Prompt word improvement system and method

Abstract

The invention discloses a cue word perfection system and method, the cue word perfection system comprises a server, a plurality of client devices and a plurality of cameras, the server receives camera data sent by the plurality of cameras; a client device obtains a prompt word input by a user at a client and sends the prompt word, information of a current account logged in by the client and a current window layout strategy of the client to a server, and the server sends the prompt word to the server according to the information of the current account logged in by the client and / or the current window layout strategy of the client. Determining a region-of-interest identification number bound with the current account information; determining a current service group of the current account information according to the identification number of the region of interest; according to the current service group of the current account information, a database corresponding to the current service group is called to perfect the cue word, and cue word perfection information is obtained. According to the invention, the prompt words of the user can be automatically improved according to the specific business grouping.

Description

Technical Field

[0001] The present application relates to the technical field of language processing, and in particular to a prompt word improvement system and method. Background Art

[0002] With the continuous development of science and technology, large language models have become an important part of natural language processing, text generation, and dialogue systems, and are widely used in various fields. For example, after fine-tuning the general large language model through legal interpretation and logic checking, it can become a good legal tool platform, automatically providing users with draft text recommendations for writing regulations and materials. However, the quality of draft text generation depends on the appropriate prompt words. For good prompt words, the legal tool platform can provide targeted draft texts, while for inappropriate prompt words, the draft texts generated by the legal tool platform are not very meaningful for reference.

[0003] Therefore, how to generate a better prompt word becomes a problem that needs to be solved urgently. Summary of the invention

[0004] The purpose of the embodiments of the present application is to provide a prompt word improvement system and method for automatically improving prompt words efficiently and accurately.

[0005] In a first aspect, the present application provides a prompt word improvement system, which includes: a server, multiple client devices and multiple cameras, wherein the server is communicatively connected to the multiple client devices and the multiple cameras; wherein the server is used to receive the video data sent by the multiple cameras and send it to the client device; the client device is used to obtain the prompt word entered by the user on the client, and send the prompt word, the current account information logged in by the client and the current window layout strategy of the client to the server, wherein the current window layout strategy of the client includes binding information of the camera identification number and the window pane identification number; the server is also used to receive the prompt word, the current account information logged in by the client and the current window layout strategy of the client, and determine the focus area identification number bound to the current account information according to the current account information logged in by the client and / or the current window layout strategy of the client; the server is also used to determine the current business group of the current account information according to the focus area identification number; the server is also used to retrieve the database corresponding to the current business group according to the current business group of the current account information to improve the prompt word and obtain the prompt word improvement information.

[0006] In one embodiment, before the client device is used to obtain the prompt word input by the user at the client, and sends the prompt word, the current account information of the client login and the current window layout strategy of the client to the server, it also includes: the client device is also used to send the current account information of the user login at the client to the server; the server is also used to determine whether there is a pre-stored window layout strategy bound to the current account information according to the current account information; when the server determines that there is a pre-stored window layout strategy bound to the current account information, the server directly sends the pre-stored window layout strategy to the client device; the client device displays the camera data according to the pre-stored window layout strategy, and receives the user's revision information for the pre-stored window layout strategy in real time; when the client device receives the user's revision information for the pre-stored window layout strategy, the client device sends the revision information to the server, and the server updates the pre-stored window layout strategy according to the revision information; when the server determines that there is no pre-stored window layout strategy bound to the current account information, the server sends a supplementary instruction to the client device; the client device sends the window layout strategy input by the user to the server for storage according to the supplementary instruction.

[0007] In one embodiment, before the server determines the focus area identification number bound to the current account information based on the current account information logged in by the client and / or the current window layout strategy of the client, it also includes: the server is also used to determine whether the working years of the user bound to the current account information are greater than a first preset threshold; when the server determines that the working years of the user bound to the current account information are greater than the first preset threshold, the server sends an indication of a supplementary focus area identification number to the client device; the client device is also used to send the focus area identification number input by the user to the server according to the indication of the supplementary focus area identification number; the server is also used to bind the focus area identification number input by the user returned by the client device to the current account information; the server is also used to determine the camera set focused on by each focus area identification number based on the account information bound to each focus area identification number and the window layout strategy bound to each account information.

[0008] In one embodiment, the server is also used to determine the camera set that each area of ​​interest identification number focuses on according to the account information bound to each area of ​​interest identification number and the window layout strategy bound to each account information, including: the server is also used to identify the account information bound to each area of ​​interest identification number, and identify the window layout strategy bound to each account information according to the account information; the server is also used to assign importance to the camera identification number bound to it according to the pane identification number in each window layout strategy, and group and merge according to each area of ​​interest identification number to obtain the total importance of each camera identification number; the server is also used to select camera identification numbers whose total importance is greater than a second preset threshold to form the camera set that each corresponding area of ​​interest identification number focuses on.

[0009] In one embodiment, when the server determines that the working years of the user bound to the current account information are less than or equal to a first preset threshold, the server sends a supplementary instruction to the client device; the client device sends the partial window layout strategy and the total number of current panes input by the user to the server according to the supplementary instruction; the server generates at least one recommended window layout strategy based on the partial window layout strategy, the total number of current panes and the set of cameras concerned by each focus area identification number, and sends it to the client device; the client device displays the at least one recommended window layout strategy and obtains feedback information input by the user on the at least one recommended window layout strategy; the client device sends the feedback information to the server; the server determines the focus area identification number bound to the current account information based on the feedback information.

[0010] In one embodiment, the server generates at least one recommended window layout strategy and sends it to the client device based on the partial window layout strategy, the total number of current panes and the camera set concerned by each focus area identification number, including: the server identifies the corresponding target camera set based on the camera identification number in the partial window layout strategy, and identifies the bound focus area identification number based on the target camera set; the server determines whether the number of cameras in the target camera set is greater than the total number of current panes; when the server determines that the number of cameras in the target camera set is greater than the total number of current panes, the server is also used to sort the cameras in the target camera set according to the importance from large to small to obtain a sorting queue; the server is also used to select the target camera corresponding to the total number of current panes based on the sorting queue, and determine the binding relationship between the target camera and the pane in turn to form a recommended window layout strategy.

