Conversation recommendation method and device, storage medium, and electronic device

Abstract

This application discloses a conversation recommendation method and apparatus, storage medium, and electronic device. The method comprises: constructing a social graph between a target account and associated accounts on an enterprise collaborative office platform, where the associated accounts are accounts associated with the target account; dynamically querying the target account's associated conversation information based on the social graph; and recommending the associated conversation information to the target account on the enterprise collaborative office platform. This application addresses the technical issue of related technologies that prevents efficient conversation information recommendation for employees.

Description

Technical Field

[0001] The present application relates to the field of big data, and more specifically, to a method and device for recommending conversations, a storage medium, and an electronic device. Background Art

[0002] With the deepening of digitalization, enterprise collaborative office platforms have experienced rapid development, with the emergence of a large number of enterprise collaboration software. These platforms, targeting the characteristics of knowledge-intensive enterprises that prioritize knowledge over processes, have developed tools such as team communication, collaborative video conferencing, and collaborative cloud documents to promote teamwork, improve organizational efficiency, accelerate innovation, and drive digital transformation. This digital transformation has led to an exponential increase in employee conversation data. Since daily work efficiency is directly related to the processing of individual conversation data, how to more effectively recommend conversation information to employees and expedite their extraction of the most relevant information from these large volumes of conversations, thereby significantly improving their daily work efficiency, has become a pressing issue.

[0003] To address the above-mentioned problems, no effective solutions have been proposed so far. Summary of the Invention

[0004] The embodiments of the present application provide a conversation recommendation method and device, a storage medium, and an electronic device to at least solve the technical problem in the related art that conversation information cannot be efficiently recommended to employees.

[0005] According to one aspect of an embodiment of the present application, a method for recommending a conversation is provided, comprising: constructing a social graph between a target account and associated accounts on an enterprise collaborative office platform, where the associated accounts are accounts associated with the target account; dynamically querying associated conversation information of the target account based on the social graph; and recommending the associated conversation information to the target account on the enterprise collaborative office platform.

[0006] Optionally, constructing a social graph between the target account and the associated accounts on the enterprise collaborative office platform includes: constructing a social graph with the target account and the associated accounts as nodes and the degree of association between the target account and the associated accounts as edges, wherein the degree of association is determined based on the interaction frequency and interaction time between the target account and the associated accounts.

[0007] Optionally, the correlation degree deg is determined according to the following formula:

[0008]

[0009] The value of n ranges from 1 to an integer m, C n represents the interaction frequency on day n, r n Indicates the attenuation factor for the nth day in the range (0,1].

[0010] Optionally, dynamically querying the associated session information of the target account based on the social graph includes: obtaining first session information, wherein the first session information is the session information of which the target account is reminded, and the associated session information includes the first session information; obtaining second session information, wherein the second session information includes session information sent by the first account to the target account and session information sent by the second account to the target account, the first account is used to manage the target account, the second account is a customer account, and the associated session information includes the second session information.

[0011] Optionally, dynamically querying the target account's associated session information based on the social graph also includes: dynamically querying the social graph for a third account whose association with the target account is greater than a preset threshold; and obtaining the third account's read session information, wherein the associated session information includes the read session information.

[0012] Optionally, the associated session information is recommended to the target account on the enterprise collaborative office platform, including: dividing the associated session information into two types of session information, wherein the two types of session information include information that must be viewed and information that is optionally viewed; and recommending each type of session information to the target account on the enterprise collaborative office platform in chronological order.

[0013] Optionally, dividing the associated session information into two types of session information includes: acquiring a business parsing rule, wherein the business parsing rule is a predefined message classification rule; and dividing the associated session information into two types of session information according to the business parsing rule.

[0014] According to another aspect of an embodiment of the present application, a conversation recommendation device is also provided, including: a construction unit for constructing a social graph between a target account and associated accounts on an enterprise collaborative office platform, wherein the associated account is an account associated with the target account; a query unit for dynamically querying associated conversation information of the target account based on the social graph; and a recommendation unit for recommending the associated conversation information to the target account on the enterprise collaborative office platform.

[0015] According to another aspect of an embodiment of the present application, a storage medium is further provided, which includes a stored program, and the above method is executed when the program is run.

[0016] According to another aspect of an embodiment of the present application, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the above method through the computer program.

