to achieve the above purpose, the present invention also proposes a storage medium, which is a computer-readable storage medium and stores a computer program. When the computer program is executed by a processor, the steps of the office portal menu personalized recommendation method as described above are implemented.

[0038] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the steps of the above-mentioned office portal menu personalized recommendation method are implemented.

[0039] The present application provides a personalized recommendation method for office portal menus. Based on the historical menu operation information of the target user in the office portal system and the menu recommendation model, the recommendation score of each menu in the office portal system is determined, and multiple scoring rules are stored in the menu recommendation model; based on the recommendation score of each menu in the office portal system, the recommended menu of the target user is determined; and the recommended menu is pushed to the target user in a preset area in the office portal system. The present application finds the relevant content of interest and the relevant content of demand of the user according to the actual operation behavior of the user, and formulates a personalized recommendation menu for the user. The user can quickly obtain the desired information based on the recommendation menu, reduce unnecessary operations such as searching and browsing, improve the efficiency of information acquisition, and at the same time ensure the user's use experience, improve user satisfaction and stickiness, and solve the technical problem that the menu personalization of the office portal system is low and affects the efficiency of user information acquisition. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0041] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0042] Figure 1 This is a flowchart of the first embodiment of the personalized recommendation method for the office portal menu of the present application;

[0043] Figure 2 A menu classification diagram of the office portal menu personalized recommendation method provided in the first embodiment of the present application;

[0044] Figure 3 A schematic diagram of a preset area for the personalized recommendation method for an office portal menu provided in the first embodiment of the present application;

[0045] Figure 4 This is a flow chart of Embodiment 2 of the method for personalized recommendation of office portal menu in this application;

[0046] Figure 5 This is a flowchart of Embodiment 3 of the method for personalized recommendation of office portal menu in this application;

[0047] Figure 6 A brief flowchart of the personalized recommendation method for the office portal menu provided in Embodiment 3 of the present application;

[0048] Figure 7 This is a schematic diagram of the module structure of the personalized recommendation device for office portal menu according to an embodiment of the present application;

[0049] Figure 8 This is a schematic diagram of the device structure of the hardware operating environment involved in the office portal menu personalized recommendation method in the embodiment of the present application.

[0050] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0051] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0052] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0053] The main solution of the embodiment of the present application is: based on the historical menu operation information of the target user in the office portal system and the menu recommendation model, the recommendation score of each menu in the office portal system is determined, and multiple scoring rules are stored in the menu recommendation model; based on the recommendation score of each menu in the office portal system, the recommended menu of the target user is determined; and the recommended menu is pushed to the target user in a preset area in the office portal system.

[0054] At present, the personalization level of menus in office portal systems is low. Users usually need to spend a certain amount of time searching and filtering menus. It is difficult for users to quickly find the menus they want and they cannot timely learn about the relevant content of their interests and needs, which affects the efficiency of information acquisition and the user experience.

[0055] The present application provides a solution, which finds relevant content that the user is interested in and relevant content that the user needs according to the user's actual operation behavior, and formulates a personalized recommendation menu for the user. The user can quickly obtain the desired information based on the recommendation menu, reduce unnecessary operations such as searching and browsing, improve the efficiency of information acquisition, and at the same time ensure the user's usage experience, improve user satisfaction and stickiness, and solve the technical problem that the menu personalization of the office portal system is low, which affects the user's information acquisition efficiency.

[0056] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, an office portal menu personalized recommendation device, etc., and this embodiment does not specifically limit this. The following takes the office portal menu personalized recommendation device as an example to illustrate this embodiment and the following embodiments.

[0057] The present application embodiment provides a method for personalized recommendation of office portal menus. Figure 1 , Figure 1 This is a flowchart of the first embodiment of the personalized recommendation method for office portal menu of the present application.

[0058] In this embodiment, the office portal menu personalized recommendation method includes steps S10 to S40:

[0059] Step S10, determining the recommendation score of each menu in the office portal system based on the target user's historical menu operation information in the office portal system and a menu recommendation model, wherein the menu recommendation model stores a plurality of scoring rules;

[0060] It should be noted that the office portal system in this embodiment can be any office portal system that needs to improve personalization, and there is no specific limitation on this. The target user refers to the user who needs menu recommendation among all users of the office portal system. The user can usually set whether to turn on the menu recommendation function in the office portal system. If it is turned on, it will be used as the target user and menu recommendation will be performed using the office portal menu personalized recommendation method of this embodiment. If it is turned off, it will not be used as the target user and menu recommendation will not be performed.

[0061] In addition, it should be noted that an office portal system usually has multiple menus, such as attendance, process, schedule, management, notification, knowledge base, etc. The menus of different office portal systems are usually different and need to be determined according to actual conditions. There is no specific limitation on this. Generally speaking, menus can be divided into first-level menus, second-level menus, third-level menus, etc. A first-level menu can have multiple second-level menus, a second-level menu can have multiple third-level menus, and so on. For example, refer to Figure 2 , assuming that attendance and process are first-level menus, under the first-level menu attendance, you can set up second-level menus such as attendance statistics, shift information, and attendance reports. Under the second-level menu attendance report, you can set up third-level menus such as attendance summary report, daily statistics report, and holiday balance report. Under the first-level menu process, you can set up second-level menus such as to-do process, new process, and completed process. Under the second-level menu new process, you can set up third-level menus such as administrative process, personnel process, general process, financial process, and technical assistance process.

