Service platform data optimization system and method based on artificial intelligence

Abstract

The invention discloses a service platform data optimization system and method based on artificial intelligence, and relates to the technical field of service platform communication, and the system comprises an access information collection module, an information matching module, a transmission information optimization module and a data communication module. After a user inputs a consultation question on a platform, reference data capable of answering the corresponding input consultation question is matched through an information matching module, the marked condition of the matched reference data is analyzed through a transmission information optimization module, and the matched reference data is selectively sorted according to the marked condition. The final optimized reference data is generated through the data communication module, and the final optimized reference data is transmitted to the client where the user who inputs the consultation question on the platform currently is located, so that the validity of data provided by the artificial intelligence double-creation service platform is improved, and meanwhile, the waste of data transmission resources is reduced.

Description

Technical Field

[0001] The present invention relates to the field of service platform communication technology, and in particular to an artificial intelligence-based service platform data optimization system and method. Background Art

[0002] The AI ​​entrepreneurship and innovation service platform refers to a public platform that provides professional innovation and entrepreneurship services such as R&D tools, testing and evaluation, safety, standards, intellectual property rights, and entrepreneurship information consulting in the field of AI. Users who have information consulting needs can log in to the AI ​​entrepreneurship and innovation service platform, enter the questions they want to consult on the platform, and the platform will transmit data related to solving the consulting questions to the user's client for the user's query and reference. Users can also provide information to the platform as information providers; With the rapid growth of the amount of information stored on the artificial intelligence entrepreneurship and innovation service platform, after the user enters the question he wants to consult, the platform may provide a large amount of reference information, and the user is required to check the corresponding reference information one by one to find valid information. When receiving a large amount of reference information, the user may not be able to quickly find truly effective data. Some users may exit the service platform after viewing some information and finding that there is no useful reference information. The existing service platform is unable to adaptively optimize the platform's data provision method based on the user's information reception situation, which reduces the effectiveness of information supply on the artificial intelligence entrepreneurship and innovation service platform. Summary of the invention

[0003] The purpose of the present invention is to provide a service platform data optimization system and method based on artificial intelligence to solve the problems raised in the prior art.

[0004] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: a service platform data optimization system based on artificial intelligence, the system comprising an access information acquisition module, an information matching module, a transmission information optimization module and a data communication module; The access information collection module is used to collect access information of the artificial intelligence dual innovation service platform; The information matching module is used to match reference data that can answer the consulting questions inputted by the user on the platform; The transmission information optimization module is used to analyze the marking status of the matched reference data, and selectively sort the matched reference data according to the marking status; The data communication module is used to selectively screen the reference data after the selective sorting process, generate final optimized reference data, and transmit the final optimized reference data to the client of the user who currently inputs the consulting question on the platform.

[0005] Preferably, the access information collection module includes a platform login data collection unit and an input information collection unit; The platform login data collection unit is used to confirm the user's identity information after the user logs in to the artificial intelligence dual innovation service platform, and the user's identity information is collected after the user grants permission; The input information collection unit is used to collect the consulting question information input by the current user on the platform after logging in.

[0006] Preferably, the information matching module includes an input information identification unit and a reference data retrieval unit; The input information recognition unit is used to use NLP technology to recognize and semantically analyze the consulting question information input by the user on the platform; The reference data retrieval unit is used to use intelligent AI question-and-answer technology to retrieve reference data from the platform's database that can answer the consulting questions input by users. The artificial intelligence dual innovation service platform has an intelligent AI question-and-answer function. Intelligent AI question-and-answer technology is an innovative application based on artificial intelligence technology. It uses natural language processing technology, namely NLP technology and machine learning technology, to achieve the function of answering user questions.

[0007] Preferably, the transmission information optimization module includes a queried information statistics unit and a supply mode optimization unit; The queried information statistics unit is used to count the feedback information after each reference data is viewed. After the user has viewed each reference data, the platform will pop up the content of "whether the corresponding reference data is valid data" for the user to choose. If the user selects the "yes" option, the corresponding reference data will be recorded as being marked once; if the user selects the "no" option, the marking information will not be counted. The feedback information includes the number of times each reference data that can answer the same consulting question is marked. There is more than one reference data that can answer the same consulting question; The supply mode optimization unit is used to select whether to sort several reference data items for the same consulting question based on the number of times all reference data items that can answer the corresponding consulting question are marked: a threshold for the difference in the number of times marked is set, and if the difference in the number of times marked of several reference data items exceeds the threshold, the several reference data items are selected for sorting; otherwise, no sorting is performed, and the final arrangement order of the reference data that can answer the same consulting question is confirmed.