[0017] According to one aspect of the present application, a computer program product or computer program is provided, the computer program product or computer program including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the steps of any of the above-described method embodiments.

[0018] The present application can provide recommendation technical support in the recommendation system, such as performing personalized recommendations. In an embodiment of the present application, a social graph is constructed between a target account and associated accounts on an enterprise collaborative office platform, where an associated account is an account associated with the target account; associated session information of the target account is dynamically queried based on the social graph; and the associated session information is recommended to the target account on the enterprise collaborative office platform. By deeply studying the graph structure of the social network of enterprise employees and utilizing the information dissemination method based on the graph structure, the communication efficiency of enterprise employees is effectively enhanced, thereby solving the technical problem in related technologies of not being able to efficiently recommend session information to employees. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0020] Figure 1 is a schematic diagram of a hardware environment for a session recommendation method according to an embodiment of the present application;

[0021] Figure 2 is a flowchart of an optional conversation recommendation method according to an embodiment of the present application;

[0022] Figure 3 is a schematic diagram of an optional social graph according to an embodiment of the present application;

[0023] Figure 4 is a schematic diagram of an optional conversation recommendation device according to an embodiment of the present application; and

[0024] Figure 5 This is a structural block diagram of a terminal according to an embodiment of the present application. DETAILED DESCRIPTION

[0025] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this application.

[0026] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in a sequence other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0027] First, some nouns or terms that appear in the description of the embodiments of the present application are subject to the following interpretations:

[0028] Time validity: Conversational information within an enterprise places great emphasis on time validity, such as handling a complaint, information that is reminded (such as with the "@" symbol), meetings that need to be held on a scheduled basis, etc. In addition, expired information must be filtered out.

[0029] Information relevance: There are a large number of group messages within the enterprise, and many groups are about the same project or the same thing. It is very important for users to be able to integrate related content. In addition, the enterprise is a social structure, and the information connected through social friends is highly correlated, so the integration of this information is also very necessary.

[0030] Currently, recommendation based on session data is a new scenario, and new changes are needed in technical applications to adapt. The available approach to session data recommendation is based on recommendation algorithms and recommendation systems. Of course, because session data recommendation has its own unique scenarios, its main characteristics are concentrated on time validity and information relevance. These characteristics require upgrades to recommendation algorithms and recommendation systems.

[0031] If we only use recommendation algorithms and recommendation systems, we cannot handle the characteristics of time validity and information relevance well. Of course, we can also handle these scenarios by adding many business rules.

[0032] The solution described above, which combines a large number of business rules into recommendation algorithms and systems, has the advantage of being able to quickly respond to changes in demand. However, its disadvantage is that it is difficult to maintain a large number of rules. If the needs of different industries and customers vary significantly, and if machine learning cannot be used to learn patterns from large amounts of data, the subsequent implementation costs will become increasingly high.

[0033] Based on this, according to one aspect of an embodiment of the present application, a method embodiment of a conversation recommendation method is provided.

[0034] Optionally, in this embodiment, the above session recommendation method can be applied to Figure 1 In the hardware environment composed of the terminal 101 and the server 103 shown in FIG. Figure 1 As shown, the server 103 is connected to the terminal 101 via a network, and can be used to provide services (such as enterprise collaboration services) for the terminal or a client installed on the terminal. A database 105 can be set on the server or independently of the server to provide data storage services for the server 103. The above-mentioned network includes but is not limited to: a wide area network, a metropolitan area network or a local area network, and the terminal 101 is not limited to a PC, a mobile phone, a tablet computer, etc.

[0035] The conversation recommendation method of the embodiment of the present application can be executed by the server 103, or can be executed jointly by the server 103 and the terminal 101. Figure 2 is a flowchart of an optional conversation recommendation method according to an embodiment of the present application, such as Figure 2 As shown, the method may include the following steps:

[0036] In step S202 , the server constructs a social graph between the target account and associated accounts on the enterprise collaborative office platform, where the associated accounts are accounts associated with the target account.

[0037] The target account is any account in any enterprise, such as employee account 1 in enterprise A. The associated account is an account associated with the target account, such as an account in the same enterprise (ie, enterprise A) or an account in a different enterprise with which the target account has business dealings.