[0062] It can be understood that the historical menu operation information is the relevant behavior data collected when the target user browses and uses the menu, such as: records of opening menus, records of closing menus, favorite menus, actual time of favorite menus, used search keywords, etc.

[0063] In addition, it is usually necessary to collect the basic information of the target user, that is, the basic situation of the target user, including at least personnel category, team information, department information, hierarchical organization information and authority information. Personnel category refers to the job category of the target user, such as administration, sales, technology, finance, etc. Team information refers to the team to which the target user belongs. Department information refers to the department to which the target user belongs, such as sales department 1, technical department 2, administration department, finance department, etc. Hierarchical organization information refers to the hierarchical organization to which the target user belongs, which can be the branch to which the target user belongs, the branch to which the target user belongs, the branch company to which the target user belongs, and the branch office to which the target user belongs, without specific limitation. Authority information refers to the corresponding authority of the target user in the office portal system.

[0064] It should be understood that the basic information of the target user and the information of the menu usually do not change significantly, and the timeliness requirement is low. Therefore, when collecting information, a longer update cycle can be set, such as a few days or weeks, which is not specifically limited and is set according to actual needs. This embodiment finds the relevant content that the user is interested in and the relevant content that the user needs based on the historical menu operation information of the target user, so as to formulate a personalized recommendation menu for the user. It is necessary to fully understand the behavior of the target user, and the behavior of the target user is constantly occurring. It can be seen that the historical menu operation information has a high timeliness requirement. When collecting, a shorter update cycle can be set, such as once an hour, which is not specifically limited and is set according to actual needs.

[0065] It is understandable that after the target user's basic information, menu information, and historical menu operation information are collected, data cleaning is usually required, such as removing duplicate data, removing blank data, data classification, etc., in order to extract features later.

[0066] It should be noted that the menu recommendation model is a model used to determine the recommended menus, which stores multiple scoring rules. The scoring rules can score the menus, measure the user interest / user demand for each menu, and finally obtain a corresponding score, which is the recommendation score.

[0067] In the specific implementation, according to the actual operation behavior of the target users, the menu recommendation model is used to score all the menus of the office portal system to find the menus that the users are interested in and the menus that they need, so that personalized recommendation menus can be formulated for the users to ensure the users' information acquisition efficiency and usage experience.

[0068] Step S20, determining a recommended menu for the target user based on the recommendation score of each menu in the office portal system;

[0069] It can be understood that the higher the recommendation score, the higher the user interest / user demand for the menu, and the lower the recommendation score, the lower the user interest / user demand for the menu. Recommended menus are usually menus with higher user interest / user demand.

[0070] In a feasible implementation, step S20 may include steps S201 to S202:

[0071] Step S201, based on the recommendation score of each menu in the office portal system, sorting the menus in descending order to obtain a menu sequence;

[0072] It should be noted that after obtaining the recommendation scores of all menus in the office portal system, these menus are usually sorted according to the recommendation scores. This embodiment adopts a descending method, that is, sorting them in order from high to low recommendation scores. The final sorted menus are the menu sequence. The higher the menu is ranked, the higher the recommendation score is, and the higher the user interest / user demand is.

[0073] It is understandable that when two or more menus have the same recommendation score, they can be sorted by the first letter of the menu name, or randomly, or according to the user's access or collection status, without specific limitation.

[0074] Step S202: based on a preset number of recommendations, a corresponding menu is selected from the menu sequence as a recommended menu for the target user.

[0075] It should be noted that the preset recommendation number, i.e., the number of recommended menus, is, for example, 10, which can be flexibly adjusted according to actual conditions and is not specifically limited. According to the preset recommendation number, the corresponding recommended menu is pushed to the target user. Since the menus in the menu sequence are sorted in descending order according to the recommendation score, the menus with higher rankings should be recommended. Therefore, this embodiment starts with the first menu in the menu sequence and selects in sequence until the number of selected menus meets the preset recommendation number. For example, assuming that the preset recommendation number is 10 and there are 200 menus in the menu sequence, the first 10 menus are selected as recommended menus.

[0076] In this implementation, all menus are sorted in descending order according to the recommendation scores, and menus with higher recommendation scores are selected as the final recommended menus. This can ensure that the recommended menus are content that the user is interested in and needs. The user can quickly obtain the information they want based on the recommended menus, thereby improving the personalization of the menus and improving the efficiency of information acquisition.

[0077] It should be understood that since different users usually have different permissions, after selecting the recommended menus, it is necessary to determine whether these recommended menus are within the permission range of the target user. If they are within the permission range of the target user, the recommended menu will be retained; if they are not within the permission range of the target user, the recommended menu will be deleted and replaced with the next sorted menu to further ensure the accuracy and effectiveness of the recommended menu.

[0078] Step S30, pushing the recommendation menu to the target user in a preset area in the office portal system;

[0079] It should be noted that the preset area is the area set to push the recommended menu to the user, and the user can select / set the corresponding area in the office portal system according to his own habits. Figure 3 In the figure, A is the homepage of the office portal system, and B is the preset area of ​​the target user C. At this time, the recommended menu of the target user C will be pushed to the preset area B.

[0080] This embodiment provides a personalized recommendation method for office portal menus. Based on the historical menu operation information of the target user in the office portal system and the menu recommendation model, the recommendation score of each menu in the office portal system is determined, and multiple scoring rules are stored in the menu recommendation model; based on the recommendation score of each menu in the office portal system, the recommended menu of the target user is determined; and the recommended menu is pushed to the target user in a preset area in the office portal system. According to the actual operation behavior of the user, the relevant content of interest and the relevant content of the user's needs are found, and a personalized recommendation menu is formulated for the user. The user can quickly obtain the desired information based on the recommendation menu, reduce unnecessary operations such as searching and browsing, improve the efficiency of information acquisition, and at the same time ensure the user's use experience, and improve user satisfaction and stickiness.