[0008] Preferably, the data communication module includes a supply information confirmation unit and a supply data transmission unit; The supply information confirmation unit is used to collect the amount of reference data that users viewed before exiting the platform due to failure to find valid reference data. If the user selected the "No" option before exiting the platform, it means that the user did not find valid reference data. The acceptable amount of data for the user is predicted based on the amount of reference data. If the user currently inputting the consulting question is a user logging into the platform for the first time, the reference data that can answer the consulting question input by the current user will not be screened, and the acceptable amount of data will not be predicted for the user logging into the platform for the first time. It is confirmed that the data provided to the current user is all the reference data that can answer the consulting question input by the current user. If the user currently inputting the consulting question is not a user logging into the platform for the first time, the reference data that can answer the consulting question input by the current user will be screened, and it is confirmed that the data provided to the current user is the data after the screening process. Here, the reference data that can answer the consulting question input by the current user before the screening process is the reference data with the confirmed final arrangement order. The supply data transmission unit is used to transmit the confirmed data provided to the current user to the client where the current user is located, and the confirmed data provided to the current user is the final optimized reference data.

[0009] A service platform data optimization method based on artificial intelligence, comprising the following steps: S1: Collect access information of the artificial intelligence entrepreneurship and innovation service platform; S2: After the user inputs a consulting question on the platform, matching reference data that can answer the corresponding input consulting question; S3: analyzing the labeling status of the matched reference data, and selectively sorting the matched reference data according to the labeling status; S4: selectively screening the reference data after the selective sorting process to generate final optimized reference data, and transmitting the final optimized reference data to the client of the user who currently inputs the consulting question on the platform.

[0010] Preferably, S1 includes: confirming the user's identity information after the user logs in to the artificial intelligence dual innovation service platform, and collecting the consultation question information entered by the current user on the platform after logging in.

[0011] Preferably, S2 includes: using NLP technology to identify and semantically analyze the consulting question information input by the current user on the platform, and using intelligent AI question-answering technology to retrieve all reference data that can answer the consulting question input by the current user from the platform's database.

[0012] Preferably, S3 includes: for all reference data that can answer the consulting question currently input by the user, counting the marked information of each reference data after it has been viewed in the past, and counting the number of times each reference data has been marked in history as {H1, H2, ... H n}, n represents the number of reference data items that can answer the consultation question currently entered by the user. The difference in the number of times the n reference data items are marked is calculated according to the formula, P=[∑ n i=1 (H i -(∑ n i=1 (H i )) / n) 2 / n] 1 / 2 , i represents the i-th reference data, set the threshold of the number of times marked to R, and compare P and R: if P>R, select n reference data for sorting, and sort the i reference data in descending order of the number of times they have been marked in history, and randomly sort the reference data with the same number of times marked; if P≤R, no sorting is performed, that is, the n reference data are randomly arranged; For the same consulting question, whether the reference data that can answer the corresponding consulting question is valid for different users, that is, whether it has reference value, cannot be accurately judged in the prior art. The present invention sets a page pop-up on the service platform for users to provide feedback on whether the corresponding reference data is valid after viewing and completing different items of reference data. Compared with the prior art, the present invention can accurately obtain users' feedback information on the reference data, and before transmitting the reference data that can answer the corresponding consulting question to the user, selective sorting is performed based on the marking status of the reference data. The reason for selective sorting is that there may be a situation where the number of times the reference data is marked is not much different. In this case, there is no need to perform sorting. Transmitting the sorted reference data to the user is conducive to increasing the probability of users quickly finding valid reference data, while simplifying unnecessary sorting work of the system.