[0011] In one embodiment, the prompt word improvement system further includes a multicast group, the server is communicatively connected to the multicast group, and the plurality of client devices are connected to a network of the multicast group.

[0012] In one embodiment, the target client device sends the current account information input by the user on the client to the server; the server is also used to determine whether the working years of the user bound to the current account information are greater than a first preset threshold; when the server determines that the working years of the user bound to the current account information are greater than the first preset threshold, the server sends the focus area identification number bound to the current account information, the camera set focused on by the focus area identification number and / or the window layout strategy bound to the current account information to the target client device; when the server determines that the working years of the user bound to the current account information are less than or equal to the first preset threshold, the client device sends the partial window layout strategy and the current total number of panes input by the user to all other client devices in the multicast group in the form of multicast; the other client devices determine whether the working years of the user bound to their own current account information are greater than the first preset threshold, and the whether the camera identification number in the partial window layout strategy exists in the locally pre-stored camera set; when the other client device determines that the working years of the user bound to its current account information is greater than the first preset threshold, and the camera identification number in the partial window layout strategy exists in the locally pre-stored camera set, the other client device sends the locally pre-stored camera set and the focus area identification number associated therewith to the target client device; the target client device generates at least one recommended window layout strategy according to the locally pre-stored camera set and the focus area identification number associated therewith sent by the other client device; the target client device displays the at least one recommended window layout strategy and obtains feedback information input by the user on the at least one recommended window layout strategy; the target client device sends the feedback information to the server; the server determines the focus area identification number bound to the current account information according to the feedback information.

[0013] In one embodiment, the locally pre-stored camera set includes: one or more of the camera identification number, the IP address of the camera, and the importance of the camera.

[0014] In one embodiment, the server is also used to retrieve the database corresponding to the current business group to improve the prompt word according to the current business group of the current account information. After obtaining the prompt word improvement information, it also includes: the server is also used to input the prompt word improvement information into the large language model to generate a draft text; or, the server is also used to send the prompt word improvement information to the client device and display it on the interactive interface of the client device; the client device receives the user's modification information on the prompt word improvement information and sends the final prompt word improvement information to the server; the server is also used to input the final prompt word improvement information into the large language model to generate a draft text.

[0015] In a second aspect, the present application provides a prompt word improvement method, which is applied to a prompt word improvement system, the prompt word improvement system comprising: a server, multiple client devices and multiple cameras, the server being communicatively connected to the multiple client devices and the multiple cameras; the method comprising: the server receiving the video data sent by the multiple cameras and sending it to the client device; the client device acquiring the prompt word input by the user on the client, and sending the prompt word, the current account information logged in by the client and the current window layout strategy of the client to the server, the current window layout strategy of the client comprising binding information of a camera identification number and a pane identification number; the server receiving the prompt word, the current account information logged in by the client and the current window layout strategy of the client, and determining the focus area identification number bound to the current account information according to the current account information logged in by the client and / or the current window layout strategy of the client; the server determining the current business group of the current account information according to the focus area identification number; the server retrieving the database corresponding to the current business group according to the current business group of the current account information to improve the prompt word and obtain the prompt word improvement information.

[0016] Compared with the prior art, the prompt word improvement system and method provided by this application has the following advantages: The present application can determine the business content that different users are concerned about according to the cameras they are concerned about, based on the current window layout strategy of the client, and realize the correct business grouping of different users according to the business content they are concerned about, so as to automatically improve the user's prompt words according to the specific business grouping, which is conducive to the subsequent large language model to generate more targeted draft texts based on the improved prompt words, thereby improving the efficiency and accuracy of generating draft texts.

[0017] In addition, this application can also intelligently determine the business content that users are concerned about, intelligently recommend reasonable window layouts, improve the workflow of some non-experienced users, and help some non-experienced users quickly determine the window layout and become familiar with the work content, thereby improving work efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0019] Figure 1 This is a schematic diagram of the structure of a prompt word improvement system according to an embodiment of the present application.

[0020] Figure 2 This is a schematic diagram of the structure of a prompt word improvement system according to an embodiment of the present application.

[0021] Figure 3 The figure is a flowchart of a prompt word improvement method according to an embodiment of the present application.

[0022] Labels: 100 - prompt word improvement system; 110 - camera; 120 - server; 130 - multicast group; 131 - client device. DETAILED DESCRIPTION

[0023] In the description of the present application, the terms "first", "second", etc. are only used to distinguish the description and do not indicate the order of arrangement, nor can they be understood as indicating or implying relative importance.

[0024] In the description of the present application, the terms "include", "comprising", etc. indicate the existence of the described features, integers, steps, operations, elements and / or components, but do not exclude the existence or addition of one or more other features, steps, operations, elements, components and / or collections thereof.

[0025] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application.

[0026] Please refer to Figure 1 , which is a schematic diagram of the structure of a prompt word improvement system 100 according to an embodiment of the present application. The prompt word improvement system 100 includes a server 120, multiple client devices 131, and multiple cameras 110. The prompt word improvement system 100 may be a computing system composed of multiple computers, and the prompt word improvement system 100 may also include Figure 1 More or fewer components as shown, or with Figure 1For example, the prompt word improvement system 100 also includes input and output devices for human-computer interaction.

[0027] There are multiple cameras 110 for collecting video data and sending the video data to the server 120 .

[0028] There are multiple client devices 131, and the multiple client devices 131 can correspond to terminal devices used by different users or staff members. The terminal device can be a mobile phone, a laptop computer, a desktop computer, or a computing system composed of multiple computers. Each terminal device can be installed with a client, and users log in to the client (such as a video playback client) through their respective account information to perform daily work and view the video data collected by the camera 110 of interest. In one embodiment, the interactive interface of the client is provided with multiple panes, and the user can deploy the multiple cameras 110 of interest in the multiple panes of the interactive interface respectively.