[0081] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can refer to the above introduction, and will not be repeated later. Figure 4 , step S10 may include steps S101 to S103:

[0082] Step S101, determining valid feature data of each menu in the office portal system based on the historical menu operation information of the target user;

[0083] It should be noted that effective feature data refers to relevant features that can reflect the user's interest in / demand for a menu. In this embodiment, effective feature data at least includes visits, collection time, and search keywords. The visits refer to the number of visits to the menu, which can also be considered as the number of clicks on the menu. The collection time refers to the actual time when the menu is collected by the user. The search keywords refer to the effective keywords / words used by the user when searching for the desired menu.

[0084] It is understandable that, based on the historical menu operation information of the target user, the characteristics of each menu, such as the number of visits, the collection time, and the search keyword, can be determined. Based on the number of visits to the menu, it can be determined which menus are frequently used by the target user, based on the collection time of the menu, it can be determined which menus are recently collected by the target user, and based on the search keyword, it can be determined which menus the target user wants to find quickly.

[0085] Step S102, dividing the menus of the office portal system into candidate menus and non-candidate menus based on the valid feature data and the recall strategy;

[0086] It should be noted that the recall strategy refers to a strategy used to recall the content that the target user is interested in and needs, including at least a high-frequency recall strategy, a collection time recall strategy, a search keyword recall strategy, a same category recall strategy, a same team recall strategy, a same department recall strategy, and a same-level institution recall strategy. The high-frequency recall strategy is to recall menus that users use frequently, the collection time recall strategy is to recall menus that users have recently collected, the search keyword recall strategy is to recall menus that users have searched, the same category recall strategy is to recall menus that are frequently used by people of the same category, the same team recall strategy is to recall menus that are frequently used by people of the same team, the same department recall strategy is to recall menus that are frequently used by people of the same department, and the same-level institution recall strategy is to recall menus that are frequently used by people of the same level of institution. Among them, people of the same category are other users in the same position as the target user, people of the same team are other users in the same team as the target user, people of the same department are other users in the same department as the target user, and people of the same-level institution are other users in the same-level institution as the target user (for example: users of the same branch, users of the same sub-branch, and users of the same branch).

[0087] In addition, it should be noted that the candidate menu is a menu that is recalled, and the non-candidate menu is a menu that is not recalled.

[0088] In a feasible implementation, step S102 may include steps S1021 to S1023:

[0089] Step S1021, sorting the menus of the office portal system based on the valid feature data, selecting the frequently used menus under the frequently used recall strategy, the recently collected menus under the collection time recall strategy, and the search related menus under the search keyword recall strategy, and determining frequently used menus of the same type based on the frequently used menus;

[0090] It should be noted that the frequently used menus are menus that are frequently used by the target users, that is, menus with a high number of visits by the target users. According to the number of visits to the menus by the target users, all menus are sorted (the higher the number of visits, the higher the ranking), and the menus with the highest ranking are selected as the frequently used menus. The number of frequently used menus can be set according to actual needs, for example: 10, and there is no specific limit on this. In specific implementation, a time range can usually be set, for example: the past 3 months, and the number of visits to the menus by the target users within the time range is counted to determine the frequently used menus to ensure that the frequently used menus meet the latest needs and interests of the users. Frequently used menus of the same type are menus of the same type / category as the frequently used menus that are frequently used by the target users. First, find the menus of the same type / category as the frequently used menus, sort these menus according to the number of visits (the higher the number of visits, the higher the ranking), and select the menus with the highest ranking as the frequently used menus of the same type. The number of frequently used menus of the same type can be set according to actual needs, for example: 10, and there is no specific limit on this.

[0091] In addition, it should be noted that the recently collected menu is the menu that the target user has recently collected. According to the time when the target user collected the menu, all menus are sorted (the closer the time, the higher the ranking), and the menu with the highest ranking is selected as the recently collected menu. The number of recently collected menus selected can be set according to actual needs, for example: 4, and there is no specific limit on this. The search-related menu is the menu related to the search keyword of the target user. According to the search keyword and the correlation between the menu and the search keyword, all menus are sorted (the higher the correlation, the higher the ranking), and the menu with the highest ranking is selected as the search-related menu. The number of search-related menus selected can be set according to actual needs, for example: 10, and there is no specific limit on this.

[0092] It can be understood that this embodiment recalls the corresponding frequently used menus and frequently used menus of the same type according to the effective feature data and the frequently used recall strategy, recalls the corresponding recently collected menus according to the collection time recall strategy, and recalls the search-related menus according to the search keyword recall strategy.