[0038] Optionally, when constructing a social graph, a social graph may be constructed with the target account and the associated accounts as nodes and the degree of association between the target account and the associated accounts as edges. The degree of association is determined based on the frequency and duration of interactions between the target account and the associated accounts. The degree of association deg is determined according to the following formula:

[0039]

[0040] The value of n ranges from 1 to an integer m (m is set as needed, such as referring to the user's chat records within 10 days), C n represents the interaction frequency on the nth day, for example, the interaction frequency on the first day is 10, and the interaction frequency on the second day is 5; r n It represents the attenuation factor of the nth day in the range of (0,1]. r is the preset attenuation factor, such as 0.9. In this case, the attenuation factor of the first day is 0.9, the attenuation factor of the second day is 0.81, and so on.

[0041] If account 1 is associated with account 2, account 3, and account 4, a social graph consisting of four nodes, account 1 to account 4, will be established. Account 1 will have three edges, connected to account 2, account 3, and account 4 respectively. The weight of the edges (i.e., the degree of association) can be determined according to the above formula.

[0042] In step S204, the server dynamically queries the associated session information of the target account based on the social graph.

[0043] Optionally, dynamically querying the target account's associated session information based on the social graph includes:

[0044] Obtaining session information for reminders for the target account, such as reminders from leaders or colleagues;

[0045] Acquire the session information (such as information sent by a leader) sent by the first account (the first account is used to manage the target account) to the target account and the session information (such as information sent by a customer) sent by the second account (the second account is a customer account) to the target account.

[0046] Optionally, a third account whose correlation with the target account is greater than a preset threshold (such as 10) can be queried in the social graph dynamics; the read conversation information of the third account is obtained, and other people who frequently interact with the user must be related people, such as those in the same project team. Therefore, the read information of the same project team can be pushed to the user to facilitate timely understanding of related information.

[0047] In step S206 , the server recommends the associated session information to the target account on the enterprise collaborative office platform.

[0048] Optionally, the associated session information can be divided into two types of session information, including information that must be viewed and information that is selected for viewing. Pre-defined message classification rules can be used to divide the associated session information into two types of session information according to business analysis rules; each type of session information can be recommended to the target account on the enterprise collaborative office platform in chronological order.

[0049] Through the above steps, a social graph is constructed between the target account and associated accounts on the enterprise collaborative office platform, where the associated accounts are accounts that are associated with the target account; the associated session information of the target account is dynamically queried based on the social graph; and the associated session information is recommended to the target account on the enterprise collaborative office platform. By deeply studying the graph structure of the social network of enterprise employees and utilizing the information dissemination method based on the graph structure, the communication efficiency of enterprise employees is effectively enhanced, which can solve the technical problem of the inability to efficiently recommend session information to employees in related technologies.

[0050] This solution can solve the problems of time validity and information relevance in conversational recommendations, thereby making conversational recommendations more effective in processing information in the actual work of enterprise employees. As an optional embodiment, the following further details the technical solution of this application in conjunction with specific implementation methods:

[0051] Step 1: Build an employee social graph.

[0052] The enterprise work platform can build a social graph among employees from the following data: company organizational structure data, work communication data between employees, work group information, meeting information, email communication information, etc.

[0053] The interaction frequency and interaction time can be extracted from this information. This application mainly describes the intimacy between employees or the closeness of working relationships based on the interaction frequency and interaction time.

[0054] The calculation of working relationship closeness here is closely related to time. It can be understood that the closer the time is to the present, the closer the relationship should be. This solution introduces a time decay function to solve this problem: sum the daily interaction frequency, and multiply the daily frequency by a discount function that accounts for the daily difference from the current time. The specific formula is as follows:

[0055]

[0056] n represents the current time, m represents the time of the day, from n to m represents the sum of the frequencies from the current time to m days later, Cn represents the interaction frequency on the nth day, and r represents the discount factor (the value range here is (0,1]). The discount factor controls the degree of influence of the frequency of a specific day on the total frequency.

[0057] Step 2: Dynamically query session information based on the social graph, such as Figure 3 shown.

[0058] In the previous step, we established employee intimacy or work intensiveness, which reflects the degree of relevance between conversational information within the company and the individual. This can be understood as the following three dimensions:

[0059] The first dimension: conversation information that mentions your name: understood as the information that is reminded in the conversation information, the information sent to yourself, and the system reminder information (such as meeting reminders, etc.).