[0029] The server 120 is communicatively connected to the plurality of cameras 110 and the plurality of client devices 131, and is used to receive, store and process one or more video data sent by the camera 110, and to manage, communicate and process information sent by the client device 131. The server 120 may be an independently arranged mobile phone, a laptop computer, a desktop computer, or a computing system composed of multiple computers. The server 120 may include a management service module and a media service module, wherein the management service module is used to manage, communicate and process information sent by the client device 131, and the media service module is used to receive, store and process one or more video data sent by the camera 110.

[0030] In one operation process, the server 120 is used to receive video data sent by multiple cameras 110; the client device 131 is used to obtain the prompt word input by the user on the client, and send the prompt word, the current account information of the client login and the current window layout strategy of the client to the server 120, and the current window layout strategy of the client includes the binding information of the camera identification number and the window pane identification number; the server 120 is also used to receive the prompt word, the current account information of the client login and the current window layout strategy of the client, and determine the focus area identification number bound to the current account information according to the current account information logged in and / or the current window layout strategy of the client; the server 120 is also used to determine the current business group of the current account information according to the focus area identification number; the server 120 is also used to retrieve the database corresponding to the current business group according to the current business group of the current account information to improve the prompt word and obtain the prompt word improvement information.

[0031] Therefore, this embodiment can determine the business content that different users are concerned about according to the camera 110 that they are concerned about, based on the current window layout strategy of the client, and realize the correct business grouping of different users according to the business content they are concerned about, so as to automatically improve the user's prompt words according to the specific business grouping, which is conducive to the subsequent large language model to generate more targeted draft text based on the improved prompt words, thereby improving the efficiency and accuracy of generating draft texts.

[0032] Please refer to Figure 2 , which is a schematic diagram of the structure of a prompt word improvement system 100 according to an embodiment of the present application. The prompt word improvement system 100 further includes a multicast group 130, a server 120 is connected to the multicast group 130 for communication, and a plurality of client devices 131 are connected to the network of the multicast group 130.

[0033] In one embodiment, the multicast group 130 may also include multiple gateway routers, which support multicast. The gateway router is used to connect at least one client device 131 to the network of the multicast group 130. All Internet access data of each client device 131 will first be sent to the gateway router, and then the gateway router will forward it to the server 120.

[0034] In an operation process, if the network IP address of the multicast group 130 is, for example, 226.100.100.100, each client device 131 can send a join message of the IGMP protocol (Internet Group Management Protocol) to join the multicast group 130 with the address 226.100.100.100, so that each client device 131 can receive the camera data of the multicast group 130 with the destination IP address 226.100.100.100. That is, if the server 120 sends the camera data to the multicast group 130 in a multicast manner, the multicast group 130 will automatically copy and distribute the camera data to multiple client devices 131. Therefore, this embodiment adopts the multicast mode to transmit data, so that the server 120 only needs to generate one copy of the camera data, thereby reducing the workload of data transmission. In addition, multiple client devices 131 can also communicate with each other in the form of multicast, avoiding the server 120 becoming a performance bottleneck for scheduling, and improving data transmission efficiency.

[0035] Please refer to Figure 3 , which is a flow chart of a prompt word improvement method according to an embodiment of the present application, the prompt word improvement method includes the following steps S110-S150, which are described above Figure 1 or Figure 2 The prompt word completion system 100 is shown to be implemented and used to automatically complete prompt words efficiently and accurately.

[0036] Step S110 : the server 120 receives the video data sent by the plurality of cameras 110 and sends the video data to the client device 131 .

[0037] In one embodiment, before step S110, the following further includes: step S111: multiple cameras 110 collect video data and send the video data to the server 120. It should be noted that multiple cameras 110 send the video data to the server 120 in a unicast, broadcast or multicast manner. All cameras 110 register with the management service module of the server 120 to obtain a unique camera identification number.

[0038] Step S120 : the client device 131 obtains the prompt word input by the user at the client, and sends the prompt word, the current account information of the client login, and the current window layout strategy of the client to the server 120 .

[0039] The current window layout strategy of the client in this step includes the binding information of the camera identification number and the pane identification number; according to the current window layout strategy of the client, the camera 110 currently viewed by the user can be determined, the user's daily work content can be determined, and the user's attention to the camera 110 and the importance of the camera in his daily work content can be determined based on the current window layout strategy.

[0040] In this step, the prompt word entered by the user on the client triggers the prompt word improvement function, and the client device 131 sends the prompt word, the current account information of the client login, and the current window layout strategy of the client to the server 120, so that the server 120 can perform subsequent business grouping or improve the prompt word according to the user's current actual information to improve efficiency and accuracy.

[0041] Step S130: the server 120 receives the prompt word, the current account information of the client login and the current window layout strategy of the client, and determines the focus area identification number bound to the current account information according to the current account information of the client login and / or the current window layout strategy of the client.

[0042] The concerned area identification number in this step refers to the area concerned by the user in daily work. Taking the community video surveillance service as an example, the area identification number concerned by the user, i.e., the community ID, can be determined based on the multiple cameras 110 that the user deploys in multiple panes of the client interaction interface. It should be noted that this does not mean that the user's administrative affiliation belongs to the community, but only means that the user pays attention to the community and his daily work is closely related to the community.

[0043] Among them, the server 120 determines the focus area identification number bound to the current account information according to the current account information logged in by the client and / or the current window layout strategy of the client, which means that the server can retrieve the binding relationship table between the current account information and the focus area identification number only according to the current account information logged in by the client, and directly determine the focus area identification number; the server 120 can also first determine the camera set displayed in the current window pane of the client according to the current window layout strategy of the client, and then determine the focus area identification number based on the camera set; the server 120 can also determine the focus area identification numbers corresponding to the current account information and the current window layout strategy respectively according to the current account information and the current window layout strategy, and determine the final focus area identification number after mutual verification.

[0044] Step S140: the server 120 determines the current service group of the current account information according to the focus area identification number.

[0045] The applicant found that even if users (or staff) belong to the same administrative department, the businesses they care about are not the same and there are overlaps. Therefore, in this step, instead of directly grouping according to the administrative department, the identification number of the area concerned by the user, that is, the community ID, is used as reference information for subsequent business grouping, that is, intelligent business grouping is performed according to the user's daily work content, so as to improve the accuracy of the prompt words.