[0093] Step S1022, based on the basic information of the target user, respectively determine the same category high-frequency use menu under the same category recall strategy, the same team high-frequency use menu under the same team recall strategy, the same department high-frequency use menu under the same department recall strategy, and the same level institution high-frequency use menu under the same level institution recall strategy;

[0094] It should be noted that the menus with high frequency use in the same category are menus with high frequency use by people of the same category as the target user, that is, menus with high visit volume by people of the same category as the target user. According to the number of visits to the menus by people of the same category, all menus are sorted (the higher the number of visits, the higher the ranking), and the menus with high ranking are selected as the menus with high frequency use in the same category. The number of menus with high frequency use in the same category selected can be set according to actual needs, for example: 10, and there is no specific limit on this. The menus with high frequency use in the same team are menus with high frequency use by people of the same team as the target user, that is, menus with high visit volume by people of the same team as the target user. According to the number of visits to the menus by people of the same team, all menus are sorted (the higher the number of visits, the higher the ranking), and the menus with high ranking are selected as the menus with high frequency use in the same team. The number of menus with high frequency use in the same team selected can be set according to actual needs, for example: 10, and there is no specific limit on this.

[0095] In addition, it should be noted that the menus frequently used in the same department are menus frequently used by people in the same department of the target user, that is, menus with high visits by people in the same department of the target user. According to the number of visits to the menus by people in the same department, all menus are sorted (the higher the number of visits, the higher the ranking), and the menus with the highest ranking are selected as the menus frequently used in the same department. The number of menus frequently used in the same department can be set according to actual needs, for example: 10, and there is no specific limitation on this. The menus frequently used in the same-level organization are menus frequently used by people in the same-level organization of the target user, that is, menus with high visits by people in the same-level organization of the target user. According to the number of visits to the menus by people in the same-level organization, all menus are sorted (the higher the number of visits, the higher the ranking), and the menus with the highest ranking are selected as the menus frequently used in the same-level organization. The number of menus frequently used in the same-level organization can be set according to actual needs, for example: 10, and there is no specific limitation on this.

[0096] It can be understood that this embodiment finds people of the same category, team, department and level of organization of the target user based on the basic information of the target user, and recalls frequently used menus of the same category according to the same category recall strategy, recalls frequently used menus of the same team according to the same team recall strategy, recalls frequently used menus of the same department according to the same department recall strategy, and recalls frequently used menus of the same level of organization according to the same level of organization recall strategy.

[0097] Step S1023, based on the frequently used menus, the frequently used menus of the same type, the recently collected menus, the search-related menus, the frequently used menus of the same category, the frequently used menus of the same team, the frequently used menus of the same department, and the frequently used menus of the same-level organization, determine the candidate menus, and use the menus in the office portal system other than the candidate menus as the non-candidate menus.

[0098] It should be noted that frequently used menus, frequently used menus of the same type, recently collected menus, search-related menus, frequently used menus of the same category, frequently used menus of the same team, frequently used menus of the same department, and frequently used menus of the same-level institutions are all candidate menus, and all other menus in the office portal system except candidate menus are non-candidate menus.

[0099] In a specific implementation, this embodiment utilizes a variety of recall strategies to recall as much content that the target user is interested in and needs as possible, so as to improve the accuracy of the recommended menu.

[0100] In addition to the candidate menus obtained by the recall strategy, it is usually necessary to consider the personalized settings of the target user on the menu, such as customized preference tags. If a menu has a preference tag set by the target user, it is considered to be the user's preferred menu, that is, the preference menu.

[0101] In a feasible implementation, based on the preference tag of the target user, the preference menu of the target user is determined in the menu of the office portal system; the preference menu, the frequently used menu, the frequently used menu of the same type, the recently collected menu, the search-related menu, the frequently used menu of the same category, the frequently used menu of the same team, the frequently used menu of the same department and the frequently used menu of the same-level organization are used as the candidate menus.

[0102] It is understandable that all candidate menus can be obtained based on the preference menu, frequently used menu, frequently used menu of the same type, recent favorites menu, search related menu, frequently used menu of the same category, frequently used menu of the same team, frequently used menu of the same department and frequently used menu of the same level organization.

[0103] It should be understood that the same menus may exist in the preference menu, frequently used menu, frequently used menu of the same type, recent favorites menu, search-related menu, frequently used menu of the same category, frequently used menu of the same team, frequently used menu of the same department, and frequently used menu of the same-level organization. The duplicate content can be removed to obtain the final candidate menu.

[0104] Step S103, determining the recommendation score of the candidate menu based on the scoring rule of the menu recommendation model;

[0105] In a feasible implementation, step S103 may include steps S1031 to S1033:

[0106] Step S1031, based on the scoring rule of the menu recommendation model, determining the associated scoring rules corresponding to the candidate menus respectively;

[0107] It should be noted that there are multiple scoring rules in the menu recommendation model, and not all the rules need to be used for scoring of each candidate menu. For example, if the candidate menu is a frequently used menu, it is necessary to use the scoring rules corresponding to the frequently used menu for scoring; if the candidate menu is both a frequently used menu and a recently collected menu, it is necessary to use the scoring rules corresponding to the frequently used menu and the scoring rules corresponding to the recently collected menu for scoring; the scoring rules that need to be used for each candidate menu are the associated scoring rules of the candidate menu.

[0108] In addition, it should be noted that the scoring rules at least include preference menu scoring rules, high-frequency menu scoring rules, high-frequency menu scoring rules, recently collected menu scoring rules, search-related menu scoring rules, high-frequency menu scoring rules, high-frequency menu scoring rules, high-frequency menu scoring rules, high-frequency menu scoring rules, high-frequency menu scoring rules, high-frequency menu scoring rules, high-frequency menu scoring rules, high-frequency menu scoring rules, high-frequency menu scoring rules, and high-frequency menu scoring rules, which correspond to preference menus, high-frequency menus, high-frequency menus, recently collected menus, search-related menus, high-frequency menus, high-frequency menus, high-frequency menus, high-frequency menus, high-frequency menus, high-frequency menus, high-frequency menus, high-frequency menus, high-frequency menus, high-frequency menus, high-frequency menus. The specific content of the scoring rules can be set according to actual needs, and there is no specific limitation on this.