[0013] Preferably, S4 includes: confirming whether the user who currently inputs the consultation question is a user who logs in to the platform for the first time: if so, transmitting n reference data as the final optimized reference data to the client where the current user is located; if not, collecting the amount of reference data that the current user viewed before exiting the platform due to failure to find valid reference data for the consultation question: the reference data amount set is V={V1,V2,...V m}, m represents the number of times the current user has exited the platform due to failure to find valid reference data. The amount of data that the current user can accept is predicted to be V m+1 :V m+1 =θ*V m+(1-θ)*D m , where D m It represents the smoothed value of the reference data viewed by the user before the mth exit from the platform, 0<θ<1, θ represents the smoothing coefficient, θ is the default setting of the system, and the total amount of the first k reference data in the n reference data that have been selectively sorted does not exceed V m+1 And the total amount of the first k+1 reference data exceeds V m+1 , the first k reference data are transmitted as the final optimized reference data to the client where the current user is located; Optimize data transmission for different users: Considering that some users may be logging into the service platform for the first time, while some users may have logged in several times, for users who are logging into the service platform for the first time, since it is impossible to obtain the user's historical viewing behavior data, all reference data that can answer the corresponding consulting questions will be directly transmitted to the user's client; for users who have already logged in to the platform, the acceptable amount of data for the user is predicted by analyzing the number of times the corresponding user has exited the platform due to failure to find valid reference data. That is, the user may exit the service platform after viewing a part of the data and finding that there is no valid reference data. According to the user's acceptable amount of data, several reference data with appropriate data volume are screened out, and the screened data are transmitted to the corresponding user's client. The platform's data provision method is adaptively optimized according to the user's information reception situation, which improves the effectiveness of information supply of the artificial intelligence dual innovation service platform and reduces the waste of data transmission resources.

[0014] Compared with the prior art, the present invention has the following beneficial effects: Considering that for the same consulting question, whether the reference data that can answer the corresponding consulting question is valid for different users, that is, whether it has reference value, cannot be accurately judged in the prior art, the present invention sets a page pop-up on the service platform for users to feedback whether the corresponding reference data is valid after viewing and completing different reference data. Compared with the prior art, the present invention can accurately obtain the user's feedback information on the reference data, and before the reference data that can answer the corresponding consulting question is transmitted to the user, the reference data is selectively sorted according to the marking situation. The reason for the selective sorting is that there may be a situation where the number of times the reference data is marked is not much different. In this case, there is no need to sort. Transmitting the sorted reference data to the user is conducive to increasing the probability that the user can quickly find valid reference data, and at the same time simplifies the unnecessary sorting work of the system. Optimize data transmission for different users: Considering that some users may be logging into the service platform for the first time, while some users may have logged in several times, for users who are logging into the service platform for the first time, since it is impossible to obtain the user's historical viewing behavior data, all reference data that can answer the corresponding consulting questions will be directly transmitted to the user's client; for users who have already logged in to the platform, the acceptable amount of data for the user is predicted by analyzing the number of times the corresponding user has exited the platform due to failure to find valid reference data. That is, the user may exit the service platform after viewing a part of the data and finding that there is no valid reference data. According to the user's acceptable amount of data, several reference data with appropriate data volume are screened out, and the screened data are transmitted to the corresponding user's client. The platform's data provision method is adaptively optimized according to the user's information reception situation, which improves the effectiveness of information supply of the artificial intelligence dual innovation service platform and reduces the waste of data transmission resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 This is a structural schematic diagram of a service platform data optimization system based on artificial intelligence in the present invention; Figure 2 The present invention is a flowchart of a service platform data optimization method based on artificial intelligence. DETAILED DESCRIPTION

[0016] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions 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 of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0017] Example 1: Figure 1 As shown, this embodiment provides a service platform data optimization system based on artificial intelligence, the system includes: an access information acquisition module, an information matching module, a transmission information optimization module and a data communication module; The access information collection module is used to collect access information of the artificial intelligence dual innovation service platform; The information matching module is used to match reference data that can answer the corresponding consulting questions after the user enters the consulting questions on the platform; The transmission information optimization module is used to analyze the labeling status of the matched reference data and selectively sort the matched reference data according to the labeling status; The data communication module is used to selectively screen the reference data after selective sorting, generate final optimized reference data, and transmit the final optimized reference data to the client of the user who is currently inputting consulting questions on the platform, wherein selective sorting refers to the two situations of choosing to sort the data and choosing not to sort the data; selective screening refers to the two situations of choosing to screen the data and choosing not to screen the data.