[0046] Step S150: the server 120 retrieves the database corresponding to the current business group according to the current business group of the current account information to improve the prompt word and obtain prompt word improvement information.

[0047] The applicant discovered that the same prompt word represents completely different meanings in different business contexts. For example, "Please provide an explanation about the port number". In the device hardware management business, the port number refers to a port number of a physical device with several physical ports; and in the interactive protocol management business, the port number refers to the protocol port number of TCP or UDP. For the former, it may need to be automatically completed to "Please provide an explanation about the physical port number of the device", and for the latter, it may need to be automatically completed to "Please provide an explanation about the port number of the TCP or UDP protocol". Similarly, "Please provide an introduction to this community" will be automatically completed to "Please provide an explanation about the XXX community" for staff members of different communities. This "XXX community" should be targeted and improved according to the staff members of different communities. The same principle applies to regulatory documents. Therefore, this embodiment realizes the automatic completion of prompt words on the premise of correctly grouping users according to the business they are concerned about, and preparing different databases for different business groups.

[0048] During a specific operation, a community staff member outputs the prompt "Please generate a brief introduction text about this community". The server 120 searches for the bound focus area identification number (such as community ID) based on the staff member's account information, finds out the current business group (such as community name) corresponding to the focus area identification number (such as community ID), for example, "XX community", and further obtains the database corresponding to the current business group, for example, "the administrative units above the XX community, namely XX street, XX district, XX city", so that the prompt can be improved to "Please generate a brief introduction text about XX community, XX street, XX district, XX city".

[0049] In one embodiment, after step S150, the method further includes: step S151.

[0050] Step S151: the server 120 is further configured to input the prompt word completion information into the large language model to generate a draft text.

[0051] In one embodiment, after step S15, the following steps are also included: step S152 to step S154.

[0052] Step S152: the server 120 is further configured to send prompt word completion information to the client device 131 and display it on the interactive interface of the client device 131; Step S153: the client device 131 receives the user's modification information on the prompt word improvement information, and sends the final prompt word improvement information to the server 120; Step S154: the server 120 is further configured to input the final prompt word improvement information into the large language model to generate a draft text.

[0053] In this way, the prompt word improvement information can be displayed on the interactive interface of the client device 131. The user can modify or confirm to form the final prompt word improvement information, which is conducive to the subsequent large language model to generate more targeted draft text based on the final improved prompt word, thereby improving the efficiency and accuracy of generating draft text.

[0054] In one embodiment, in order to determine the window layout strategy of each client device 131 , steps S1201 to S1206 are further included before step S120 .

[0055] Step S1201: The server 120 determines whether there is a pre-stored window layout strategy bound to the current account information based on the current account information; if so, execute steps S1202-S1204, for the server 120 to directly call the existing pre-stored window layout strategy, and when the user changes the layout, update the window layout strategy stored in the server 120 in real time; if not, execute steps S1205-S1206, for the user to arrange the window by himself and send it to the server 120 for storage.

[0056] Step S1202: the server 120 directly sends the pre-stored window layout strategy to the client device 131; Step S1203: the client device 131 displays the video data according to the pre-stored window layout strategy, and receives in real time the revision information of the pre-stored window layout strategy from the user; Step S1204: when the client device 131 receives the user's revision information for the pre-stored window layout strategy, the client device 131 sends the revision information to the server 120, and the server 120 updates the pre-stored window layout strategy according to the revision information; The above steps S1203-S1204 are used for when there is a pre-stored window layout strategy bound to the current account information, the server 120 directly calls the existing pre-stored window layout strategy and sends it to the client device 131 for layout, and when the user changes the window layout, the information stored in the server 120 is updated in real time.

[0057] For example, when the account information logged in by the client is user A. The camera identification number is the camera ID, including: 9001, 9102, 9100, etc., and the pane identification number is the pane sequence number, including: pane 1, pane 2, pane 3, pane 4, etc.

[0058] If: the binding relationship between the pane identification number and the pane identification number in the pre-stored window layout strategy bound to user A is "pane 1-camera 9001" and "pane 2-camera 9102", the server 120 sends the pre-stored window layout strategy to the client device 131 for layout, so that the camera ID played by pane 1 in the client is 9001, and the camera ID played by pane 2 is 9102". When the user changes the camera 110 played by pane 2 to 9100, the revision information of "pane 2-camera 9100" is sent to the server 120, and the server 120 updates the camera 110 bound to pane 2 under the name of user A to 9100, that is, updates the pre-stored window layout strategy bound to user A to "pane 1-camera 9001" and "pane 2-camera 9100".

[0059] Step S1205: the server 120 sends a supplemental instruction to the client device 131; Step S1206: the client device 131 sends the window layout policy input by the user to the server 120 for storage according to the supplementary instruction.

[0060] The above steps S1205 to S1206 are used for allowing the user to arrange windows by himself when there is no pre-stored window layout strategy bound to the current account information, and send them to the server 120 for storage.

[0061] In one embodiment, in order to intelligently determine the business content that the staff is concerned about and intelligently recommend a reasonable window layout, before step S120, the following steps are also included: step S2201-step S2211.

[0062] Step S2201: The server 120 determines whether the working years of the user bound to the current account information are greater than a first preset threshold; if so, execute steps S2202-S2205, that is, when it is determined that the current user is a senior staff member, the senior staff member himself inputs the identification number of his / her area of ​​interest, and based on the camera 110 that the senior staff member is concerned about, determines the relationship between the camera 110 and the area of ​​interest for reference; if not, execute steps S2206-S2211, that is, when it is determined that the current user is a non-senior staff member, the server 120 intelligently determines the business content that the non-senior staff member is concerned about, and intelligently recommends a reasonable window layout strategy.

[0063] The first preset threshold may be a manually input specified value, for example, it may be configured by a system administrator, such as 3 years, 4 years, 5 years, 6 years, 10 years, etc.