[0109] Exemplarily, preference menu scoring rules: determined according to the preference tags of target users, different preference tags are set with different values, for example: a menu with preference tag 1 gets 80 points, and a menu with preference tag 2 gets 50 points; high-frequency menu scoring rules: determined according to the number of visits to high-frequency menus, 20 points if the number of visits is in the range of 1%-10%, 40 points if the number of visits is in the range of 10%-30%, 60 points if the number of visits is in the range of 30%-50%, 80 points if the number of visits is in the range of 50%-80%, and 1000 points if the number of visits is in the range of 80%-100%; high-frequency use of the same type of menus The scoring rules for the most frequently used menus of the same type are determined according to the number of visits to the most frequently used menus of the same type. The 10 most frequently used menus of the same type are awarded 100 points, 90 points, 80 points, 70 points, 60 points, 50 points, 40 points, 30 points, 20 points, and 10 points in descending order of the number of visits; the scoring rules for the most recently collected menus are determined according to the time when the most recently collected menus were collected. The 4 most recently collected menus are awarded 100 points, 75 points, 50 points, and 25 points in descending order of the time when they were collected; the scoring rules for the search-related menus are determined according to the relevance of the search-related menus. The 10 search-related menus are awarded 100 points, 90 points, 40 points, 30 points, 20 points, and 10 points in descending order of the relevance. 80 points, 70 points, 60 points, 50 points, 40 points, 30 points, 20 points, 10 points; Scoring rules for high-frequency menus of the same category: determined according to the number of visits to high-frequency menus of the same category, 10 high-frequency menus of the same category will receive 100 points, 90 points, 80 points, 70 points, 60 points, 50 points, 40 points, 30 points, 20 points, 10 points in descending order of the number of visits; Scoring rules for high-frequency menus of the same team: determined according to the number of visits to high-frequency menus of the same team, 10 high-frequency menus of the same team will receive 100 points, 90 points, 80 points, 70 points, 60 points, 50 points, 40 points, 30 points, 20 points, 10 points in descending order of the number of visits. , 30 points, 20 points, 10 points; Scoring rules for high-frequency menus in the same department: determined according to the number of visits to high-frequency menus in the same department, 10 high-frequency menus in the same department will get 100 points, 90 points, 80 points, 70 points, 60 points, 50 points, 40 points, 30 points, 20 points, 10 points in descending order of visits; Scoring rules for high-frequency menus in institutions at the same level: determined according to the number of visits to high-frequency menus in institutions at the same level, 10 high-frequency menus in the same level will get 100 points, 90 points, 80 points, 70 points, 60 points, 50 points, 40 points, 30 points, 20 points, 10 points in descending order of visits. The specific score and value range can be flexibly adjusted according to actual needs, and there is no specific limitation on this.

[0110] It is understandable that the number of menus involved in each scoring rule needs to be consistent with the number of menus recalled by the relevant recall strategy.

[0111] Step S1032, scoring the candidate menu based on the associated scoring rules and valid feature data corresponding to the candidate menu, and determining the initial recommendation score of the candidate menu under each associated scoring rule;

[0112] It is understandable that the score is scored according to the associated scoring rule corresponding to each candidate menu, and the score that the candidate menu can obtain under each associated scoring rule is the initial recommendation score.

[0113] Step S1033, adding the initial recommendation scores of the candidate menus under various associated scoring rules to obtain the recommendation score of the candidate menus.

[0114] It should be understood that the final recommendation score of the candidate menu can be calculated by adding the initial recommendation scores of the candidate menus under each association scoring rule. For example, the initial recommendation score of candidate menu X under association scoring rule 1 is a, and the initial recommendation score under association scoring rule 2 is b, then the recommendation score of candidate menu X is a+b.

[0115] Step S104: Using the preset initial value as the recommendation score of the non-candidate menu.

[0116] It should be noted that the preset initial value is a set initial score, which is usually 0. In this case, the recommendation scores of non-candidate menus are all 0.

[0117] This embodiment provides a personalized recommendation method for office portal menus. Based on the historical menu operation information of the target user, the effective feature data of each menu in the office portal system is determined; based on the effective feature data and the recall strategy, the menus of the office portal system are divided into candidate menus and non-candidate menus; based on the scoring rules of the menu recommendation model, the recommendation score of the candidate menu is determined; and the preset initial value is used as the recommendation score of the non-candidate menu. According to the actual operation behavior of the user, the relevant content of interest and the relevant content of the user's needs are recalled, and corresponding rules are formulated for scoring, so as to obtain the recommendation scores of all menus, and a personalized recommendation menu is formulated for the user according to the recommendation score. The user can quickly obtain the desired information based on the recommendation menu, reduce unnecessary operations such as searching and browsing, improve the efficiency of information acquisition, and at the same time ensure the user's use experience, and improve user satisfaction and stickiness.

[0118] Based on the above embodiments of the present application, in the third embodiment of the present application, the same or similar contents as those in the above embodiments can be referred to the above introduction, and will not be described in detail later. Figure 5 , step S30 may include steps S401 to S403:

[0119] Step S401, obtaining the visit volume change data and the collection volume change data of the recommended menu;

[0120] It should be noted that the visit volume change data refers to the change in the target users' visits to these recommended menus after the recommended menus are pushed to the target users. If the visit volume change data is a positive number, it means that the visit volume has increased, and the recommended menu is in line with the needs and interests of the target users. If the visit volume change data is a negative number, it means that the visit volume has decreased, and the recommended menu is not in line with the needs and interests of the target users. If the visit volume change data is zero, it means that the visit volume has not changed, and the recommended menu is not in line with the needs and interests of the target users.