[0018] The access information collection module includes a platform login data collection unit and an input information collection unit; The platform login data collection unit is used to confirm the user's identity information after the user logs into the artificial intelligence entrepreneurship and innovation service platform; The input information collection unit is used to collect the consulting question information entered by the current user on the platform after logging in.

[0019] The information matching module includes an input information recognition unit and a reference data retrieval unit; The input information recognition unit is used to use NLP technology to recognize and semantically analyze the consulting question information input by the user on the platform; The reference data retrieval unit is used to use intelligent AI question-answering technology to retrieve reference data from the platform's database that can answer the consulting questions entered by the user.

[0020] The transmission information optimization module includes a queried information statistics unit and a supply mode optimization unit; The queried information statistics unit is used to count the feedback information after each reference data is viewed. After the user has viewed each reference data, the platform will pop up the content of "whether the corresponding reference data is valid data" for the user to choose. If the user selects the "yes" option, the corresponding reference data will be recorded as being marked once; if the user selects the "no" option, the marking information will not be counted. The feedback information includes the number of times each reference data that can answer the same consulting question has been marked. There is more than one reference data that can answer the same consulting question. The supply mode optimization unit is used to select whether to sort several reference data items for the same consulting question based on the number of times all reference data items that can answer the corresponding consulting question are marked: a threshold for the difference in the number of times marked is set. If the difference in the number of times marked of several reference data items exceeds the threshold, the several reference data items are selected for sorting; otherwise, no sorting is performed, and the final arrangement order of the reference data that can answer the same consulting question is confirmed.

[0021] The data communication module includes a supply information confirmation unit and a supply data transmission unit; The supply information confirmation unit is used to collect the amount of reference data that users viewed before exiting the platform due to failure to find valid reference data. If the user selected the "No" option before exiting the platform, it means that the user did not find valid reference data. The acceptable amount of data for the user is predicted based on the amount of reference data. If the user currently inputting the consulting question is a user logging into the platform for the first time, the reference data that can answer the consulting question input by the current user will not be screened, and the acceptable amount of data will not be predicted for the user logging into the platform for the first time. It is confirmed that the data provided to the current user is all the reference data that can answer the consulting question input by the current user. If the user currently inputting the consulting question is not a user logging into the platform for the first time, the reference data that can answer the consulting question input by the current user will be screened, and it is confirmed that the data provided to the current user is the data after screening. Here, the reference data that can answer the consulting question input by the current user before screening is the reference data with the confirmed final arrangement order. The supply data transmission unit is used to transmit the confirmed data provided to the current user to the client where the current user is located, and the confirmed data provided to the current user is the final optimized reference data.