[0064] Step S2202: the server 120 sends an instruction to supplement the identification number of the region of interest to the client device 131; Step S2203: the client device 131 sends the region of interest identification number input by the user to the server 120 according to the instruction of supplementing the region of interest identification number; Step S2204: the server 120 binds the focus area identification number input by the user and returned by the client device 131 to the current account information; Step S2205: the server 120 determines the camera set that each area of ​​interest identification number focuses on according to the account information bound to each area of ​​interest identification number and the window layout strategy bound to each account information.

[0065] The above steps S2202 to S2205 are used when the server 120 determines that the working years of the user bound to the current account information are greater than the first preset threshold, that is, when it is determined that the current user is a senior staff member, the senior staff member can fill in the identification number (community ID) of his / her area of ​​interest by himself / herself, and the server 120 directly binds the identification number (community ID) of the area of ​​interest to the account information of the senior staff member; and uses the work selection of the senior staff member as a reference for determining the relationship between the camera 110 and the area of ​​interest, so as to subsequently form a recommended window layout strategy and provide it to non-senior staff for reference.

[0066] It should be noted that the camera set concerned by the attention area identification number indicates that when the user's business content is related to the community, the user will pay attention to these cameras 110 in the set. Among them, different communities may pay attention to certain cameras 110 together, and a camera 110 may also be a camera 110 concerned by multiple communities at the same time. And even if a camera 110 physically belongs to a community, it may not be the camera 110 concerned by the community, but may be the camera 110 that the neighboring community pays the most attention to. Therefore, in order to improve the accuracy of business grouping and the accuracy of the recommended window layout strategy, it is necessary to accurately determine the camera set concerned by each attention area identification number.

[0067] In a specific operation process, in order to accurately determine the camera set that each focus area identification number focuses on, step S2205 includes: step S22051-step S22053.

[0068] Step S22051: the server 120 identifies the account information bound to each focus area identification number, and identifies the window layout strategy bound to each account information according to the account information; Step S22052: the server 120 assigns importance values ​​to the camera identification numbers bound to the pane identification numbers in each window layout strategy, and performs grouping and merging processing according to each focus area identification number to obtain the total importance of each camera identification number; Step S22053: the server 120 selects the camera identification numbers whose total importance is greater than the second preset threshold to form a camera set concerned by each corresponding focus area identification number.

[0069] The second preset threshold may be a manually input specified value, for example, configurable by a system administrator, such as 0, 10, 100, etc.

[0070] In the above steps, the smaller the value of the pane identification number (i.e., the position number of the pane), the closer the pane is to the front, indicating that the camera 110 played in the pane is more important. Therefore, the importance of the camera 110 played in the pane of order 1 is 1000, the importance of the camera 110 played in the pane of order 2 is 999, and so on. The importance of the camera 110 not played in the pane is 0. Therefore, for each focus area identification number (community ID), the server 120 can obtain the total importance of each camera 110 by traversing the account information of all senior staff members bound to the focus area identification number (community ID) and the window layout strategy under their name, and determine the camera set focused on by each focus area identification number.

[0071] For example, for a camera with a community ID of X and a camera identification number of 2, in the window layout strategy under the name of senior staff member A (user A), the window pane number bound to the camera with camera identification number 2 is 3, and the corresponding importance of the camera with camera identification number 2 is determined to be 998; in the window layout strategy under the name of senior staff member B (user B), the window pane number bound to the camera with camera identification number 2 is 1, and the corresponding importance of camera 110 with camera identification number 2 is determined to be 1000.

[0072] For the camera with community ID Y and camera identification number 2, in the window layout strategy under the name of senior staff member C (user C), the window pane number bound to the camera with camera identification number 2 is 4, so the corresponding importance of the camera with camera identification number 2 is determined to be 997; in the window layout strategy under the name of senior staff member D (user D), the window pane number bound to the camera with camera identification number 2 is 3, so the corresponding importance of camera 110 with camera identification number 2 is determined to be 998.

[0073] Then, importance grouping and merging processing is performed, and it is calculated that the total importance of the camera with camera identification number 2 in the community X is 1998, and the total importance of the camera with camera identification number 2 in the community Y is 1995.

[0074] Finally, cameras related to community X and with a total importance greater than 0 are selected to form a camera set and bound to community X; cameras related to community Y and with a total importance greater than 0 are selected to form a camera set and bound to community Y.

[0075] Step S2206: the server 120 sends a supplemental instruction to the client device 131; Step S2207: the client device 131 sends the partial window layout strategy input by the user and the total number of current panes to the server 120 according to the supplementary instruction; Step S2208: the server 120 generates at least one recommended window layout strategy according to the partial window layout strategy, the total number of current panes, and the camera set concerned by each focus area identification number, and sends the strategy to the client device 131; Step S2209: the client device 131 displays at least one recommended window layout strategy, and obtains feedback information input by the user on the at least one recommended window layout strategy; Step S2210: the client device 131 sends feedback information to the server 120; Step S2211: The server 120 determines the focus area identification number bound to the current account information according to the feedback information.

[0076] The above steps S2206 to S2211 are used when the server 120 determines that the working years of the user bound to the current account information are less than or equal to the first preset threshold value and determines that the current user is a non-senior staff member. The server 120 intelligently determines the business content that the non-senior staff member is concerned about and intelligently recommends a reasonable window layout strategy, thereby improving the workflow of some non-senior users, helping some non-senior users to quickly determine the window layout and become familiar with the work content, thereby improving work efficiency.

[0077] During an operation, the server 120 first sends a message of supplementary instructions (such as reporting the total number of current panes and the camera identification number) to the corresponding client. When the non-experienced staff has configured the partial window layout, the client device 131 sends the partial window layout strategy and the current total number of panes input by the user to the server 120 according to the supplementary instructions. For example, when the user binds the first camera 110 to the first pane, the client sends the current total number of panes M and the camera identification number bound to the first pane to the server 120.