[0060] The second dimension: conversation information from team leaders or customers: It is understood that the information sent by direct leaders and customers must be extracted.

[0061] The third dimension: by extracting the information that employees with whom I work closely have seen in a timely manner: I understand that I also need to see the conversation information that employees with whom I work closely have seen.

[0062] When extracting conversation information in the current three dimensions, the data of the first and second dimensions must be extracted, and the data of the third dimension is extracted based on the strength of the intimacy relationship to extract the conversation information viewed by the employees in the third dimension.

[0063] Step 3: Build recommendation session information.

[0064] Based on the above steps, we have extracted session information that can be used for recommendations. Based on this session information, we need to sort it. This process can be processed by adding some filtering information based on business rules. The general process is constructed as follows:

[0065] Divide session information into required and optional information. Sort the two sections in ascending order by time. Group required information first, then optional information. Business rule parsing can be used to categorize information. For example, given whitelist filtering rules, if there are requirements for the length of the information list, push information in a top-N order, such as displaying the first 10 messages.

[0066] In the technical solution of this application, based on the new scenario of conversation recommendation, a conversation recommendation method based on social network is proposed. By deeply studying the graph structure of the social network of enterprise employees, the information dissemination method on the graph structure is used to effectively enhance the communication efficiency of enterprise employees.

[0067] It should be noted that for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by this application.

[0068] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus the necessary general hardware platform, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0069] According to another aspect of the embodiments of the present application, a session recommendation device for implementing the above-mentioned session recommendation method is also provided. Figure 4 is a schematic diagram of an optional conversation recommendation device according to an embodiment of the present application, such as Figure 4 As shown, the device may include:

[0070] A construction unit 41 is configured to construct a social graph between a target account and associated accounts on an enterprise collaborative office platform, wherein the associated accounts are accounts associated with the target account;

[0071] A query unit 43, configured to dynamically query the associated session information of the target account based on the social graph;

[0072] The recommendation unit 45 is configured to recommend the associated session information to a target account on the enterprise collaborative office platform.

[0073] It should be noted that the construction unit 41 in this embodiment can be used to execute step S202 in the embodiment of the present application, the query unit 43 in this embodiment can be used to execute step S204 in the embodiment of the present application, and the recommendation unit 45 in this embodiment can be used to execute step S206 in the embodiment of the present application.

[0074] It should be noted that the examples and application scenarios implemented by the above modules and corresponding steps are the same, but are not limited to the contents disclosed in the above embodiments. Figure 1 In the hardware environment shown, it can be implemented by software or by hardware.

[0075] Through the above modules, a social graph is constructed between a target account and associated accounts on an enterprise collaborative office platform, where the associated accounts are accounts associated with the target account; associated session information of the target account is dynamically queried based on the social graph; and the associated session information is recommended to the target account on the enterprise collaborative office platform. By deeply studying the graph structure of enterprise employees' social networks and utilizing information dissemination methods based on the graph structure, the communication efficiency of enterprise employees is effectively enhanced, thereby resolving the technical problem in related technologies of being unable to efficiently recommend session information to employees.

[0076] Optionally, when constructing a social graph between a target account and associated accounts on an enterprise collaborative office platform, the construction unit is further configured to: construct the social graph with the target account and the associated account as nodes and the degree of association between the target account and the associated account as edges, wherein the degree of association is determined based on the interaction frequency and interaction time between the target account and the associated account.

[0077] Optionally, the correlation degree deg is determined according to the following formula:

[0078]

[0079] The value of n ranges from 1 to an integer m, C n represents the interaction frequency on day n, r n Indicates the attenuation factor for the nth day in the range (0,1].

[0080] Optionally, when dynamically querying the associated session information of the target account based on the social graph, the query unit is further used to: obtain first session information, wherein the first session information is the session information of which the target account is reminded, and the associated session information includes the first session information; obtain second session information, wherein the second session information includes session information sent by the first account to the target account and session information sent by the second account to the target account, the first account is used to manage the target account, the second account is a customer account, and the associated session information includes the second session information.

[0081] Optionally, when the query unit dynamically queries the associated session information of the target account based on the social graph, it is also used to: query a third account whose association degree with the target account is greater than a preset threshold in the social graph dynamics; obtain the read session information of the third account, wherein the associated session information includes the read session information.