[0022] Example 2: Figure 2 As shown, this embodiment provides a service platform data optimization method based on artificial intelligence, which is implemented based on the service platform data optimization system in the embodiment, and specifically includes the following steps: S1: Collecting access information of the artificial intelligence mass entrepreneurship and innovation service platform: confirming the user's identity information after the user logs in to the artificial intelligence mass entrepreneurship and innovation service platform, and collecting the consultation question information entered by the current user on the platform after logging in; S2: After the user enters a consulting question on the platform, match the reference data that can answer the corresponding consulting question: Use NLP technology to identify and semantically analyze the consulting question information entered by the current user on the platform, and use intelligent AI question-answering technology to retrieve all reference data that can answer the consulting question entered by the current user from the platform's database; S3: Analyze the marking status of the matched reference data, and selectively sort the matched reference data according to the marking status: for all reference data that can answer the consulting question input by the current user, count the marking information of each reference data after it has been viewed in the past, and count the number of times each reference data has been marked in history as {H1, H2, ... H n}, n represents the number of reference data items that can answer the consultation question currently entered by the user. The difference in the number of times the n reference data items are marked is calculated according to the formula, P=[∑ n i=1 (H i -(∑ n i=1 (Hi )) / n) 2 / n] 1 / 2 , i represents the i-th reference data, set the threshold of the number of times marked to R, and compare P and R: if P>R, select n reference data for sorting, and sort the i reference data in descending order of the number of times they have been marked in history, and randomly sort the reference data with the same number of times marked; if P≤R, no sorting is performed, that is, the n reference data are randomly arranged; S4: Selectively screen the reference data after the selective sorting process to generate the final optimized reference data, and transmit the final optimized reference data to the client of the user who currently inputs the consulting question on the platform: confirm whether the user who currently inputs the consulting question is the user who logs in to the platform for the first time: if so, transmit n reference data as the final optimized reference data to the client of the current user; if not, collect the reference data that the current user viewed before exiting the platform due to failure to find valid reference data for the consulting question: the reference data volume set is V={V1,V2,...V m}, m represents the number of times the current user has exited the platform due to failure to find valid reference data. The amount of data that the current user can accept is predicted to be V m+1 :V m+1 =θ*V m +(1-θ)*D m , where * represents the multiplication sign, D m It represents the smoothed value of the amount of reference data viewed by the user before exiting the platform for the mth time. According to D1=θ*V1+(1-θ)*[(V1+V2+V3) / 3], the smoothed value of the amount of reference data viewed by the user before exiting the platform for the first time is obtained. According to D2=θ*V1+(1-θ)*D1, D2 is obtained. According to D3=θ*V2+(1-θ)*D2, D3 is obtained. The final result is D m , 0<θ<1, θ represents the smoothing coefficient, θ is the system default setting, and the total amount of the first k reference data in the n reference data that have been selectively sorted does not exceed V m+1 And the total amount of the first k+1 reference data exceeds V m+1 , the first k reference data are transmitted as the final optimized reference data to the client where the current user is located; For example: The predicted acceptable data volume for the current user is V m+1 = 10KB, it is found that among the 10 reference data items that have been selectively sorted, the total amount of data of the first 5 reference data items does not exceed V m+1 And the total amount of data of the first 6 reference data exceeds V m+1, the first 6 reference data are transmitted to the client where the current user is located as the final optimization reference data.

[0023] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. A service platform data optimization system based on artificial intelligence, characterized by: The system includes an access information acquisition module, an information matching module, a transmission information optimization module and a data communication module; The access information collection module is used to collect access information of the artificial intelligence dual innovation service platform; The information matching module is used to match reference data that can answer the consulting questions inputted by the user on the platform; The transmission information optimization module is used to analyze the marking status of the matched reference data, and selectively sort the matched reference data according to the marking status; The data communication module is used to selectively screen the reference data after the selective sorting process, generate final optimized reference data, and transmit the final optimized reference data to the client of the user who currently inputs the consulting question on the platform; The transmission information optimization module includes a queried information statistics unit and a supply mode optimization unit; The queried information statistics unit is used to count the feedback information after each reference data is viewed. After the user has viewed each reference data, the platform will pop up the content of "whether the corresponding reference data is valid data" for the user to choose. If the user selects the "yes" option, the corresponding reference data will be recorded as being marked once; if the user selects the "no" option, the marking information will not be counted. The feedback information includes the number of times each reference data that can answer the same consulting question has been marked; The supply mode optimization unit is used to select whether to sort several reference data items according to the number of times all reference data items that can answer the corresponding consulting question are marked for the same consulting question: a threshold value of the difference in the number of times marked is set, and if the difference in the number of times marked for several reference data items exceeds the threshold, the several reference data items are selected for sorting; Otherwise, no sorting is performed, and the final arrangement order of the reference data that can answer the same consulting question is determined.

2. The service platform data optimization system based on artificial intelligence according to claim 1, characterized in that: The access information collection module includes a platform login data collection unit and an input information collection unit; The platform login data collection unit is used to confirm the user's identity information after the user logs in to the artificial intelligence dual innovation service platform; The input information collection unit is used to collect the consulting question information input by the current user on the platform after logging in.