[0078] Then, the server 120 generates at least one recommended window layout strategy based on the partial window layout strategy, the total number of current panes, and the set of cameras concerned by each focus area identification number, and sends it to the client device 131; the client device 131 displays the recommended window layout strategies in sequence, and obtains feedback information input by the user for the recommended window layout strategies; the feedback information may be agreement to use the recommended window layout strategy, disagreement to use the recommended window layout strategy, or revision information of the recommended window layout strategy.

[0079] For example, when there are multiple recommended window layout strategies, the client device 131 is first displayed on the interactive interface according to the first recommended window layout strategy, wherein the management service module of the server 120 can send a video stream copy message to the media service module of the server 120 according to the camera identification number or the camera IP address in the window layout strategy, and the media service module copies a copy of the video stream of the camera 110 and sends it to the client device 131 and displays it on the corresponding pane.

[0080] Then, after the client device 131 displays the recommended window layout strategy for the preset time, the client device 131 will pop up a prompt window, asking the non-senior staff member whether he agrees to use the recommended window layout strategy. If the non-senior staff member agrees to use the recommended window layout strategy, he clicks "Confirm", and the client device 131 feeds back the result to the server 120; if the non-senior staff member does not agree to use the recommended window layout strategy, he clicks "Change", and the client displays the next recommended window layout strategy, and continues to pop up prompt windows, asking the non-senior staff member whether he agrees to use the recommended window layout strategy, until the non-senior staff member clicks "Confirm" and agrees to use the recommended window layout strategy.

[0081] Then, the client device 131 sends feedback information to the server 120. The server 120 determines the recommended window layout strategy agreed to by the non-senior staff member based on the feedback information, and uses the focus area identification number (community ID) bound to the recommended window layout strategy as the focus area identification number (community ID) under the name of the non-senior staff member.

[0082] In one embodiment, to accurately generate a recommended window layout strategy, step S2208 includes: steps S22081 to S22085.

[0083] Step S22081: the server 120 identifies the corresponding target camera set according to the camera identification number in the partial window layout strategy, and identifies the bound focus area identification number according to the target camera set.

[0084] The server 120 identifies the corresponding target camera set according to the camera identification number in the partial window layout strategy, and identifies the bound focus area identification number according to the target camera set, and determines the community ID that focuses on the camera. When there are multiple corresponding community IDs, multiple recommended window layout strategies are generated in sequence according to the matching order; when there is one corresponding community ID, one recommended window layout strategy is generated.

[0085] To generate each recommended window layout strategy, the following steps need to be performed, wherein, step S22082: the server 120 determines whether the number of cameras 110 in the target camera set is greater than the total number of current panes; if so, steps S22083-S22084 are performed, step S22083: the server 120 sorts the cameras 110 in the target camera set according to the principle of importance from large to small to obtain a sorting queue, step S22084: the server 120 selects the target camera 110 corresponding to the total number of current panes according to the sorting queue, and determines the binding of the target camera 110 to the pane in turn. A recommended window layout strategy is formed, that is, M cameras 110 with the highest total importance are selected from the target camera set corresponding to the community ID, and they are bound to each pane in order from high to low in terms of total importance; if not, step S22085 is executed. Step S22085: the server 120 sorts the cameras 110 in the target camera set according to the principle of importance from large to small, and arranges them in the corresponding panes in order to form a recommended window layout strategy, that is, all cameras 110 in the target camera set corresponding to the community ID are bound to each pane in order from high to low in terms of total importance.

[0086] In one embodiment, in order to prevent the server 120 from becoming a performance bottleneck of the scheduling, multiple client devices 131 may also communicate with each other in the form of multicast, and before step S120, it also includes: steps S3201-S3211.

[0087] Step S3201: the target client device sends the current account information entered by the user on the client to the server 120 .

[0088] Step S3202: The server 120 determines whether the working years of the user bound to the current account information are greater than the first preset threshold. If so, step S3203 is executed, that is, the current user is determined to be a senior staff member, and the server 120 directly sends the relevant information to the target client device, and the target client device displays the relevant content; if not, steps S3204-S3211 are executed, that is, when the current user is determined to be a non-senior staff member, other client devices and the target client device intelligently determine the business content that the non-senior staff member is concerned about, and intelligently recommend a reasonable window layout strategy.

[0089] Step S3203: the server 120 sends the focus area identification number bound to the current account information, the camera set focused on by the focus area identification number, and / or the window layout strategy bound to the current account information to the target client device.

[0090] In this step, the server 120 sends one or more information including the focus area identification number bound to the current account information, the camera set focused on by the focus area identification number, and the window layout strategy bound to the current account information to the target client device. The target client device retrieves the corresponding video data based on the one or more information, and displays the video data that the senior staff is concerned about.

[0091] Step S3204: the client device 131 sends the partial window layout strategy input by the user and the total number of current panes to all other client devices in the multicast group 130 in a multicast form.

[0092] Step S3205: Other client devices determine whether the working years of the user bound to their current account information are greater than the first preset threshold, and whether the camera identification number in the partial window layout strategy exists in the locally pre-stored camera set; if not, execute step S3206, and other client devices ignore the information sent by the target client device; if so, execute steps S3207-S3211, and other client devices send the locally pre-stored camera set and the associated focus area identification number to the target client device, and determine the area identification number that the non-senior staff is concerned about.

[0093] Step S3207: the other client devices send the locally stored camera set and the identification number of the area of ​​interest associated therewith to the target client device; wherein the locally stored camera set includes: one or more of the camera identification number, the IP address of the camera 110, and the importance of the camera 110; Step S3208: the target client device generates at least one recommended window layout strategy according to the locally pre-stored camera set and the associated focus area identification number sent by other client devices; Step S3209: the target client device displays at least one recommended window layout strategy, and obtains feedback information input by the user on the at least one recommended window layout strategy; Step S3210: the target client device sends feedback information to the server 120; Step S3211: The server 120 determines the focus area identification number bound to the current account information according to the feedback information.

[0094] In a specific operation process, when a non-experienced staff member completes the configuration of a partial window layout, the client device 131 sends the partial window layout strategy and the current total number of panes input by the user to all other client devices in the form of multicast. For example, when the user binds the first camera 110 to the first pane, the target client device will send the current total number of panes M and the camera identification number bound to the first pane to the server 120.