[0082] Optionally, when recommending the associated session information to the target account on the enterprise collaborative office platform, the recommendation unit is further used to: divide the associated session information into two types of session information, wherein the two types of session information include information that must be viewed and information that is optionally viewed; and recommend each type of session information to the target account on the enterprise collaborative office platform in chronological order.

[0083] Optionally, when classifying the associated session information into two types of session information, the recommendation unit is further configured to: obtain a service parsing rule, which is a predefined message classification rule; and classify the associated session information into two types of session information according to the service parsing rule.

[0084] It should be noted that the examples and application scenarios implemented by the above modules and corresponding steps are the same, but are not limited to the contents disclosed in the above embodiments. Figure 1 The hardware environment shown can be implemented through software or hardware, wherein the hardware environment includes a network environment.

[0085] According to another aspect of the embodiments of the present application, a server or terminal for implementing the above-mentioned session recommendation method is also provided.

[0086] Figure 5 is a structural block diagram of a terminal according to an embodiment of the present application, such as Figure 5 As shown, the terminal may include: one or more ( Figure 5 (only one is shown) processor 501, memory 503, and transmission device 505, as shown Figure 5 As shown, the terminal may further include input and output devices 507 .

[0087] Among them, the memory 503 can be used to store software programs and modules, such as the program instructions / modules corresponding to the conversation recommendation method and device in the embodiment of the present application. The processor 501 executes various functional applications and data processing by running the software programs and modules stored in the memory 503, that is, realizing the above-mentioned conversation recommendation method. The memory 503 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 503 may further include a memory remotely located relative to the processor 501, and these remote memories can be connected to the terminal via a network. Examples of the above-mentioned network include but are not limited to the Internet, corporate intranet, local area network, mobile communication network and combinations thereof.

[0088] The above-mentioned transmission device 505 is used to receive or send data via a network, and can also be used for data transmission between a processor and a memory. Specific examples of the above-mentioned network may include wired networks and wireless networks. In one embodiment, the transmission device 505 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices and routers via a network cable so as to communicate with the Internet or a local area network. In one embodiment, the transmission device 505 is a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0089] Specifically, the memory 503 is used to store application programs.

[0090] The processor 501 may call the application stored in the memory 503 through the transmission device 505 to perform the following steps:

[0091] Constructing a social graph between a target account and associated accounts on an enterprise collaborative office platform, wherein the associated accounts are accounts associated with the target account;

[0092] Dynamically querying the associated session information of the target account based on the social graph;

[0093] The associated session information is recommended to a target account on the enterprise collaborative office platform.

[0094] The processor 501 is further configured to perform the following steps:

[0095] Acquire first session information, wherein the first session information is session information in which the target account is reminded, and the associated session information includes the first session information;

[0096] Obtain second session information, wherein the second session information includes session information sent by the first account to the target account and session information sent by the second account to the target account, the first account is used to manage the target account, the second account is a customer account, and the associated session information includes the second session information.

[0097] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments, and this embodiment will not be described in detail here.

[0098] It can be understood by those skilled in the art that Figure 5 The structure shown is for illustration only, and the terminal may be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a PDA, a mobile Internet device (Mobile Internet Devices, MID), a PAD, or other terminal devices. Figure 5 It does not limit the structure of the above electronic device. For example, the terminal may also include Figure 5 More or fewer components (such as network interfaces, display devices, etc.) shown in, or with Figure 5 Different configurations shown.

[0099] A person skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the hardware related to the terminal device through a program, and the program can be stored in a computer-readable storage medium, which may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0100] The embodiment of the present application further provides a storage medium. Optionally, in this embodiment, the storage medium can be used to execute the program code of the conversation recommendation method.

[0101] Optionally, in this embodiment, the above-mentioned storage medium may be located on at least one network device among the multiple network devices in the network shown in the above-mentioned embodiment.

[0102] Optionally, in this embodiment, the storage medium is configured to store program codes for executing the following steps:

[0103] Constructing a social graph between a target account and associated accounts on an enterprise collaborative office platform, wherein the associated accounts are accounts associated with the target account;

[0104] Dynamically querying the associated session information of the target account based on the social graph;

[0105] The associated session information is recommended to a target account on the enterprise collaborative office platform.