3. The service platform data optimization system based on artificial intelligence according to claim 2, characterized in that: The information matching module includes an input information identification unit and a reference data retrieval unit; The input information recognition unit is used to use NLP technology to recognize and semantically analyze the consulting question information input by the user on the platform; The reference data retrieval unit is used to use intelligent AI question-answering technology to retrieve reference data from the platform's database that can answer the consulting questions input by the user.

4. The service platform data optimization system based on artificial intelligence according to claim 1, characterized in that: The data communication module includes a supply information confirmation unit and a supply data transmission unit; The supply information confirmation unit is used to collect the amount of reference data that the user viewed before exiting the platform due to failure to find valid reference data. If the user selected the "No" option before exiting the platform, it means that the user did not find valid reference data. The acceptable amount of data for the user is predicted based on the amount of reference data. If the user currently inputting the consulting question is a user who logs into the platform for the first time, the reference data that can answer the consulting question input by the current user is not screened, and the data provided to the current user is confirmed to be all the reference data that can answer the consulting question input by the current user. If the user currently inputting the consultation question is not a user logging into the platform for the first time, the reference data that can answer the consultation question input by the current user is screened and processed to confirm that the data provided to the current user is the screened data; The supply data transmission unit is used to transmit the confirmed data provided to the current user to the client where the current user is located.

5. A service platform data optimization method based on artificial intelligence, applied to a service platform data optimization system based on artificial intelligence as claimed in any one of claims 1 to 4, characterized in that: The following steps are involved: S1: Collect access information of the artificial intelligence entrepreneurship and innovation service platform; S2: After the user inputs a consulting question on the platform, matching reference data that can answer the corresponding input consulting question; S3: analyzing the labeling status of the matched reference data, and selectively sorting the matched reference data according to the labeling status; S4: selectively screening the reference data after the selective sorting process to generate final optimized reference data, and transmitting the final optimized reference data to the client of the user who currently inputs the consulting question on the platform.

6. The method for optimizing service platform data based on artificial intelligence according to claim 5, characterized in that: The S1 includes: confirming the user's identity information after the user logs in to the artificial intelligence dual innovation service platform, and collecting the consultation question information entered by the current user on the platform after logging in.

7. The method for optimizing service platform data based on artificial intelligence according to claim 6, characterized in that: The S2 includes: using NLP technology to identify and semantically analyze the consulting question information entered by the current user on the platform, and using intelligent AI question-answering technology to retrieve all reference data that can answer the consulting question entered by the current user from the platform's database.

8. The method for optimizing service platform data based on artificial intelligence according to claim 7, characterized in that: S3 includes: for all reference data that can answer the consultation question currently input by the user, counting the marked information of each reference data after it has been viewed in the past, and counting the number of times each reference data has been marked in history as {H1, H2, ... H n }, n represents the number of reference data items that can answer the consultation question currently entered by the user. The difference in the number of times the n reference data items are marked is calculated according to the formula, P=[∑ n i=1 (H i -(∑ n i=1 (H i )) / n) 2 / n] 1 / 2 , i represents the i-th reference data, set the difference threshold of the number of times marked to R, and compare P and R: if P>R, choose to sort the n reference data, and sort the i reference data in descending order according to the number of historical markings. Reference data with the same number of markings are randomly sorted; if P≤R, no sorting is performed.

9. The method for optimizing service platform data based on artificial intelligence according to claim 8, characterized in that: S4 includes: confirming whether the user who currently inputs the consultation question is a user who logs into the platform for the first time; if so, transmitting n reference data as the final optimized reference data to the client where the current user is located; if not, collecting the amount of reference data that the current user viewed before exiting the platform due to failure to find valid reference data for the consultation question: the reference data amount set is V={V1,V2,...V m }, m represents the number of times the current user has exited the platform due to failure to find valid reference data. The amount of data that the current user can accept is predicted to be V m+1 :V m+1 =θ*V m +(1-θ)*D m , where D m V represents the smoothed value of the reference data viewed by the user before the mth exit from the platform, 0<θ<1, θ represents the smoothing coefficient, and the total amount of the first k reference data in the n reference data that have been selectively sorted does not exceed V m+1 And the total amount of the first k+1 reference data exceeds V m+1 , the first k reference data are transmitted as the final optimized reference data to the client where the current user is located.

Images