[0121] In addition, it should be noted that the collection volume change data refers to the change in the collection volume of the target users for these recommended menus after the recommended menus are pushed to the target users. If the collection volume change data is a positive number, it means that the collection volume has increased, and the recommended menu is in line with the needs and interests of the target users. If the collection volume change data is a negative number, it means that the collection volume has decreased, and the recommended menu is not in line with the needs and interests of the target users. If the collection volume change data is zero, it means that the collection volume has not changed, and the recommended menu is not in line with the needs and interests of the target users.

[0122] It is understandable that the visit volume change data and the collection volume change data can be obtained from the visit status data report and the collection status data report.

[0123] Step S402, based on the visit volume change data and the collection volume change data, the accuracy of the recommendation score is evaluated to obtain an evaluation result;

[0124] It should be noted that the accuracy of the recommendation score is comprehensively evaluated based on the visit volume change data and the collection volume change data. The evaluation result is the accuracy of the recommendation score, for example: high accuracy, low accuracy.

[0125] It is understandable that if the recommended menu does not meet the needs and interests of the target users, it means that the recommendation score of the recommended menu is inaccurate, that is, the accuracy of the recommendation score needs to be optimized, and the evaluation result at this time can be considered to be of low accuracy; if the recommended menu meets the needs and interests of the target users, it means that the recommendation scores of all recommended menus are accurate, that is, the accuracy of the recommendation score has reached the target, and the evaluation result at this time can be considered to be of high accuracy.

[0126] Step S403: optimizing the menu recommendation model based on the evaluation result to optimize the recommended menu.

[0127] It can be understood that optimizing the menu recommendation model, that is, optimizing the scoring rules of the menu recommendation model, can optimize the final recommended menu.

[0128] It should be understood that when the accuracy of the recommendation is low, optimizing the menu recommendation model can calculate a more accurate recommendation score, thereby more accurately determining the recommended menu, improving the accuracy of the recommendation, and increasing users' visits and collections of the recommended menu.

[0129] This embodiment provides a personalized recommendation method for office portal menus, which obtains visit volume change data and collection volume change data of the recommended menu; based on the visit volume change data and collection volume change data, the accuracy of the recommendation score is evaluated to obtain an evaluation result; based on the evaluation result, the menu recommendation model is optimized to optimize the recommended menu. By optimizing the menu recommendation model, a more accurate recommendation score can be calculated, thereby more accurately determining the recommended menu, improving the recommendation accuracy, and increasing the number of visits and collections of the recommended menu by users.

[0130] For example, in order to help understand the implementation process of the office portal menu personalized recommendation method obtained by combining this embodiment with the above-mentioned embodiment 3, please refer to Figure 6 , Figure 6 A brief flowchart of a personalized recommendation method for an office portal menu is provided, specifically:

[0131] Collect user operation data on menus in the office portal system; clean the collected data; calculate the recommendation scores of all menus using the set scoring rules and the scores set by the rules; output recommended menus based on the recommended scores; collect user feedback on the recommended menus and optimize the scoring process.

[0132] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the personalized recommendation method of the office portal menu of the present application. More simple transformations based on this technical concept are all within the protection scope of the present application.

[0133] This application also provides a personalized recommendation device for office portal menus, please refer to Figure 7 , the personalized recommendation device of the office portal menu includes:

[0134] The menu scoring module 10 is used to determine the recommendation score of each menu in the office portal system based on the historical menu operation information of the target user in the office portal system and a menu recommendation model, wherein the menu recommendation model stores a variety of scoring rules.

[0135] The menu recommendation module 20 is used to determine the recommended menu for the target user based on the recommendation score of each menu in the office portal system.

[0136] The menu recommendation module 20 is further configured to push the recommended menu to the target user in a preset area in the office portal system.

[0137] In a feasible implementation manner, the menu scoring module 10 is further used to determine effective feature data of each menu in the office portal system based on the historical menu operation information of the target user, wherein the effective feature data at least includes the number of visits, the collection time, and the search keyword;

[0138] Based on the valid feature data and the recall strategy, the menus of the office portal system are divided into candidate menus and non-candidate menus, and the recall strategy at least includes a high-frequency use recall strategy, a collection time recall strategy, a search keyword recall strategy, a same category recall strategy, a same team recall strategy, a same department recall strategy, and a same-level organization recall strategy;

[0139] Determining the recommendation score of the candidate menu based on the scoring rule of the menu recommendation model;

[0140] A preset initial value is used as the recommendation score of the non-candidate menu.

[0141] In a feasible implementation manner, the menu scoring module 10 is further used to sort the menus of the office portal system based on the effective feature data, respectively select the frequently used menus under the frequently used recall strategy, the recently collected menus under the collection time recall strategy, and the search related menus under the search keyword recall strategy, and determine the frequently used menus of the same type based on the frequently used menus;

[0142] Based on the basic information of the target user, determine the same category high-frequency use menu under the same category recall strategy, the same team high-frequency use menu under the same team recall strategy, the same department high-frequency use menu under the same department recall strategy, and the same level institution high-frequency use menu under the same level institution recall strategy, respectively, wherein the basic information includes at least personnel category, team information, department information, level institution information, and authority information;

[0143] Based on the frequently used menus, the frequently used menus of the same type, the recently collected menus, the search-related menus, the frequently used menus of the same category, the frequently used menus of the same team, the frequently used menus of the same department, and the frequently used menus of the same-level organization, the candidate menus are determined, and the menus in the office portal system other than the candidate menus are used as non-candidate menus.