[0106] Optionally, the storage medium is further configured to store program codes for executing the following steps:

[0107] Acquire first session information, wherein the first session information is session information in which the target account is reminded, and the associated session information includes the first session information;

[0108] Obtain second session information, wherein the second session information includes session information sent by the first account to the target account and session information sent by the second account to the target account, the first account is used to manage the target account, the second account is a customer account, and the associated session information includes the second session information.

[0109] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments, and this embodiment will not be described in detail here.

[0110] Optionally, in this embodiment, the above-mentioned storage medium may include but is not limited to: a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and other media that can store program codes.

[0111] The serial numbers of the above embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0112] If the integrated units in the above embodiments are implemented in the form of software functional units and sold or used as independent products, they can be stored in the above-mentioned computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling one or more computer devices (which can be personal computers, servers, or network devices, etc.) to execute all or part of the steps of the methods described in each embodiment of the present application.

[0113] In the above embodiments of the present application, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0114] In the several embodiments provided in this application, it should be understood that the disclosed client can be implemented in other ways. Among them, the device embodiments described above are merely illustrative. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, and can be electrical or other forms.

[0115] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0116] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0117] The above is only a preferred embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A conversation recommendation method, characterized in that: include: Constructing a social graph between a target account and associated accounts on an enterprise collaborative office platform, comprising: constructing the social graph with the target account and the associated accounts as nodes and with the degree of association between the target account and the associated accounts as edges, wherein the degree of association is determined based on the frequency and duration of interactions between the target account and the associated accounts, and the associated accounts are accounts associated with the target account; Dynamically querying the associated session information of the target account based on the social graph includes: obtaining first session information, wherein the first session information is session information of which the target account is reminded, and the associated session information includes the first session information; obtaining second session information, wherein the second session information includes session information sent by the first account to the target account and session information sent by the second account to the target account, the first account is used to manage the target account, the second account is a customer account, the associated session information includes the second session information, and the associated accounts include the first account and the second account; dynamically querying the social graph for a third account whose association with the target account is greater than a preset threshold, wherein the associated accounts include the third account; obtaining read session information of the third account, wherein the associated session information includes the read session information; The associated session information is recommended to the target account on the enterprise collaborative office platform.

2. The method according to claim 1, characterized in that The degree of association Determine according to the following formula: ， The value of n is 1 to an integer m, represents the interaction frequency on day n, Indicates the attenuation factor for the nth day in the range (0,1].

3. The method according to any one of claims 1 to 2, characterized in that Recommending the associated session information to a target account on the enterprise collaborative office platform includes: Dividing the associated session information into two types of session information, wherein the two types of session information include mandatory-to-view information and optional-to-view information; The conversation information of each type is recommended to the target account on the enterprise collaborative office platform in chronological order.

4. The method according to claim 3, characterized in that The associated session information is divided into two types of session information, including: Obtaining a business parsing rule, wherein the business parsing rule is a predefined message classification rule; The associated session information is divided into two types of session information according to the business parsing rule.

5. A conversation recommendation device, characterized in that: include: A construction unit, configured to construct a social graph between a target account and associated accounts on an enterprise collaborative office platform, comprising: constructing the social graph with the target account and the associated accounts as nodes and with the degree of association between the target account and the associated accounts as edges, wherein the degree of association is determined based on the frequency and duration of interaction between the target account and the associated accounts, and the associated accounts are accounts associated with the target account; A query unit, configured to dynamically query associated session information of the target account based on the social graph, comprising: obtaining first session information, wherein the first session information is session information of which the target account is reminded, and the associated session information includes the first session information; obtaining second session information, wherein the second session information includes session information sent by the first account to the target account and session information sent by the second account to the target account, the first account being used to manage the target account, the second account being a customer account, the associated session information includes the second session information, and the associated accounts include the first account and the second account; dynamically querying the social graph for a third account whose association with the target account is greater than a preset threshold, wherein the associated accounts include the third account; and obtaining read session information of the third account, wherein the associated session information includes the read session information; The recommendation unit is configured to recommend the associated session information to a target account on the enterprise collaborative office platform.

6. A storage medium, characterized in that The storage medium includes a stored program, wherein the program executes the method described in any one of claims 1 to 4 when executed.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: The processor executes the method according to any one of claims 1 to 4 through the computer program.

Images