[0095] All other client devices will receive the message. Other client devices will first determine whether the working years of the user bound to their current account information is greater than the first preset threshold. When other client devices determine that the working years of the user bound to their current account information is less than or equal to the first preset threshold, that is, the users of other client devices are non-senior staff, then the information will be ignored; when other client devices determine that the working years of the user bound to their current account information is greater than the first preset threshold, that is, the users of other client devices are senior staff, then they will continue to determine whether the camera identification number in the partial window layout strategy exists in the locally pre-stored camera set.

[0096] When other client devices determine that the camera identification number in the partial window layout strategy does not exist in the locally pre-stored camera set, the message is ignored; when other client devices determine that the camera identification number in the partial window layout strategy exists in the locally pre-stored camera set, the other client devices send the locally pre-stored camera set and its associated focus area identification number to the source IP address of the multicast message, i.e., the target client device.

[0097] The target client device may receive information sent by multiple other client devices at the same time, and thus can generate a recommended window layout strategy according to the information sent by each other client device. The target client device displays the recommended window layout strategies in turn and obtains feedback information input by the user on the recommended window layout strategies; the feedback information may be agreement to use the recommended window layout strategy, disagreement to use the recommended window layout strategy, or revision information of the recommended window layout strategy.

[0098] For example, when there are multiple recommended window layout strategies, the target client device is first displayed on the interactive interface according to the first recommended window layout strategy, wherein the management service module of the server 120 can send a video stream copy message to the media service module of the server 120 according to the camera identification number or the camera IP address in the window layout strategy, and the media service module copies a copy of the video stream of the camera 110 and sends it to the target client device and displays it on the corresponding pane.

[0099] Then, after the target client device displays the recommended window layout strategy for the preset time, the target client device will pop up a prompt window, asking the non-senior staff member whether he agrees to use the recommended window layout strategy. If the non-senior staff member agrees to use the recommended window layout strategy, he clicks "Confirm", and the target client device feeds back the result to the server 120; if the non-senior staff member does not agree to use the recommended window layout strategy, he clicks "Change", the client displays the next recommended window layout strategy, and continues to pop up prompt windows, asking the non-senior staff member whether he agrees to use the recommended window layout strategy, until the non-senior staff member clicks "Confirm" and agrees to use the recommended window layout strategy.

[0100] Then, the target client device sends feedback information to the server 120. The server 120 determines the recommended window layout strategy agreed to by the non-senior staff member based on the feedback information, and uses the focus area identification number (community ID) bound to the recommended window layout strategy as the focus area identification number (community ID) under the name of the non-senior staff member.

[0101] In another embodiment, the target client device generates each recommended window layout strategy, and the following steps need to be performed: the target client device determines whether the number N of cameras 110 in the locally pre-stored camera set is greater than the total number M of current window panes; if so, the M camera identification numbers with the highest total importance are selected from the locally pre-stored camera set, and they are bound to each window pane in order from high to low in terms of total importance; if not, all cameras 110 in the locally pre-stored camera set are bound to each window pane in order from high to low in terms of total importance.

[0102] In another embodiment, step S3207 "other client devices send the locally pre-stored camera set and the focus area identification numbers associated therewith to the target client device" includes the following steps: the other client devices determine whether the number N of cameras 110 in the locally pre-stored camera set is greater than the total number M of current window panes; if so, then select the M camera identification numbers with the highest total importance from the locally pre-stored camera set, and send the camera identification numbers and other information selected from the locally pre-stored camera set and the focus area identification number to the target client device; if not, then send all the camera identification numbers and other information of the locally pre-stored camera set and the focus area identification number to the target client device.

[0103] In the embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0104] In addition, the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0105] Furthermore, the functional modules in the various embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

[0106] It should be noted that if the function is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a 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 the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0107] In this document, relational terms such as first and second, etc. are used merely to distinguish one entity or operation from another entity or operation, but do not necessarily require or imply any such actual relationship or order between these entities or operations.

[0108] The above are only embodiments of the present application and are not intended to limit the scope of protection of the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the scope of protection of the present application.

Claims

1. A prompt word improvement system, characterized in that: include: A server, a plurality of client devices and a plurality of cameras, wherein the server is communicatively connected to the plurality of client devices and the plurality of cameras; The server is used to receive the video data sent by the multiple cameras and send it to the client device; The client device is used to obtain a prompt word input by a user on the client, and send the prompt word, the current account information of the client login and the current window layout strategy of the client to the server, wherein the current window layout strategy of the client includes binding information of the camera identification number and the window pane identification number; The server is further configured to receive the prompt word, the current account information of the client logged in, and the current window layout strategy of the client, and determine the focus area identification number bound to the current account information according to the current account information of the client logged in and / or the current window layout strategy of the client; The server is further configured to determine a current service group of the current account information according to the concerned area identification number; The server is further configured to retrieve a database corresponding to the current business group according to the current business group of the current account information to improve the prompt word and obtain prompt word improvement information.

2. The prompt word improvement system according to claim 1, characterized in that: Before the client device is used to obtain a prompt word input by a user on the client and sends the prompt word, the current account information of the client login and the current window layout strategy of the client to the server, it also includes: The client device is also used to send the current account information of the user logged in at the client to the server; The server is also used to determine whether there is a pre-stored window layout strategy bound to the current account information according to the current account information; When the server determines that there is a pre-stored window layout strategy bound to the current account information, the server directly sends the pre-stored window layout strategy to the client device; The client device displays the camera data according to the pre-stored window layout strategy, and receives in real time the revision information of the pre-stored window layout strategy from the user; When the client device receives the revision information of the user for the pre-stored window layout strategy, the client device sends the revision information to the server, and the server updates the pre-stored window layout strategy according to the revision information; When the server determines that there is no pre-stored window layout strategy bound to the current account information, the server sends a supplementary instruction to the client device; The client device sends the window layout policy input by the user to the server for storage according to the supplementary instruction.