[0144] In a feasible implementation manner, the menu scoring module 10 is further used to determine the target user's preferred menu in the menu of the office portal system based on the target user's preference tag;

[0145] The preference menu, the frequently used menu, the frequently used menu of the same type, the recently collected menu, the search-related menu, the frequently used menu of the same category, the frequently used menu of the same team, the frequently used menu of the same department and the frequently used menu of the same-level organization are taken as the candidate menus.

[0146] In a feasible implementation manner, the menu scoring module 10 is further used to determine the associated scoring rules corresponding to the candidate menus based on the scoring rules of the menu recommendation model, wherein the scoring rules at least include preferred menu scoring rules, frequently used menu scoring rules, frequently used same type menu scoring rules, recently collected menu scoring rules, search related menu scoring rules, frequently used menu scoring rules of the same category, frequently used menu scoring rules of the same team, frequently used menu scoring rules of the same department, and frequently used menu scoring rules of the same level institution;

[0147] Scoring the candidate menus based on the associated scoring rules and valid feature data corresponding to the candidate menus, and determining the initial recommendation scores of the candidate menus under each associated scoring rule;

[0148] The initial recommendation scores of the candidate menus under various associated scoring rules are added together to obtain the recommendation score of the candidate menus.

[0149] In a feasible implementation manner, the menu recommendation module 20 is further used to sort the menus in descending order based on the recommendation scores of the menus in the office portal system to obtain a menu sequence;

[0150] Based on the preset recommendation quantity, a corresponding menu is selected from the menu sequence as a recommended menu for the target user.

[0151] In a feasible implementation manner, the menu recommendation module 20 is further used to obtain visit volume change data and collection volume change data of the recommended menu;

[0152] Based on the visit volume change data and the collection volume change data, the accuracy of the recommendation score is evaluated to obtain an evaluation result;

[0153] Based on the evaluation result, the menu recommendation model is optimized to optimize the recommended menu.

[0154] The personalized recommendation device for office portal menus provided by the present application adopts the personalized recommendation method for office portal menus in the above embodiment, which can solve the technical problem that the menu personalization degree of the office portal system is low, affecting the efficiency of user information acquisition. Compared with the prior art, the beneficial effects of the personalized recommendation device for office portal menus provided by the present application are the same as the beneficial effects of the personalized recommendation method for office portal menus provided by the above embodiment, and other technical features in the personalized recommendation device for office portal menus are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0155] The present application provides an office portal menu personalized recommendation device, which includes: 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 so that the at least one processor can execute the office portal menu personalized recommendation method in the above-mentioned embodiment 1.

[0156] Reference below Figure 8 , which shows a schematic diagram of the structure of an office portal menu personalized recommendation device suitable for implementing the embodiment of the present application. The office portal menu personalized recommendation device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 8 The office portal menu personalized recommendation device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0157] like Figure 8As shown, the office portal menu personalized recommendation device may include a processing device 1001 (such as a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the office portal menu personalized recommendation device are also stored. The processing device 1001, ROM1002 and RAM1004 are connected to each other via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 1003 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 1009. The communication device 1009 can allow the office portal menu personalized recommendation device to communicate wirelessly or wired with other devices to exchange data. Although the figure shows an office portal menu personalized recommendation device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be implemented or have alternatively.

[0158] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0159] The personalized menu recommendation device for office portals provided by the present application adopts the personalized menu recommendation method for office portals in the above embodiment, which can solve the technical problem that the menu personalization degree of the office portal system is low, affecting the efficiency of user information acquisition. Compared with the prior art, the beneficial effects of the personalized menu recommendation device for office portals provided by the present application are the same as the beneficial effects of the personalized menu recommendation method for office portals provided by the above embodiment, and other technical features in the personalized menu recommendation device for office portals are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0160] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0161] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0162] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the personalized recommendation method for office portal menus in the above-mentioned embodiment.

[0163] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0164] The computer-readable storage medium may be included in the office portal menu personalized recommendation device; or may exist independently without being assembled into the office portal menu personalized recommendation device.

[0165] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the office portal menu personalized recommendation device, the office portal menu personalized recommendation device: determines the recommendation score of each menu in the office portal system based on the historical menu operation information of the target user in the office portal system and the menu recommendation model, wherein a plurality of scoring rules are stored in the menu recommendation model; determines the recommended menu for the target user based on the recommendation score of each menu in the office portal system; and pushes the recommended menu to the target user in a preset area in the office portal system.

[0166] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0167] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0168] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0169] The readable storage medium provided by the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned personalized recommendation method for office portal menus, and can solve the technical problem that the menu personalization degree of the office portal system is low, which affects the efficiency of user information acquisition. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as the beneficial effects of the personalized recommendation method for office portal menus provided by the above-mentioned embodiment, and will not be repeated here.

[0170] The present application also provides a computer program product, including a computer program, which implements the steps of the above-mentioned office portal menu personalized recommendation method when the computer program is executed by a processor.

[0171] The computer program product provided by the present application can solve the technical problem that the menu personalization of the office portal system is low, which affects the efficiency of user information acquisition. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as the beneficial effects of the office portal menu personalization recommendation method provided by the above embodiment, which will not be elaborated here.