3. The prompt word improvement system according to claim 1, characterized in that: Before the client device is used to obtain a prompt word input by a user on the client and sends the prompt word, the current account information of the client login and the current window layout strategy of the client to the server, it also includes: The server is further configured to determine whether the working years of the user bound to the current account information is greater than a first preset threshold; When the server determines that the working years of the user bound to the current account information are greater than a first preset threshold, the server sends an instruction to supplement the identification number of the area of ​​interest to the client device; The client device is further configured to send the area of ​​interest identification number input by the user to the server according to the instruction of the supplementary area of ​​interest identification number; The server is further used to bind the focus area identification number input by the user and returned by the client device to the current account information; The server is further configured to determine the camera set that each area of ​​interest identification number focuses on, based on the account information bound to each area of ​​interest identification number and the window layout strategy bound to each of the account information.

4. The prompt word improvement system according to claim 3, characterized in that: The server is further configured to determine the camera set that each area of ​​interest identification number focuses on according to the account information bound to each area of ​​interest identification number and the window layout strategy bound to each of the account information, including: The server is further used to identify the account information bound to each focus area identification number, and identify the window layout strategy bound to each account information according to the account information; The server is also used to assign importance values ​​to the camera identification numbers bound to the pane identification numbers in each of the window layout strategies, and to perform grouping and merging processing according to each focus area identification number to obtain the total importance of each camera identification number; The server is further used to select camera identification numbers whose total importance is greater than a second preset threshold to form a camera set concerned by each corresponding concerned area identification number.

5. The prompt word improvement system according to claim 4, characterized in that: When the server determines that the working years of the user bound to the current account information is less than or equal to a first preset threshold, the server sends a supplementary instruction to the client device; The client device sends the partial window layout strategy and the total number of current panes input by the user to the server according to the supplementary instruction; The server generates at least one recommended window layout strategy according to the partial window layout strategy, the total number of current panes, and the camera set concerned by each focus area identification number, and sends the strategy to the client device; The client device displays the at least one recommended window layout strategy, and obtains feedback information input by a user on the at least one recommended window layout strategy; The client device sends the feedback information to the server; The server determines the concerned area identification number bound to the current account information according to the feedback information.

6. The prompt word improvement system according to claim 5, characterized in that: The server generates at least one recommended window layout strategy according to the partial window layout strategy, the total number of current panes, and the camera set concerned by each focus area identification number, and sends the strategy to the client device, including: The server identifies the corresponding target camera set according to the camera identification number in the partial window layout strategy, and identifies the bound focus area identification number according to the target camera set; The server determines whether the number of cameras in the target camera set is greater than the total number of current panes; When the server determines that the number of cameras in the target camera set is greater than the total number of the current panes, the server is further used to sort the cameras in the target camera set according to the importance in descending order to obtain a sorted queue; The server is also used to select target cameras corresponding to the total number of current window panes according to the sorting queue, and determine the binding relationship between the target cameras and the window panes in turn to form a recommended window layout strategy.

7. The prompt word improvement system according to claim 1, characterized in that: The prompt word improvement system also includes a multicast group, the server is communicatively connected to the multicast group, and the multiple client devices are connected to the network of the multicast group.

8. The prompt word improvement system according to claim 7, characterized in that: The target client device sends the current account information entered by the user on the client to the server; The server is further configured to determine whether the working years of the user bound to the current account information is greater than a first preset threshold; When the server determines that the working years of the user bound to the current account information are greater than a first preset threshold, the server sends the focus area identification number bound to the current account information, the camera set focused on by the focus area identification number, and / or the window layout strategy bound to the current account information to the target client device; When the server determines that the working years of the user bound to the current account information are less than or equal to a first preset threshold, the client device sends the partial window layout strategy and the total number of current panes input by the user to all other client devices in the multicast group in a multicast form; The other client device determines whether the working years of the user bound to the current account information of the other client device is greater than a first preset threshold, and whether the camera identification number in the partial window layout strategy exists in the locally pre-stored camera set; When the other client device determines that the working years of the user bound to its current account information is greater than a first preset threshold, and the camera identification number in the partial window layout strategy exists in the locally pre-stored camera set, the other client device sends the locally pre-stored camera set and the associated focus area identification number to the target client device; The target client device generates at least one recommended window layout strategy according to the locally pre-stored camera set and the associated focus area identification number sent by the other client devices; The target client device displays the at least one recommended window layout strategy, and obtains feedback information input by a user on the at least one recommended window layout strategy; The target client device sends the feedback information to the server; The server determines the concerned area identification number bound to the current account information according to the feedback information.

9. The prompt word improvement system according to any one of claims 1 to 8, characterized in that: The server is further configured to retrieve a database corresponding to the current business group according to the current business group of the current account information to improve the prompt word, and after obtaining the prompt word improvement information, further comprising: The server is also used to input the prompt word improvement information into the large language model to generate a draft text; or, The server is also used to send the prompt word completion information to the client device and display it on the interactive interface of the client device; The client device receives the modification information of the prompt word improvement information by the user, and sends the final prompt word improvement information to the server; The server is further configured to input the final prompt word completion information into a large language model to generate a draft text.

10. A prompt word improvement method, characterized in that: The method is applied to a prompt word improvement system, the prompt word improvement system comprises: a server, a plurality of client devices and a plurality of cameras, the server is communicatively connected to the plurality of client devices and the plurality of cameras; the method comprises: The server receives the video data sent by the multiple cameras and sends it to the client device; The client device obtains a prompt word input by a user on the client, and sends the prompt word, current account information logged in by the client, and a current window layout strategy of the client to the server, wherein the current window layout strategy of the client includes binding information of a camera identification number and a pane identification number; The server receives the prompt word, the current account information of the client login and the current window layout strategy of the client, and determines the focus area identification number bound to the current account information according to the current account information of the client login and / or the current window layout strategy of the client; The server determines the current service group of the current account information according to the concerned area identification number; The server retrieves a database corresponding to the current business group according to the current business group of the current account information to improve the prompt word and obtain prompt word improvement information.

Images