[0172] The above are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect application in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A personalized recommendation method for office portal menu, characterized in that: The method comprises: Determining a recommendation score for each menu in the office portal system based on historical menu operation information of a target user in the office portal system and a menu recommendation model, wherein the menu recommendation model stores a plurality of scoring rules; Determining a recommended menu for the target user based on the recommendation score of each menu in the office portal system; The recommendation menu is pushed to the target user in a preset area in the office portal system.

2. The method according to claim 1, characterized in that The step of determining the recommendation score of each menu in the office portal system based on the historical menu operation information of the target user in the office portal system and the menu recommendation model comprises: Based on the historical menu operation information of the target user, determining the effective feature data of each menu in the office portal system, wherein the effective feature data at least includes the number of visits, the collection time and the search keyword; Based on the valid feature data and the recall strategy, the menus of the office portal system are divided into candidate menus and non-candidate menus, and the recall strategy at least includes a high-frequency use recall strategy, a collection time recall strategy, a search keyword recall strategy, a same category recall strategy, a same team recall strategy, a same department recall strategy, and a same-level organization recall strategy; Determining the recommendation score of the candidate menu based on the scoring rule of the menu recommendation model; A preset initial value is used as the recommendation score of the non-candidate menu.

3. The method according to claim 2, characterized in that The step of dividing the menus of the office portal system into candidate menus and non-candidate menus based on the effective feature data and the recall strategy comprises: Based on the effective feature data, the menus of the office portal system are sorted, and the frequently used menus under the frequently used recall strategy, the recently collected menus under the collection time recall strategy, and the search-related menus under the search keyword recall strategy are respectively selected, and based on the frequently used menus, frequently used menus of the same type are determined; Based on the basic information of the target user, determine the same category high-frequency use menu under the same category recall strategy, the same team high-frequency use menu under the same team recall strategy, the same department high-frequency use menu under the same department recall strategy, and the same level institution high-frequency use menu under the same level institution recall strategy, respectively, wherein the basic information includes at least personnel category, team information, department information, level institution information, and authority information; Based on the frequently used menus, the frequently used menus of the same type, the recently collected menus, the search-related menus, the frequently used menus of the same category, the frequently used menus of the same team, the frequently used menus of the same department, and the frequently used menus of the same-level organization, the candidate menus are determined, and the menus in the office portal system other than the candidate menus are used as non-candidate menus.

4. The method according to claim 3, characterized in that The step of determining the candidate menu based on the frequently used menu, the frequently used menu of the same type, the recently collected menu, the search-related menu, the frequently used menu of the same category, the frequently used menu of the same team, the frequently used menu of the same department, and the frequently used menu of the same level organization includes: Based on the preference tag of the target user, determining the preference menu of the target user in the menu of the office portal system; The preference menu, the frequently used menu, the frequently used menu of the same type, the recently collected menu, the search-related menu, the frequently used menu of the same category, the frequently used menu of the same team, the frequently used menu of the same department and the frequently used menu of the same-level organization are taken as the candidate menus.

5. The method according to claim 3, characterized in that The step of determining the recommendation score of the candidate menu based on the scoring rule of the menu recommendation model comprises: Based on the scoring rules of the menu recommendation model, the associated scoring rules corresponding to the candidate menus are determined respectively, wherein the scoring rules at least include a preferred menu scoring rule, a frequently used menu scoring rule, a frequently used menu of the same type scoring rule, a recently collected menu scoring rule, a search-related menu scoring rule, a frequently used menu of the same category scoring rule, a frequently used menu of the same team scoring rule, a frequently used menu of the same department scoring rule, and a frequently used menu of the same level institution scoring rule; Scoring the candidate menus based on the associated scoring rules and valid feature data corresponding to the candidate menus, and determining the initial recommendation scores of the candidate menus under each associated scoring rule; The initial recommendation scores of the candidate menus under various associated scoring rules are added together to obtain the recommendation score of the candidate menus.

6. The method according to claim 1, characterized in that The step of determining the recommended menu for the target user based on the recommendation score of each menu in the office portal system further includes: Based on the recommendation scores of the menus in the office portal system, the menus are sorted in descending order to obtain a menu sequence; Based on the preset recommendation quantity, a corresponding menu is selected from the menu sequence as a recommended menu for the target user.

7. The method according to any one of claims 1 to 6, characterized in that After the step of displaying the recommended menu to the target user in the preset area of ​​the office portal system, the following step further includes: Obtaining visit volume change data and favorite volume change data of the recommended menu; Based on the visit volume change data and the collection volume change data, the accuracy of the recommendation score is evaluated to obtain an evaluation result; Based on the evaluation result, the menu recommendation model is optimized to optimize the recommended menu.

8. A personalized recommendation device for office portal menu, characterized in that: The device comprises: A menu scoring module, used to determine the recommendation score of each menu in the office portal system based on the historical menu operation information of the target user in the office portal system and a menu recommendation model, wherein the menu recommendation model stores a plurality of scoring rules; A menu recommendation module, used for determining a recommended menu for the target user based on the recommendation score of each menu in the office portal system; The menu recommendation module is further configured to push the recommended menu to the target user in a preset area in the office portal system.

9. A personalized recommendation device for office portal menu, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the office portal menu personalized recommendation method according to any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the office portal menu personalized recommendation method according to any one of claims 1 to 7 are implemented.

Images